Limits on the Efficiency of Event-Based Algorithms for Monte Carlo Neutron Transport

DOE PAGES

Romano, Paul K.; Siegel, Andrew R.

2017-07-01

The traditional form of parallelism in Monte Carlo particle transport simulations, wherein each individual particle history is considered a unit of work, does not lend itself well to data-level parallelism. Event-based algorithms, which were originally used for simulations on vector processors, may offer a path toward better utilizing data-level parallelism in modern computer architectures. In this study, a simple model is developed for estimating the efficiency of the event-based particle transport algorithm under two sets of assumptions. Data collected from simulations of four reactor problems using OpenMC was then used in conjunction with the models to calculate the speedup duemore » to vectorization as a function of the size of the particle bank and the vector width. When each event type is assumed to have constant execution time, the achievable speedup is directly related to the particle bank size. We observed that the bank size generally needs to be at least 20 times greater than vector size to achieve vector efficiency greater than 90%. Lastly, when the execution times for events are allowed to vary, the vector speedup is also limited by differences in execution time for events being carried out in a single event-iteration.« less

A Visual Database System for Image Analysis on Parallel Computers and its Application to the EOS Amazon Project

NASA Technical Reports Server (NTRS)

Shapiro, Linda G.; Tanimoto, Steven L.; Ahrens, James P.

1996-01-01

The goal of this task was to create a design and prototype implementation of a database environment that is particular suited for handling the image, vision and scientific data associated with the NASA's EOC Amazon project. The focus was on a data model and query facilities that are designed to execute efficiently on parallel computers. A key feature of the environment is an interface which allows a scientist to specify high-level directives about how query execution should occur.

Accessing sparse arrays in parallel memories

DOE Office of Scientific and Technical Information (OSTI.GOV)

Banerjee, U.; Gajski, D.; Kuck, D.

The concept of dense and sparse execution of arrays is introduced. Arrays themselves can be stored in a dense or sparse manner in a parallel memory with m memory modules. The paper proposes hardware for speeding up the execution of array operations of the form c(c/sub 0/+ci)=a(a/sub 0/+ai) op b(b/sub 0/+bi), where a/sub 0/, a, b/sub 0/, b, c/sub 0/, c are integer constants and i is an index variable. The hardware handles 'sparse execution', in which the operation op is not executed for every value of i. The hardware also makes provision for 'sparse storage', in which memory spacemore » is not provided for every array element. It is shown how to access array elements of the above form without conflict in an efficient way. The efficiency is obtained by using some specialised units which are basically smart memories with priority detection, one's counting or associative searching. Generalisation to multidimensional arrays is shown possible under restrictions defined in the paper. 12 references.« less

Efficient Parallelization of a Dynamic Unstructured Application on the Tera MTA

NASA Technical Reports Server (NTRS)

Oliker, Leonid; Biswas, Rupak

1999-01-01

The success of parallel computing in solving real-life computationally-intensive problems relies on their efficient mapping and execution on large-scale multiprocessor architectures. Many important applications are both unstructured and dynamic in nature, making their efficient parallel implementation a daunting task. This paper presents the parallelization of a dynamic unstructured mesh adaptation algorithm using three popular programming paradigms on three leading supercomputers. We examine an MPI message-passing implementation on the Cray T3E and the SGI Origin2OOO, a shared-memory implementation using cache coherent nonuniform memory access (CC-NUMA) of the Origin2OOO, and a multi-threaded version on the newly-released Tera Multi-threaded Architecture (MTA). We compare several critical factors of this parallel code development, including runtime, scalability, programmability, and memory overhead. Our overall results demonstrate that multi-threaded systems offer tremendous potential for quickly and efficiently solving some of the most challenging real-life problems on parallel computers.

Scaling Optimization of the SIESTA MHD Code

NASA Astrophysics Data System (ADS)

Seal, Sudip; Hirshman, Steven; Perumalla, Kalyan

2013-10-01

SIESTA is a parallel three-dimensional plasma equilibrium code capable of resolving magnetic islands at high spatial resolutions for toroidal plasmas. Originally designed to exploit small-scale parallelism, SIESTA has now been scaled to execute efficiently over several thousands of processors P. This scaling improvement was accomplished with minimal intrusion to the execution flow of the original version. First, the efficiency of the iterative solutions was improved by integrating the parallel tridiagonal block solver code BCYCLIC. Krylov-space generation in GMRES was then accelerated using a customized parallel matrix-vector multiplication algorithm. Novel parallel Hessian generation algorithms were integrated and memory access latencies were dramatically reduced through loop nest optimizations and data layout rearrangement. These optimizations sped up equilibria calculations by factors of 30-50. It is possible to compute solutions with granularity N/P near unity on extremely fine radial meshes (N > 1024 points). Grid separation in SIESTA, which manifests itself primarily in the resonant components of the pressure far from rational surfaces, is strongly suppressed by finer meshes. Large problem sizes of up to 300 K simultaneous non-linear coupled equations have been solved on the NERSC supercomputers. Work supported by U.S. DOE under Contract DE-AC05-00OR22725 with UT-Battelle, LLC.

On extending parallelism to serial simulators

NASA Technical Reports Server (NTRS)

Nicol, David; Heidelberger, Philip

1994-01-01

This paper describes an approach to discrete event simulation modeling that appears to be effective for developing portable and efficient parallel execution of models of large distributed systems and communication networks. In this approach, the modeler develops submodels using an existing sequential simulation modeling tool, using the full expressive power of the tool. A set of modeling language extensions permit automatically synchronized communication between submodels; however, the automation requires that any such communication must take a nonzero amount off simulation time. Within this modeling paradigm, a variety of conservative synchronization protocols can transparently support conservative execution of submodels on potentially different processors. A specific implementation of this approach, U.P.S. (Utilitarian Parallel Simulator), is described, along with performance results on the Intel Paragon.

Visual analysis of inter-process communication for large-scale parallel computing.

PubMed

Muelder, Chris; Gygi, Francois; Ma, Kwan-Liu

2009-01-01

In serial computation, program profiling is often helpful for optimization of key sections of code. When moving to parallel computation, not only does the code execution need to be considered but also communication between the different processes which can induce delays that are detrimental to performance. As the number of processes increases, so does the impact of the communication delays on performance. For large-scale parallel applications, it is critical to understand how the communication impacts performance in order to make the code more efficient. There are several tools available for visualizing program execution and communications on parallel systems. These tools generally provide either views which statistically summarize the entire program execution or process-centric views. However, process-centric visualizations do not scale well as the number of processes gets very large. In particular, the most common representation of parallel processes is a Gantt char t with a row for each process. As the number of processes increases, these charts can become difficult to work with and can even exceed screen resolution. We propose a new visualization approach that affords more scalability and then demonstrate it on systems running with up to 16,384 processes.

A Pervasive Parallel Processing Framework for Data Visualization and Analysis at Extreme Scale

DOE Office of Scientific and Technical Information (OSTI.GOV)

Moreland, Kenneth; Geveci, Berk

2014-11-01

The evolution of the computing world from teraflop to petaflop has been relatively effortless, with several of the existing programming models scaling effectively to the petascale. The migration to exascale, however, poses considerable challenges. All industry trends infer that the exascale machine will be built using processors containing hundreds to thousands of cores per chip. It can be inferred that efficient concurrency on exascale machines requires a massive amount of concurrent threads, each performing many operations on a localized piece of data. Currently, visualization libraries and applications are based off what is known as the visualization pipeline. In the pipelinemore » model, algorithms are encapsulated as filters with inputs and outputs. These filters are connected by setting the output of one component to the input of another. Parallelism in the visualization pipeline is achieved by replicating the pipeline for each processing thread. This works well for today’s distributed memory parallel computers but cannot be sustained when operating on processors with thousands of cores. Our project investigates a new visualization framework designed to exhibit the pervasive parallelism necessary for extreme scale machines. Our framework achieves this by defining algorithms in terms of worklets, which are localized stateless operations. Worklets are atomic operations that execute when invoked unlike filters, which execute when a pipeline request occurs. The worklet design allows execution on a massive amount of lightweight threads with minimal overhead. Only with such fine-grained parallelism can we hope to fill the billions of threads we expect will be necessary for efficient computation on an exascale machine.« less

cuTauLeaping: A GPU-Powered Tau-Leaping Stochastic Simulator for Massive Parallel Analyses of Biological Systems

PubMed Central

Besozzi, Daniela; Pescini, Dario; Mauri, Giancarlo

2014-01-01

Tau-leaping is a stochastic simulation algorithm that efficiently reconstructs the temporal evolution of biological systems, modeled according to the stochastic formulation of chemical kinetics. The analysis of dynamical properties of these systems in physiological and perturbed conditions usually requires the execution of a large number of simulations, leading to high computational costs. Since each simulation can be executed independently from the others, a massive parallelization of tau-leaping can bring to relevant reductions of the overall running time. The emerging field of General Purpose Graphic Processing Units (GPGPU) provides power-efficient high-performance computing at a relatively low cost. In this work we introduce cuTauLeaping, a stochastic simulator of biological systems that makes use of GPGPU computing to execute multiple parallel tau-leaping simulations, by fully exploiting the Nvidia's Fermi GPU architecture. We show how a considerable computational speedup is achieved on GPU by partitioning the execution of tau-leaping into multiple separated phases, and we describe how to avoid some implementation pitfalls related to the scarcity of memory resources on the GPU streaming multiprocessors. Our results show that cuTauLeaping largely outperforms the CPU-based tau-leaping implementation when the number of parallel simulations increases, with a break-even directly depending on the size of the biological system and on the complexity of its emergent dynamics. In particular, cuTauLeaping is exploited to investigate the probability distribution of bistable states in the Schlögl model, and to carry out a bidimensional parameter sweep analysis to study the oscillatory regimes in the Ras/cAMP/PKA pathway in S. cerevisiae. PMID:24663957

Parallel Computing Strategies for Irregular Algorithms

NASA Technical Reports Server (NTRS)

Biswas, Rupak; Oliker, Leonid; Shan, Hongzhang; Biegel, Bryan (Technical Monitor)

2002-01-01

Parallel computing promises several orders of magnitude increase in our ability to solve realistic computationally-intensive problems, but relies on their efficient mapping and execution on large-scale multiprocessor architectures. Unfortunately, many important applications are irregular and dynamic in nature, making their effective parallel implementation a daunting task. Moreover, with the proliferation of parallel architectures and programming paradigms, the typical scientist is faced with a plethora of questions that must be answered in order to obtain an acceptable parallel implementation of the solution algorithm. In this paper, we consider three representative irregular applications: unstructured remeshing, sparse matrix computations, and N-body problems, and parallelize them using various popular programming paradigms on a wide spectrum of computer platforms ranging from state-of-the-art supercomputers to PC clusters. We present the underlying problems, the solution algorithms, and the parallel implementation strategies. Smart load-balancing, partitioning, and ordering techniques are used to enhance parallel performance. Overall results demonstrate the complexity of efficiently parallelizing irregular algorithms.

Efficient iteration in data-parallel programs with irregular and dynamically distributed data structures

DOE Office of Scientific and Technical Information (OSTI.GOV)

Littlefield, R.J.

1990-02-01

To implement an efficient data-parallel program on a non-shared memory MIMD multicomputer, data and computations must be properly partitioned to achieve good load balance and locality of reference. Programs with irregular data reference patterns often require irregular partitions. Although good partitions may be easy to determine, they can be difficult or impossible to implement in programming languages that provide only regular data distributions, such as blocked or cyclic arrays. We are developing Onyx, a programming system that provides a shared memory model of distributed data structures and extends the concept of data distribution to include irregular and dynamic distributions. Thismore » provides a powerful means to specify irregular partitions. Perhaps surprisingly, programs using it can also execute efficiently. In this paper, we describe and evaluate the Onyx implementation of a model problem that repeatedly executes an irregular but fixed data reference pattern. On an NCUBE hypercube, the speed of the Onyx implementation is comparable to that of carefully handwritten message-passing code.« less

A parallel approach of COFFEE objective function to multiple sequence alignment

NASA Astrophysics Data System (ADS)

Zafalon, G. F. D.; Visotaky, J. M. V.; Amorim, A. R.; Valêncio, C. R.; Neves, L. A.; de Souza, R. C. G.; Machado, J. M.

2015-09-01

The computational tools to assist genomic analyzes show even more necessary due to fast increasing of data amount available. With high computational costs of deterministic algorithms for sequence alignments, many works concentrate their efforts in the development of heuristic approaches to multiple sequence alignments. However, the selection of an approach, which offers solutions with good biological significance and feasible execution time, is a great challenge. Thus, this work aims to show the parallelization of the processing steps of MSA-GA tool using multithread paradigm in the execution of COFFEE objective function. The standard objective function implemented in the tool is the Weighted Sum of Pairs (WSP), which produces some distortions in the final alignments when sequences sets with low similarity are aligned. Then, in studies previously performed we implemented the COFFEE objective function in the tool to smooth these distortions. Although the nature of COFFEE objective function implies in the increasing of execution time, this approach presents points, which can be executed in parallel. With the improvements implemented in this work, we can verify the execution time of new approach is 24% faster than the sequential approach with COFFEE. Moreover, the COFFEE multithreaded approach is more efficient than WSP, because besides it is slightly fast, its biological results are better.

Architecture and data processing alternatives for the TSE computer. Volume 3: Execution of a parallel counting algorithm using array logic (Tse) devices

NASA Technical Reports Server (NTRS)

Metcalfe, A. G.; Bodenheimer, R. E.

1976-01-01

A parallel algorithm for counting the number of logic-l elements in a binary array or image developed during preliminary investigation of the Tse concept is described. The counting algorithm is implemented using a basic combinational structure. Modifications which improve the efficiency of the basic structure are also presented. A programmable Tse computer structure is proposed, along with a hardware control unit, Tse instruction set, and software program for execution of the counting algorithm. Finally, a comparison is made between the different structures in terms of their more important characteristics.

IOPA: I/O-aware parallelism adaption for parallel programs

PubMed Central

Liu, Tao; Liu, Yi; Qian, Chen; Qian, Depei

2017-01-01

With the development of multi-/many-core processors, applications need to be written as parallel programs to improve execution efficiency. For data-intensive applications that use multiple threads to read/write files simultaneously, an I/O sub-system can easily become a bottleneck when too many of these types of threads exist; on the contrary, too few threads will cause insufficient resource utilization and hurt performance. Therefore, programmers must pay much attention to parallelism control to find the appropriate number of I/O threads for an application. This paper proposes a parallelism control mechanism named IOPA that can adjust the parallelism of applications to adapt to the I/O capability of a system and balance computing resources and I/O bandwidth. The programming interface of IOPA is also provided to programmers to simplify parallel programming. IOPA is evaluated using multiple applications with both solid state and hard disk drives. The results show that the parallel applications using IOPA can achieve higher efficiency than those with a fixed number of threads. PMID:28278236

IOPA: I/O-aware parallelism adaption for parallel programs.

PubMed

Liu, Tao; Liu, Yi; Qian, Chen; Qian, Depei

2017-01-01

With the development of multi-/many-core processors, applications need to be written as parallel programs to improve execution efficiency. For data-intensive applications that use multiple threads to read/write files simultaneously, an I/O sub-system can easily become a bottleneck when too many of these types of threads exist; on the contrary, too few threads will cause insufficient resource utilization and hurt performance. Therefore, programmers must pay much attention to parallelism control to find the appropriate number of I/O threads for an application. This paper proposes a parallelism control mechanism named IOPA that can adjust the parallelism of applications to adapt to the I/O capability of a system and balance computing resources and I/O bandwidth. The programming interface of IOPA is also provided to programmers to simplify parallel programming. IOPA is evaluated using multiple applications with both solid state and hard disk drives. The results show that the parallel applications using IOPA can achieve higher efficiency than those with a fixed number of threads.

Efficient Helicopter Aerodynamic and Aeroacoustic Predictions on Parallel Computers

NASA Technical Reports Server (NTRS)

Wissink, Andrew M.; Lyrintzis, Anastasios S.; Strawn, Roger C.; Oliker, Leonid; Biswas, Rupak

1996-01-01

This paper presents parallel implementations of two codes used in a combined CFD/Kirchhoff methodology to predict the aerodynamics and aeroacoustics properties of helicopters. The rotorcraft Navier-Stokes code, TURNS, computes the aerodynamic flowfield near the helicopter blades and the Kirchhoff acoustics code computes the noise in the far field, using the TURNS solution as input. The overall parallel strategy adds MPI message passing calls to the existing serial codes to allow for communication between processors. As a result, the total code modifications required for parallel execution are relatively small. The biggest bottleneck in running the TURNS code in parallel comes from the LU-SGS algorithm that solves the implicit system of equations. We use a new hybrid domain decomposition implementation of LU-SGS to obtain good parallel performance on the SP-2. TURNS demonstrates excellent parallel speedups for quasi-steady and unsteady three-dimensional calculations of a helicopter blade in forward flight. The execution rate attained by the code on 114 processors is six times faster than the same cases run on one processor of the Cray C-90. The parallel Kirchhoff code also shows excellent parallel speedups and fast execution rates. As a performance demonstration, unsteady acoustic pressures are computed at 1886 far-field observer locations for a sample acoustics problem. The calculation requires over two hundred hours of CPU time on one C-90 processor but takes only a few hours on 80 processors of the SP2. The resultant far-field acoustic field is analyzed with state of-the-art audio and video rendering of the propagating acoustic signals.

Execution of a parallel edge-based Navier-Stokes solver on commodity graphics processor units

NASA Astrophysics Data System (ADS)

Corral, Roque; Gisbert, Fernando; Pueblas, Jesus

2017-02-01

The implementation of an edge-based three-dimensional Reynolds Average Navier-Stokes solver for unstructured grids able to run on multiple graphics processing units (GPUs) is presented. Loops over edges, which are the most time-consuming part of the solver, have been written to exploit the massively parallel capabilities of GPUs. Non-blocking communications between parallel processes and between the GPU and the central processor unit (CPU) have been used to enhance code scalability. The code is written using a mixture of C++ and OpenCL, to allow the execution of the source code on GPUs. The Message Passage Interface (MPI) library is used to allow the parallel execution of the solver on multiple GPUs. A comparative study of the solver parallel performance is carried out using a cluster of CPUs and another of GPUs. It is shown that a single GPU is up to 64 times faster than a single CPU core. The parallel scalability of the solver is mainly degraded due to the loss of computing efficiency of the GPU when the size of the case decreases. However, for large enough grid sizes, the scalability is strongly improved. A cluster featuring commodity GPUs and a high bandwidth network is ten times less costly and consumes 33% less energy than a CPU-based cluster with an equivalent computational power.

Parallel-vector out-of-core equation solver for computational mechanics

NASA Technical Reports Server (NTRS)

Qin, J.; Agarwal, T. K.; Storaasli, O. O.; Nguyen, D. T.; Baddourah, M. A.

1993-01-01

A parallel/vector out-of-core equation solver is developed for shared-memory computers, such as the Cray Y-MP machine. The input/ output (I/O) time is reduced by using the a synchronous BUFFER IN and BUFFER OUT, which can be executed simultaneously with the CPU instructions. The parallel and vector capability provided by the supercomputers is also exploited to enhance the performance. Numerical applications in large-scale structural analysis are given to demonstrate the efficiency of the present out-of-core solver.

A Genetic Algorithm for UAV Routing Integrated with a Parallel Swarm Simulation

DTIC Science & Technology

2005-03-01

Metrics. 2.3.5.1 Amdahl’s, Gustafson-Barsis’s, and Sun-Ni’s Laws . At the heart of parallel computing is the ratio of communication time to...parallel execution. Three ‘ laws ’ in particular are of interest with regard to this ratio: Amdahl’s Law , the Gustafson-Barsis’s Law , and Sun-Ni’s Law ...Amdahl’s Law makes the case for fixed size speedup. This conjecture states that speedup saturates and efficiency drops as a consequence of holding the

Parallelization of elliptic solver for solving 1D Boussinesq model

NASA Astrophysics Data System (ADS)

Tarwidi, D.; Adytia, D.

2018-03-01

In this paper, a parallel implementation of an elliptic solver in solving 1D Boussinesq model is presented. Numerical solution of Boussinesq model is obtained by implementing a staggered grid scheme to continuity, momentum, and elliptic equation of Boussinesq model. Tridiagonal system emerging from numerical scheme of elliptic equation is solved by cyclic reduction algorithm. The parallel implementation of cyclic reduction is executed on multicore processors with shared memory architectures using OpenMP. To measure the performance of parallel program, large number of grids is varied from 28 to 214. Two test cases of numerical experiment, i.e. propagation of solitary and standing wave, are proposed to evaluate the parallel program. The numerical results are verified with analytical solution of solitary and standing wave. The best speedup of solitary and standing wave test cases is about 2.07 with 214 of grids and 1.86 with 213 of grids, respectively, which are executed by using 8 threads. Moreover, the best efficiency of parallel program is 76.2% and 73.5% for solitary and standing wave test cases, respectively.

Limits on the Efficiency of Event-Based Algorithms for Monte Carlo Neutron Transport

DOE Office of Scientific and Technical Information (OSTI.GOV)

Romano, Paul K.; Siegel, Andrew R.

The traditional form of parallelism in Monte Carlo particle transport simulations, wherein each individual particle history is considered a unit of work, does not lend itself well to data-level parallelism. Event-based algorithms, which were originally used for simulations on vector processors, may offer a path toward better utilizing data-level parallelism in modern computer architectures. In this study, a simple model is developed for estimating the efficiency of the event-based particle transport algorithm under two sets of assumptions. Data collected from simulations of four reactor problems using OpenMC was then used in conjunction with the models to calculate the speedup duemore » to vectorization as a function of two parameters: the size of the particle bank and the vector width. When each event type is assumed to have constant execution time, the achievable speedup is directly related to the particle bank size. We observed that the bank size generally needs to be at least 20 times greater than vector size in order to achieve vector efficiency greater than 90%. When the execution times for events are allowed to vary, however, the vector speedup is also limited by differences in execution time for events being carried out in a single event-iteration. For some problems, this implies that vector effciencies over 50% may not be attainable. While there are many factors impacting performance of an event-based algorithm that are not captured by our model, it nevertheless provides insights into factors that may be limiting in a real implementation.« less

Knowledge representation into Ada parallel processing

NASA Technical Reports Server (NTRS)

Masotto, Tom; Babikyan, Carol; Harper, Richard

1990-01-01

The Knowledge Representation into Ada Parallel Processing project is a joint NASA and Air Force funded project to demonstrate the execution of intelligent systems in Ada on the Charles Stark Draper Laboratory fault-tolerant parallel processor (FTPP). Two applications were demonstrated - a portion of the adaptive tactical navigator and a real time controller. Both systems are implemented as Activation Framework Objects on the Activation Framework intelligent scheduling mechanism developed by Worcester Polytechnic Institute. The implementations, results of performance analyses showing speedup due to parallelism and initial efficiency improvements are detailed and further areas for performance improvements are suggested.

Performance comparison analysis library communication cluster system using merge sort

NASA Astrophysics Data System (ADS)

Wulandari, D. A. R.; Ramadhan, M. E.

2018-04-01

Begins by using a single processor, to increase the speed of computing time, the use of multi-processor was introduced. The second paradigm is known as parallel computing, example cluster. The cluster must have the communication potocol for processing, one of it is message passing Interface (MPI). MPI have many library, both of them OPENMPI and MPICH2. Performance of the cluster machine depend on suitable between performance characters of library communication and characters of the problem so this study aims to analyze the comparative performances libraries in handling parallel computing process. The case study in this research are MPICH2 and OpenMPI. This case research execute sorting’s problem to know the performance of cluster system. The sorting problem use mergesort method. The research method is by implementing OpenMPI and MPICH2 on a Linux-based cluster by using five computer virtual then analyze the performance of the system by different scenario tests and three parameters for to know the performance of MPICH2 and OpenMPI. These performances are execution time, speedup and efficiency. The results of this study showed that the addition of each data size makes OpenMPI and MPICH2 have an average speed-up and efficiency tend to increase but at a large data size decreases. increased data size doesn’t necessarily increased speed up and efficiency but only execution time example in 100000 data size. OpenMPI has a execution time greater than MPICH2 example in 1000 data size average execution time with MPICH2 is 0,009721 and OpenMPI is 0,003895 OpenMPI can customize communication needs.

A Systems Approach to Scalable Transportation Network Modeling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perumalla, Kalyan S

2006-01-01

Emerging needs in transportation network modeling and simulation are raising new challenges with respect to scal-ability of network size and vehicular traffic intensity, speed of simulation for simulation-based optimization, and fidel-ity of vehicular behavior for accurate capture of event phe-nomena. Parallel execution is warranted to sustain the re-quired detail, size and speed. However, few parallel simulators exist for such applications, partly due to the challenges underlying their development. Moreover, many simulators are based on time-stepped models, which can be computationally inefficient for the purposes of modeling evacuation traffic. Here an approach is presented to de-signing a simulator with memory andmore » speed efficiency as the goals from the outset, and, specifically, scalability via parallel execution. The design makes use of discrete event modeling techniques as well as parallel simulation meth-ods. Our simulator, called SCATTER, is being developed, incorporating such design considerations. Preliminary per-formance results are presented on benchmark road net-works, showing scalability to one million vehicles simu-lated on one processor.« less

Distributed parallel computing in stochastic modeling of groundwater systems.

PubMed

Dong, Yanhui; Li, Guomin; Xu, Haizhen

2013-03-01

Stochastic modeling is a rapidly evolving, popular approach to the study of the uncertainty and heterogeneity of groundwater systems. However, the use of Monte Carlo-type simulations to solve practical groundwater problems often encounters computational bottlenecks that hinder the acquisition of meaningful results. To improve the computational efficiency, a system that combines stochastic model generation with MODFLOW-related programs and distributed parallel processing is investigated. The distributed computing framework, called the Java Parallel Processing Framework, is integrated into the system to allow the batch processing of stochastic models in distributed and parallel systems. As an example, the system is applied to the stochastic delineation of well capture zones in the Pinggu Basin in Beijing. Through the use of 50 processing threads on a cluster with 10 multicore nodes, the execution times of 500 realizations are reduced to 3% compared with those of a serial execution. Through this application, the system demonstrates its potential in solving difficult computational problems in practical stochastic modeling. © 2012, The Author(s). Groundwater © 2012, National Ground Water Association.

Cache Locality Optimization for Recursive Programs

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lifflander, Jonathan; Krishnamoorthy, Sriram

We present an approach to optimize the cache locality for recursive programs by dynamically splicing--recursively interleaving--the execution of distinct function invocations. By utilizing data effect annotations, we identify concurrency and data reuse opportunities across function invocations and interleave them to reduce reuse distance. We present algorithms that efficiently track effects in recursive programs, detect interference and dependencies, and interleave execution of function invocations using user-level (non-kernel) lightweight threads. To enable multi-core execution, a program is parallelized using a nested fork/join programming model. Our cache optimization strategy is designed to work in the context of a random work stealing scheduler. Wemore » present an implementation using the MIT Cilk framework that demonstrates significant improvements in sequential and parallel performance, competitive with a state-of-the-art compile-time optimizer for loop programs and a domain- specific optimizer for stencil programs.« less

Expressing Parallelism with ROOT

NASA Astrophysics Data System (ADS)

Piparo, D.; Tejedor, E.; Guiraud, E.; Ganis, G.; Mato, P.; Moneta, L.; Valls Pla, X.; Canal, P.

2017-10-01

The need for processing the ever-increasing amount of data generated by the LHC experiments in a more efficient way has motivated ROOT to further develop its support for parallelism. Such support is being tackled both for shared-memory and distributed-memory environments. The incarnations of the aforementioned parallelism are multi-threading, multi-processing and cluster-wide executions. In the area of multi-threading, we discuss the new implicit parallelism and related interfaces, as well as the new building blocks to safely operate with ROOT objects in a multi-threaded environment. Regarding multi-processing, we review the new MultiProc framework, comparing it with similar tools (e.g. multiprocessing module in Python). Finally, as an alternative to PROOF for cluster-wide executions, we introduce the efforts on integrating ROOT with state-of-the-art distributed data processing technologies like Spark, both in terms of programming model and runtime design (with EOS as one of the main components). For all the levels of parallelism, we discuss, based on real-life examples and measurements, how our proposals can increase the productivity of scientists.

Expressing Parallelism with ROOT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Piparo, D.; Tejedor, E.; Guiraud, E.

The need for processing the ever-increasing amount of data generated by the LHC experiments in a more efficient way has motivated ROOT to further develop its support for parallelism. Such support is being tackled both for shared-memory and distributed-memory environments. The incarnations of the aforementioned parallelism are multi-threading, multi-processing and cluster-wide executions. In the area of multi-threading, we discuss the new implicit parallelism and related interfaces, as well as the new building blocks to safely operate with ROOT objects in a multi-threaded environment. Regarding multi-processing, we review the new MultiProc framework, comparing it with similar tools (e.g. multiprocessing module inmore » Python). Finally, as an alternative to PROOF for cluster-wide executions, we introduce the efforts on integrating ROOT with state-of-the-art distributed data processing technologies like Spark, both in terms of programming model and runtime design (with EOS as one of the main components). For all the levels of parallelism, we discuss, based on real-life examples and measurements, how our proposals can increase the productivity of scientists.« less

Parallel processing optimization strategy based on MapReduce model in cloud storage environment

NASA Astrophysics Data System (ADS)

Cui, Jianming; Liu, Jiayi; Li, Qiuyan

2017-05-01

Currently, a large number of documents in the cloud storage process employed the way of packaging after receiving all the packets. From the local transmitter this stored procedure to the server, packing and unpacking will consume a lot of time, and the transmission efficiency is low as well. A new parallel processing algorithm is proposed to optimize the transmission mode. According to the operation machine graphs model work, using MPI technology parallel execution Mapper and Reducer mechanism. It is good to use MPI technology to implement Mapper and Reducer parallel mechanism. After the simulation experiment of Hadoop cloud computing platform, this algorithm can not only accelerate the file transfer rate, but also shorten the waiting time of the Reducer mechanism. It will break through traditional sequential transmission constraints and reduce the storage coupling to improve the transmission efficiency.

Parallel processing and expert systems

NASA Technical Reports Server (NTRS)

Lau, Sonie; Yan, Jerry C.

1991-01-01

Whether it be monitoring the thermal subsystem of Space Station Freedom, or controlling the navigation of the autonomous rover on Mars, NASA missions in the 1990s cannot enjoy an increased level of autonomy without the efficient implementation of expert systems. Merely increasing the computational speed of uniprocessors may not be able to guarantee that real-time demands are met for larger systems. Speedup via parallel processing must be pursued alongside the optimization of sequential implementations. Prototypes of parallel expert systems have been built at universities and industrial laboratories in the U.S. and Japan. The state-of-the-art research in progress related to parallel execution of expert systems is surveyed. The survey discusses multiprocessors for expert systems, parallel languages for symbolic computations, and mapping expert systems to multiprocessors. Results to date indicate that the parallelism achieved for these systems is small. The main reasons are (1) the body of knowledge applicable in any given situation and the amount of computation executed by each rule firing are small, (2) dividing the problem solving process into relatively independent partitions is difficult, and (3) implementation decisions that enable expert systems to be incrementally refined hamper compile-time optimization. In order to obtain greater speedups, data parallelism and application parallelism must be exploited.

Orchid: a novel management, annotation and machine learning framework for analyzing cancer mutations.

PubMed

Cario, Clinton L; Witte, John S

2018-03-15

As whole-genome tumor sequence and biological annotation datasets grow in size, number and content, there is an increasing basic science and clinical need for efficient and accurate data management and analysis software. With the emergence of increasingly sophisticated data stores, execution environments and machine learning algorithms, there is also a need for the integration of functionality across frameworks. We present orchid, a python based software package for the management, annotation and machine learning of cancer mutations. Building on technologies of parallel workflow execution, in-memory database storage and machine learning analytics, orchid efficiently handles millions of mutations and hundreds of features in an easy-to-use manner. We describe the implementation of orchid and demonstrate its ability to distinguish tissue of origin in 12 tumor types based on 339 features using a random forest classifier. Orchid and our annotated tumor mutation database are freely available at https://github.com/wittelab/orchid. Software is implemented in python 2.7, and makes use of MySQL or MemSQL databases. Groovy 2.4.5 is optionally required for parallel workflow execution. JWitte@ucsf.edu. Supplementary data are available at Bioinformatics online.

Speculation and replication in temperature accelerated dynamics

DOE PAGES

Zamora, Richard J.; Perez, Danny; Voter, Arthur F.

2018-02-12

Accelerated Molecular Dynamics (AMD) is a class of MD-based algorithms for the long-time scale simulation of atomistic systems that are characterized by rare-event transitions. Temperature-Accelerated Dynamics (TAD), a traditional AMD approach, hastens state-to-state transitions by performing MD at an elevated temperature. Recently, Speculatively-Parallel TAD (SpecTAD) was introduced, allowing the TAD procedure to exploit parallel computing systems by concurrently executing in a dynamically generated list of speculative future states. Although speculation can be very powerful, it is not always the most efficient use of parallel resources. In this paper, we compare the performance of speculative parallelism with a replica-based technique, similarmore » to the Parallel Replica Dynamics method. A hybrid SpecTAD approach is also presented, in which each speculation process is further accelerated by a local set of replicas. Finally and overall, this work motivates the use of hybrid parallelism whenever possible, as some combination of speculation and replication is typically most efficient.« less

Speculation and replication in temperature accelerated dynamics

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zamora, Richard J.; Perez, Danny; Voter, Arthur F.

Accelerated Molecular Dynamics (AMD) is a class of MD-based algorithms for the long-time scale simulation of atomistic systems that are characterized by rare-event transitions. Temperature-Accelerated Dynamics (TAD), a traditional AMD approach, hastens state-to-state transitions by performing MD at an elevated temperature. Recently, Speculatively-Parallel TAD (SpecTAD) was introduced, allowing the TAD procedure to exploit parallel computing systems by concurrently executing in a dynamically generated list of speculative future states. Although speculation can be very powerful, it is not always the most efficient use of parallel resources. In this paper, we compare the performance of speculative parallelism with a replica-based technique, similarmore » to the Parallel Replica Dynamics method. A hybrid SpecTAD approach is also presented, in which each speculation process is further accelerated by a local set of replicas. Finally and overall, this work motivates the use of hybrid parallelism whenever possible, as some combination of speculation and replication is typically most efficient.« less

Tolerant (parallel) Programming

NASA Technical Reports Server (NTRS)

DiNucci, David C.; Bailey, David H. (Technical Monitor)

1997-01-01

In order to be truly portable, a program must be tolerant of a wide range of development and execution environments, and a parallel program is just one which must be tolerant of a very wide range. This paper first defines the term "tolerant programming", then describes many layers of tools to accomplish it. The primary focus is on F-Nets, a formal model for expressing computation as a folded partial-ordering of operations, thereby providing an architecture-independent expression of tolerant parallel algorithms. For implementing F-Nets, Cooperative Data Sharing (CDS) is a subroutine package for implementing communication efficiently in a large number of environments (e.g. shared memory and message passing). Software Cabling (SC), a very-high-level graphical programming language for building large F-Nets, possesses many of the features normally expected from today's computer languages (e.g. data abstraction, array operations). Finally, L2(sup 3) is a CASE tool which facilitates the construction, compilation, execution, and debugging of SC programs.

Aggregating job exit statuses of a plurality of compute nodes executing a parallel application

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aho, Michael E.; Attinella, John E.; Gooding, Thomas M.

Aggregating job exit statuses of a plurality of compute nodes executing a parallel application, including: identifying a subset of compute nodes in the parallel computer to execute the parallel application; selecting one compute node in the subset of compute nodes in the parallel computer as a job leader compute node; initiating execution of the parallel application on the subset of compute nodes; receiving an exit status from each compute node in the subset of compute nodes, where the exit status for each compute node includes information describing execution of some portion of the parallel application by the compute node; aggregatingmore » each exit status from each compute node in the subset of compute nodes; and sending an aggregated exit status for the subset of compute nodes in the parallel computer.« less

Diderot: a Domain-Specific Language for Portable Parallel Scientific Visualization and Image Analysis.

PubMed

Kindlmann, Gordon; Chiw, Charisee; Seltzer, Nicholas; Samuels, Lamont; Reppy, John

2016-01-01

Many algorithms for scientific visualization and image analysis are rooted in the world of continuous scalar, vector, and tensor fields, but are programmed in low-level languages and libraries that obscure their mathematical foundations. Diderot is a parallel domain-specific language that is designed to bridge this semantic gap by providing the programmer with a high-level, mathematical programming notation that allows direct expression of mathematical concepts in code. Furthermore, Diderot provides parallel performance that takes advantage of modern multicore processors and GPUs. The high-level notation allows a concise and natural expression of the algorithms and the parallelism allows efficient execution on real-world datasets.

Experiences with hypercube operating system instrumentation

NASA Technical Reports Server (NTRS)

Reed, Daniel A.; Rudolph, David C.

1989-01-01

The difficulties in conceptualizing the interactions among a large number of processors make it difficult both to identify the sources of inefficiencies and to determine how a parallel program could be made more efficient. This paper describes an instrumentation system that can trace the execution of distributed memory parallel programs by recording the occurrence of parallel program events. The resulting event traces can be used to compile summary statistics that provide a global view of program performance. In addition, visualization tools permit the graphic display of event traces. Visual presentation of performance data is particularly useful, indeed, necessary for large-scale parallel computers; the enormous volume of performance data mandates visual display.

Modern multicore and manycore architectures: Modelling, optimisation and benchmarking a multiblock CFD code

NASA Astrophysics Data System (ADS)

Hadade, Ioan; di Mare, Luca

2016-08-01

Modern multicore and manycore processors exhibit multiple levels of parallelism through a wide range of architectural features such as SIMD for data parallel execution or threads for core parallelism. The exploitation of multi-level parallelism is therefore crucial for achieving superior performance on current and future processors. This paper presents the performance tuning of a multiblock CFD solver on Intel SandyBridge and Haswell multicore CPUs and the Intel Xeon Phi Knights Corner coprocessor. Code optimisations have been applied on two computational kernels exhibiting different computational patterns: the update of flow variables and the evaluation of the Roe numerical fluxes. We discuss at great length the code transformations required for achieving efficient SIMD computations for both kernels across the selected devices including SIMD shuffles and transpositions for flux stencil computations and global memory transformations. Core parallelism is expressed through threading based on a number of domain decomposition techniques together with optimisations pertaining to alleviating NUMA effects found in multi-socket compute nodes. Results are correlated with the Roofline performance model in order to assert their efficiency for each distinct architecture. We report significant speedups for single thread execution across both kernels: 2-5X on the multicore CPUs and 14-23X on the Xeon Phi coprocessor. Computations at full node and chip concurrency deliver a factor of three speedup on the multicore processors and up to 24X on the Xeon Phi manycore coprocessor.

Bayer image parallel decoding based on GPU

NASA Astrophysics Data System (ADS)

Hu, Rihui; Xu, Zhiyong; Wei, Yuxing; Sun, Shaohua

2012-11-01

In the photoelectrical tracking system, Bayer image is decompressed in traditional method, which is CPU-based. However, it is too slow when the images become large, for example, 2K×2K×16bit. In order to accelerate the Bayer image decoding, this paper introduces a parallel speedup method for NVIDA's Graphics Processor Unit (GPU) which supports CUDA architecture. The decoding procedure can be divided into three parts: the first is serial part, the second is task-parallelism part, and the last is data-parallelism part including inverse quantization, inverse discrete wavelet transform (IDWT) as well as image post-processing part. For reducing the execution time, the task-parallelism part is optimized by OpenMP techniques. The data-parallelism part could advance its efficiency through executing on the GPU as CUDA parallel program. The optimization techniques include instruction optimization, shared memory access optimization, the access memory coalesced optimization and texture memory optimization. In particular, it can significantly speed up the IDWT by rewriting the 2D (Tow-dimensional) serial IDWT into 1D parallel IDWT. Through experimenting with 1K×1K×16bit Bayer image, data-parallelism part is 10 more times faster than CPU-based implementation. Finally, a CPU+GPU heterogeneous decompression system was designed. The experimental result shows that it could achieve 3 to 5 times speed increase compared to the CPU serial method.

WARP

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bergmann, Ryan M.; Rowland, Kelly L.

2017-04-12

WARP, which can stand for ``Weaving All the Random Particles,'' is a three-dimensional (3D) continuous energy Monte Carlo neutron transport code developed at UC Berkeley to efficiently execute on NVIDIA graphics processing unit (GPU) platforms. WARP accelerates Monte Carlo simulations while preserving the benefits of using the Monte Carlo method, namely, that very few physical and geometrical simplifications are applied. WARP is able to calculate multiplication factors, neutron flux distributions (in both space and energy), and fission source distributions for time-independent neutron transport problems. It can run in both criticality or fixed source modes, but fixed source mode is currentlymore » not robust, optimized, or maintained in the newest version. WARP can transport neutrons in unrestricted arrangements of parallelepipeds, hexagonal prisms, cylinders, and spheres. The goal of developing WARP is to investigate algorithms that can grow into a full-featured, continuous energy, Monte Carlo neutron transport code that is accelerated by running on GPUs. The crux of the effort is to make Monte Carlo calculations faster while producing accurate results. Modern supercomputers are commonly being built with GPU coprocessor cards in their nodes to increase their computational efficiency and performance. GPUs execute efficiently on data-parallel problems, but most CPU codes, including those for Monte Carlo neutral particle transport, are predominantly task-parallel. WARP uses a data-parallel neutron transport algorithm to take advantage of the computing power GPUs offer.« less

A parallel computational model for GATE simulations.

PubMed

Rannou, F R; Vega-Acevedo, N; El Bitar, Z

2013-12-01

GATE/Geant4 Monte Carlo simulations are computationally demanding applications, requiring thousands of processor hours to produce realistic results. The classical strategy of distributing the simulation of individual events does not apply efficiently for Positron Emission Tomography (PET) experiments, because it requires a centralized coincidence processing and large communication overheads. We propose a parallel computational model for GATE that handles event generation and coincidence processing in a simple and efficient way by decentralizing event generation and processing but maintaining a centralized event and time coordinator. The model is implemented with the inclusion of a new set of factory classes that can run the same executable in sequential or parallel mode. A Mann-Whitney test shows that the output produced by this parallel model in terms of number of tallies is equivalent (but not equal) to its sequential counterpart. Computational performance evaluation shows that the software is scalable and well balanced. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

An intelligent processing environment for real-time simulation

NASA Technical Reports Server (NTRS)

Carroll, Chester C.; Wells, Buren Earl, Jr.

1988-01-01

The development of a highly efficient and thus truly intelligent processing environment for real-time general purpose simulation of continuous systems is described. Such an environment can be created by mapping the simulation process directly onto the University of Alamba's OPERA architecture. To facilitate this effort, the field of continuous simulation is explored, highlighting areas in which efficiency can be improved. Areas in which parallel processing can be applied are also identified, and several general OPERA type hardware configurations that support improved simulation are investigated. Three direct execution parallel processing environments are introduced, each of which greatly improves efficiency by exploiting distinct areas of the simulation process. These suggested environments are candidate architectures around which a highly intelligent real-time simulation configuration can be developed.

Data communications in a parallel active messaging interface of a parallel computer

DOEpatents

Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E

2013-11-12

Data communications in a parallel active messaging interface (`PAMI`) of a parallel computer composed of compute nodes that execute a parallel application, each compute node including application processors that execute the parallel application and at least one management processor dedicated to gathering information regarding data communications. The PAMI is composed of data communications endpoints, each endpoint composed of a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes and the endpoints coupled for data communications through the PAMI and through data communications resources. Embodiments function by gathering call site statistics describing data communications resulting from execution of data communications instructions and identifying in dependence upon the call cite statistics a data communications algorithm for use in executing a data communications instruction at a call site in the parallel application.

Functional networks in parallel with cortical development associate with executive functions in children.

PubMed

Zhong, Jidan; Rifkin-Graboi, Anne; Ta, Anh Tuan; Yap, Kar Lai; Chuang, Kai-Hsiang; Meaney, Michael J; Qiu, Anqi

2014-07-01

Children begin performing similarly to adults on tasks requiring executive functions in late childhood, a transition that is probably due to neuroanatomical fine-tuning processes, including myelination and synaptic pruning. In parallel to such structural changes in neuroanatomical organization, development of functional organization may also be associated with cognitive behaviors in children. We examined 6- to 10-year-old children's cortical thickness, functional organization, and cognitive performance. We used structural magnetic resonance imaging (MRI) to identify areas with cortical thinning, resting-state fMRI to identify functional organization in parallel to cortical development, and working memory/response inhibition tasks to assess executive functioning. We found that neuroanatomical changes in the form of cortical thinning spread over bilateral frontal, parietal, and occipital regions. These regions were engaged in 3 functional networks: sensorimotor and auditory, executive control, and default mode network. Furthermore, we found that working memory and response inhibition only associated with regional functional connectivity, but not topological organization (i.e., local and global efficiency of information transfer) of these functional networks. Interestingly, functional connections associated with "bottom-up" as opposed to "top-down" processing were more clearly related to children's performance on working memory and response inhibition, implying an important role for brain systems involved in late childhood. © The Author 2013. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Two criteria for the selection of assembly plans - Maximizing the flexibility of sequencing the assembly tasks and minimizing the assembly time through parallel execution of assembly tasks

NASA Technical Reports Server (NTRS)

Homem De Mello, Luiz S.; Sanderson, Arthur C.

1991-01-01

The authors introduce two criteria for the evaluation and selection of assembly plans. The first criterion is to maximize the number of different sequences in which the assembly tasks can be executed. The second criterion is to minimize the total assembly time through simultaneous execution of assembly tasks. An algorithm that performs a heuristic search for the best assembly plan over the AND/OR graph representation of assembly plans is discussed. Admissible heuristics for each of the two criteria introduced are presented. Some implementation issues that affect the computational efficiency are addressed.

Problems in characterizing barrier performance

NASA Technical Reports Server (NTRS)

Jordan, Harry F.

1988-01-01

The barrier is a synchronization construct which is useful in separating a parallel program into parallel sections which are executed in sequence. The completion of a barrier requires cooperation among all executing processes. This requirement not only introduces the wait for the slowest process delay which is inherent in the definition of the synchronization, but also has implications for the efficient implementation and measurement of barrier performance in different systems. Types of barrier implementation and their relationship to different multiprocessor environments are described. Then the problem of measuring the performance of barrier implementations on specific machine architecture is discussed. The fact that the barrier synchronization requires the cooperation of all processes makes the problem of performance measurement similarly global. Making non-intrusive measurements of sufficient accuracy can be tricky on systems offering only rudimentary measurement tools.

Demonstration of Hadoop-GIS: A Spatial Data Warehousing System Over MapReduce.

PubMed

Aji, Ablimit; Sun, Xiling; Vo, Hoang; Liu, Qioaling; Lee, Rubao; Zhang, Xiaodong; Saltz, Joel; Wang, Fusheng

2013-11-01

The proliferation of GPS-enabled devices, and the rapid improvement of scientific instruments have resulted in massive amounts of spatial data in the last decade. Support of high performance spatial queries on large volumes data has become increasingly important in numerous fields, which requires a scalable and efficient spatial data warehousing solution as existing approaches exhibit scalability limitations and efficiency bottlenecks for large scale spatial applications. In this demonstration, we present Hadoop-GIS - a scalable and high performance spatial query system over MapReduce. Hadoop-GIS provides an efficient spatial query engine to process spatial queries, data and space based partitioning, and query pipelines that parallelize queries implicitly on MapReduce. Hadoop-GIS also provides an expressive, SQL-like spatial query language for workload specification. We will demonstrate how spatial queries are expressed in spatially extended SQL queries, and submitted through a command line/web interface for execution. Parallel to our system demonstration, we explain the system architecture and details on how queries are translated to MapReduce operators, optimized, and executed on Hadoop. In addition, we will showcase how the system can be used to support two representative real world use cases: large scale pathology analytical imaging, and geo-spatial data warehousing.

Collectively loading an application in a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aho, Michael E.; Attinella, John E.; Gooding, Thomas M.

Collectively loading an application in a parallel computer, the parallel computer comprising a plurality of compute nodes, including: identifying, by a parallel computer control system, a subset of compute nodes in the parallel computer to execute a job; selecting, by the parallel computer control system, one of the subset of compute nodes in the parallel computer as a job leader compute node; retrieving, by the job leader compute node from computer memory, an application for executing the job; and broadcasting, by the job leader to the subset of compute nodes in the parallel computer, the application for executing the job.

Efficient Thread Labeling for Monitoring Programs with Nested Parallelism

NASA Astrophysics Data System (ADS)

Ha, Ok-Kyoon; Kim, Sun-Sook; Jun, Yong-Kee

It is difficult and cumbersome to detect data races occurred in an execution of parallel programs. Any on-the-fly race detection techniques using Lamport's happened-before relation needs a thread labeling scheme for generating unique identifiers which maintain logical concurrency information for the parallel threads. NR labeling is an efficient thread labeling scheme for the fork-join program model with nested parallelism, because its efficiency depends only on the nesting depth for every fork and join operation. This paper presents an improved NR labeling, called e-NR labeling, in which every thread generates its label by inheriting the pointer to its ancestor list from the parent threads or by updating the pointer in a constant amount of time and space. This labeling is more efficient than the NR labeling, because its efficiency does not depend on the nesting depth for every fork and join operation. Some experiments were performed with OpenMP programs having nesting depths of three or four and maximum parallelisms varying from 10,000 to 1,000,000. The results show that e-NR is 5 times faster than NR labeling and 4.3 times faster than OS labeling in the average time for creating and maintaining the thread labels. In average space required for labeling, it is 3.5 times smaller than NR labeling and 3 times smaller than OS labeling.

Efficient partitioning and assignment on programs for multiprocessor execution

NASA Technical Reports Server (NTRS)

Standley, Hilda M.

1993-01-01

The general problem studied is that of segmenting or partitioning programs for distribution across a multiprocessor system. Efficient partitioning and the assignment of program elements are of great importance since the time consumed in this overhead activity may easily dominate the computation, effectively eliminating any gains made by the use of the parallelism. In this study, the partitioning of sequentially structured programs (written in FORTRAN) is evaluated. Heuristics, developed for similar applications are examined. Finally, a model for queueing networks with finite queues is developed which may be used to analyze multiprocessor system architectures with a shared memory approach to the problem of partitioning. The properties of sequentially written programs form obstacles to large scale (at the procedure or subroutine level) parallelization. Data dependencies of even the minutest nature, reflecting the sequential development of the program, severely limit parallelism. The design of heuristic algorithms is tied to the experience gained in the parallel splitting. Parallelism obtained through the physical separation of data has seen some success, especially at the data element level. Data parallelism on a grander scale requires models that accurately reflect the effects of blocking caused by finite queues. A model for the approximation of the performance of finite queueing networks is developed. This model makes use of the decomposition approach combined with the efficiency of product form solutions.

: A Scalable and Transparent System for Simulating MPI Programs

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perumalla, Kalyan S

2010-01-01

is a scalable, transparent system for experimenting with the execution of parallel programs on simulated computing platforms. The level of simulated detail can be varied for application behavior as well as for machine characteristics. Unique features of are repeatability of execution, scalability to millions of simulated (virtual) MPI ranks, scalability to hundreds of thousands of host (real) MPI ranks, portability of the system to a variety of host supercomputing platforms, and the ability to experiment with scientific applications whose source-code is available. The set of source-code interfaces supported by is being expanded to support a wider set of applications, andmore » MPI-based scientific computing benchmarks are being ported. In proof-of-concept experiments, has been successfully exercised to spawn and sustain very large-scale executions of an MPI test program given in source code form. Low slowdowns are observed, due to its use of purely discrete event style of execution, and due to the scalability and efficiency of the underlying parallel discrete event simulation engine, sik. In the largest runs, has been executed on up to 216,000 cores of a Cray XT5 supercomputer, successfully simulating over 27 million virtual MPI ranks, each virtual rank containing its own thread context, and all ranks fully synchronized by virtual time.« less

Clinical image processing engine

NASA Astrophysics Data System (ADS)

Han, Wei; Yao, Jianhua; Chen, Jeremy; Summers, Ronald

2009-02-01

Our group provides clinical image processing services to various institutes at NIH. We develop or adapt image processing programs for a variety of applications. However, each program requires a human operator to select a specific set of images and execute the program, as well as store the results appropriately for later use. To improve efficiency, we design a parallelized clinical image processing engine (CIPE) to streamline and parallelize our service. The engine takes DICOM images from a PACS server, sorts and distributes the images to different applications, multithreads the execution of applications, and collects results from the applications. The engine consists of four modules: a listener, a router, a job manager and a data manager. A template filter in XML format is defined to specify the image specification for each application. A MySQL database is created to store and manage the incoming DICOM images and application results. The engine achieves two important goals: reduce the amount of time and manpower required to process medical images, and reduce the turnaround time for responding. We tested our engine on three different applications with 12 datasets and demonstrated that the engine improved the efficiency dramatically.

Parallel processing and expert systems

NASA Technical Reports Server (NTRS)

Yan, Jerry C.; Lau, Sonie

1991-01-01

Whether it be monitoring the thermal subsystem of Space Station Freedom, or controlling the navigation of the autonomous rover on Mars, NASA missions in the 90's cannot enjoy an increased level of autonomy without the efficient use of expert systems. Merely increasing the computational speed of uniprocessors may not be able to guarantee that real time demands are met for large expert systems. Speed-up via parallel processing must be pursued alongside the optimization of sequential implementations. Prototypes of parallel expert systems have been built at universities and industrial labs in the U.S. and Japan. The state-of-the-art research in progress related to parallel execution of expert systems was surveyed. The survey is divided into three major sections: (1) multiprocessors for parallel expert systems; (2) parallel languages for symbolic computations; and (3) measurements of parallelism of expert system. Results to date indicate that the parallelism achieved for these systems is small. In order to obtain greater speed-ups, data parallelism and application parallelism must be exploited.

Highly parallel sparse Cholesky factorization

NASA Technical Reports Server (NTRS)

Gilbert, John R.; Schreiber, Robert

1990-01-01

Several fine grained parallel algorithms were developed and compared to compute the Cholesky factorization of a sparse matrix. The experimental implementations are on the Connection Machine, a distributed memory SIMD machine whose programming model conceptually supplies one processor per data element. In contrast to special purpose algorithms in which the matrix structure conforms to the connection structure of the machine, the focus is on matrices with arbitrary sparsity structure. The most promising algorithm is one whose inner loop performs several dense factorizations simultaneously on a 2-D grid of processors. Virtually any massively parallel dense factorization algorithm can be used as the key subroutine. The sparse code attains execution rates comparable to those of the dense subroutine. Although at present architectural limitations prevent the dense factorization from realizing its potential efficiency, it is concluded that a regular data parallel architecture can be used efficiently to solve arbitrarily structured sparse problems. A performance model is also presented and it is used to analyze the algorithms.

Execution time supports for adaptive scientific algorithms on distributed memory machines

NASA Technical Reports Server (NTRS)

Berryman, Harry; Saltz, Joel; Scroggs, Jeffrey

1990-01-01

Optimizations are considered that are required for efficient execution of code segments that consists of loops over distributed data structures. The PARTI (Parallel Automated Runtime Toolkit at ICASE) execution time primitives are designed to carry out these optimizations and can be used to implement a wide range of scientific algorithms on distributed memory machines. These primitives allow the user to control array mappings in a way that gives an appearance of shared memory. Computations can be based on a global index set. Primitives are used to carry out gather and scatter operations on distributed arrays. Communications patterns are derived at runtime, and the appropriate send and receive messages are automatically generated.

Execution time support for scientific programs on distributed memory machines

NASA Technical Reports Server (NTRS)

Berryman, Harry; Saltz, Joel; Scroggs, Jeffrey

1990-01-01

Optimizations are considered that are required for efficient execution of code segments that consists of loops over distributed data structures. The PARTI (Parallel Automated Runtime Toolkit at ICASE) execution time primitives are designed to carry out these optimizations and can be used to implement a wide range of scientific algorithms on distributed memory machines. These primitives allow the user to control array mappings in a way that gives an appearance of shared memory. Computations can be based on a global index set. Primitives are used to carry out gather and scatter operations on distributed arrays. Communications patterns are derived at runtime, and the appropriate send and receive messages are automatically generated.

A Hybrid Shared-Memory Parallel Max-Tree Algorithm for Extreme Dynamic-Range Images.

PubMed

Moschini, Ugo; Meijster, Arnold; Wilkinson, Michael H F

2018-03-01

Max-trees, or component trees, are graph structures that represent the connected components of an image in a hierarchical way. Nowadays, many application fields rely on images with high-dynamic range or floating point values. Efficient sequential algorithms exist to build trees and compute attributes for images of any bit depth. However, we show that the current parallel algorithms perform poorly already with integers at bit depths higher than 16 bits per pixel. We propose a parallel method combining the two worlds of flooding and merging max-tree algorithms. First, a pilot max-tree of a quantized version of the image is built in parallel using a flooding method. Later, this structure is used in a parallel leaf-to-root approach to compute efficiently the final max-tree and to drive the merging of the sub-trees computed by the threads. We present an analysis of the performance both on simulated and actual 2D images and 3D volumes. Execution times are about better than the fastest sequential algorithm and speed-up goes up to on 64 threads.

Efficient parallel architecture for highly coupled real-time linear system applications

NASA Technical Reports Server (NTRS)

Carroll, Chester C.; Homaifar, Abdollah; Barua, Soumavo

1988-01-01

A systematic procedure is developed for exploiting the parallel constructs of computation in a highly coupled, linear system application. An overall top-down design approach is adopted. Differential equations governing the application under consideration are partitioned into subtasks on the basis of a data flow analysis. The interconnected task units constitute a task graph which has to be computed in every update interval. Multiprocessing concepts utilizing parallel integration algorithms are then applied for efficient task graph execution. A simple scheduling routine is developed to handle task allocation while in the multiprocessor mode. Results of simulation and scheduling are compared on the basis of standard performance indices. Processor timing diagrams are developed on the basis of program output accruing to an optimal set of processors. Basic architectural attributes for implementing the system are discussed together with suggestions for processing element design. Emphasis is placed on flexible architectures capable of accommodating widely varying application specifics.

Efficient Parallel Video Processing Techniques on GPU: From Framework to Implementation

PubMed Central

Su, Huayou; Wen, Mei; Wu, Nan; Ren, Ju; Zhang, Chunyuan

2014-01-01

Through reorganizing the execution order and optimizing the data structure, we proposed an efficient parallel framework for H.264/AVC encoder based on massively parallel architecture. We implemented the proposed framework by CUDA on NVIDIA's GPU. Not only the compute intensive components of the H.264 encoder are parallelized but also the control intensive components are realized effectively, such as CAVLC and deblocking filter. In addition, we proposed serial optimization methods, including the multiresolution multiwindow for motion estimation, multilevel parallel strategy to enhance the parallelism of intracoding as much as possible, component-based parallel CAVLC, and direction-priority deblocking filter. More than 96% of workload of H.264 encoder is offloaded to GPU. Experimental results show that the parallel implementation outperforms the serial program by 20 times of speedup ratio and satisfies the requirement of the real-time HD encoding of 30 fps. The loss of PSNR is from 0.14 dB to 0.77 dB, when keeping the same bitrate. Through the analysis to the kernels, we found that speedup ratios of the compute intensive algorithms are proportional with the computation power of the GPU. However, the performance of the control intensive parts (CAVLC) is much related to the memory bandwidth, which gives an insight for new architecture design. PMID:24757432

Demonstration of Hadoop-GIS: A Spatial Data Warehousing System Over MapReduce

PubMed Central

Aji, Ablimit; Sun, Xiling; Vo, Hoang; Liu, Qioaling; Lee, Rubao; Zhang, Xiaodong; Saltz, Joel; Wang, Fusheng

2016-01-01

The proliferation of GPS-enabled devices, and the rapid improvement of scientific instruments have resulted in massive amounts of spatial data in the last decade. Support of high performance spatial queries on large volumes data has become increasingly important in numerous fields, which requires a scalable and efficient spatial data warehousing solution as existing approaches exhibit scalability limitations and efficiency bottlenecks for large scale spatial applications. In this demonstration, we present Hadoop-GIS – a scalable and high performance spatial query system over MapReduce. Hadoop-GIS provides an efficient spatial query engine to process spatial queries, data and space based partitioning, and query pipelines that parallelize queries implicitly on MapReduce. Hadoop-GIS also provides an expressive, SQL-like spatial query language for workload specification. We will demonstrate how spatial queries are expressed in spatially extended SQL queries, and submitted through a command line/web interface for execution. Parallel to our system demonstration, we explain the system architecture and details on how queries are translated to MapReduce operators, optimized, and executed on Hadoop. In addition, we will showcase how the system can be used to support two representative real world use cases: large scale pathology analytical imaging, and geo-spatial data warehousing. PMID:27617325

A new parallel-vector finite element analysis software on distributed-memory computers

NASA Technical Reports Server (NTRS)

Qin, Jiangning; Nguyen, Duc T.

1993-01-01

A new parallel-vector finite element analysis software package MPFEA (Massively Parallel-vector Finite Element Analysis) is developed for large-scale structural analysis on massively parallel computers with distributed-memory. MPFEA is designed for parallel generation and assembly of the global finite element stiffness matrices as well as parallel solution of the simultaneous linear equations, since these are often the major time-consuming parts of a finite element analysis. Block-skyline storage scheme along with vector-unrolling techniques are used to enhance the vector performance. Communications among processors are carried out concurrently with arithmetic operations to reduce the total execution time. Numerical results on the Intel iPSC/860 computers (such as the Intel Gamma with 128 processors and the Intel Touchstone Delta with 512 processors) are presented, including an aircraft structure and some very large truss structures, to demonstrate the efficiency and accuracy of MPFEA.

Solving very large, sparse linear systems on mesh-connected parallel computers

NASA Technical Reports Server (NTRS)

Opsahl, Torstein; Reif, John

1987-01-01

The implementation of Pan and Reif's Parallel Nested Dissection (PND) algorithm on mesh connected parallel computers is described. This is the first known algorithm that allows very large, sparse linear systems of equations to be solved efficiently in polylog time using a small number of processors. How the processor bound of PND can be matched to the number of processors available on a given parallel computer by slowing down the algorithm by constant factors is described. Also, for the important class of problems where G(A) is a grid graph, a unique memory mapping that reduces the inter-processor communication requirements of PND to those that can be executed on mesh connected parallel machines is detailed. A description of an implementation on the Goodyear Massively Parallel Processor (MPP), located at Goddard is given. Also, a detailed discussion of data mappings and performance issues is given.

Support for Debugging Automatically Parallelized Programs

NASA Technical Reports Server (NTRS)

Jost, Gabriele; Hood, Robert; Biegel, Bryan (Technical Monitor)

2001-01-01

We describe a system that simplifies the process of debugging programs produced by computer-aided parallelization tools. The system uses relative debugging techniques to compare serial and parallel executions in order to show where the computations begin to differ. If the original serial code is correct, errors due to parallelization will be isolated by the comparison. One of the primary goals of the system is to minimize the effort required of the user. To that end, the debugging system uses information produced by the parallelization tool to drive the comparison process. In particular the debugging system relies on the parallelization tool to provide information about where variables may have been modified and how arrays are distributed across multiple processes. User effort is also reduced through the use of dynamic instrumentation. This allows us to modify the program execution without changing the way the user builds the executable. The use of dynamic instrumentation also permits us to compare the executions in a fine-grained fashion and only involve the debugger when a difference has been detected. This reduces the overhead of executing instrumentation.

Relative Debugging of Automatically Parallelized Programs

NASA Technical Reports Server (NTRS)

Jost, Gabriele; Hood, Robert; Biegel, Bryan (Technical Monitor)

2002-01-01

We describe a system that simplifies the process of debugging programs produced by computer-aided parallelization tools. The system uses relative debugging techniques to compare serial and parallel executions in order to show where the computations begin to differ. If the original serial code is correct, errors due to parallelization will be isolated by the comparison. One of the primary goals of the system is to minimize the effort required of the user. To that end, the debugging system uses information produced by the parallelization tool to drive the comparison process. In particular, the debugging system relies on the parallelization tool to provide information about where variables may have been modified and how arrays are distributed across multiple processes. User effort is also reduced through the use of dynamic instrumentation. This allows us to modify, the program execution with out changing the way the user builds the executable. The use of dynamic instrumentation also permits us to compare the executions in a fine-grained fashion and only involve the debugger when a difference has been detected. This reduces the overhead of executing instrumentation.

Parallel multi-join query optimization algorithm for distributed sensor network in the internet of things

NASA Astrophysics Data System (ADS)

Zheng, Yan

2015-03-01

Internet of things (IoT), focusing on providing users with information exchange and intelligent control, attracts a lot of attention of researchers from all over the world since the beginning of this century. IoT is consisted of large scale of sensor nodes and data processing units, and the most important features of IoT can be illustrated as energy confinement, efficient communication and high redundancy. With the sensor nodes increment, the communication efficiency and the available communication band width become bottle necks. Many research work is based on the instance which the number of joins is less. However, it is not proper to the increasing multi-join query in whole internet of things. To improve the communication efficiency between parallel units in the distributed sensor network, this paper proposed parallel query optimization algorithm based on distribution attributes cost graph. The storage information relations and the network communication cost are considered in this algorithm, and an optimized information changing rule is established. The experimental result shows that the algorithm has good performance, and it would effectively use the resource of each node in the distributed sensor network. Therefore, executive efficiency of multi-join query between different nodes could be improved.

Parallel and Efficient Sensitivity Analysis of Microscopy Image Segmentation Workflows in Hybrid Systems

PubMed Central

Barreiros, Willian; Teodoro, George; Kurc, Tahsin; Kong, Jun; Melo, Alba C. M. A.; Saltz, Joel

2017-01-01

We investigate efficient sensitivity analysis (SA) of algorithms that segment and classify image features in a large dataset of high-resolution images. Algorithm SA is the process of evaluating variations of methods and parameter values to quantify differences in the output. A SA can be very compute demanding because it requires re-processing the input dataset several times with different parameters to assess variations in output. In this work, we introduce strategies to efficiently speed up SA via runtime optimizations targeting distributed hybrid systems and reuse of computations from runs with different parameters. We evaluate our approach using a cancer image analysis workflow on a hybrid cluster with 256 nodes, each with an Intel Phi and a dual socket CPU. The SA attained a parallel efficiency of over 90% on 256 nodes. The cooperative execution using the CPUs and the Phi available in each node with smart task assignment strategies resulted in an additional speedup of about 2×. Finally, multi-level computation reuse lead to an additional speedup of up to 2.46× on the parallel version. The level of performance attained with the proposed optimizations will allow the use of SA in large-scale studies. PMID:29081725

Long Read Alignment with Parallel MapReduce Cloud Platform

PubMed Central

Al-Absi, Ahmed Abdulhakim; Kang, Dae-Ki

2015-01-01

Genomic sequence alignment is an important technique to decode genome sequences in bioinformatics. Next-Generation Sequencing technologies produce genomic data of longer reads. Cloud platforms are adopted to address the problems arising from storage and analysis of large genomic data. Existing genes sequencing tools for cloud platforms predominantly consider short read gene sequences and adopt the Hadoop MapReduce framework for computation. However, serial execution of map and reduce phases is a problem in such systems. Therefore, in this paper, we introduce Burrows-Wheeler Aligner's Smith-Waterman Alignment on Parallel MapReduce (BWASW-PMR) cloud platform for long sequence alignment. The proposed cloud platform adopts a widely accepted and accurate BWA-SW algorithm for long sequence alignment. A custom MapReduce platform is developed to overcome the drawbacks of the Hadoop framework. A parallel execution strategy of the MapReduce phases and optimization of Smith-Waterman algorithm are considered. Performance evaluation results exhibit an average speed-up of 6.7 considering BWASW-PMR compared with the state-of-the-art Bwasw-Cloud. An average reduction of 30% in the map phase makespan is reported across all experiments comparing BWASW-PMR with Bwasw-Cloud. Optimization of Smith-Waterman results in reducing the execution time by 91.8%. The experimental study proves the efficiency of BWASW-PMR for aligning long genomic sequences on cloud platforms. PMID:26839887

GaAs Supercomputing: Architecture, Language, And Algorithms For Image Processing

NASA Astrophysics Data System (ADS)

Johl, John T.; Baker, Nick C.

1988-10-01

The application of high-speed GaAs processors in a parallel system matches the demanding computational requirements of image processing. The architecture of the McDonnell Douglas Astronautics Company (MDAC) vector processor is described along with the algorithms and language translator. Most image and signal processing algorithms can utilize parallel processing and show a significant performance improvement over sequential versions. The parallelization performed by this system is within each vector instruction. Since each vector has many elements, each requiring some computation, useful concurrent arithmetic operations can easily be performed. Balancing the memory bandwidth with the computation rate of the processors is an important design consideration for high efficiency and utilization. The architecture features a bus-based execution unit consisting of four to eight 32-bit GaAs RISC microprocessors running at a 200 MHz clock rate for a peak performance of 1.6 BOPS. The execution unit is connected to a vector memory with three buses capable of transferring two input words and one output word every 10 nsec. The address generators inside the vector memory perform different vector addressing modes and feed the data to the execution unit. The functions discussed in this paper include basic MATRIX OPERATIONS, 2-D SPATIAL CONVOLUTION, HISTOGRAM, and FFT. For each of these algorithms, assembly language programs were run on a behavioral model of the system to obtain performance figures.

Long Read Alignment with Parallel MapReduce Cloud Platform.

PubMed

Al-Absi, Ahmed Abdulhakim; Kang, Dae-Ki

2015-01-01

Genomic sequence alignment is an important technique to decode genome sequences in bioinformatics. Next-Generation Sequencing technologies produce genomic data of longer reads. Cloud platforms are adopted to address the problems arising from storage and analysis of large genomic data. Existing genes sequencing tools for cloud platforms predominantly consider short read gene sequences and adopt the Hadoop MapReduce framework for computation. However, serial execution of map and reduce phases is a problem in such systems. Therefore, in this paper, we introduce Burrows-Wheeler Aligner's Smith-Waterman Alignment on Parallel MapReduce (BWASW-PMR) cloud platform for long sequence alignment. The proposed cloud platform adopts a widely accepted and accurate BWA-SW algorithm for long sequence alignment. A custom MapReduce platform is developed to overcome the drawbacks of the Hadoop framework. A parallel execution strategy of the MapReduce phases and optimization of Smith-Waterman algorithm are considered. Performance evaluation results exhibit an average speed-up of 6.7 considering BWASW-PMR compared with the state-of-the-art Bwasw-Cloud. An average reduction of 30% in the map phase makespan is reported across all experiments comparing BWASW-PMR with Bwasw-Cloud. Optimization of Smith-Waterman results in reducing the execution time by 91.8%. The experimental study proves the efficiency of BWASW-PMR for aligning long genomic sequences on cloud platforms.

Online System for Faster Multipoint Linkage Analysis via Parallel Execution on Thousands of Personal Computers

PubMed Central

Silberstein, M.; Tzemach, A.; Dovgolevsky, N.; Fishelson, M.; Schuster, A.; Geiger, D.

2006-01-01

Computation of LOD scores is a valuable tool for mapping disease-susceptibility genes in the study of Mendelian and complex diseases. However, computation of exact multipoint likelihoods of large inbred pedigrees with extensive missing data is often beyond the capabilities of a single computer. We present a distributed system called “SUPERLINK-ONLINE,” for the computation of multipoint LOD scores of large inbred pedigrees. It achieves high performance via the efficient parallelization of the algorithms in SUPERLINK, a state-of-the-art serial program for these tasks, and through the use of the idle cycles of thousands of personal computers. The main algorithmic challenge has been to efficiently split a large task for distributed execution in a highly dynamic, nondedicated running environment. Notably, the system is available online, which allows computationally intensive analyses to be performed with no need for either the installation of software or the maintenance of a complicated distributed environment. As the system was being developed, it was extensively tested by collaborating medical centers worldwide on a variety of real data sets, some of which are presented in this article. PMID:16685644

SCaLeM: A Framework for Characterizing and Analyzing Execution Models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chavarría-Miranda, Daniel; Manzano Franco, Joseph B.; Krishnamoorthy, Sriram

2014-10-13

As scalable parallel systems evolve towards more complex nodes with many-core architectures and larger trans-petascale & upcoming exascale deployments, there is a need to understand, characterize and quantify the underlying execution models being used on such systems. Execution models are a conceptual layer between applications & algorithms and the underlying parallel hardware and systems software on which those applications run. This paper presents the SCaLeM (Synchronization, Concurrency, Locality, Memory) framework for characterizing and execution models. SCaLeM consists of three basic elements: attributes, compositions and mapping of these compositions to abstract parallel systems. The fundamental Synchronization, Concurrency, Locality and Memory attributesmore » are used to characterize each execution model, while the combinations of those attributes in the form of compositions are used to describe the primitive operations of the execution model. The mapping of the execution model’s primitive operations described by compositions, to an underlying abstract parallel system can be evaluated quantitatively to determine its effectiveness. Finally, SCaLeM also enables the representation and analysis of applications in terms of execution models, for the purpose of evaluating the effectiveness of such mapping.« less

Performance enhancement of various real-time image processing techniques via speculative execution

NASA Astrophysics Data System (ADS)

Younis, Mohamed F.; Sinha, Purnendu; Marlowe, Thomas J.; Stoyenko, Alexander D.

1996-03-01

In real-time image processing, an application must satisfy a set of timing constraints while ensuring the semantic correctness of the system. Because of the natural structure of digital data, pure data and task parallelism have been used extensively in real-time image processing to accelerate the handling time of image data. These types of parallelism are based on splitting the execution load performed by a single processor across multiple nodes. However, execution of all parallel threads is mandatory for correctness of the algorithm. On the other hand, speculative execution is an optimistic execution of part(s) of the program based on assumptions on program control flow or variable values. Rollback may be required if the assumptions turn out to be invalid. Speculative execution can enhance average, and sometimes worst-case, execution time. In this paper, we target various image processing techniques to investigate applicability of speculative execution. We identify opportunities for safe and profitable speculative execution in image compression, edge detection, morphological filters, and blob recognition.

Application of parallelized software architecture to an autonomous ground vehicle

NASA Astrophysics Data System (ADS)

Shakya, Rahul; Wright, Adam; Shin, Young Ho; Momin, Orko; Petkovsek, Steven; Wortman, Paul; Gautam, Prasanna; Norton, Adam

2011-01-01

This paper presents improvements made to Q, an autonomous ground vehicle designed to participate in the Intelligent Ground Vehicle Competition (IGVC). For the 2010 IGVC, Q was upgraded with a new parallelized software architecture and a new vision processor. Improvements were made to the power system reducing the number of batteries required for operation from six to one. In previous years, a single state machine was used to execute the bulk of processing activities including sensor interfacing, data processing, path planning, navigation algorithms and motor control. This inefficient approach led to poor software performance and made it difficult to maintain or modify. For IGVC 2010, the team implemented a modular parallel architecture using the National Instruments (NI) LabVIEW programming language. The new architecture divides all the necessary tasks - motor control, navigation, sensor data collection, etc. into well-organized components that execute in parallel, providing considerable flexibility and facilitating efficient use of processing power. Computer vision is used to detect white lines on the ground and determine their location relative to the robot. With the new vision processor and some optimization of the image processing algorithm used last year, two frames can be acquired and processed in 70ms. With all these improvements, Q placed 2nd in the autonomous challenge.

Analysis of multigrid methods on massively parallel computers: Architectural implications

NASA Technical Reports Server (NTRS)

Matheson, Lesley R.; Tarjan, Robert E.

1993-01-01

We study the potential performance of multigrid algorithms running on massively parallel computers with the intent of discovering whether presently envisioned machines will provide an efficient platform for such algorithms. We consider the domain parallel version of the standard V cycle algorithm on model problems, discretized using finite difference techniques in two and three dimensions on block structured grids of size 10(exp 6) and 10(exp 9), respectively. Our models of parallel computation were developed to reflect the computing characteristics of the current generation of massively parallel multicomputers. These models are based on an interconnection network of 256 to 16,384 message passing, 'workstation size' processors executing in an SPMD mode. The first model accomplishes interprocessor communications through a multistage permutation network. The communication cost is a logarithmic function which is similar to the costs in a variety of different topologies. The second model allows single stage communication costs only. Both models were designed with information provided by machine developers and utilize implementation derived parameters. With the medium grain parallelism of the current generation and the high fixed cost of an interprocessor communication, our analysis suggests an efficient implementation requires the machine to support the efficient transmission of long messages, (up to 1000 words) or the high initiation cost of a communication must be significantly reduced through an alternative optimization technique. Furthermore, with variable length message capability, our analysis suggests the low diameter multistage networks provide little or no advantage over a simple single stage communications network.

Fencing data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-06-02

Fencing data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task; the compute nodes coupled for data communications through the PAMI and through data communications resources including at least one segment of shared random access memory; including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers through a segment of shared memory; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.

Fencing data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-06-09

Fencing data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task; the compute nodes coupled for data communications through the PAMI and through data communications resources including at least one segment of shared random access memory; including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers through a segment of shared memory; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.

Fencing data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-08-11

Fencing data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint comprising a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes coupled for data communications through the PAMI and through data communications resources including a deterministic data communications network, including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.

Fencing data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-06-30

Fencing data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint comprising a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes coupled for data communications through the PAMI and through data communications resources including a deterministic data communications network, including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.

Parallel Newton-Krylov-Schwarz algorithms for the transonic full potential equation

NASA Technical Reports Server (NTRS)

Cai, Xiao-Chuan; Gropp, William D.; Keyes, David E.; Melvin, Robin G.; Young, David P.

1996-01-01

We study parallel two-level overlapping Schwarz algorithms for solving nonlinear finite element problems, in particular, for the full potential equation of aerodynamics discretized in two dimensions with bilinear elements. The overall algorithm, Newton-Krylov-Schwarz (NKS), employs an inexact finite-difference Newton method and a Krylov space iterative method, with a two-level overlapping Schwarz method as a preconditioner. We demonstrate that NKS, combined with a density upwinding continuation strategy for problems with weak shocks, is robust and, economical for this class of mixed elliptic-hyperbolic nonlinear partial differential equations, with proper specification of several parameters. We study upwinding parameters, inner convergence tolerance, coarse grid density, subdomain overlap, and the level of fill-in in the incomplete factorization, and report their effect on numerical convergence rate, overall execution time, and parallel efficiency on a distributed-memory parallel computer.

Constant time worker thread allocation via configuration caching

DOE Office of Scientific and Technical Information (OSTI.GOV)

Eichenberger, Alexandre E; O'Brien, John K. P.

Mechanisms are provided for allocating threads for execution of a parallel region of code. A request for allocation of worker threads to execute the parallel region of code is received from a master thread. Cached thread allocation information identifying prior thread allocations that have been performed for the master thread are accessed. Worker threads are allocated to the master thread based on the cached thread allocation information. The parallel region of code is executed using the allocated worker threads.

Exploiting Vector and Multicore Parallelsim for Recursive, Data- and Task-Parallel Programs

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ren, Bin; Krishnamoorthy, Sriram; Agrawal, Kunal

Modern hardware contains parallel execution resources that are well-suited for data-parallelism-vector units-and task parallelism-multicores. However, most work on parallel scheduling focuses on one type of hardware or the other. In this work, we present a scheduling framework that allows for a unified treatment of task- and data-parallelism. Our key insight is an abstraction, task blocks, that uniformly handles data-parallel iterations and task-parallel tasks, allowing them to be scheduled on vector units or executed independently as multicores. Our framework allows us to define schedulers that can dynamically select between executing task- blocks on vector units or multicores. We show that thesemore » schedulers are asymptotically optimal, and deliver the maximum amount of parallelism available in computation trees. To evaluate our schedulers, we develop program transformations that can convert mixed data- and task-parallel pro- grams into task block-based programs. Using a prototype instantiation of our scheduling framework, we show that, on an 8-core system, we can simultaneously exploit vector and multicore parallelism to achieve 14×-108× speedup over sequential baselines.« less

Endpoint-based parallel data processing in a parallel active messaging interface of a parallel computer

DOEpatents

Archer, Charles J; Blocksome, Michael E; Ratterman, Joseph D; Smith, Brian E

2014-02-11

Endpoint-based parallel data processing in a parallel active messaging interface ('PAMI') of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes coupled for data communications through the PAMI, including establishing a data communications geometry, the geometry specifying, for tasks representing processes of execution of the parallel application, a set of endpoints that are used in collective operations of the PAMI including a plurality of endpoints for one of the tasks; receiving in endpoints of the geometry an instruction for a collective operation; and executing the instruction for a collective opeartion through the endpoints in dependence upon the geometry, including dividing data communications operations among the plurality of endpoints for one of the tasks.

Endpoint-based parallel data processing in a parallel active messaging interface of a parallel computer

DOEpatents

Archer, Charles J.; Blocksome, Michael A.; Ratterman, Joseph D.; Smith, Brian E.

2014-08-12

Endpoint-based parallel data processing in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes coupled for data communications through the PAMI, including establishing a data communications geometry, the geometry specifying, for tasks representing processes of execution of the parallel application, a set of endpoints that are used in collective operations of the PAMI including a plurality of endpoints for one of the tasks; receiving in endpoints of the geometry an instruction for a collective operation; and executing the instruction for a collective operation through the endpoints in dependence upon the geometry, including dividing data communications operations among the plurality of endpoints for one of the tasks.

Optimization of the coherence function estimation for multi-core central processing unit

NASA Astrophysics Data System (ADS)

Cheremnov, A. G.; Faerman, V. A.; Avramchuk, V. S.

2017-02-01

The paper considers use of parallel processing on multi-core central processing unit for optimization of the coherence function evaluation arising in digital signal processing. Coherence function along with other methods of spectral analysis is commonly used for vibration diagnosis of rotating machinery and its particular nodes. An algorithm is given for the function evaluation for signals represented with digital samples. The algorithm is analyzed for its software implementation and computational problems. Optimization measures are described, including algorithmic, architecture and compiler optimization, their results are assessed for multi-core processors from different manufacturers. Thus, speeding-up of the parallel execution with respect to sequential execution was studied and results are presented for Intel Core i7-4720HQ и AMD FX-9590 processors. The results show comparatively high efficiency of the optimization measures taken. In particular, acceleration indicators and average CPU utilization have been significantly improved, showing high degree of parallelism of the constructed calculating functions. The developed software underwent state registration and will be used as a part of a software and hardware solution for rotating machinery fault diagnosis and pipeline leak location with acoustic correlation method.

Parallel processing for scientific computations

NASA Technical Reports Server (NTRS)

Alkhatib, Hasan S.

1991-01-01

The main contribution of the effort in the last two years is the introduction of the MOPPS system. After doing extensive literature search, we introduced the system which is described next. MOPPS employs a new solution to the problem of managing programs which solve scientific and engineering applications on a distributed processing environment. Autonomous computers cooperate efficiently in solving large scientific problems with this solution. MOPPS has the advantage of not assuming the presence of any particular network topology or configuration, computer architecture, or operating system. It imposes little overhead on network and processor resources while efficiently managing programs concurrently. The core of MOPPS is an intelligent program manager that builds a knowledge base of the execution performance of the parallel programs it is managing under various conditions. The manager applies this knowledge to improve the performance of future runs. The program manager learns from experience.

Architecture and design of a 500-MHz gallium-arsenide processing element for a parallel supercomputer

NASA Technical Reports Server (NTRS)

Fouts, Douglas J.; Butner, Steven E.

1991-01-01

The design of the processing element of GASP, a GaAs supercomputer with a 500-MHz instruction issue rate and 1-GHz subsystem clocks, is presented. The novel, functionally modular, block data flow architecture of GASP is described. The architecture and design of a GASP processing element is then presented. The processing element (PE) is implemented in a hybrid semiconductor module with 152 custom GaAs ICs of eight different types. The effects of the implementation technology on both the system-level architecture and the PE design are discussed. SPICE simulations indicate that parts of the PE are capable of being clocked at 1 GHz, while the rest of the PE uses a 500-MHz clock. The architecture utilizes data flow techniques at a program block level, which allows efficient execution of parallel programs while maintaining reasonably good performance on sequential programs. A simulation study of the architecture indicates that an instruction execution rate of over 30,000 MIPS can be attained with 65 PEs.

Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems

NASA Technical Reports Server (NTRS)

Biswas, Rupak; Oliker, Leonid; Sohn, Andrew

1996-01-01

Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load imbalance among processors on a parallel machine. This paper describes the parallel implementation of a tetrahedral mesh adaption scheme and a new global load balancing method. A heuristic remapping algorithm is presented that assigns partitions to processors such that the redistribution cost is minimized. Results indicate that the parallel performance of the mesh adaption code depends on the nature of the adaption region and show a 35.5X speedup on 64 processors of an SP2 when 35% of the mesh is randomly adapted. For large-scale scientific computations, our load balancing strategy gives almost a sixfold reduction in solver execution times over non-balanced loads. Furthermore, our heuristic remapper yields processor assignments that are less than 3% off the optimal solutions but requires only 1% of the computational time.

Performance analysis of a parallel Monte Carlo code for simulating solar radiative transfer in cloudy atmospheres using CUDA-enabled NVIDIA GPU

NASA Astrophysics Data System (ADS)

Russkova, Tatiana V.

2017-11-01

One tool to improve the performance of Monte Carlo methods for numerical simulation of light transport in the Earth's atmosphere is the parallel technology. A new algorithm oriented to parallel execution on the CUDA-enabled NVIDIA graphics processor is discussed. The efficiency of parallelization is analyzed on the basis of calculating the upward and downward fluxes of solar radiation in both a vertically homogeneous and inhomogeneous models of the atmosphere. The results of testing the new code under various atmospheric conditions including continuous singlelayered and multilayered clouds, and selective molecular absorption are presented. The results of testing the code using video cards with different compute capability are analyzed. It is shown that the changeover of computing from conventional PCs to the architecture of graphics processors gives more than a hundredfold increase in performance and fully reveals the capabilities of the technology used.

Parallelization of implicit finite difference schemes in computational fluid dynamics

NASA Technical Reports Server (NTRS)

Decker, Naomi H.; Naik, Vijay K.; Nicoules, Michel

1990-01-01

Implicit finite difference schemes are often the preferred numerical schemes in computational fluid dynamics, requiring less stringent stability bounds than the explicit schemes. Each iteration in an implicit scheme involves global data dependencies in the form of second and higher order recurrences. Efficient parallel implementations of such iterative methods are considerably more difficult and non-intuitive. The parallelization of the implicit schemes that are used for solving the Euler and the thin layer Navier-Stokes equations and that require inversions of large linear systems in the form of block tri-diagonal and/or block penta-diagonal matrices is discussed. Three-dimensional cases are emphasized and schemes that minimize the total execution time are presented. Partitioning and scheduling schemes for alleviating the effects of the global data dependencies are described. An analysis of the communication and the computation aspects of these methods is presented. The effect of the boundary conditions on the parallel schemes is also discussed.

A Parallel Pipelined Renderer for the Time-Varying Volume Data

NASA Technical Reports Server (NTRS)

Chiueh, Tzi-Cker; Ma, Kwan-Liu

1997-01-01

This paper presents a strategy for efficiently rendering time-varying volume data sets on a distributed-memory parallel computer. Time-varying volume data take large storage space and visualizing them requires reading large files continuously or periodically throughout the course of the visualization process. Instead of using all the processors to collectively render one volume at a time, a pipelined rendering process is formed by partitioning processors into groups to render multiple volumes concurrently. In this way, the overall rendering time may be greatly reduced because the pipelined rendering tasks are overlapped with the I/O required to load each volume into a group of processors; moreover, parallelization overhead may be reduced as a result of partitioning the processors. We modify an existing parallel volume renderer to exploit various levels of rendering parallelism and to study how the partitioning of processors may lead to optimal rendering performance. Two factors which are important to the overall execution time are re-source utilization efficiency and pipeline startup latency. The optimal partitioning configuration is the one that balances these two factors. Tests on Intel Paragon computers show that in general optimal partitionings do exist for a given rendering task and result in 40-50% saving in overall rendering time.

A Fault Oblivious Extreme-Scale Execution Environment

DOE Office of Scientific and Technical Information (OSTI.GOV)

McKie, Jim

The FOX project, funded under the ASCR X-stack I program, developed systems software and runtime libraries for a new approach to the data and work distribution for massively parallel, fault oblivious application execution. Our work was motivated by the premise that exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today’s machines. To deliver the capability of exascale hardware, the systems software must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massivemore » data analysis in a highly unreliable hardware environment with billions of threads of execution. Our OS research has prototyped new methods to provide efficient resource sharing, synchronization, and protection in a many-core compute node. We have experimented with alternative task/dataflow programming models and shown scalability in some cases to hundreds of thousands of cores. Much of our software is in active development through open source projects. Concepts from FOX are being pursued in next generation exascale operating systems. Our OS work focused on adaptive, application tailored OS services optimized for multi → many core processors. We developed a new operating system NIX that supports role-based allocation of cores to processes which was released to open source. We contributed to the IBM FusedOS project, which promoted the concept of latency-optimized and throughput-optimized cores. We built a task queue library based on distributed, fault tolerant key-value store and identified scaling issues. A second fault tolerant task parallel library was developed, based on the Linda tuple space model, that used low level interconnect primitives for optimized communication. We designed fault tolerance mechanisms for task parallel computations employing work stealing for load balancing that scaled to the largest existing supercomputers. Finally, we implemented the Elastic Building Blocks runtime, a library to manage object-oriented distributed software components. To support the research, we won two INCITE awards for time on Intrepid (BG/P) and Mira (BG/Q). Much of our work has had impact in the OS and runtime community through the ASCR Exascale OS/R workshop and report, leading to the research agenda of the Exascale OS/R program. Our project was, however, also affected by attrition of multiple PIs. While the PIs continued to participate and offer guidance as time permitted, losing these key individuals was unfortunate both for the project and for the DOE HPC community.« less

Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2013-09-03

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A; Mamidala, Amith R

2014-02-11

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

Fencing network direct memory access data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-07-07

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to a deterministic data communications network through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and the deterministic data communications network; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

Fencing network direct memory access data transfers in a parallel active messaging interface of a parallel computer

DOEpatents

Blocksome, Michael A.; Mamidala, Amith R.

2015-07-14

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to a deterministic data communications network through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and the deterministic data communications network; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

Efficient Irregular Wavefront Propagation Algorithms on Hybrid CPU-GPU Machines

PubMed Central

Teodoro, George; Pan, Tony; Kurc, Tahsin; Kong, Jun; Cooper, Lee; Saltz, Joel

2013-01-01

We address the problem of efficient execution of a computation pattern, referred to here as the irregular wavefront propagation pattern (IWPP), on hybrid systems with multiple CPUs and GPUs. The IWPP is common in several image processing operations. In the IWPP, data elements in the wavefront propagate waves to their neighboring elements on a grid if a propagation condition is satisfied. Elements receiving the propagated waves become part of the wavefront. This pattern results in irregular data accesses and computations. We develop and evaluate strategies for efficient computation and propagation of wavefronts using a multi-level queue structure. This queue structure improves the utilization of fast memories in a GPU and reduces synchronization overheads. We also develop a tile-based parallelization strategy to support execution on multiple CPUs and GPUs. We evaluate our approaches on a state-of-the-art GPU accelerated machine (equipped with 3 GPUs and 2 multicore CPUs) using the IWPP implementations of two widely used image processing operations: morphological reconstruction and euclidean distance transform. Our results show significant performance improvements on GPUs. The use of multiple CPUs and GPUs cooperatively attains speedups of 50× and 85× with respect to single core CPU executions for morphological reconstruction and euclidean distance transform, respectively. PMID:23908562

Multi-thread parallel algorithm for reconstructing 3D large-scale porous structures

NASA Astrophysics Data System (ADS)

Ju, Yang; Huang, Yaohui; Zheng, Jiangtao; Qian, Xu; Xie, Heping; Zhao, Xi

2017-04-01

Geomaterials inherently contain many discontinuous, multi-scale, geometrically irregular pores, forming a complex porous structure that governs their mechanical and transport properties. The development of an efficient reconstruction method for representing porous structures can significantly contribute toward providing a better understanding of the governing effects of porous structures on the properties of porous materials. In order to improve the efficiency of reconstructing large-scale porous structures, a multi-thread parallel scheme was incorporated into the simulated annealing reconstruction method. In the method, four correlation functions, which include the two-point probability function, the linear-path functions for the pore phase and the solid phase, and the fractal system function for the solid phase, were employed for better reproduction of the complex well-connected porous structures. In addition, a random sphere packing method and a self-developed pre-conditioning method were incorporated to cast the initial reconstructed model and select independent interchanging pairs for parallel multi-thread calculation, respectively. The accuracy of the proposed algorithm was evaluated by examining the similarity between the reconstructed structure and a prototype in terms of their geometrical, topological, and mechanical properties. Comparisons of the reconstruction efficiency of porous models with various scales indicated that the parallel multi-thread scheme significantly shortened the execution time for reconstruction of a large-scale well-connected porous model compared to a sequential single-thread procedure.

PLUM: Parallel Load Balancing for Unstructured Adaptive Meshes. Degree awarded by Colorado Univ.

NASA Technical Reports Server (NTRS)

Oliker, Leonid

1998-01-01

Dynamic mesh adaption on unstructured grids is a powerful tool for computing large-scale problems that require grid modifications to efficiently resolve solution features. By locally refining and coarsening the mesh to capture physical phenomena of interest, such procedures make standard computational methods more cost effective. Unfortunately, an efficient parallel implementation of these adaptive methods is rather difficult to achieve, primarily due to the load imbalance created by the dynamically-changing nonuniform grid. This requires significant communication at runtime, leading to idle processors and adversely affecting the total execution time. Nonetheless, it is generally thought that unstructured adaptive- grid techniques will constitute a significant fraction of future high-performance supercomputing. Various dynamic load balancing methods have been reported to date; however, most of them either lack a global view of loads across processors or do not apply their techniques to realistic large-scale applications.

An Efficient Algorithm for Mapping Imaging Data to 3D Unstructured Grids in Computational Biomechanics

DOE Office of Scientific and Technical Information (OSTI.GOV)

Einstein, Daniel R.; Kuprat, Andrew P.; Jiao, Xiangmin

2013-01-01

Geometries for organ scale and multiscale simulations of organ function are now routinely derived from imaging data. However, medical images may also contain spatially heterogeneous information other than geometry that are relevant to such simulations either as initial conditions or in the form of model parameters. In this manuscript, we present an algorithm for the efficient and robust mapping of such data to imaging based unstructured polyhedral grids in parallel. We then illustrate the application of our mapping algorithm to three different mapping problems: 1) the mapping of MRI diffusion tensor data to an unstuctured ventricular grid; 2) the mappingmore » of serial cyro-section histology data to an unstructured mouse brain grid; and 3) the mapping of CT-derived volumetric strain data to an unstructured multiscale lung grid. Execution times and parallel performance are reported for each case.« less

DOE Office of Scientific and Technical Information (OSTI.GOV)

Luszczek, Piotr R; Tomov, Stanimire Z; Dongarra, Jack J

We present an efficient and scalable programming model for the development of linear algebra in heterogeneous multi-coprocessor environments. The model incorporates some of the current best design and implementation practices for the heterogeneous acceleration of dense linear algebra (DLA). Examples are given as the basis for solving linear systems' algorithms - the LU, QR, and Cholesky factorizations. To generate the extreme level of parallelism needed for the efficient use of coprocessors, algorithms of interest are redesigned and then split into well-chosen computational tasks. The tasks execution is scheduled over the computational components of a hybrid system of multi-core CPUs andmore » coprocessors using a light-weight runtime system. The use of lightweight runtime systems keeps scheduling overhead low, while enabling the expression of parallelism through otherwise sequential code. This simplifies the development efforts and allows the exploration of the unique strengths of the various hardware components.« less

Parallel evolutionary computation in bioinformatics applications.

PubMed

Pinho, Jorge; Sobral, João Luis; Rocha, Miguel

2013-05-01

A large number of optimization problems within the field of Bioinformatics require methods able to handle its inherent complexity (e.g. NP-hard problems) and also demand increased computational efforts. In this context, the use of parallel architectures is a necessity. In this work, we propose ParJECoLi, a Java based library that offers a large set of metaheuristic methods (such as Evolutionary Algorithms) and also addresses the issue of its efficient execution on a wide range of parallel architectures. The proposed approach focuses on the easiness of use, making the adaptation to distinct parallel environments (multicore, cluster, grid) transparent to the user. Indeed, this work shows how the development of the optimization library can proceed independently of its adaptation for several architectures, making use of Aspect-Oriented Programming. The pluggable nature of parallelism related modules allows the user to easily configure its environment, adding parallelism modules to the base source code when needed. The performance of the platform is validated with two case studies within biological model optimization. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Distributed Parallel Processing and Dynamic Load Balancing Techniques for Multidisciplinary High Speed Aircraft Design

NASA Technical Reports Server (NTRS)

Krasteva, Denitza T.

1998-01-01

Multidisciplinary design optimization (MDO) for large-scale engineering problems poses many challenges (e.g., the design of an efficient concurrent paradigm for global optimization based on disciplinary analyses, expensive computations over vast data sets, etc.) This work focuses on the application of distributed schemes for massively parallel architectures to MDO problems, as a tool for reducing computation time and solving larger problems. The specific problem considered here is configuration optimization of a high speed civil transport (HSCT), and the efficient parallelization of the embedded paradigm for reasonable design space identification. Two distributed dynamic load balancing techniques (random polling and global round robin with message combining) and two necessary termination detection schemes (global task count and token passing) were implemented and evaluated in terms of effectiveness and scalability to large problem sizes and a thousand processors. The effect of certain parameters on execution time was also inspected. Empirical results demonstrated stable performance and effectiveness for all schemes, and the parametric study showed that the selected algorithmic parameters have a negligible effect on performance.

Geospatial Applications on Different Parallel and Distributed Systems in enviroGRIDS Project

NASA Astrophysics Data System (ADS)

Rodila, D.; Bacu, V.; Gorgan, D.

2012-04-01

The execution of Earth Science applications and services on parallel and distributed systems has become a necessity especially due to the large amounts of Geospatial data these applications require and the large geographical areas they cover. The parallelization of these applications comes to solve important performance issues and can spread from task parallelism to data parallelism as well. Parallel and distributed architectures such as Grid, Cloud, Multicore, etc. seem to offer the necessary functionalities to solve important problems in the Earth Science domain: storing, distribution, management, processing and security of Geospatial data, execution of complex processing through task and data parallelism, etc. A main goal of the FP7-funded project enviroGRIDS (Black Sea Catchment Observation and Assessment System supporting Sustainable Development) [1] is the development of a Spatial Data Infrastructure targeting this catchment region but also the development of standardized and specialized tools for storing, analyzing, processing and visualizing the Geospatial data concerning this area. For achieving these objectives, the enviroGRIDS deals with the execution of different Earth Science applications, such as hydrological models, Geospatial Web services standardized by the Open Geospatial Consortium (OGC) and others, on parallel and distributed architecture to maximize the obtained performance. This presentation analysis the integration and execution of Geospatial applications on different parallel and distributed architectures and the possibility of choosing among these architectures based on application characteristics and user requirements through a specialized component. Versions of the proposed platform have been used in enviroGRIDS project on different use cases such as: the execution of Geospatial Web services both on Web and Grid infrastructures [2] and the execution of SWAT hydrological models both on Grid and Multicore architectures [3]. The current focus is to integrate in the proposed platform the Cloud infrastructure, which is still a paradigm with critical problems to be solved despite the great efforts and investments. Cloud computing comes as a new way of delivering resources while using a large set of old as well as new technologies and tools for providing the necessary functionalities. The main challenges in the Cloud computing, most of them identified also in the Open Cloud Manifesto 2009, address resource management and monitoring, data and application interoperability and portability, security, scalability, software licensing, etc. We propose a platform able to execute different Geospatial applications on different parallel and distributed architectures such as Grid, Cloud, Multicore, etc. with the possibility of choosing among these architectures based on application characteristics and complexity, user requirements, necessary performances, cost support, etc. The execution redirection on a selected architecture is realized through a specialized component and has the purpose of offering a flexible way in achieving the best performances considering the existing restrictions.

cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on CPU+GPU.

PubMed

Zhang, Jing; Wang, Hao; Feng, Wu-Chun

2017-01-01

BLAST, short for Basic Local Alignment Search Tool, is a ubiquitous tool used in the life sciences for pairwise sequence search. However, with the advent of next-generation sequencing (NGS), whether at the outset or downstream from NGS, the exponential growth of sequence databases is outstripping our ability to analyze the data. While recent studies have utilized the graphics processing unit (GPU) to speedup the BLAST algorithm for searching protein sequences (i.e., BLASTP), these studies use coarse-grained parallelism, where one sequence alignment is mapped to only one thread. Such an approach does not efficiently utilize the capabilities of a GPU, particularly due to the irregularity of BLASTP in both execution paths and memory-access patterns. To address the above shortcomings, we present a fine-grained approach to parallelize BLASTP, where each individual phase of sequence search is mapped to many threads on a GPU. This approach, which we refer to as cuBLASTP, reorders data-access patterns and reduces divergent branches of the most time-consuming phases (i.e., hit detection and ungapped extension). In addition, cuBLASTP optimizes the remaining phases (i.e., gapped extension and alignment with trace back) on a multicore CPU and overlaps their execution with the phases running on the GPU.

Distributing an executable job load file to compute nodes in a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Gooding, Thomas M.

Distributing an executable job load file to compute nodes in a parallel computer, the parallel computer comprising a plurality of compute nodes, including: determining, by a compute node in the parallel computer, whether the compute node is participating in a job; determining, by the compute node in the parallel computer, whether a descendant compute node is participating in the job; responsive to determining that the compute node is participating in the job or that the descendant compute node is participating in the job, communicating, by the compute node to a parent compute node, an identification of a data communications linkmore » over which the compute node receives data from the parent compute node; constructing a class route for the job, wherein the class route identifies all compute nodes participating in the job; and broadcasting the executable load file for the job along the class route for the job.« less

MARBLE: A system for executing expert systems in parallel

NASA Technical Reports Server (NTRS)

Myers, Leonard; Johnson, Coe; Johnson, Dean

1990-01-01

This paper details the MARBLE 2.0 system which provides a parallel environment for cooperating expert systems. The work has been done in conjunction with the development of an intelligent computer-aided design system, ICADS, by the CAD Research Unit of the Design Institute at California Polytechnic State University. MARBLE (Multiple Accessed Rete Blackboard Linked Experts) is a system of C Language Production Systems (CLIPS) expert system tool. A copied blackboard is used for communication between the shells to establish an architecture which supports cooperating expert systems that execute in parallel. The design of MARBLE is simple, but it provides support for a rich variety of configurations, while making it relatively easy to demonstrate the correctness of its parallel execution features. In its most elementary configuration, individual CLIPS expert systems execute on their own processors and communicate with each other through a modified blackboard. Control of the system as a whole, and specifically of writing to the blackboard is provided by one of the CLIPS expert systems, an expert control system.

Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Blocksome, Michael A.; Mamidala, Amith R.

2013-09-03

Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segmentmore » of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.« less

Automatic analysis (aa): efficient neuroimaging workflows and parallel processing using Matlab and XML.

PubMed

Cusack, Rhodri; Vicente-Grabovetsky, Alejandro; Mitchell, Daniel J; Wild, Conor J; Auer, Tibor; Linke, Annika C; Peelle, Jonathan E

2014-01-01

Recent years have seen neuroimaging data sets becoming richer, with larger cohorts of participants, a greater variety of acquisition techniques, and increasingly complex analyses. These advances have made data analysis pipelines complicated to set up and run (increasing the risk of human error) and time consuming to execute (restricting what analyses are attempted). Here we present an open-source framework, automatic analysis (aa), to address these concerns. Human efficiency is increased by making code modular and reusable, and managing its execution with a processing engine that tracks what has been completed and what needs to be (re)done. Analysis is accelerated by optional parallel processing of independent tasks on cluster or cloud computing resources. A pipeline comprises a series of modules that each perform a specific task. The processing engine keeps track of the data, calculating a map of upstream and downstream dependencies for each module. Existing modules are available for many analysis tasks, such as SPM-based fMRI preprocessing, individual and group level statistics, voxel-based morphometry, tractography, and multi-voxel pattern analyses (MVPA). However, aa also allows for full customization, and encourages efficient management of code: new modules may be written with only a small code overhead. aa has been used by more than 50 researchers in hundreds of neuroimaging studies comprising thousands of subjects. It has been found to be robust, fast, and efficient, for simple-single subject studies up to multimodal pipelines on hundreds of subjects. It is attractive to both novice and experienced users. aa can reduce the amount of time neuroimaging laboratories spend performing analyses and reduce errors, expanding the range of scientific questions it is practical to address.

Runtime optimization of an application executing on a parallel computer

DOEpatents

None

2014-11-25

Identifying a collective operation within an application executing on a parallel computer; identifying a call site of the collective operation; determining whether the collective operation is root-based; if the collective operation is not root-based: establishing a tuning session and executing the collective operation in the tuning session; if the collective operation is root-based, determining whether all compute nodes executing the application identified the collective operation at the same call site; if all compute nodes identified the collective operation at the same call site, establishing a tuning session and executing the collective operation in the tuning session; and if all compute nodes executing the application did not identify the collective operation at the same call site, executing the collective operation without establishing a tuning session.

Runtime optimization of an application executing on a parallel computer

DOEpatents

Faraj, Daniel A; Smith, Brian E

2014-11-18

Identifying a collective operation within an application executing on a parallel computer; identifying a call site of the collective operation; determining whether the collective operation is root-based; if the collective operation is not root-based: establishing a tuning session and executing the collective operation in the tuning session; if the collective operation is root-based, determining whether all compute nodes executing the application identified the collective operation at the same call site; if all compute nodes identified the collective operation at the same call site, establishing a tuning session and executing the collective operation in the tuning session; and if all compute nodes executing the application did not identify the collective operation at the same call site, executing the collective operation without establishing a tuning session.

Runtime optimization of an application executing on a parallel computer

DOEpatents

Faraj, Daniel A.; Smith, Brian E.

2013-01-29

Identifying a collective operation within an application executing on a parallel computer; identifying a call site of the collective operation; determining whether the collective operation is root-based; if the collective operation is not root-based: establishing a tuning session and executing the collective operation in the tuning session; if the collective operation is root-based, determining whether all compute nodes executing the application identified the collective operation at the same call site; if all compute nodes identified the collective operation at the same call site, establishing a tuning session and executing the collective operation in the tuning session; and if all compute nodes executing the application did not identify the collective operation at the same call site, executing the collective operation without establishing a tuning session.

User-Assisted Store Recycling for Dynamic Task Graph Schedulers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kurt, Mehmet Can; Krishnamoorthy, Sriram; Agrawal, Gagan

The emergence of the multi-core era has led to increased interest in designing effective yet practical parallel programming models. Models based on task graphs that operate on single-assignment data are attractive in several ways: they can support dynamic applications and precisely represent the available concurrency. However, they also require nuanced algorithms for scheduling and memory management for efficient execution. In this paper, we consider memory-efficient dynamic scheduling of task graphs. Specifically, we present a novel approach for dynamically recycling the memory locations assigned to data items as they are produced by tasks. We develop algorithms to identify memory-efficient store recyclingmore » functions by systematically evaluating the validity of a set of (user-provided or automatically generated) alternatives. Because recycling function can be input data-dependent, we have also developed support for continued correct execution of a task graph in the presence of a potentially incorrect store recycling function. Experimental evaluation demonstrates that our approach to automatic store recycling incurs little to no overheads, achieves memory usage comparable to the best manually derived solutions, often produces recycling functions valid across problem sizes and input parameters, and efficiently recovers from an incorrect choice of store recycling functions.« less

Scalable Cloning on Large-Scale GPU Platforms with Application to Time-Stepped Simulations on Grids

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yoginath, Srikanth B.; Perumalla, Kalyan S.

Cloning is a technique to efficiently simulate a tree of multiple what-if scenarios that are unraveled during the course of a base simulation. However, cloned execution is highly challenging to realize on large, distributed memory computing platforms, due to the dynamic nature of the computational load across clones, and due to the complex dependencies spanning the clone tree. In this paper, we present the conceptual simulation framework, algorithmic foundations, and runtime interface of CloneX, a new system we designed for scalable simulation cloning. It efficiently and dynamically creates whole logical copies of a dynamic tree of simulations across a largemore » parallel system without full physical duplication of computation and memory. The performance of a prototype implementation executed on up to 1,024 graphical processing units of a supercomputing system has been evaluated with three benchmarks—heat diffusion, forest fire, and disease propagation models—delivering a speed up of over two orders of magnitude compared to replicated runs. Finally, the results demonstrate a significantly faster and scalable way to execute many what-if scenario ensembles of large simulations via cloning using the CloneX interface.« less

Scalable Cloning on Large-Scale GPU Platforms with Application to Time-Stepped Simulations on Grids

DOE PAGES

Yoginath, Srikanth B.; Perumalla, Kalyan S.

2018-01-31

Cloning is a technique to efficiently simulate a tree of multiple what-if scenarios that are unraveled during the course of a base simulation. However, cloned execution is highly challenging to realize on large, distributed memory computing platforms, due to the dynamic nature of the computational load across clones, and due to the complex dependencies spanning the clone tree. In this paper, we present the conceptual simulation framework, algorithmic foundations, and runtime interface of CloneX, a new system we designed for scalable simulation cloning. It efficiently and dynamically creates whole logical copies of a dynamic tree of simulations across a largemore » parallel system without full physical duplication of computation and memory. The performance of a prototype implementation executed on up to 1,024 graphical processing units of a supercomputing system has been evaluated with three benchmarks—heat diffusion, forest fire, and disease propagation models—delivering a speed up of over two orders of magnitude compared to replicated runs. Finally, the results demonstrate a significantly faster and scalable way to execute many what-if scenario ensembles of large simulations via cloning using the CloneX interface.« less

Scheduling applications for execution on a plurality of compute nodes of a parallel computer to manage temperature of the nodes during execution

DOEpatents

Archer, Charles J; Blocksome, Michael A; Peters, Amanda E; Ratterman, Joseph D; Smith, Brian E

2012-10-16

Methods, apparatus, and products are disclosed for scheduling applications for execution on a plurality of compute nodes of a parallel computer to manage temperature of the plurality of compute nodes during execution that include: identifying one or more applications for execution on the plurality of compute nodes; creating a plurality of physically discontiguous node partitions in dependence upon temperature characteristics for the compute nodes and a physical topology for the compute nodes, each discontiguous node partition specifying a collection of physically adjacent compute nodes; and assigning, for each application, that application to one or more of the discontiguous node partitions for execution on the compute nodes specified by the assigned discontiguous node partitions.

Parallel Vision Algorithm Design and Implementation 1988 End of Year Report

DTIC Science & Technology

1989-08-01

as a local operation, the provided C code used raster order processing to speed up execution time. This made it impossible to implement the code using...Apply, which does not allow the programmer to take advantage of raster order processing . Therefore, the 5x5 median filter algorithm was a straight...possible to exploit raster- order processing in W2, giving greater efficiency. The first advantage is the reason that connected components and the Hough

A Parallel Nonrigid Registration Algorithm Based on B-Spline for Medical Images.

PubMed

Du, Xiaogang; Dang, Jianwu; Wang, Yangping; Wang, Song; Lei, Tao

2016-01-01

The nonrigid registration algorithm based on B-spline Free-Form Deformation (FFD) plays a key role and is widely applied in medical image processing due to the good flexibility and robustness. However, it requires a tremendous amount of computing time to obtain more accurate registration results especially for a large amount of medical image data. To address the issue, a parallel nonrigid registration algorithm based on B-spline is proposed in this paper. First, the Logarithm Squared Difference (LSD) is considered as the similarity metric in the B-spline registration algorithm to improve registration precision. After that, we create a parallel computing strategy and lookup tables (LUTs) to reduce the complexity of the B-spline registration algorithm. As a result, the computing time of three time-consuming steps including B-splines interpolation, LSD computation, and the analytic gradient computation of LSD, is efficiently reduced, for the B-spline registration algorithm employs the Nonlinear Conjugate Gradient (NCG) optimization method. Experimental results of registration quality and execution efficiency on the large amount of medical images show that our algorithm achieves a better registration accuracy in terms of the differences between the best deformation fields and ground truth and a speedup of 17 times over the single-threaded CPU implementation due to the powerful parallel computing ability of Graphics Processing Unit (GPU).

Data communications in a parallel active messaging interface of a parallel computer

DOEpatents

Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E

2014-02-11

Data communications in a parallel active messaging interface ('PAMI') or a parallel computer, the parallel computer including a plurality of compute nodes that execute a parallel application, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution of a compute node, including specification of a client, a context, and a task, the compute nodes and the endpoints coupled for data communications instruction, the instruction characterized by instruction type, the instruction specifying a transmission of transfer data from the origin endpoint to a target endpoint and transmitting, in accordance witht the instruction type, the transfer data from the origin endpoin to the target endpoint.

Global Load Balancing with Parallel Mesh Adaption on Distributed-Memory Systems

NASA Technical Reports Server (NTRS)

Biswas, Rupak; Oliker, Leonid; Sohn, Andrew

1996-01-01

Dynamic mesh adaptation on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately, this causes load inbalances among processors on a parallel machine. This paper described the parallel implementation of a tetrahedral mesh adaption scheme and a new global load balancing method. A heuristic remapping algorithm is presented that assigns partitions to processors such that the redistribution coast is minimized. Results indicate that the parallel performance of the mesh adaption code depends on the nature of the adaption region and show a 35.5X speedup on 64 processors of an SP2 when 35 percent of the mesh is randomly adapted. For large scale scientific computations, our load balancing strategy gives an almost sixfold reduction in solver execution times over non-balanced loads. Furthermore, our heuristic remappier yields processor assignments that are less than 3 percent of the optimal solutions, but requires only 1 percent of the computational time.

Performance of a parallel code for the Euler equations on hypercube computers

NASA Technical Reports Server (NTRS)

Barszcz, Eric; Chan, Tony F.; Jesperson, Dennis C.; Tuminaro, Raymond S.

1990-01-01

The performance of hypercubes were evaluated on a computational fluid dynamics problem and the parallel environment issues were considered that must be addressed, such as algorithm changes, implementation choices, programming effort, and programming environment. The evaluation focuses on a widely used fluid dynamics code, FLO52, which solves the two dimensional steady Euler equations describing flow around the airfoil. The code development experience is described, including interacting with the operating system, utilizing the message-passing communication system, and code modifications necessary to increase parallel efficiency. Results from two hypercube parallel computers (a 16-node iPSC/2, and a 512-node NCUBE/ten) are discussed and compared. In addition, a mathematical model of the execution time was developed as a function of several machine and algorithm parameters. This model accurately predicts the actual run times obtained and is used to explore the performance of the code in interesting but yet physically realizable regions of the parameter space. Based on this model, predictions about future hypercubes are made.

Backtracking and Re-execution in the Automatic Debugging of Parallelized Programs

NASA Technical Reports Server (NTRS)

Matthews, Gregory; Hood, Robert; Johnson, Stephen; Leggett, Peter; Biegel, Bryan (Technical Monitor)

2002-01-01

In this work we describe a new approach using relative debugging to find differences in computation between a serial program and a parallel version of th it program. We use a combination of re-execution and backtracking in order to find the first difference in computation that may ultimately lead to an incorrect value that the user has indicated. In our prototype implementation we use static analysis information from a parallelization tool in order to perform the backtracking as well as the mapping required between serial and parallel computations.

PUP: An Architecture to Exploit Parallel Unification in Prolog

DTIC Science & Technology

1988-03-01

environment stacking mo del similar to the Warren Abstract Machine [23] since it has been shown to be super ior to other known models (see [21]). The storage...execute in groups of independent operations. Unifications belonging to different group s may not overlap. Also unification operations belonging to the...since all parallel operations on the unification units must complete before any of the units can star t executing the next group of parallel

Strategies for Energy Efficient Resource Management of Hybrid Programming Models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Li, Dong; Supinski, Bronis de; Schulz, Martin

2013-01-01

Many scientific applications are programmed using hybrid programming models that use both message-passing and shared-memory, due to the increasing prevalence of large-scale systems with multicore, multisocket nodes. Previous work has shown that energy efficiency can be improved using software-controlled execution schemes that consider both the programming model and the power-aware execution capabilities of the system. However, such approaches have focused on identifying optimal resource utilization for one programming model, either shared-memory or message-passing, in isolation. The potential solution space, thus the challenge, increases substantially when optimizing hybrid models since the possible resource configurations increase exponentially. Nonetheless, with the accelerating adoptionmore » of hybrid programming models, we increasingly need improved energy efficiency in hybrid parallel applications on large-scale systems. In this work, we present new software-controlled execution schemes that consider the effects of dynamic concurrency throttling (DCT) and dynamic voltage and frequency scaling (DVFS) in the context of hybrid programming models. Specifically, we present predictive models and novel algorithms based on statistical analysis that anticipate application power and time requirements under different concurrency and frequency configurations. We apply our models and methods to the NPB MZ benchmarks and selected applications from the ASC Sequoia codes. Overall, we achieve substantial energy savings (8.74% on average and up to 13.8%) with some performance gain (up to 7.5%) or negligible performance loss.« less

SCELib2: the new revision of SCELib, the parallel computational library of molecular properties in the single center approach

NASA Astrophysics Data System (ADS)

Sanna, N.; Morelli, G.

2004-09-01

In this paper we present the new version of the SCELib program (CPC Catalogue identifier ADMG) a full numerical implementation of the Single Center Expansion (SCE) method. The physics involved is that of producing the SCE description of molecular electronic densities, of molecular electrostatic potentials and of molecular perturbed potentials due to a point negative or positive charge. This new revision of the program has been optimized to run in serial as well as in parallel execution mode, to support a larger set of molecular symmetries and to permit the restart of long-lasting calculations. To measure the performance of this new release, a comparative study has been carried out on the most powerful computing architectures in serial and parallel runs. The results of the calculations reported in this paper refer to real cases medium to large molecular systems and they are reported in full details to benchmark at best the parallel architectures the new SCELib code will run on. Program summaryTitle of program: SCELib2 Catalogue identifier: ADGU Program summary URL:http://cpc.cs.qub.ac.uk/summaries/ADGU Program obtainable from: CPC Program Library, Queen's University of Belfast, N. Ireland Reference to previous versions: Comput. Phys. Commun. 128 (2) (2000) 139 (CPC catalogue identifier: ADMG) Does the new version supersede the original program?: Yes Computer for which the program is designed and others on which it has been tested: HP ES45 and rx2600, SUN ES4500, IBM SP and any single CPU workstation based on Alpha, SPARC, POWER, Itanium2 and X86 processors Installations: CASPUR, local Operating systems under which the program has been tested: HP Tru64 V5.X, SUNOS V5.8, IBM AIX V5.X, Linux RedHat V8.0 Programming language used: C Memory required to execute with typical data: 10 Mwords. Up to 2000 Mwords depending on the molecular system and runtime parameters No. of bits in a word: 64 No. of processors used: 1 to 32 Has the code been vectorized or parallelized?: Yes No. of bytes in distributed program, including test data, etc.: 3 798 507 No. of lines in distributed program, including test data, etc.: 187 226 Distribution format: tar.gz Nature of physical problem: In this set of codes an efficient procedure is implemented to describe the wavefunction and related molecular properties of a polyatomic molecular system within the Single Center of Expansion (SCE) approximation. The resulting SCE wavefunction, electron density, electrostatic and exchange/correlation potentials can then be used via a proper Application Programming Interface (API) to describe the target molecular system which can be employed in electron-molecule scattering calculations. The molecular properties expanded over a single center turn out to also be of more general application and some possible uses in quantum chemistry, biomodelling and drug design are also outlined. Method of solution: The polycentre Hartee-Fock solution for a molecule of arbitrary geometry, based on linear combination of Gaussian-Type Orbital (GTO), is expanded over a single center, typically the Center Of Mass (C.O.M.), by means of a Gauss-Legendre/Chebyschev quadrature over the θ, φ angular coordinates. The resulting SCE numerical wavefunction is then used to calculate the one-particle electron density, the electrostatic potential and two different models for the correlation/polarization potentials induced by the impinging electron, which have the correct asymptotic behaviour for the leading dipole molecular polarizabilities. Restrictions on the complexity of the problem: Depending on the molecular system under study and on the operating conditions the program may or may not fit into available RAM memory. In this case a feature of the program is to memory map a disk file in order to efficiently access the memory data through a disk device. Typical running time: The execution time strongly depends on the molecular target description and on the hardware/OS chosen, it is directly proportional to the ( r, θ, φ) grid size and to the number of angular basis functions used. Thus, from the program printout of the main arrays memory occupancy, the user can approximately derive the expected computer time needed for a given calculation executed in serial mode. For parallel executions the overall efficiency must be further taken into account, and this depends on the no. of processors used as well as on the parallel architecture chosen, so a simple general law is at present not determinable. Unusual features of the program: The code has been engineered to use dynamical, runtime determined, global parameters with the aim to have all the data fitted in the RAM memory. Some unusual circumstances, e.g., when using large values of those parameters, may cause the program to run with unexpected performance reductions due to runtime bottlenecks like those caused by memory swap operations which strongly depend on the hardware used. In such cases, a parallel execution of the code is generally sufficient to fix the problem since the data size is partitioned over the available processors. When a suitable parallel system is not available for execution, a mechanism of memory mapped file can be used; with this option on, all the available memory will be used as a buffer for a disk file which contains the whole data set, thus having a better throughput with respect to the traditional swapping/paging of the Unix OS.

Applications of New Surrogate Global Optimization Algorithms including Efficient Synchronous and Asynchronous Parallelism for Calibration of Expensive Nonlinear Geophysical Simulation Models.

NASA Astrophysics Data System (ADS)

Shoemaker, C. A.; Pang, M.; Akhtar, T.; Bindel, D.

2016-12-01

New parallel surrogate global optimization algorithms are developed and applied to objective functions that are expensive simulations (possibly with multiple local minima). The algorithms can be applied to most geophysical simulations, including those with nonlinear partial differential equations. The optimization does not require simulations be parallelized. Asynchronous (and synchronous) parallel execution is available in the optimization toolbox "pySOT". The parallel algorithms are modified from serial to eliminate fine grained parallelism. The optimization is computed with open source software pySOT, a Surrogate Global Optimization Toolbox that allows user to pick the type of surrogate (or ensembles), the search procedure on surrogate, and the type of parallelism (synchronous or asynchronous). pySOT also allows the user to develop new algorithms by modifying parts of the code. In the applications here, the objective function takes up to 30 minutes for one simulation, and serial optimization can take over 200 hours. Results from Yellowstone (NSF) and NCSS (Singapore) supercomputers are given for groundwater contaminant hydrology simulations with applications to model parameter estimation and decontamination management. All results are compared with alternatives. The first results are for optimization of pumping at many wells to reduce cost for decontamination of groundwater at a superfund site. The optimization runs with up to 128 processors. Superlinear speed up is obtained for up to 16 processors, and efficiency with 64 processors is over 80%. Each evaluation of the objective function requires the solution of nonlinear partial differential equations to describe the impact of spatially distributed pumping and model parameters on model predictions for the spatial and temporal distribution of groundwater contaminants. The second application uses an asynchronous parallel global optimization for groundwater quality model calibration. The time for a single objective function evaluation varies unpredictably, so efficiency is improved with asynchronous parallel calculations to improve load balancing. The third application (done at NCSS) incorporates new global surrogate multi-objective parallel search algorithms into pySOT and applies it to a large watershed calibration problem.

Communication overhead on the Intel Paragon, IBM SP2 and Meiko CS-2

NASA Technical Reports Server (NTRS)

Bokhari, Shahid H.

1995-01-01

Interprocessor communication overhead is a crucial measure of the power of parallel computing systems-its impact can severely limit the performance of parallel programs. This report presents measurements of communication overhead on three contemporary commercial multicomputer systems: the Intel Paragon, the IBM SP2 and the Meiko CS-2. In each case the time to communicate between processors is presented as a function of message length. The time for global synchronization and memory access is discussed. The performance of these machines in emulating hypercubes and executing random pairwise exchanges is also investigated. It is shown that the interprocessor communication time depends heavily on the specific communication pattern required. These observations contradict the commonly held belief that communication overhead on contemporary machines is independent of the placement of tasks on processors. The information presented in this report permits the evaluation of the efficiency of parallel algorithm implementations against standard baselines.

Efficient implementation of real-time programs under the VAX/VMS operating system

NASA Technical Reports Server (NTRS)

Johnson, S. C.

1985-01-01

Techniques for writing efficient real-time programs under the VAX/VMS oprating system are presented. Basic operations are presented for executing at real-time priority and for avoiding needlless processing delays. A highly efficient technique for accessing physical devices by mapping to the input/output space and accessing the device registrs directly is described. To illustrate the application of the technique, examples are included of different uses of the technique on three devices in the Langley Avionics Integration Research Lab (AIRLAB): the KW11-K dual programmable real-time clock, the Parallel Communications Link (PCL11-B) communication system, and the Datacom Synchronization Network. Timing data are included to demonstrate the performance improvements realized with these applications of the technique.

Work stealing for GPU-accelerated parallel programs in a global address space framework: WORK STEALING ON GPU-ACCELERATED SYSTEMS

DOE Office of Scientific and Technical Information (OSTI.GOV)

Arafat, Humayun; Dinan, James; Krishnamoorthy, Sriram

Task parallelism is an attractive approach to automatically load balance the computation in a parallel system and adapt to dynamism exhibited by parallel systems. Exploiting task parallelism through work stealing has been extensively studied in shared and distributed-memory contexts. In this paper, we study the design of a system that uses work stealing for dynamic load balancing of task-parallel programs executed on hybrid distributed-memory CPU-graphics processing unit (GPU) systems in a global-address space framework. We take into account the unique nature of the accelerator model employed by GPUs, the significant performance difference between GPU and CPU execution as a functionmore » of problem size, and the distinct CPU and GPU memory domains. We consider various alternatives in designing a distributed work stealing algorithm for CPU-GPU systems, while taking into account the impact of task distribution and data movement overheads. These strategies are evaluated using microbenchmarks that capture various execution configurations as well as the state-of-the-art CCSD(T) application module from the computational chemistry domain.« less

Work stealing for GPU-accelerated parallel programs in a global address space framework

DOE Office of Scientific and Technical Information (OSTI.GOV)

Arafat, Humayun; Dinan, James; Krishnamoorthy, Sriram

Task parallelism is an attractive approach to automatically load balance the computation in a parallel system and adapt to dynamism exhibited by parallel systems. Exploiting task parallelism through work stealing has been extensively studied in shared and distributed-memory contexts. In this paper, we study the design of a system that uses work stealing for dynamic load balancing of task-parallel programs executed on hybrid distributed-memory CPU-graphics processing unit (GPU) systems in a global-address space framework. We take into account the unique nature of the accelerator model employed by GPUs, the significant performance difference between GPU and CPU execution as a functionmore » of problem size, and the distinct CPU and GPU memory domains. We consider various alternatives in designing a distributed work stealing algorithm for CPU-GPU systems, while taking into account the impact of task distribution and data movement overheads. These strategies are evaluated using microbenchmarks that capture various execution configurations as well as the state-of-the-art CCSD(T) application module from the computational chemistry domain« less

Privacy-Preserving Location-Based Query Using Location Indexes and Parallel Searching in Distributed Networks

PubMed Central

Liu, Lei; Zhao, Jing

2014-01-01

An efficient location-based query algorithm of protecting the privacy of the user in the distributed networks is given. This algorithm utilizes the location indexes of the users and multiple parallel threads to search and select quickly all the candidate anonymous sets with more users and their location information with more uniform distribution to accelerate the execution of the temporal-spatial anonymous operations, and it allows the users to configure their custom-made privacy-preserving location query requests. The simulated experiment results show that the proposed algorithm can offer simultaneously the location query services for more users and improve the performance of the anonymous server and satisfy the anonymous location requests of the users. PMID:24790579

Algorithms and analyses for stochastic optimization for turbofan noise reduction using parallel reduced-order modeling

NASA Astrophysics Data System (ADS)

Yang, Huanhuan; Gunzburger, Max

2017-06-01

Simulation-based optimization of acoustic liner design in a turbofan engine nacelle for noise reduction purposes can dramatically reduce the cost and time needed for experimental designs. Because uncertainties are inevitable in the design process, a stochastic optimization algorithm is posed based on the conditional value-at-risk measure so that an ideal acoustic liner impedance is determined that is robust in the presence of uncertainties. A parallel reduced-order modeling framework is developed that dramatically improves the computational efficiency of the stochastic optimization solver for a realistic nacelle geometry. The reduced stochastic optimization solver takes less than 500 seconds to execute. In addition, well-posedness and finite element error analyses of the state system and optimization problem are provided.

Privacy-preserving location-based query using location indexes and parallel searching in distributed networks.

PubMed

Zhong, Cheng; Liu, Lei; Zhao, Jing

2014-01-01

An efficient location-based query algorithm of protecting the privacy of the user in the distributed networks is given. This algorithm utilizes the location indexes of the users and multiple parallel threads to search and select quickly all the candidate anonymous sets with more users and their location information with more uniform distribution to accelerate the execution of the temporal-spatial anonymous operations, and it allows the users to configure their custom-made privacy-preserving location query requests. The simulated experiment results show that the proposed algorithm can offer simultaneously the location query services for more users and improve the performance of the anonymous server and satisfy the anonymous location requests of the users.

Multilevel Parallelization of AutoDock 4.2.

PubMed

Norgan, Andrew P; Coffman, Paul K; Kocher, Jean-Pierre A; Katzmann, David J; Sosa, Carlos P

2011-04-28

Virtual (computational) screening is an increasingly important tool for drug discovery. AutoDock is a popular open-source application for performing molecular docking, the prediction of ligand-receptor interactions. AutoDock is a serial application, though several previous efforts have parallelized various aspects of the program. In this paper, we report on a multi-level parallelization of AutoDock 4.2 (mpAD4). Using MPI and OpenMP, AutoDock 4.2 was parallelized for use on MPI-enabled systems and to multithread the execution of individual docking jobs. In addition, code was implemented to reduce input/output (I/O) traffic by reusing grid maps at each node from docking to docking. Performance of mpAD4 was examined on two multiprocessor computers. Using MPI with OpenMP multithreading, mpAD4 scales with near linearity on the multiprocessor systems tested. In situations where I/O is limiting, reuse of grid maps reduces both system I/O and overall screening time. Multithreading of AutoDock's Lamarkian Genetic Algorithm with OpenMP increases the speed of execution of individual docking jobs, and when combined with MPI parallelization can significantly reduce the execution time of virtual screens. This work is significant in that mpAD4 speeds the execution of certain molecular docking workloads and allows the user to optimize the degree of system-level (MPI) and node-level (OpenMP) parallelization to best fit both workloads and computational resources.

The specificity of learned parallelism in dual-memory retrieval.

PubMed

Strobach, Tilo; Schubert, Torsten; Pashler, Harold; Rickard, Timothy

2014-05-01

Retrieval of two responses from one visually presented cue occurs sequentially at the outset of dual-retrieval practice. Exclusively for subjects who adopt a mode of grouping (i.e., synchronizing) their response execution, however, reaction times after dual-retrieval practice indicate a shift to learned retrieval parallelism (e.g., Nino & Rickard, in Journal of Experimental Psychology: Learning, Memory, and Cognition, 29, 373-388, 2003). In the present study, we investigated how this learned parallelism is achieved and why it appears to occur only for subjects who group their responses. Two main accounts were considered: a task-level versus a cue-level account. The task-level account assumes that learned retrieval parallelism occurs at the level of the task as a whole and is not limited to practiced cues. Grouping response execution may thus promote a general shift to parallel retrieval following practice. The cue-level account states that learned retrieval parallelism is specific to practiced cues. This type of parallelism may result from cue-specific response chunking that occurs uniquely as a consequence of grouped response execution. The results of two experiments favored the second account and were best interpreted in terms of a structural bottleneck model.

Parallel processors and nonlinear structural dynamics algorithms and software

NASA Technical Reports Server (NTRS)

Belytschko, Ted

1990-01-01

Techniques are discussed for the implementation and improvement of vectorization and concurrency in nonlinear explicit structural finite element codes. In explicit integration methods, the computation of the element internal force vector consumes the bulk of the computer time. The program can be efficiently vectorized by subdividing the elements into blocks and executing all computations in vector mode. The structuring of elements into blocks also provides a convenient way to implement concurrency by creating tasks which can be assigned to available processors for evaluation. The techniques were implemented in a 3-D nonlinear program with one-point quadrature shell elements. Concurrency and vectorization were first implemented in a single time step version of the program. Techniques were developed to minimize processor idle time and to select the optimal vector length. A comparison of run times between the program executed in scalar, serial mode and the fully vectorized code executed concurrently using eight processors shows speed-ups of over 25. Conjugate gradient methods for solving nonlinear algebraic equations are also readily adapted to a parallel environment. A new technique for improving convergence properties of conjugate gradients in nonlinear problems is developed in conjunction with other techniques such as diagonal scaling. A significant reduction in the number of iterations required for convergence is shown for a statically loaded rigid bar suspended by three equally spaced springs.

Manyscale Computing for Sensor Processing in Support of Space Situational Awareness

NASA Astrophysics Data System (ADS)

Schmalz, M.; Chapman, W.; Hayden, E.; Sahni, S.; Ranka, S.

2014-09-01

Increasing image and signal data burden associated with sensor data processing in support of space situational awareness implies continuing computational throughput growth beyond the petascale regime. In addition to growing applications data burden and diversity, the breadth, diversity and scalability of high performance computing architectures and their various organizations challenge the development of a single, unifying, practicable model of parallel computation. Therefore, models for scalable parallel processing have exploited architectural and structural idiosyncrasies, yielding potential misapplications when legacy programs are ported among such architectures. In response to this challenge, we have developed a concise, efficient computational paradigm and software called Manyscale Computing to facilitate efficient mapping of annotated application codes to heterogeneous parallel architectures. Our theory, algorithms, software, and experimental results support partitioning and scheduling of application codes for envisioned parallel architectures, in terms of work atoms that are mapped (for example) to threads or thread blocks on computational hardware. Because of the rigor, completeness, conciseness, and layered design of our manyscale approach, application-to-architecture mapping is feasible and scalable for architectures at petascales, exascales, and above. Further, our methodology is simple, relying primarily on a small set of primitive mapping operations and support routines that are readily implemented on modern parallel processors such as graphics processing units (GPUs) and hybrid multi-processors (HMPs). In this paper, we overview the opportunities and challenges of manyscale computing for image and signal processing in support of space situational awareness applications. We discuss applications in terms of a layered hardware architecture (laboratory > supercomputer > rack > processor > component hierarchy). Demonstration applications include performance analysis and results in terms of execution time as well as storage, power, and energy consumption for bus-connected and/or networked architectures. The feasibility of the manyscale paradigm is demonstrated by addressing four principal challenges: (1) architectural/structural diversity, parallelism, and locality, (2) masking of I/O and memory latencies, (3) scalability of design as well as implementation, and (4) efficient representation/expression of parallel applications. Examples will demonstrate how manyscale computing helps solve these challenges efficiently on real-world computing systems.

Time-dependent density-functional theory in massively parallel computer architectures: the octopus project

NASA Astrophysics Data System (ADS)

Andrade, Xavier; Alberdi-Rodriguez, Joseba; Strubbe, David A.; Oliveira, Micael J. T.; Nogueira, Fernando; Castro, Alberto; Muguerza, Javier; Arruabarrena, Agustin; Louie, Steven G.; Aspuru-Guzik, Alán; Rubio, Angel; Marques, Miguel A. L.

2012-06-01

Octopus is a general-purpose density-functional theory (DFT) code, with a particular emphasis on the time-dependent version of DFT (TDDFT). In this paper we present the ongoing efforts to achieve the parallelization of octopus. We focus on the real-time variant of TDDFT, where the time-dependent Kohn-Sham equations are directly propagated in time. This approach has great potential for execution in massively parallel systems such as modern supercomputers with thousands of processors and graphics processing units (GPUs). For harvesting the potential of conventional supercomputers, the main strategy is a multi-level parallelization scheme that combines the inherent scalability of real-time TDDFT with a real-space grid domain-partitioning approach. A scalable Poisson solver is critical for the efficiency of this scheme. For GPUs, we show how using blocks of Kohn-Sham states provides the required level of data parallelism and that this strategy is also applicable for code optimization on standard processors. Our results show that real-time TDDFT, as implemented in octopus, can be the method of choice for studying the excited states of large molecular systems in modern parallel architectures.

Time-dependent density-functional theory in massively parallel computer architectures: the OCTOPUS project.

PubMed

Andrade, Xavier; Alberdi-Rodriguez, Joseba; Strubbe, David A; Oliveira, Micael J T; Nogueira, Fernando; Castro, Alberto; Muguerza, Javier; Arruabarrena, Agustin; Louie, Steven G; Aspuru-Guzik, Alán; Rubio, Angel; Marques, Miguel A L

2012-06-13

Octopus is a general-purpose density-functional theory (DFT) code, with a particular emphasis on the time-dependent version of DFT (TDDFT). In this paper we present the ongoing efforts to achieve the parallelization of octopus. We focus on the real-time variant of TDDFT, where the time-dependent Kohn-Sham equations are directly propagated in time. This approach has great potential for execution in massively parallel systems such as modern supercomputers with thousands of processors and graphics processing units (GPUs). For harvesting the potential of conventional supercomputers, the main strategy is a multi-level parallelization scheme that combines the inherent scalability of real-time TDDFT with a real-space grid domain-partitioning approach. A scalable Poisson solver is critical for the efficiency of this scheme. For GPUs, we show how using blocks of Kohn-Sham states provides the required level of data parallelism and that this strategy is also applicable for code optimization on standard processors. Our results show that real-time TDDFT, as implemented in octopus, can be the method of choice for studying the excited states of large molecular systems in modern parallel architectures.

Run-time parallelization and scheduling of loops

NASA Technical Reports Server (NTRS)

Saltz, Joel H.; Mirchandaney, Ravi; Crowley, Kay

1990-01-01

Run time methods are studied to automatically parallelize and schedule iterations of a do loop in certain cases, where compile-time information is inadequate. The methods presented involve execution time preprocessing of the loop. At compile-time, these methods set up the framework for performing a loop dependency analysis. At run time, wave fronts of concurrently executable loop iterations are identified. Using this wavefront information, loop iterations are reordered for increased parallelism. Symbolic transformation rules are used to produce: inspector procedures that perform execution time preprocessing and executors or transformed versions of source code loop structures. These transformed loop structures carry out the calculations planned in the inspector procedures. Performance results are presented from experiments conducted on the Encore Multimax. These results illustrate that run time reordering of loop indices can have a significant impact on performance. Furthermore, the overheads associated with this type of reordering are amortized when the loop is executed several times with the same dependency structure.

3-D modeling of ductile tearing using finite elements: Computational aspects and techniques

NASA Astrophysics Data System (ADS)

Gullerud, Arne Stewart

This research focuses on the development and application of computational tools to perform large-scale, 3-D modeling of ductile tearing in engineering components under quasi-static to mild loading rates. Two standard models for ductile tearing---the computational cell methodology and crack growth controlled by the crack tip opening angle (CTOA)---are described and their 3-D implementations are explored. For the computational cell methodology, quantification of the effects of several numerical issues---computational load step size, procedures for force release after cell deletion, and the porosity for cell deletion---enables construction of computational algorithms to remove the dependence of predicted crack growth on these issues. This work also describes two extensions of the CTOA approach into 3-D: a general 3-D method and a constant front technique. Analyses compare the characteristics of the extensions, and a validation study explores the ability of the constant front extension to predict crack growth in thin aluminum test specimens over a range of specimen geometries, absolutes sizes, and levels of out-of-plane constraint. To provide a computational framework suitable for the solution of these problems, this work also describes the parallel implementation of a nonlinear, implicit finite element code. The implementation employs an explicit message-passing approach using the MPI standard to maintain portability, a domain decomposition of element data to provide parallel execution, and a master-worker organization of the computational processes to enhance future extensibility. A linear preconditioned conjugate gradient (LPCG) solver serves as the core of the solution process. The parallel LPCG solver utilizes an element-by-element (EBE) structure of the computations to permit a dual-level decomposition of the element data: domain decomposition of the mesh provides efficient coarse-grain parallel execution, while decomposition of the domains into blocks of similar elements (same type, constitutive model, etc.) provides fine-grain parallel computation on each processor. A major focus of the LPCG solver is a new implementation of the Hughes-Winget element-by-element (HW) preconditioner. The implementation employs a weighted dependency graph combined with a new coloring algorithm to provide load-balanced scheduling for the preconditioner and overlapped communication/computation. This approach enables efficient parallel application of the HW preconditioner for arbitrary unstructured meshes.

Parallel discrete-event simulation of FCFS stochastic queueing networks

NASA Technical Reports Server (NTRS)

Nicol, David M.

1988-01-01

Physical systems are inherently parallel. Intuition suggests that simulations of these systems may be amenable to parallel execution. The parallel execution of a discrete-event simulation requires careful synchronization of processes in order to ensure the execution's correctness; this synchronization can degrade performance. Largely negative results were recently reported in a study which used a well-known synchronization method on queueing network simulations. Discussed here is a synchronization method (appointments), which has proven itself to be effective on simulations of FCFS queueing networks. The key concept behind appointments is the provision of lookahead. Lookahead is a prediction on a processor's future behavior, based on an analysis of the processor's simulation state. It is shown how lookahead can be computed for FCFS queueing network simulations, give performance data that demonstrates the method's effectiveness under moderate to heavy loads, and discuss performance tradeoffs between the quality of lookahead, and the cost of computing lookahead.

Dual compile strategy for parallel heterogeneous execution

DOE Office of Scientific and Technical Information (OSTI.GOV)

Smith, Tyler Barratt; Perry, James Thomas

2012-06-01

The purpose of the Dual Compile Strategy is to increase our trust in the Compute Engine during its execution of instructions. This is accomplished by introducing a heterogeneous Monitor Engine that checks the execution of the Compute Engine. This leads to the production of a second and custom set of instructions designed for monitoring the execution of the Compute Engine at runtime. This use of multiple engines differs from redundancy in that one engine is working on the application while the other engine is monitoring and checking in parallel instead of both applications (and engines) performing the same work atmore » the same time.« less

Data preprocessing for determining outer/inner parallelization in the nested loop problem using OpenMP

NASA Astrophysics Data System (ADS)

Handhika, T.; Bustamam, A.; Ernastuti, Kerami, D.

2017-07-01

Multi-thread programming using OpenMP on the shared-memory architecture with hyperthreading technology allows the resource to be accessed by multiple processors simultaneously. Each processor can execute more than one thread for a certain period of time. However, its speedup depends on the ability of the processor to execute threads in limited quantities, especially the sequential algorithm which contains a nested loop. The number of the outer loop iterations is greater than the maximum number of threads that can be executed by a processor. The thread distribution technique that had been found previously only be applied by the high-level programmer. This paper generates a parallelization procedure for low-level programmer in dealing with 2-level nested loop problems with the maximum number of threads that can be executed by a processor is smaller than the number of the outer loop iterations. Data preprocessing which is related to the number of the outer loop and the inner loop iterations, the computational time required to execute each iteration and the maximum number of threads that can be executed by a processor are used as a strategy to determine which parallel region that will produce optimal speedup.

GPU and APU computations of Finite Time Lyapunov Exponent fields

NASA Astrophysics Data System (ADS)

Conti, Christian; Rossinelli, Diego; Koumoutsakos, Petros

2012-03-01

We present GPU and APU accelerated computations of Finite-Time Lyapunov Exponent (FTLE) fields. The calculation of FTLEs is a computationally intensive process, as in order to obtain the sharp ridges associated with the Lagrangian Coherent Structures an extensive resampling of the flow field is required. The computational performance of this resampling is limited by the memory bandwidth of the underlying computer architecture. The present technique harnesses data-parallel execution of many-core architectures and relies on fast and accurate evaluations of moment conserving functions for the mesh to particle interpolations. We demonstrate how the computation of FTLEs can be efficiently performed on a GPU and on an APU through OpenCL and we report over one order of magnitude improvements over multi-threaded executions in FTLE computations of bluff body flows.

Octree-based, GPU implementation of a continuous cellular automaton for the simulation of complex, evolving surfaces

NASA Astrophysics Data System (ADS)

Ferrando, N.; Gosálvez, M. A.; Cerdá, J.; Gadea, R.; Sato, K.

2011-03-01

Presently, dynamic surface-based models are required to contain increasingly larger numbers of points and to propagate them over longer time periods. For large numbers of surface points, the octree data structure can be used as a balance between low memory occupation and relatively rapid access to the stored data. For evolution rules that depend on neighborhood states, extended simulation periods can be obtained by using simplified atomistic propagation models, such as the Cellular Automata (CA). This method, however, has an intrinsic parallel updating nature and the corresponding simulations are highly inefficient when performed on classical Central Processing Units (CPUs), which are designed for the sequential execution of tasks. In this paper, a series of guidelines is presented for the efficient adaptation of octree-based, CA simulations of complex, evolving surfaces into massively parallel computing hardware. A Graphics Processing Unit (GPU) is used as a cost-efficient example of the parallel architectures. For the actual simulations, we consider the surface propagation during anisotropic wet chemical etching of silicon as a computationally challenging process with a wide-spread use in microengineering applications. A continuous CA model that is intrinsically parallel in nature is used for the time evolution. Our study strongly indicates that parallel computations of dynamically evolving surfaces simulated using CA methods are significantly benefited by the incorporation of octrees as support data structures, substantially decreasing the overall computational time and memory usage.

Parallel workflow manager for non-parallel bioinformatic applications to solve large-scale biological problems on a supercomputer.

PubMed

Suplatov, Dmitry; Popova, Nina; Zhumatiy, Sergey; Voevodin, Vladimir; Švedas, Vytas

2016-04-01

Rapid expansion of online resources providing access to genomic, structural, and functional information associated with biological macromolecules opens an opportunity to gain a deeper understanding of the mechanisms of biological processes due to systematic analysis of large datasets. This, however, requires novel strategies to optimally utilize computer processing power. Some methods in bioinformatics and molecular modeling require extensive computational resources. Other algorithms have fast implementations which take at most several hours to analyze a common input on a modern desktop station, however, due to multiple invocations for a large number of subtasks the full task requires a significant computing power. Therefore, an efficient computational solution to large-scale biological problems requires both a wise parallel implementation of resource-hungry methods as well as a smart workflow to manage multiple invocations of relatively fast algorithms. In this work, a new computer software mpiWrapper has been developed to accommodate non-parallel implementations of scientific algorithms within the parallel supercomputing environment. The Message Passing Interface has been implemented to exchange information between nodes. Two specialized threads - one for task management and communication, and another for subtask execution - are invoked on each processing unit to avoid deadlock while using blocking calls to MPI. The mpiWrapper can be used to launch all conventional Linux applications without the need to modify their original source codes and supports resubmission of subtasks on node failure. We show that this approach can be used to process huge amounts of biological data efficiently by running non-parallel programs in parallel mode on a supercomputer. The C++ source code and documentation are available from http://biokinet.belozersky.msu.ru/mpiWrapper .

An efficient spectral crystal plasticity solver for GPU architectures

NASA Astrophysics Data System (ADS)

Malahe, Michael

2018-03-01

We present a spectral crystal plasticity (CP) solver for graphics processing unit (GPU) architectures that achieves a tenfold increase in efficiency over prior GPU solvers. The approach makes use of a database containing a spectral decomposition of CP simulations performed using a conventional iterative solver over a parameter space of crystal orientations and applied velocity gradients. The key improvements in efficiency come from reducing global memory transactions, exposing more instruction-level parallelism, reducing integer instructions and performing fast range reductions on trigonometric arguments. The scheme also makes more efficient use of memory than prior work, allowing for larger problems to be solved on a single GPU. We illustrate these improvements with a simulation of 390 million crystal grains on a consumer-grade GPU, which executes at a rate of 2.72 s per strain step.

GPU accelerated manifold correction method for spinning compact binaries

NASA Astrophysics Data System (ADS)

Ran, Chong-xi; Liu, Song; Zhong, Shuang-ying

2018-04-01

The graphics processing unit (GPU) acceleration of the manifold correction algorithm based on the compute unified device architecture (CUDA) technology is designed to simulate the dynamic evolution of the Post-Newtonian (PN) Hamiltonian formulation of spinning compact binaries. The feasibility and the efficiency of parallel computation on GPU have been confirmed by various numerical experiments. The numerical comparisons show that the accuracy on GPU execution of manifold corrections method has a good agreement with the execution of codes on merely central processing unit (CPU-based) method. The acceleration ability when the codes are implemented on GPU can increase enormously through the use of shared memory and register optimization techniques without additional hardware costs, implying that the speedup is nearly 13 times as compared with the codes executed on CPU for phase space scan (including 314 × 314 orbits). In addition, GPU-accelerated manifold correction method is used to numerically study how dynamics are affected by the spin-induced quadrupole-monopole interaction for black hole binary system.

A Parallel Nonrigid Registration Algorithm Based on B-Spline for Medical Images

PubMed Central

Wang, Yangping; Wang, Song

2016-01-01

The nonrigid registration algorithm based on B-spline Free-Form Deformation (FFD) plays a key role and is widely applied in medical image processing due to the good flexibility and robustness. However, it requires a tremendous amount of computing time to obtain more accurate registration results especially for a large amount of medical image data. To address the issue, a parallel nonrigid registration algorithm based on B-spline is proposed in this paper. First, the Logarithm Squared Difference (LSD) is considered as the similarity metric in the B-spline registration algorithm to improve registration precision. After that, we create a parallel computing strategy and lookup tables (LUTs) to reduce the complexity of the B-spline registration algorithm. As a result, the computing time of three time-consuming steps including B-splines interpolation, LSD computation, and the analytic gradient computation of LSD, is efficiently reduced, for the B-spline registration algorithm employs the Nonlinear Conjugate Gradient (NCG) optimization method. Experimental results of registration quality and execution efficiency on the large amount of medical images show that our algorithm achieves a better registration accuracy in terms of the differences between the best deformation fields and ground truth and a speedup of 17 times over the single-threaded CPU implementation due to the powerful parallel computing ability of Graphics Processing Unit (GPU). PMID:28053653

Implementing the PM Programming Language using MPI and OpenMP - a New Tool for Programming Geophysical Models on Parallel Systems

NASA Astrophysics Data System (ADS)

Bellerby, Tim

2015-04-01

PM (Parallel Models) is a new parallel programming language specifically designed for writing environmental and geophysical models. The language is intended to enable implementers to concentrate on the science behind the model rather than the details of running on parallel hardware. At the same time PM leaves the programmer in control - all parallelisation is explicit and the parallel structure of any given program may be deduced directly from the code. This paper describes a PM implementation based on the Message Passing Interface (MPI) and Open Multi-Processing (OpenMP) standards, looking at issues involved with translating the PM parallelisation model to MPI/OpenMP protocols and considering performance in terms of the competing factors of finer-grained parallelisation and increased communication overhead. In order to maximise portability, the implementation stays within the MPI 1.3 standard as much as possible, with MPI-2 MPI-IO file handling the only significant exception. Moreover, it does not assume a thread-safe implementation of MPI. PM adopts a two-tier abstract representation of parallel hardware. A PM processor is a conceptual unit capable of efficiently executing a set of language tasks, with a complete parallel system consisting of an abstract N-dimensional array of such processors. PM processors may map to single cores executing tasks using cooperative multi-tasking, to multiple cores or even to separate processing nodes, efficiently sharing tasks using algorithms such as work stealing. While tasks may move between hardware elements within a PM processor, they may not move between processors without specific programmer intervention. Tasks are assigned to processors using a nested parallelism approach, building on ideas from Reyes et al. (2009). The main program owns all available processors. When the program enters a parallel statement then either processors are divided out among the newly generated tasks (number of new tasks < number of processors) or tasks are divided out among the available processors (number of tasks > number of processors). Nested parallel statements may further subdivide the processor set owned by a given task. Tasks or processors are distributed evenly by default, but uneven distributions are possible under programmer control. It is also possible to explicitly enable child tasks to migrate within the processor set owned by their parent task, reducing load unbalancing at the potential cost of increased inter-processor message traffic. PM incorporates some programming structures from the earlier MIST language presented at a previous EGU General Assembly, while adopting a significantly different underlying parallelisation model and type system. PM code is available at www.pm-lang.org under an unrestrictive MIT license. Reference Ruymán Reyes, Antonio J. Dorta, Francisco Almeida, Francisco de Sande, 2009. Automatic Hybrid MPI+OpenMP Code Generation with llc, Recent Advances in Parallel Virtual Machine and Message Passing Interface, Lecture Notes in Computer Science Volume 5759, 185-195

OceanXtremes: Scalable Anomaly Detection in Oceanographic Time-Series

NASA Astrophysics Data System (ADS)

Wilson, B. D.; Armstrong, E. M.; Chin, T. M.; Gill, K. M.; Greguska, F. R., III; Huang, T.; Jacob, J. C.; Quach, N.

2016-12-01

The oceanographic community must meet the challenge to rapidly identify features and anomalies in complex and voluminous observations to further science and improve decision support. Given this data-intensive reality, we are developing an anomaly detection system, called OceanXtremes, powered by an intelligent, elastic Cloud-based analytic service backend that enables execution of domain-specific, multi-scale anomaly and feature detection algorithms across the entire archive of 15 to 30-year ocean science datasets.Our parallel analytics engine is extending the NEXUS system and exploits multiple open-source technologies: Apache Cassandra as a distributed spatial "tile" cache, Apache Spark for in-memory parallel computation, and Apache Solr for spatial search and storing pre-computed tile statistics and other metadata. OceanXtremes provides these key capabilities: Parallel generation (Spark on a compute cluster) of 15 to 30-year Ocean Climatologies (e.g. sea surface temperature or SST) in hours or overnight, using simple pixel averages or customizable Gaussian-weighted "smoothing" over latitude, longitude, and time; Parallel pre-computation, tiling, and caching of anomaly fields (daily variables minus a chosen climatology) with pre-computed tile statistics; Parallel detection (over the time-series of tiles) of anomalies or phenomena by regional area-averages exceeding a specified threshold (e.g. high SST in El Nino or SST "blob" regions), or more complex, custom data mining algorithms; Shared discovery and exploration of ocean phenomena and anomalies (facet search using Solr), along with unexpected correlations between key measured variables; Scalable execution for all capabilities on a hybrid Cloud, using our on-premise OpenStack Cloud cluster or at Amazon. The key idea is that the parallel data-mining operations will be run "near" the ocean data archives (a local "network" hop) so that we can efficiently access the thousands of files making up a three decade time-series. The presentation will cover the architecture of OceanXtremes, parallelization of the climatology computation and anomaly detection algorithms using Spark, example results for SST and other time-series, and parallel performance metrics.

A Novel Design of 4-Class BCI Using Two Binary Classifiers and Parallel Mental Tasks

PubMed Central

Geng, Tao; Gan, John Q.; Dyson, Matthew; Tsui, Chun SL; Sepulveda, Francisco

2008-01-01

A novel 4-class single-trial brain computer interface (BCI) based on two (rather than four or more) binary linear discriminant analysis (LDA) classifiers is proposed, which is called a “parallel BCI.” Unlike other BCIs where mental tasks are executed and classified in a serial way one after another, the parallel BCI uses properly designed parallel mental tasks that are executed on both sides of the subject body simultaneously, which is the main novelty of the BCI paradigm used in our experiments. Each of the two binary classifiers only classifies the mental tasks executed on one side of the subject body, and the results of the two binary classifiers are combined to give the result of the 4-class BCI. Data was recorded in experiments with both real movement and motor imagery in 3 able-bodied subjects. Artifacts were not detected or removed. Offline analysis has shown that, in some subjects, the parallel BCI can generate a higher accuracy than a conventional 4-class BCI, although both of them have used the same feature selection and classification algorithms. PMID:18584040

Solution of the within-group multidimensional discrete ordinates transport equations on massively parallel architectures

NASA Astrophysics Data System (ADS)

Zerr, Robert Joseph

2011-12-01

The integral transport matrix method (ITMM) has been used as the kernel of new parallel solution methods for the discrete ordinates approximation of the within-group neutron transport equation. The ITMM abandons the repetitive mesh sweeps of the traditional source iterations (SI) scheme in favor of constructing stored operators that account for the direct coupling factors among all the cells and between the cells and boundary surfaces. The main goals of this work were to develop the algorithms that construct these operators and employ them in the solution process, determine the most suitable way to parallelize the entire procedure, and evaluate the behavior and performance of the developed methods for increasing number of processes. This project compares the effectiveness of the ITMM with the SI scheme parallelized with the Koch-Baker-Alcouffe (KBA) method. The primary parallel solution method involves a decomposition of the domain into smaller spatial sub-domains, each with their own transport matrices, and coupled together via interface boundary angular fluxes. Each sub-domain has its own set of ITMM operators and represents an independent transport problem. Multiple iterative parallel solution methods have investigated, including parallel block Jacobi (PBJ), parallel red/black Gauss-Seidel (PGS), and parallel GMRES (PGMRES). The fastest observed parallel solution method, PGS, was used in a weak scaling comparison with the PARTISN code. Compared to the state-of-the-art SI-KBA with diffusion synthetic acceleration (DSA), this new method without acceleration/preconditioning is not competitive for any problem parameters considered. The best comparisons occur for problems that are difficult for SI DSA, namely highly scattering and optically thick. SI DSA execution time curves are generally steeper than the PGS ones. However, until further testing is performed it cannot be concluded that SI DSA does not outperform the ITMM with PGS even on several thousand or tens of thousands of processors. The PGS method does outperform SI DSA for the periodic heterogeneous layers (PHL) configuration problems. Although this demonstrates a relative strength/weakness between the two methods, the practicality of these problems is much less, further limiting instances where it would be beneficial to select ITMM over SI DSA. The results strongly indicate a need for a robust, stable, and efficient acceleration method (or preconditioner for PGMRES). The spatial multigrid (SMG) method is currently incomplete in that it does not work for all cases considered and does not effectively improve the convergence rate for all values of scattering ratio c or cell dimension h. Nevertheless, it does display the desired trend for highly scattering, optically thin problems. That is, it tends to lower the rate of growth of number of iterations with increasing number of processes, P, while not increasing the number of additional operations per iteration to the extent that the total execution time of the rapidly converging accelerated iterations exceeds that of the slower unaccelerated iterations. A predictive parallel performance model has been developed for the PBJ method. Timing tests were performed such that trend lines could be fitted to the data for the different components and used to estimate the execution times. Applied to the weak scaling results, the model notably underestimates construction time, but combined with a slight overestimation in iterative solution time, the model predicts total execution time very well for large P. It also does a decent job with the strong scaling results, closely predicting the construction time and time per iteration, especially as P increases. Although not shown to be competitive up to 1,024 processing elements with the current state of the art, the parallelized ITMM exhibits promising scaling trends. Ultimately, compared to the KBA method, the parallelized ITMM may be found to be a very attractive option for transport calculations spatially decomposed over several tens of thousands of processes. Acceleration/preconditioning of the parallelized ITMM once developed will improve the convergence rate and improve its competitiveness. (Abstract shortened by UMI.)

Discrete Event Modeling and Massively Parallel Execution of Epidemic Outbreak Phenomena

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perumalla, Kalyan S; Seal, Sudip K

2011-01-01

In complex phenomena such as epidemiological outbreaks, the intensity of inherent feedback effects and the significant role of transients in the dynamics make simulation the only effective method for proactive, reactive or post-facto analysis. The spatial scale, runtime speed, and behavioral detail needed in detailed simulations of epidemic outbreaks make it necessary to use large-scale parallel processing. Here, an optimistic parallel execution of a new discrete event formulation of a reaction-diffusion simulation model of epidemic propagation is presented to facilitate in dramatically increasing the fidelity and speed by which epidemiological simulations can be performed. Rollback support needed during optimistic parallelmore » execution is achieved by combining reverse computation with a small amount of incremental state saving. Parallel speedup of over 5,500 and other runtime performance metrics of the system are observed with weak-scaling execution on a small (8,192-core) Blue Gene / P system, while scalability with a weak-scaling speedup of over 10,000 is demonstrated on 65,536 cores of a large Cray XT5 system. Scenarios representing large population sizes exceeding several hundreds of millions of individuals in the largest cases are successfully exercised to verify model scalability.« less

A Distributed Parallel Genetic Algorithm of Placement Strategy for Virtual Machines Deployment on Cloud Platform

PubMed Central

Dong, Yu-Shuang; Xu, Gao-Chao; Fu, Xiao-Dong

2014-01-01

The cloud platform provides various services to users. More and more cloud centers provide infrastructure as the main way of operating. To improve the utilization rate of the cloud center and to decrease the operating cost, the cloud center provides services according to requirements of users by sharding the resources with virtualization. Considering both QoS for users and cost saving for cloud computing providers, we try to maximize performance and minimize energy cost as well. In this paper, we propose a distributed parallel genetic algorithm (DPGA) of placement strategy for virtual machines deployment on cloud platform. It executes the genetic algorithm parallelly and distributedly on several selected physical hosts in the first stage. Then it continues to execute the genetic algorithm of the second stage with solutions obtained from the first stage as the initial population. The solution calculated by the genetic algorithm of the second stage is the optimal one of the proposed approach. The experimental results show that the proposed placement strategy of VM deployment can ensure QoS for users and it is more effective and more energy efficient than other placement strategies on the cloud platform. PMID:25097872

A distributed parallel genetic algorithm of placement strategy for virtual machines deployment on cloud platform.

PubMed

Dong, Yu-Shuang; Xu, Gao-Chao; Fu, Xiao-Dong

2014-01-01

The cloud platform provides various services to users. More and more cloud centers provide infrastructure as the main way of operating. To improve the utilization rate of the cloud center and to decrease the operating cost, the cloud center provides services according to requirements of users by sharding the resources with virtualization. Considering both QoS for users and cost saving for cloud computing providers, we try to maximize performance and minimize energy cost as well. In this paper, we propose a distributed parallel genetic algorithm (DPGA) of placement strategy for virtual machines deployment on cloud platform. It executes the genetic algorithm parallelly and distributedly on several selected physical hosts in the first stage. Then it continues to execute the genetic algorithm of the second stage with solutions obtained from the first stage as the initial population. The solution calculated by the genetic algorithm of the second stage is the optimal one of the proposed approach. The experimental results show that the proposed placement strategy of VM deployment can ensure QoS for users and it is more effective and more energy efficient than other placement strategies on the cloud platform.

Optimization of atmospheric transport models on HPC platforms

NASA Astrophysics Data System (ADS)

de la Cruz, Raúl; Folch, Arnau; Farré, Pau; Cabezas, Javier; Navarro, Nacho; Cela, José María

2016-12-01

The performance and scalability of atmospheric transport models on high performance computing environments is often far from optimal for multiple reasons including, for example, sequential input and output, synchronous communications, work unbalance, memory access latency or lack of task overlapping. We investigate how different software optimizations and porting to non general-purpose hardware architectures improve code scalability and execution times considering, as an example, the FALL3D volcanic ash transport model. To this purpose, we implement the FALL3D model equations in the WARIS framework, a software designed from scratch to solve in a parallel and efficient way different geoscience problems on a wide variety of architectures. In addition, we consider further improvements in WARIS such as hybrid MPI-OMP parallelization, spatial blocking, auto-tuning and thread affinity. Considering all these aspects together, the FALL3D execution times for a realistic test case running on general-purpose cluster architectures (Intel Sandy Bridge) decrease by a factor between 7 and 40 depending on the grid resolution. Finally, we port the application to Intel Xeon Phi (MIC) and NVIDIA GPUs (CUDA) accelerator-based architectures and compare performance, cost and power consumption on all the architectures. Implications on time-constrained operational model configurations are discussed.

Two schemes for rapid generation of digital video holograms using PC cluster

NASA Astrophysics Data System (ADS)

Park, Hanhoon; Song, Joongseok; Kim, Changseob; Park, Jong-Il

2017-12-01

Computer-generated holography (CGH), which is a process of generating digital holograms, is computationally expensive. Recently, several methods/systems of parallelizing the process using graphic processing units (GPUs) have been proposed. Indeed, use of multiple GPUs or a personal computer (PC) cluster (each PC with GPUs) enabled great improvements in the process speed. However, extant literature has less often explored systems involving rapid generation of multiple digital holograms and specialized systems for rapid generation of a digital video hologram. This study proposes a system that uses a PC cluster and is able to more efficiently generate a video hologram. The proposed system is designed to simultaneously generate multiple frames and accelerate the generation by parallelizing the CGH computations across a number of frames, as opposed to separately generating each individual frame while parallelizing the CGH computations within each frame. The proposed system also enables the subprocesses for generating each frame to execute in parallel through multithreading. With these two schemes, the proposed system significantly reduced the data communication time for generating a digital hologram when compared with that of the state-of-the-art system.

PVT: An Efficient Computational Procedure to Speed up Next-generation Sequence Analysis

PubMed Central

2014-01-01

Background High-throughput Next-Generation Sequencing (NGS) techniques are advancing genomics and molecular biology research. This technology generates substantially large data which puts up a major challenge to the scientists for an efficient, cost and time effective solution to analyse such data. Further, for the different types of NGS data, there are certain common challenging steps involved in analysing those data. Spliced alignment is one such fundamental step in NGS data analysis which is extremely computational intensive as well as time consuming. There exists serious problem even with the most widely used spliced alignment tools. TopHat is one such widely used spliced alignment tools which although supports multithreading, does not efficiently utilize computational resources in terms of CPU utilization and memory. Here we have introduced PVT (Pipelined Version of TopHat) where we take up a modular approach by breaking TopHat’s serial execution into a pipeline of multiple stages, thereby increasing the degree of parallelization and computational resource utilization. Thus we address the discrepancies in TopHat so as to analyze large NGS data efficiently. Results We analysed the SRA dataset (SRX026839 and SRX026838) consisting of single end reads and SRA data SRR1027730 consisting of paired-end reads. We used TopHat v2.0.8 to analyse these datasets and noted the CPU usage, memory footprint and execution time during spliced alignment. With this basic information, we designed PVT, a pipelined version of TopHat that removes the redundant computational steps during ‘spliced alignment’ and breaks the job into a pipeline of multiple stages (each comprising of different step(s)) to improve its resource utilization, thus reducing the execution time. Conclusions PVT provides an improvement over TopHat for spliced alignment of NGS data analysis. PVT thus resulted in the reduction of the execution time to ~23% for the single end read dataset. Further, PVT designed for paired end reads showed an improved performance of ~41% over TopHat (for the chosen data) with respect to execution time. Moreover we propose PVT-Cloud which implements PVT pipeline in cloud computing system. PMID:24894600

PVT: an efficient computational procedure to speed up next-generation sequence analysis.

PubMed

Maji, Ranjan Kumar; Sarkar, Arijita; Khatua, Sunirmal; Dasgupta, Subhasis; Ghosh, Zhumur

2014-06-04

High-throughput Next-Generation Sequencing (NGS) techniques are advancing genomics and molecular biology research. This technology generates substantially large data which puts up a major challenge to the scientists for an efficient, cost and time effective solution to analyse such data. Further, for the different types of NGS data, there are certain common challenging steps involved in analysing those data. Spliced alignment is one such fundamental step in NGS data analysis which is extremely computational intensive as well as time consuming. There exists serious problem even with the most widely used spliced alignment tools. TopHat is one such widely used spliced alignment tools which although supports multithreading, does not efficiently utilize computational resources in terms of CPU utilization and memory. Here we have introduced PVT (Pipelined Version of TopHat) where we take up a modular approach by breaking TopHat's serial execution into a pipeline of multiple stages, thereby increasing the degree of parallelization and computational resource utilization. Thus we address the discrepancies in TopHat so as to analyze large NGS data efficiently. We analysed the SRA dataset (SRX026839 and SRX026838) consisting of single end reads and SRA data SRR1027730 consisting of paired-end reads. We used TopHat v2.0.8 to analyse these datasets and noted the CPU usage, memory footprint and execution time during spliced alignment. With this basic information, we designed PVT, a pipelined version of TopHat that removes the redundant computational steps during 'spliced alignment' and breaks the job into a pipeline of multiple stages (each comprising of different step(s)) to improve its resource utilization, thus reducing the execution time. PVT provides an improvement over TopHat for spliced alignment of NGS data analysis. PVT thus resulted in the reduction of the execution time to ~23% for the single end read dataset. Further, PVT designed for paired end reads showed an improved performance of ~41% over TopHat (for the chosen data) with respect to execution time. Moreover we propose PVT-Cloud which implements PVT pipeline in cloud computing system.

THC-MP: High performance numerical simulation of reactive transport and multiphase flow in porous media

NASA Astrophysics Data System (ADS)

Wei, Xiaohui; Li, Weishan; Tian, Hailong; Li, Hongliang; Xu, Haixiao; Xu, Tianfu

2015-07-01

The numerical simulation of multiphase flow and reactive transport in the porous media on complex subsurface problem is a computationally intensive application. To meet the increasingly computational requirements, this paper presents a parallel computing method and architecture. Derived from TOUGHREACT that is a well-established code for simulating subsurface multi-phase flow and reactive transport problems, we developed a high performance computing THC-MP based on massive parallel computer, which extends greatly on the computational capability for the original code. The domain decomposition method was applied to the coupled numerical computing procedure in the THC-MP. We designed the distributed data structure, implemented the data initialization and exchange between the computing nodes and the core solving module using the hybrid parallel iterative and direct solver. Numerical accuracy of the THC-MP was verified through a CO2 injection-induced reactive transport problem by comparing the results obtained from the parallel computing and sequential computing (original code). Execution efficiency and code scalability were examined through field scale carbon sequestration applications on the multicore cluster. The results demonstrate successfully the enhanced performance using the THC-MP on parallel computing facilities.

Data communications in a parallel active messaging interface of a parallel computer

DOEpatents

Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E

2013-10-29

Data communications in a parallel active messaging interface (`PAMI`) of a parallel computer, the parallel computer including a plurality of compute nodes that execute a parallel application, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes and the endpoints coupled for data communications through the PAMI and through data communications resources, including receiving in an origin endpoint of the PAMI a data communications instruction, the instruction characterized by an instruction type, the instruction specifying a transmission of transfer data from the origin endpoint to a target endpoint and transmitting, in accordance with the instruction type, the transfer data from the origin endpoint to the target endpoint.

Run-time parallelization and scheduling of loops

NASA Technical Reports Server (NTRS)

Saltz, Joel H.; Mirchandaney, Ravi; Crowley, Kay

1991-01-01

Run-time methods are studied to automatically parallelize and schedule iterations of a do loop in certain cases where compile-time information is inadequate. The methods presented involve execution time preprocessing of the loop. At compile-time, these methods set up the framework for performing a loop dependency analysis. At run-time, wavefronts of concurrently executable loop iterations are identified. Using this wavefront information, loop iterations are reordered for increased parallelism. Symbolic transformation rules are used to produce: inspector procedures that perform execution time preprocessing, and executors or transformed versions of source code loop structures. These transformed loop structures carry out the calculations planned in the inspector procedures. Performance results are presented from experiments conducted on the Encore Multimax. These results illustrate that run-time reordering of loop indexes can have a significant impact on performance.

The Automated Instrumentation and Monitoring System (AIMS): Design and Architecture. 3.2

NASA Technical Reports Server (NTRS)

Yan, Jerry C.; Schmidt, Melisa; Schulbach, Cathy; Bailey, David (Technical Monitor)

1997-01-01

Whether a researcher is designing the 'next parallel programming paradigm', another 'scalable multiprocessor' or investigating resource allocation algorithms for multiprocessors, a facility that enables parallel program execution to be captured and displayed is invaluable. Careful analysis of such information can help computer and software architects to capture, and therefore, exploit behavioral variations among/within various parallel programs to take advantage of specific hardware characteristics. A software tool-set that facilitates performance evaluation of parallel applications on multiprocessors has been put together at NASA Ames Research Center under the sponsorship of NASA's High Performance Computing and Communications Program over the past five years. The Automated Instrumentation and Monitoring Systematic has three major software components: a source code instrumentor which automatically inserts active event recorders into program source code before compilation; a run-time performance monitoring library which collects performance data; and a visualization tool-set which reconstructs program execution based on the data collected. Besides being used as a prototype for developing new techniques for instrumenting, monitoring and presenting parallel program execution, AIMS is also being incorporated into the run-time environments of various hardware testbeds to evaluate their impact on user productivity. Currently, the execution of FORTRAN and C programs on the Intel Paragon and PALM workstations can be automatically instrumented and monitored. Performance data thus collected can be displayed graphically on various workstations. The process of performance tuning with AIMS will be illustrated using various NAB Parallel Benchmarks. This report includes a description of the internal architecture of AIMS and a listing of the source code.

Endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface of a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Archer, Charles J; Blocksome, Michael A; Cernohous, Bob R

Endpoint-based parallel data processing with non-blocking collective instructions in a PAMI of a parallel computer is disclosed. The PAMI is composed of data communications endpoints, each including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task. The compute nodes are coupled for data communications through the PAMI. The parallel application establishes a data communications geometry specifying a set of endpoints that are used in collective operations of the PAMI by associating with the geometry a list of collective algorithms valid for use with themore » endpoints of the geometry; registering in each endpoint in the geometry a dispatch callback function for a collective operation; and executing without blocking, through a single one of the endpoints in the geometry, an instruction for the collective operation.« less

Using Hadoop MapReduce for Parallel Genetic Algorithms: A Comparison of the Global, Grid and Island Models.

PubMed

Ferrucci, Filomena; Salza, Pasquale; Sarro, Federica

2017-06-29

The need to improve the scalability of Genetic Algorithms (GAs) has motivated the research on Parallel Genetic Algorithms (PGAs), and different technologies and approaches have been used. Hadoop MapReduce represents one of the most mature technologies to develop parallel algorithms. Based on the fact that parallel algorithms introduce communication overhead, the aim of the present work is to understand if, and possibly when, the parallel GAs solutions using Hadoop MapReduce show better performance than sequential versions in terms of execution time. Moreover, we are interested in understanding which PGA model can be most effective among the global, grid, and island models. We empirically assessed the performance of these three parallel models with respect to a sequential GA on a software engineering problem, evaluating the execution time and the achieved speedup. We also analysed the behaviour of the parallel models in relation to the overhead produced by the use of Hadoop MapReduce and the GAs' computational effort, which gives a more machine-independent measure of these algorithms. We exploited three problem instances to differentiate the computation load and three cluster configurations based on 2, 4, and 8 parallel nodes. Moreover, we estimated the costs of the execution of the experimentation on a potential cloud infrastructure, based on the pricing of the major commercial cloud providers. The empirical study revealed that the use of PGA based on the island model outperforms the other parallel models and the sequential GA for all the considered instances and clusters. Using 2, 4, and 8 nodes, the island model achieves an average speedup over the three datasets of 1.8, 3.4, and 7.0 times, respectively. Hadoop MapReduce has a set of different constraints that need to be considered during the design and the implementation of parallel algorithms. The overhead of data store (i.e., HDFS) accesses, communication, and latency requires solutions that reduce data store operations. For this reason, the island model is more suitable for PGAs than the global and grid model, also in terms of costs when executed on a commercial cloud provider.

Decision-making under risk conditions is susceptible to interference by a secondary executive task.

PubMed

Starcke, Katrin; Pawlikowski, Mirko; Wolf, Oliver T; Altstötter-Gleich, Christine; Brand, Matthias

2011-05-01

Recent research suggests two ways of making decisions: an intuitive and an analytical one. The current study examines whether a secondary executive task interferes with advantageous decision-making in the Game of Dice Task (GDT), a decision-making task with explicit and stable rules that taps executive functioning. One group of participants performed the original GDT solely, two groups performed either the GDT and a 1-back or a 2-back working memory task as a secondary task simultaneously. Results show that the group which performed the GDT and the secondary task with high executive load (2-back) decided less advantageously than the group which did not perform a secondary executive task. These findings give further evidence for the view that decision-making under risky conditions taps into the rational-analytical system which acts in a serial and not parallel way as performance on the GDT is disturbed by a parallel task that also requires executive resources.

schwimmbad: A uniform interface to parallel processing pools in Python

NASA Astrophysics Data System (ADS)

Price-Whelan, Adrian M.; Foreman-Mackey, Daniel

2017-09-01

Many scientific and computing problems require doing some calculation on all elements of some data set. If the calculations can be executed in parallel (i.e. without any communication between calculations), these problems are said to be perfectly parallel. On computers with multiple processing cores, these tasks can be distributed and executed in parallel to greatly improve performance. A common paradigm for handling these distributed computing problems is to use a processing "pool": the "tasks" (the data) are passed in bulk to the pool, and the pool handles distributing the tasks to a number of worker processes when available. schwimmbad provides a uniform interface to parallel processing pools and enables switching easily between local development (e.g., serial processing or with multiprocessing) and deployment on a cluster or supercomputer (via, e.g., MPI or JobLib).

Processing data communications events by awakening threads in parallel active messaging interface of a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Archer, Charles J.; Blocksome, Michael A.; Ratterman, Joseph D.

Processing data communications events in a parallel active messaging interface (`PAMI`) of a parallel computer that includes compute nodes that execute a parallel application, with the PAMI including data communications endpoints, and the endpoints are coupled for data communications through the PAMI and through other data communications resources, including determining by an advance function that there are no actionable data communications events pending for its context, placing by the advance function its thread of execution into a wait state, waiting for a subsequent data communications event for the context; responsive to occurrence of a subsequent data communications event for themore » context, awakening by the thread from the wait state; and processing by the advance function the subsequent data communications event now pending for the context.« less

Parallel efficient rate control methods for JPEG 2000

NASA Astrophysics Data System (ADS)

Martínez-del-Amor, Miguel Á.; Bruns, Volker; Sparenberg, Heiko

2017-09-01

Since the introduction of JPEG 2000, several rate control methods have been proposed. Among them, post-compression rate-distortion optimization (PCRD-Opt) is the most widely used, and the one recommended by the standard. The approach followed by this method is to first compress the entire image split in code blocks, and subsequently, optimally truncate the set of generated bit streams according to the maximum target bit rate constraint. The literature proposes various strategies on how to estimate ahead of time where a block will get truncated in order to stop the execution prematurely and save time. However, none of them have been defined bearing in mind a parallel implementation. Today, multi-core and many-core architectures are becoming popular for JPEG 2000 codecs implementations. Therefore, in this paper, we analyze how some techniques for efficient rate control can be deployed in GPUs. In order to do that, the design of our GPU-based codec is extended, allowing stopping the process at a given point. This extension also harnesses a higher level of parallelism on the GPU, leading to up to 40% of speedup with 4K test material on a Titan X. In a second step, three selected rate control methods are adapted and implemented in our parallel encoder. A comparison is then carried out, and used to select the best candidate to be deployed in a GPU encoder, which gave an extra 40% of speedup in those situations where it was really employed.

A High Order, Locally-Adaptive Method for the Navier-Stokes Equations

NASA Astrophysics Data System (ADS)

Chan, Daniel

1998-11-01

I have extended the FOSLS method of Cai, Manteuffel and McCormick (1997) and implemented it within the framework of a spectral element formulation using the Legendre polynomial basis function. The FOSLS method solves the Navier-Stokes equations as a system of coupled first-order equations and provides the ellipticity that is needed for fast iterative matrix solvers like multigrid to operate efficiently. Each element is treated as an object and its properties are self-contained. Only C^0 continuity is imposed across element interfaces; this design allows local grid refinement and coarsening without the burden of having an elaborate data structure, since only information along element boundaries is needed. With the FORTRAN 90 programming environment, I can maintain a high computational efficiency by employing a hybrid parallel processing model. The OpenMP directives provides parallelism in the loop level which is executed in a shared-memory SMP and the MPI protocol allows the distribution of elements to a cluster of SMP's connected via a commodity network. This talk will provide timing results and a comparison with a second order finite difference method.

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

NASA Astrophysics Data System (ADS)

Moran, Steven; Gaonkar, Bilwaj; Whitehead, William; Wolk, Aidan; Macyszyn, Luke; Iyer, Subramanian S.

2018-03-01

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the 1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

A heuristic re-mapping algorithm reducing inter-level communication in SAMR applications.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Steensland, Johan; Ray, Jaideep

2003-07-01

This paper aims at decreasing execution time for large-scale structured adaptive mesh refinement (SAMR) applications by proposing a new heuristic re-mapping algorithm and experimentally showing its effectiveness in reducing inter-level communication. Tests were done for five different SAMR applications. The overall goal is to engineer a dynamically adaptive meta-partitioner capable of selecting and configuring the most appropriate partitioning strategy at run-time based on current system and application state. Such a metapartitioner can significantly reduce execution times for general SAMR applications. Computer simulations of physical phenomena are becoming increasingly popular as they constitute an important complement to real-life testing. In manymore » cases, such simulations are based on solving partial differential equations by numerical methods. Adaptive methods are crucial to efficiently utilize computer resources such as memory and CPU. But even with adaption, the simulations are computationally demanding and yield huge data sets. Thus parallelization and the efficient partitioning of data become issues of utmost importance. Adaption causes the workload to change dynamically, calling for dynamic (re-) partitioning to maintain efficient resource utilization. The proposed heuristic algorithm reduced inter-level communication substantially. Since the complexity of the proposed algorithm is low, this decrease comes at a relatively low cost. As a consequence, we draw the conclusion that the proposed re-mapping algorithm would be useful to lower overall execution times for many large SAMR applications. Due to its usefulness and its parameterization, the proposed algorithm would constitute a natural and important component of the meta-partitioner.« less

High-Frequency Replanning Under Uncertainty Using Parallel Sampling-Based Motion Planning

PubMed Central

Sun, Wen; Patil, Sachin; Alterovitz, Ron

2015-01-01

As sampling-based motion planners become faster, they can be re-executed more frequently by a robot during task execution to react to uncertainty in robot motion, obstacle motion, sensing noise, and uncertainty in the robot’s kinematic model. We investigate and analyze high-frequency replanning (HFR), where, during each period, fast sampling-based motion planners are executed in parallel as the robot simultaneously executes the first action of the best motion plan from the previous period. We consider discrete-time systems with stochastic nonlinear (but linearizable) dynamics and observation models with noise drawn from zero mean Gaussian distributions. The objective is to maximize the probability of success (i.e., avoid collision with obstacles and reach the goal) or to minimize path length subject to a lower bound on the probability of success. We show that, as parallel computation power increases, HFR offers asymptotic optimality for these objectives during each period for goal-oriented problems. We then demonstrate the effectiveness of HFR for holonomic and nonholonomic robots including car-like vehicles and steerable medical needles. PMID:26279645

Distributed computing for membrane-based modeling of action potential propagation.

PubMed

Porras, D; Rogers, J M; Smith, W M; Pollard, A E

2000-08-01

Action potential propagation simulations with physiologic membrane currents and macroscopic tissue dimensions are computationally expensive. We, therefore, analyzed distributed computing schemes to reduce execution time in workstation clusters by parallelizing solutions with message passing. Four schemes were considered in two-dimensional monodomain simulations with the Beeler-Reuter membrane equations. Parallel speedups measured with each scheme were compared to theoretical speedups, recognizing the relationship between speedup and code portions that executed serially. A data decomposition scheme based on total ionic current provided the best performance. Analysis of communication latencies in that scheme led to a load-balancing algorithm in which measured speedups at 89 +/- 2% and 75 +/- 8% of theoretical speedups were achieved in homogeneous and heterogeneous clusters of workstations. Speedups in this scheme with the Luo-Rudy dynamic membrane equations exceeded 3.0 with eight distributed workstations. Cluster speedups were comparable to those measured during parallel execution on a shared memory machine.

Scheduling optimization of design stream line for production research and development projects

NASA Astrophysics Data System (ADS)

Liu, Qinming; Geng, Xiuli; Dong, Ming; Lv, Wenyuan; Ye, Chunming

2017-05-01

In a development project, efficient design stream line scheduling is difficult and important owing to large design imprecision and the differences in the skills and skill levels of employees. The relative skill levels of employees are denoted as fuzzy numbers. Multiple execution modes are generated by scheduling different employees for design tasks. An optimization model of a design stream line scheduling problem is proposed with the constraints of multiple executive modes, multi-skilled employees and precedence. The model considers the parallel design of multiple projects, different skills of employees, flexible multi-skilled employees and resource constraints. The objective function is to minimize the duration and tardiness of the project. Moreover, a two-dimensional particle swarm algorithm is used to find the optimal solution. To illustrate the validity of the proposed method, a case is examined in this article, and the results support the feasibility and effectiveness of the proposed model and algorithm.

A high performance scientific cloud computing environment for materials simulations

NASA Astrophysics Data System (ADS)

Jorissen, K.; Vila, F. D.; Rehr, J. J.

2012-09-01

We describe the development of a scientific cloud computing (SCC) platform that offers high performance computation capability. The platform consists of a scientific virtual machine prototype containing a UNIX operating system and several materials science codes, together with essential interface tools (an SCC toolset) that offers functionality comparable to local compute clusters. In particular, our SCC toolset provides automatic creation of virtual clusters for parallel computing, including tools for execution and monitoring performance, as well as efficient I/O utilities that enable seamless connections to and from the cloud. Our SCC platform is optimized for the Amazon Elastic Compute Cloud (EC2). We present benchmarks for prototypical scientific applications and demonstrate performance comparable to local compute clusters. To facilitate code execution and provide user-friendly access, we have also integrated cloud computing capability in a JAVA-based GUI. Our SCC platform may be an alternative to traditional HPC resources for materials science or quantum chemistry applications.

A genetic algorithm-based job scheduling model for big data analytics.

PubMed

Lu, Qinghua; Li, Shanshan; Zhang, Weishan; Zhang, Lei

Big data analytics (BDA) applications are a new category of software applications that process large amounts of data using scalable parallel processing infrastructure to obtain hidden value. Hadoop is the most mature open-source big data analytics framework, which implements the MapReduce programming model to process big data with MapReduce jobs. Big data analytics jobs are often continuous and not mutually separated. The existing work mainly focuses on executing jobs in sequence, which are often inefficient and consume high energy. In this paper, we propose a genetic algorithm-based job scheduling model for big data analytics applications to improve the efficiency of big data analytics. To implement the job scheduling model, we leverage an estimation module to predict the performance of clusters when executing analytics jobs. We have evaluated the proposed job scheduling model in terms of feasibility and accuracy.

Stress and decision making: neural correlates of the interaction between stress, executive functions, and decision making under risk.

PubMed

Gathmann, Bettina; Schulte, Frank P; Maderwald, Stefan; Pawlikowski, Mirko; Starcke, Katrin; Schäfer, Lena C; Schöler, Tobias; Wolf, Oliver T; Brand, Matthias

2014-03-01

Stress and additional load on the executive system, produced by a parallel working memory task, impair decision making under risk. However, the combination of stress and a parallel task seems to preserve the decision-making performance [e.g., operationalized by the Game of Dice Task (GDT)] from decreasing, probably by a switch from serial to parallel processing. The question remains how the brain manages such demanding decision-making situations. The current study used a 7-tesla magnetic resonance imaging (MRI) system in order to investigate the underlying neural correlates of the interaction between stress (induced by the Trier Social Stress Test), risky decision making (GDT), and a parallel executive task (2-back task) to get a better understanding of those behavioral findings. The results show that on a behavioral level, stressed participants did not show significant differences in task performance. Interestingly, when comparing the stress group (SG) with the control group, the SG showed a greater increase in neural activation in the anterior prefrontal cortex when performing the 2-back task simultaneously with the GDT than when performing each task alone. This brain area is associated with parallel processing. Thus, the results may suggest that in stressful dual-tasking situations, where a decision has to be made when in parallel working memory is demanded, a stronger activation of a brain area associated with parallel processing takes place. The findings are in line with the idea that stress seems to trigger a switch from serial to parallel processing in demanding dual-tasking situations.

Efficient particle-in-cell simulation of auroral plasma phenomena using a CUDA enabled graphics processing unit

NASA Astrophysics Data System (ADS)

Sewell, Stephen

This thesis introduces a software framework that effectively utilizes low-cost commercially available Graphic Processing Units (GPUs) to simulate complex scientific plasma phenomena that are modeled using the Particle-In-Cell (PIC) paradigm. The software framework that was developed conforms to the Compute Unified Device Architecture (CUDA), a standard for general purpose graphic processing that was introduced by NVIDIA Corporation. This framework has been verified for correctness and applied to advance the state of understanding of the electromagnetic aspects of the development of the Aurora Borealis and Aurora Australis. For each phase of the PIC methodology, this research has identified one or more methods to exploit the problem's natural parallelism and effectively map it for execution on the graphic processing unit and its host processor. The sources of overhead that can reduce the effectiveness of parallelization for each of these methods have also been identified. One of the novel aspects of this research was the utilization of particle sorting during the grid interpolation phase. The final representation resulted in simulations that executed about 38 times faster than simulations that were run on a single-core general-purpose processing system. The scalability of this framework to larger problem sizes and future generation systems has also been investigated.

Parallel, Asynchronous Executive (PAX): System concepts, facilities, and architecture

NASA Technical Reports Server (NTRS)

Jones, W. H.

1983-01-01

The Parallel, Asynchronous Executive (PAX) is a software operating system simulation that allows many computers to work on a single problem at the same time. PAX is currently implemented on a UNIVAC 1100/42 computer system. Independent UNIVAC runstreams are used to simulate independent computers. Data are shared among independent UNIVAC runstreams through shared mass-storage files. PAX has achieved the following: (1) applied several computing processes simultaneously to a single, logically unified problem; (2) resolved most parallel processor conflicts by careful work assignment; (3) resolved by means of worker requests to PAX all conflicts not resolved by work assignment; (4) provided fault isolation and recovery mechanisms to meet the problems of an actual parallel, asynchronous processing machine. Additionally, one real-life problem has been constructed for the PAX environment. This is CASPER, a collection of aerodynamic and structural dynamic problem simulation routines. CASPER is not discussed in this report except to provide examples of parallel-processing techniques.

Towards a HPC-oriented parallel implementation of a learning algorithm for bioinformatics applications

PubMed Central

2014-01-01

Background The huge quantity of data produced in Biomedical research needs sophisticated algorithmic methodologies for its storage, analysis, and processing. High Performance Computing (HPC) appears as a magic bullet in this challenge. However, several hard to solve parallelization and load balancing problems arise in this context. Here we discuss the HPC-oriented implementation of a general purpose learning algorithm, originally conceived for DNA analysis and recently extended to treat uncertainty on data (U-BRAIN). The U-BRAIN algorithm is a learning algorithm that finds a Boolean formula in disjunctive normal form (DNF), of approximately minimum complexity, that is consistent with a set of data (instances) which may have missing bits. The conjunctive terms of the formula are computed in an iterative way by identifying, from the given data, a family of sets of conditions that must be satisfied by all the positive instances and violated by all the negative ones; such conditions allow the computation of a set of coefficients (relevances) for each attribute (literal), that form a probability distribution, allowing the selection of the term literals. The great versatility that characterizes it, makes U-BRAIN applicable in many of the fields in which there are data to be analyzed. However the memory and the execution time required by the running are of O(n3) and of O(n5) order, respectively, and so, the algorithm is unaffordable for huge data sets. Results We find mathematical and programming solutions able to lead us towards the implementation of the algorithm U-BRAIN on parallel computers. First we give a Dynamic Programming model of the U-BRAIN algorithm, then we minimize the representation of the relevances. When the data are of great size we are forced to use the mass memory, and depending on where the data are actually stored, the access times can be quite different. According to the evaluation of algorithmic efficiency based on the Disk Model, in order to reduce the costs of the communications between different memories (RAM, Cache, Mass, Virtual) and to achieve efficient I/O performance, we design a mass storage structure able to access its data with a high degree of temporal and spatial locality. Then we develop a parallel implementation of the algorithm. We model it as a SPMD system together to a Message-Passing Programming Paradigm. Here, we adopt the high-level message-passing systems MPI (Message Passing Interface) in the version for the Java programming language, MPJ. The parallel processing is organized into four stages: partitioning, communication, agglomeration and mapping. The decomposition of the U-BRAIN algorithm determines the necessity of a communication protocol design among the processors involved. Efficient synchronization design is also discussed. Conclusions In the context of a collaboration between public and private institutions, the parallel model of U-BRAIN has been implemented and tested on the INTEL XEON E7xxx and E5xxx family of the CRESCO structure of Italian National Agency for New Technologies, Energy and Sustainable Economic Development (ENEA), developed in the framework of the European Grid Infrastructure (EGI), a series of efforts to provide access to high-throughput computing resources across Europe using grid computing techniques. The implementation is able to minimize both the memory space and the execution time. The test data used in this study are IPDATA (Irvine Primate splice- junction DATA set), a subset of HS3D (Homo Sapiens Splice Sites Dataset) and a subset of COSMIC (the Catalogue of Somatic Mutations in Cancer). The execution time and the speed-up on IPDATA reach the best values within about 90 processors. Then the parallelization advantage is balanced by the greater cost of non-local communications between the processors. A similar behaviour is evident on HS3D, but at a greater number of processors, so evidencing the direct relationship between data size and parallelization gain. This behaviour is confirmed on COSMIC. Overall, the results obtained show that the parallel version is up to 30 times faster than the serial one. PMID:25077818

Towards a HPC-oriented parallel implementation of a learning algorithm for bioinformatics applications.

PubMed

D'Angelo, Gianni; Rampone, Salvatore

2014-01-01

The huge quantity of data produced in Biomedical research needs sophisticated algorithmic methodologies for its storage, analysis, and processing. High Performance Computing (HPC) appears as a magic bullet in this challenge. However, several hard to solve parallelization and load balancing problems arise in this context. Here we discuss the HPC-oriented implementation of a general purpose learning algorithm, originally conceived for DNA analysis and recently extended to treat uncertainty on data (U-BRAIN). The U-BRAIN algorithm is a learning algorithm that finds a Boolean formula in disjunctive normal form (DNF), of approximately minimum complexity, that is consistent with a set of data (instances) which may have missing bits. The conjunctive terms of the formula are computed in an iterative way by identifying, from the given data, a family of sets of conditions that must be satisfied by all the positive instances and violated by all the negative ones; such conditions allow the computation of a set of coefficients (relevances) for each attribute (literal), that form a probability distribution, allowing the selection of the term literals. The great versatility that characterizes it, makes U-BRAIN applicable in many of the fields in which there are data to be analyzed. However the memory and the execution time required by the running are of O(n(3)) and of O(n(5)) order, respectively, and so, the algorithm is unaffordable for huge data sets. We find mathematical and programming solutions able to lead us towards the implementation of the algorithm U-BRAIN on parallel computers. First we give a Dynamic Programming model of the U-BRAIN algorithm, then we minimize the representation of the relevances. When the data are of great size we are forced to use the mass memory, and depending on where the data are actually stored, the access times can be quite different. According to the evaluation of algorithmic efficiency based on the Disk Model, in order to reduce the costs of the communications between different memories (RAM, Cache, Mass, Virtual) and to achieve efficient I/O performance, we design a mass storage structure able to access its data with a high degree of temporal and spatial locality. Then we develop a parallel implementation of the algorithm. We model it as a SPMD system together to a Message-Passing Programming Paradigm. Here, we adopt the high-level message-passing systems MPI (Message Passing Interface) in the version for the Java programming language, MPJ. The parallel processing is organized into four stages: partitioning, communication, agglomeration and mapping. The decomposition of the U-BRAIN algorithm determines the necessity of a communication protocol design among the processors involved. Efficient synchronization design is also discussed. In the context of a collaboration between public and private institutions, the parallel model of U-BRAIN has been implemented and tested on the INTEL XEON E7xxx and E5xxx family of the CRESCO structure of Italian National Agency for New Technologies, Energy and Sustainable Economic Development (ENEA), developed in the framework of the European Grid Infrastructure (EGI), a series of efforts to provide access to high-throughput computing resources across Europe using grid computing techniques. The implementation is able to minimize both the memory space and the execution time. The test data used in this study are IPDATA (Irvine Primate splice- junction DATA set), a subset of HS3D (Homo Sapiens Splice Sites Dataset) and a subset of COSMIC (the Catalogue of Somatic Mutations in Cancer). The execution time and the speed-up on IPDATA reach the best values within about 90 processors. Then the parallelization advantage is balanced by the greater cost of non-local communications between the processors. A similar behaviour is evident on HS3D, but at a greater number of processors, so evidencing the direct relationship between data size and parallelization gain. This behaviour is confirmed on COSMIC. Overall, the results obtained show that the parallel version is up to 30 times faster than the serial one.

Parallel heterogeneous architectures for efficient OMP compressive sensing reconstruction

NASA Astrophysics Data System (ADS)

Kulkarni, Amey; Stanislaus, Jerome L.; Mohsenin, Tinoosh

2014-05-01

Compressive Sensing (CS) is a novel scheme, in which a signal that is sparse in a known transform domain can be reconstructed using fewer samples. The signal reconstruction techniques are computationally intensive and have sluggish performance, which make them impractical for real-time processing applications . The paper presents novel architectures for Orthogonal Matching Pursuit algorithm, one of the popular CS reconstruction algorithms. We show the implementation results of proposed architectures on FPGA, ASIC and on a custom many-core platform. For FPGA and ASIC implementation, a novel thresholding method is used to reduce the processing time for the optimization problem by at least 25%. Whereas, for the custom many-core platform, efficient parallelization techniques are applied, to reconstruct signals with variant signal lengths of N and sparsity of m. The algorithm is divided into three kernels. Each kernel is parallelized to reduce execution time, whereas efficient reuse of the matrix operators allows us to reduce area. Matrix operations are efficiently paralellized by taking advantage of blocked algorithms. For demonstration purpose, all architectures reconstruct a 256-length signal with maximum sparsity of 8 using 64 measurements. Implementation on Xilinx Virtex-5 FPGA, requires 27.14 μs to reconstruct the signal using basic OMP. Whereas, with thresholding method it requires 18 μs. ASIC implementation reconstructs the signal in 13 μs. However, our custom many-core, operating at 1.18 GHz, takes 18.28 μs to complete. Our results show that compared to the previous published work of the same algorithm and matrix size, proposed architectures for FPGA and ASIC implementations perform 1.3x and 1.8x respectively faster. Also, the proposed many-core implementation performs 3000x faster than the CPU and 2000x faster than the GPU.

Processing communications events in parallel active messaging interface by awakening thread from wait state

DOEpatents

Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E

2013-10-22

Processing data communications events in a parallel active messaging interface (`PAMI`) of a parallel computer that includes compute nodes that execute a parallel application, with the PAMI including data communications endpoints, and the endpoints are coupled for data communications through the PAMI and through other data communications resources, including determining by an advance function that there are no actionable data communications events pending for its context, placing by the advance function its thread of execution into a wait state, waiting for a subsequent data communications event for the context; responsive to occurrence of a subsequent data communications event for the context, awakening by the thread from the wait state; and processing by the advance function the subsequent data communications event now pending for the context.

Reversible Parallel Discrete-Event Execution of Large-scale Epidemic Outbreak Models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perumalla, Kalyan S; Seal, Sudip K

2010-01-01

The spatial scale, runtime speed and behavioral detail of epidemic outbreak simulations together require the use of large-scale parallel processing. In this paper, an optimistic parallel discrete event execution of a reaction-diffusion simulation model of epidemic outbreaks is presented, with an implementation over themore » $$\\mu$$sik simulator. Rollback support is achieved with the development of a novel reversible model that combines reverse computation with a small amount of incremental state saving. Parallel speedup and other runtime performance metrics of the simulation are tested on a small (8,192-core) Blue Gene / P system, while scalability is demonstrated on 65,536 cores of a large Cray XT5 system. Scenarios representing large population sizes (up to several hundred million individuals in the largest case) are exercised.« less

Parallel DSMC Solution of Three-Dimensional Flow Over a Finite Flat Plate

NASA Technical Reports Server (NTRS)

Nance, Robert P.; Wilmoth, Richard G.; Moon, Bongki; Hassan, H. A.; Saltz, Joel

1994-01-01

This paper describes a parallel implementation of the direct simulation Monte Carlo (DSMC) method. Runtime library support is used for scheduling and execution of communication between nodes, and domain decomposition is performed dynamically to maintain a good load balance. Performance tests are conducted using the code to evaluate various remapping and remapping-interval policies, and it is shown that a one-dimensional chain-partitioning method works best for the problems considered. The parallel code is then used to simulate the Mach 20 nitrogen flow over a finite-thickness flat plate. It is shown that the parallel algorithm produces results which compare well with experimental data. Moreover, it yields significantly faster execution times than the scalar code, as well as very good load-balance characteristics.

The Automated Instrumentation and Monitoring System (AIMS) reference manual

NASA Technical Reports Server (NTRS)

Yan, Jerry; Hontalas, Philip; Listgarten, Sherry

1993-01-01

Whether a researcher is designing the 'next parallel programming paradigm,' another 'scalable multiprocessor' or investigating resource allocation algorithms for multiprocessors, a facility that enables parallel program execution to be captured and displayed is invaluable. Careful analysis of execution traces can help computer designers and software architects to uncover system behavior and to take advantage of specific application characteristics and hardware features. A software tool kit that facilitates performance evaluation of parallel applications on multiprocessors is described. The Automated Instrumentation and Monitoring System (AIMS) has four major software components: a source code instrumentor which automatically inserts active event recorders into the program's source code before compilation; a run time performance-monitoring library, which collects performance data; a trace file animation and analysis tool kit which reconstructs program execution from the trace file; and a trace post-processor which compensate for data collection overhead. Besides being used as prototype for developing new techniques for instrumenting, monitoring, and visualizing parallel program execution, AIMS is also being incorporated into the run-time environments of various hardware test beds to evaluate their impact on user productivity. Currently, AIMS instrumentors accept FORTRAN and C parallel programs written for Intel's NX operating system on the iPSC family of multi computers. A run-time performance-monitoring library for the iPSC/860 is included in this release. We plan to release monitors for other platforms (such as PVM and TMC's CM-5) in the near future. Performance data collected can be graphically displayed on workstations (e.g. Sun Sparc and SGI) supporting X-Windows (in particular, Xl IR5, Motif 1.1.3).

On scheduling task systems with variable service times

NASA Astrophysics Data System (ADS)

Maset, Richard G.; Banawan, Sayed A.

1993-08-01

Several strategies have been proposed for developing optimal and near-optimal schedules for task systems (jobs consisting of multiple tasks that can be executed in parallel). Most such strategies, however, implicitly assume deterministic task service times. We show that these strategies are much less effective when service times are highly variable. We then evaluate two strategies—one adaptive, one static—that have been proposed for retaining high performance despite such variability. Both strategies are extensions of critical path scheduling, which has been found to be efficient at producing near-optimal schedules. We found the adaptive approach to be quite effective.

Analysis of Parallel Algorithms on SMP Node and Cluster of Workstations Using Parallel Programming Models with New Tile-based Method for Large Biological Datasets.

PubMed

Shrimankar, D D; Sathe, S R

2016-01-01

Sequence alignment is an important tool for describing the relationships between DNA sequences. Many sequence alignment algorithms exist, differing in efficiency, in their models of the sequences, and in the relationship between sequences. The focus of this study is to obtain an optimal alignment between two sequences of biological data, particularly DNA sequences. The algorithm is discussed with particular emphasis on time, speedup, and efficiency optimizations. Parallel programming presents a number of critical challenges to application developers. Today's supercomputer often consists of clusters of SMP nodes. Programming paradigms such as OpenMP and MPI are used to write parallel codes for such architectures. However, the OpenMP programs cannot be scaled for more than a single SMP node. However, programs written in MPI can have more than single SMP nodes. But such a programming paradigm has an overhead of internode communication. In this work, we explore the tradeoffs between using OpenMP and MPI. We demonstrate that the communication overhead incurs significantly even in OpenMP loop execution and increases with the number of cores participating. We also demonstrate a communication model to approximate the overhead from communication in OpenMP loops. Our results are astonishing and interesting to a large variety of input data files. We have developed our own load balancing and cache optimization technique for message passing model. Our experimental results show that our own developed techniques give optimum performance of our parallel algorithm for various sizes of input parameter, such as sequence size and tile size, on a wide variety of multicore architectures.

Analysis of Parallel Algorithms on SMP Node and Cluster of Workstations Using Parallel Programming Models with New Tile-based Method for Large Biological Datasets

PubMed Central

Shrimankar, D. D.; Sathe, S. R.

2016-01-01

Sequence alignment is an important tool for describing the relationships between DNA sequences. Many sequence alignment algorithms exist, differing in efficiency, in their models of the sequences, and in the relationship between sequences. The focus of this study is to obtain an optimal alignment between two sequences of biological data, particularly DNA sequences. The algorithm is discussed with particular emphasis on time, speedup, and efficiency optimizations. Parallel programming presents a number of critical challenges to application developers. Today’s supercomputer often consists of clusters of SMP nodes. Programming paradigms such as OpenMP and MPI are used to write parallel codes for such architectures. However, the OpenMP programs cannot be scaled for more than a single SMP node. However, programs written in MPI can have more than single SMP nodes. But such a programming paradigm has an overhead of internode communication. In this work, we explore the tradeoffs between using OpenMP and MPI. We demonstrate that the communication overhead incurs significantly even in OpenMP loop execution and increases with the number of cores participating. We also demonstrate a communication model to approximate the overhead from communication in OpenMP loops. Our results are astonishing and interesting to a large variety of input data files. We have developed our own load balancing and cache optimization technique for message passing model. Our experimental results show that our own developed techniques give optimum performance of our parallel algorithm for various sizes of input parameter, such as sequence size and tile size, on a wide variety of multicore architectures. PMID:27932868

Instrumentation, performance visualization, and debugging tools for multiprocessors

NASA Technical Reports Server (NTRS)

Yan, Jerry C.; Fineman, Charles E.; Hontalas, Philip J.

1991-01-01

The need for computing power has forced a migration from serial computation on a single processor to parallel processing on multiprocessor architectures. However, without effective means to monitor (and visualize) program execution, debugging, and tuning parallel programs becomes intractably difficult as program complexity increases with the number of processors. Research on performance evaluation tools for multiprocessors is being carried out at ARC. Besides investigating new techniques for instrumenting, monitoring, and presenting the state of parallel program execution in a coherent and user-friendly manner, prototypes of software tools are being incorporated into the run-time environments of various hardware testbeds to evaluate their impact on user productivity. Our current tool set, the Ames Instrumentation Systems (AIMS), incorporates features from various software systems developed in academia and industry. The execution of FORTRAN programs on the Intel iPSC/860 can be automatically instrumented and monitored. Performance data collected in this manner can be displayed graphically on workstations supporting X-Windows. We have successfully compared various parallel algorithms for computational fluid dynamics (CFD) applications in collaboration with scientists from the Numerical Aerodynamic Simulation Systems Division. By performing these comparisons, we show that performance monitors and debuggers such as AIMS are practical and can illuminate the complex dynamics that occur within parallel programs.

Algorithms for parallel flow solvers on message passing architectures

NASA Technical Reports Server (NTRS)

Vanderwijngaart, Rob F.

1995-01-01

The purpose of this project has been to identify and test suitable technologies for implementation of fluid flow solvers -- possibly coupled with structures and heat equation solvers -- on MIMD parallel computers. In the course of this investigation much attention has been paid to efficient domain decomposition strategies for ADI-type algorithms. Multi-partitioning derives its efficiency from the assignment of several blocks of grid points to each processor in the parallel computer. A coarse-grain parallelism is obtained, and a near-perfect load balance results. In uni-partitioning every processor receives responsibility for exactly one block of grid points instead of several. This necessitates fine-grain pipelined program execution in order to obtain a reasonable load balance. Although fine-grain parallelism is less desirable on many systems, especially high-latency networks of workstations, uni-partition methods are still in wide use in production codes for flow problems. Consequently, it remains important to achieve good efficiency with this technique that has essentially been superseded by multi-partitioning for parallel ADI-type algorithms. Another reason for the concentration on improving the performance of pipeline methods is their applicability in other types of flow solver kernels with stronger implied data dependence. Analytical expressions can be derived for the size of the dynamic load imbalance incurred in traditional pipelines. From these it can be determined what is the optimal first-processor retardation that leads to the shortest total completion time for the pipeline process. Theoretical predictions of pipeline performance with and without optimization match experimental observations on the iPSC/860 very well. Analysis of pipeline performance also highlights the effect of uncareful grid partitioning in flow solvers that employ pipeline algorithms. If grid blocks at boundaries are not at least as large in the wall-normal direction as those immediately adjacent to them, then the first processor in the pipeline will receive a computational load that is less than that of subsequent processors, magnifying the pipeline slowdown effect. Extra compensation is needed for grid boundary effects, even if all grid blocks are equally sized.

Fluid mechanics based classification of the respiratory efficiency of several nasal cavities.

PubMed

Lintermann, Andreas; Meinke, Matthias; Schröder, Wolfgang

2013-11-01

The flow in the human nasal cavity is of great importance to understand rhinologic pathologies like impaired respiration or heating capabilities, a diminished sense of taste and smell, and the presence of dry mucous membranes. To numerically analyze this flow problem a highly efficient and scalable Thermal Lattice-BGK (TLBGK) solver is used, which is very well suited for flows in intricate geometries. The generation of the computational mesh is completely automatic and highly parallelized such that it can be executed efficiently on High Performance Computers (HPCs). An evaluation of the functionality of nasal cavities is based on an analysis of pressure drop, secondary flow structures, wall-shear stress distributions, and temperature variations from the nostrils to the pharynx. The results of the flow fields of three completely different nasal cavities allow their classification into ability groups and support the a priori decision process on surgical interventions. © 2013 Elsevier Ltd. All rights reserved.

User's Guide for TOUGH2-MP - A Massively Parallel Version of the TOUGH2 Code

DOE Office of Scientific and Technical Information (OSTI.GOV)

Earth Sciences Division; Zhang, Keni; Zhang, Keni

TOUGH2-MP is a massively parallel (MP) version of the TOUGH2 code, designed for computationally efficient parallel simulation of isothermal and nonisothermal flows of multicomponent, multiphase fluids in one, two, and three-dimensional porous and fractured media. In recent years, computational requirements have become increasingly intensive in large or highly nonlinear problems for applications in areas such as radioactive waste disposal, CO2 geological sequestration, environmental assessment and remediation, reservoir engineering, and groundwater hydrology. The primary objective of developing the parallel-simulation capability is to significantly improve the computational performance of the TOUGH2 family of codes. The particular goal for the parallel simulator ismore » to achieve orders-of-magnitude improvement in computational time for models with ever-increasing complexity. TOUGH2-MP is designed to perform parallel simulation on multi-CPU computational platforms. An earlier version of TOUGH2-MP (V1.0) was based on the TOUGH2 Version 1.4 with EOS3, EOS9, and T2R3D modules, a software previously qualified for applications in the Yucca Mountain project, and was designed for execution on CRAY T3E and IBM SP supercomputers. The current version of TOUGH2-MP (V2.0) includes all fluid property modules of the standard version TOUGH2 V2.0. It provides computationally efficient capabilities using supercomputers, Linux clusters, or multi-core PCs, and also offers many user-friendly features. The parallel simulator inherits all process capabilities from V2.0 together with additional capabilities for handling fractured media from V1.4. This report provides a quick starting guide on how to set up and run the TOUGH2-MP program for users with a basic knowledge of running the (standard) version TOUGH2 code, The report also gives a brief technical description of the code, including a discussion of parallel methodology, code structure, as well as mathematical and numerical methods used. To familiarize users with the parallel code, illustrative sample problems are presented.« less

Parallel optimization algorithms and their implementation in VLSI design

NASA Technical Reports Server (NTRS)

Lee, G.; Feeley, J. J.

1991-01-01

Two new parallel optimization algorithms based on the simplex method are described. They may be executed by a SIMD parallel processor architecture and be implemented in VLSI design. Several VLSI design implementations are introduced. An application example is reported to demonstrate that the algorithms are effective.

Density-based parallel skin lesion border detection with webCL

PubMed Central

2015-01-01

Background Dermoscopy is a highly effective and noninvasive imaging technique used in diagnosis of melanoma and other pigmented skin lesions. Many aspects of the lesion under consideration are defined in relation to the lesion border. This makes border detection one of the most important steps in dermoscopic image analysis. In current practice, dermatologists often delineate borders through a hand drawn representation based upon visual inspection. Due to the subjective nature of this technique, intra- and inter-observer variations are common. Because of this, the automated assessment of lesion borders in dermoscopic images has become an important area of study. Methods Fast density based skin lesion border detection method has been implemented in parallel with a new parallel technology called WebCL. WebCL utilizes client side computing capabilities to use available hardware resources such as multi cores and GPUs. Developed WebCL-parallel density based skin lesion border detection method runs efficiently from internet browsers. Results Previous research indicates that one of the highest accuracy rates can be achieved using density based clustering techniques for skin lesion border detection. While these algorithms do have unfavorable time complexities, this effect could be mitigated when implemented in parallel. In this study, density based clustering technique for skin lesion border detection is parallelized and redesigned to run very efficiently on the heterogeneous platforms (e.g. tablets, SmartPhones, multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units) by transforming the technique into a series of independent concurrent operations. Heterogeneous computing is adopted to support accessibility, portability and multi-device use in the clinical settings. For this, we used WebCL, an emerging technology that enables a HTML5 Web browser to execute code in parallel for heterogeneous platforms. We depicted WebCL and our parallel algorithm design. In addition, we tested parallel code on 100 dermoscopy images and showed the execution speedups with respect to the serial version. Results indicate that parallel (WebCL) version and serial version of density based lesion border detection methods generate the same accuracy rates for 100 dermoscopy images, in which mean of border error is 6.94%, mean of recall is 76.66%, and mean of precision is 99.29% respectively. Moreover, WebCL version's speedup factor for 100 dermoscopy images' lesion border detection averages around ~491.2. Conclusions When large amount of high resolution dermoscopy images considered in a usual clinical setting along with the critical importance of early detection and diagnosis of melanoma before metastasis, the importance of fast processing dermoscopy images become obvious. In this paper, we introduce WebCL and the use of it for biomedical image processing applications. WebCL is a javascript binding of OpenCL, which takes advantage of GPU computing from a web browser. Therefore, WebCL parallel version of density based skin lesion border detection introduced in this study can supplement expert dermatologist, and aid them in early diagnosis of skin lesions. While WebCL is currently an emerging technology, a full adoption of WebCL into the HTML5 standard would allow for this implementation to run on a very large set of hardware and software systems. WebCL takes full advantage of parallel computational resources including multi-cores and GPUs on a local machine, and allows for compiled code to run directly from the Web Browser. PMID:26423836

Density-based parallel skin lesion border detection with webCL.

PubMed

Lemon, James; Kockara, Sinan; Halic, Tansel; Mete, Mutlu

2015-01-01

Dermoscopy is a highly effective and noninvasive imaging technique used in diagnosis of melanoma and other pigmented skin lesions. Many aspects of the lesion under consideration are defined in relation to the lesion border. This makes border detection one of the most important steps in dermoscopic image analysis. In current practice, dermatologists often delineate borders through a hand drawn representation based upon visual inspection. Due to the subjective nature of this technique, intra- and inter-observer variations are common. Because of this, the automated assessment of lesion borders in dermoscopic images has become an important area of study. Fast density based skin lesion border detection method has been implemented in parallel with a new parallel technology called WebCL. WebCL utilizes client side computing capabilities to use available hardware resources such as multi cores and GPUs. Developed WebCL-parallel density based skin lesion border detection method runs efficiently from internet browsers. Previous research indicates that one of the highest accuracy rates can be achieved using density based clustering techniques for skin lesion border detection. While these algorithms do have unfavorable time complexities, this effect could be mitigated when implemented in parallel. In this study, density based clustering technique for skin lesion border detection is parallelized and redesigned to run very efficiently on the heterogeneous platforms (e.g. tablets, SmartPhones, multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units) by transforming the technique into a series of independent concurrent operations. Heterogeneous computing is adopted to support accessibility, portability and multi-device use in the clinical settings. For this, we used WebCL, an emerging technology that enables a HTML5 Web browser to execute code in parallel for heterogeneous platforms. We depicted WebCL and our parallel algorithm design. In addition, we tested parallel code on 100 dermoscopy images and showed the execution speedups with respect to the serial version. Results indicate that parallel (WebCL) version and serial version of density based lesion border detection methods generate the same accuracy rates for 100 dermoscopy images, in which mean of border error is 6.94%, mean of recall is 76.66%, and mean of precision is 99.29% respectively. Moreover, WebCL version's speedup factor for 100 dermoscopy images' lesion border detection averages around ~491.2. When large amount of high resolution dermoscopy images considered in a usual clinical setting along with the critical importance of early detection and diagnosis of melanoma before metastasis, the importance of fast processing dermoscopy images become obvious. In this paper, we introduce WebCL and the use of it for biomedical image processing applications. WebCL is a javascript binding of OpenCL, which takes advantage of GPU computing from a web browser. Therefore, WebCL parallel version of density based skin lesion border detection introduced in this study can supplement expert dermatologist, and aid them in early diagnosis of skin lesions. While WebCL is currently an emerging technology, a full adoption of WebCL into the HTML5 standard would allow for this implementation to run on a very large set of hardware and software systems. WebCL takes full advantage of parallel computational resources including multi-cores and GPUs on a local machine, and allows for compiled code to run directly from the Web Browser.

Automated Instrumentation, Monitoring and Visualization of PVM Programs Using AIMS

NASA Technical Reports Server (NTRS)

Mehra, Pankaj; VanVoorst, Brian; Yan, Jerry; Lum, Henry, Jr. (Technical Monitor)

1994-01-01

We present views and analysis of the execution of several PVM (Parallel Virtual Machine) codes for Computational Fluid Dynamics on a networks of Sparcstations, including: (1) NAS Parallel Benchmarks CG and MG; (2) a multi-partitioning algorithm for NAS Parallel Benchmark SP; and (3) an overset grid flowsolver. These views and analysis were obtained using our Automated Instrumentation and Monitoring System (AIMS) version 3.0, a toolkit for debugging the performance of PVM programs. We will describe the architecture, operation and application of AIMS. The AIMS toolkit contains: (1) Xinstrument, which can automatically instrument various computational and communication constructs in message-passing parallel programs; (2) Monitor, a library of runtime trace-collection routines; (3) VK (Visual Kernel), an execution-animation tool with source-code clickback; and (4) Tally, a tool for statistical analysis of execution profiles. Currently, Xinstrument can handle C and Fortran 77 programs using PVM 3.2.x; Monitor has been implemented and tested on Sun 4 systems running SunOS 4.1.2; and VK uses XIIR5 and Motif 1.2. Data and views obtained using AIMS clearly illustrate several characteristic features of executing parallel programs on networked workstations: (1) the impact of long message latencies; (2) the impact of multiprogramming overheads and associated load imbalance; (3) cache and virtual-memory effects; and (4) significant skews between workstation clocks. Interestingly, AIMS can compensate for constant skew (zero drift) by calibrating the skew between a parent and its spawned children. In addition, AIMS' skew-compensation algorithm can adjust timestamps in a way that eliminates physically impossible communications (e.g., messages going backwards in time). Our current efforts are directed toward creating new views to explain the observed performance of PVM programs. Some of the features planned for the near future include: (1) ConfigView, showing the physical topology of the virtual machine, inferred using specially formatted IP (Internet Protocol) packets: and (2) LoadView, synchronous animation of PVM-program execution and resource-utilization patterns.

UPC++ Programmer’s Guide (v1.0 2017.9)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bachan, J.; Baden, S.; Bonachea, D.

UPC++ is a C++11 library that provides Asynchronous Partitioned Global Address Space (APGAS) programming. It is designed for writing parallel programs that run efficiently and scale well on distributed-memory parallel computers. The APGAS model is single program, multiple-data (SPMD), with each separate thread of execution (referred to as a rank, a term borrowed from MPI) having access to local memory as it would in C++. However, APGAS also provides access to a global address space, which is allocated in shared segments that are distributed over the ranks. UPC++ provides numerous methods for accessing and using global memory. In UPC++, allmore » operations that access remote memory are explicit, which encourages programmers to be aware of the cost of communication and data movement. Moreover, all remote-memory access operations are by default asynchronous, to enable programmers to write code that scales well even on hundreds of thousands of cores.« less

UPC++ Programmer’s Guide, v1.0-2018.3.0

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bachan, J.; Baden, S.; Bonachea, Dan

UPC++ is a C++11 library that provides Partitioned Global Address Space (PGAS) programming. It is designed for writing parallel programs that run efficiently and scale well on distributed-memory parallel computers. The PGAS model is single program, multiple-data (SPMD), with each separate thread of execution (referred to as a rank, a term borrowed from MPI) having access to local memory as it would in C++. However, PGAS also provides access to a global address space, which is allocated in shared segments that are distributed over the ranks. UPC++ provides numerous methods for accessing and using global memory. In UPC++, all operationsmore » that access remote memory are explicit, which encourages programmers to be aware of the cost of communication and data movement. Moreover, all remote-memory access operations are by default asynchronous, to enable programmers to write code that scales well even on hundreds of thousands of cores.« less

NIRcam-NIRSpec GTO Observations of Galaxy Evolution

NASA Astrophysics Data System (ADS)

Rieke, Marcia J.; Ferruit, Pierre; Alberts, Stacey; Bunker, Andrew; Charlot, Stephane; Chevallard, Jacopo; Dressler, Alan; Egami, Eiichi; Eisenstein, Daniel; Endsley, Ryan; Franx, Marijn; Frye, Brenda L.; Hainline, Kevin; Jakobsen, Peter; Lake, Emma Curtis; Maiolino, Roberto; Rix, Hans-Walter; Robertson, Brant; Stark, Daniel; Williams, Christina; Willmer, Christopher; Willott, Chris J.

2017-06-01

The NIRSpec and and NIRCam GTO Teams are planning a joint imaging and spectroscopic study of the high redshift universe. By virtue of planning a joint program which includes medium and deep near- and mid-infrared imaging surveys and multi-object spectroscopy (MOS) of sources in the same fields, we have learned much about planning observing programs for each of the instruments and using them in parallel mode to maximize photon collection time. The design and rationale for our joint program will be explored in this talk with an emphasis on why we have chosen particular suites of filters and spectroscopic resolutions, why we have chosen particular exposure patterns, and how we have designed the parallel observations. The actual observations that we intend on executing will serve as examples of how to layout mosaics and MOS observations to maximize observing efficiency for surveys with JWST.

ls1 mardyn: The Massively Parallel Molecular Dynamics Code for Large Systems.

PubMed

Niethammer, Christoph; Becker, Stefan; Bernreuther, Martin; Buchholz, Martin; Eckhardt, Wolfgang; Heinecke, Alexander; Werth, Stephan; Bungartz, Hans-Joachim; Glass, Colin W; Hasse, Hans; Vrabec, Jadran; Horsch, Martin

2014-10-14

The molecular dynamics simulation code ls1 mardyn is presented. It is a highly scalable code, optimized for massively parallel execution on supercomputing architectures and currently holds the world record for the largest molecular simulation with over four trillion particles. It enables the application of pair potentials to length and time scales that were previously out of scope for molecular dynamics simulation. With an efficient dynamic load balancing scheme, it delivers high scalability even for challenging heterogeneous configurations. Presently, multicenter rigid potential models based on Lennard-Jones sites, point charges, and higher-order polarities are supported. Due to its modular design, ls1 mardyn can be extended to new physical models, methods, and algorithms, allowing future users to tailor it to suit their respective needs. Possible applications include scenarios with complex geometries, such as fluids at interfaces, as well as nonequilibrium molecular dynamics simulation of heat and mass transfer.

Performance Metrics for Monitoring Parallel Program Executions

NASA Technical Reports Server (NTRS)

Sarukkai, Sekkar R.; Gotwais, Jacob K.; Yan, Jerry; Lum, Henry, Jr. (Technical Monitor)

1994-01-01

Existing tools for debugging performance of parallel programs either provide graphical representations of program execution or profiles of program executions. However, for performance debugging tools to be useful, such information has to be augmented with information that highlights the cause of poor program performance. Identifying the cause of poor performance necessitates the need for not only determining the significance of various performance problems on the execution time of the program, but also needs to consider the effect of interprocessor communications of individual source level data structures. In this paper, we present a suite of normalized indices which provide a convenient mechanism for focusing on a region of code with poor performance and highlights the cause of the problem in terms of processors, procedures and data structure interactions. All the indices are generated from trace files augmented with data structure information.. Further, we show with the help of examples from the NAS benchmark suite that the indices help in detecting potential cause of poor performance, based on augmented execution traces obtained by monitoring the program.

A comprehensive study of MPI parallelism in three-dimensional discrete element method (DEM) simulation of complex-shaped granular particles

NASA Astrophysics Data System (ADS)

Yan, Beichuan; Regueiro, Richard A.

2018-02-01

A three-dimensional (3D) DEM code for simulating complex-shaped granular particles is parallelized using message-passing interface (MPI). The concepts of link-block, ghost/border layer, and migration layer are put forward for design of the parallel algorithm, and theoretical scalability function of 3-D DEM scalability and memory usage is derived. Many performance-critical implementation details are managed optimally to achieve high performance and scalability, such as: minimizing communication overhead, maintaining dynamic load balance, handling particle migrations across block borders, transmitting C++ dynamic objects of particles between MPI processes efficiently, eliminating redundant contact information between adjacent MPI processes. The code executes on multiple US Department of Defense (DoD) supercomputers and tests up to 2048 compute nodes for simulating 10 million three-axis ellipsoidal particles. Performance analyses of the code including speedup, efficiency, scalability, and granularity across five orders of magnitude of simulation scale (number of particles) are provided, and they demonstrate high speedup and excellent scalability. It is also discovered that communication time is a decreasing function of the number of compute nodes in strong scaling measurements. The code's capability of simulating a large number of complex-shaped particles on modern supercomputers will be of value in both laboratory studies on micromechanical properties of granular materials and many realistic engineering applications involving granular materials.

Efficient Iterative Methods Applied to the Solution of Transonic Flows

NASA Astrophysics Data System (ADS)

Wissink, Andrew M.; Lyrintzis, Anastasios S.; Chronopoulos, Anthony T.

1996-02-01

We investigate the use of an inexact Newton's method to solve the potential equations in the transonic regime. As a test case, we solve the two-dimensional steady transonic small disturbance equation. Approximate factorization/ADI techniques have traditionally been employed for implicit solutions of this nonlinear equation. Instead, we apply Newton's method using an exact analytical determination of the Jacobian with preconditioned conjugate gradient-like iterative solvers for solution of the linear systems in each Newton iteration. Two iterative solvers are tested; a block s-step version of the classical Orthomin(k) algorithm called orthogonal s-step Orthomin (OSOmin) and the well-known GMRES method. The preconditioner is a vectorizable and parallelizable version of incomplete LU (ILU) factorization. Efficiency of the Newton-Iterative method on vector and parallel computer architectures is the main issue addressed. In vectorized tests on a single processor of the Cray C-90, the performance of Newton-OSOmin is superior to Newton-GMRES and a more traditional monotone AF/ADI method (MAF) for a variety of transonic Mach numbers and mesh sizes. Newton-GMRES is superior to MAF for some cases. The parallel performance of the Newton method is also found to be very good on multiple processors of the Cray C-90 and on the massively parallel thinking machine CM-5, where very fast execution rates (up to 9 Gflops) are found for large problems.

Efficient Use of Distributed Systems for Scientific Applications

NASA Technical Reports Server (NTRS)

Taylor, Valerie; Chen, Jian; Canfield, Thomas; Richard, Jacques

2000-01-01

Distributed computing has been regarded as the future of high performance computing. Nationwide high speed networks such as vBNS are becoming widely available to interconnect high-speed computers, virtual environments, scientific instruments and large data sets. One of the major issues to be addressed with distributed systems is the development of computational tools that facilitate the efficient execution of parallel applications on such systems. These tools must exploit the heterogeneous resources (networks and compute nodes) in distributed systems. This paper presents a tool, called PART, which addresses this issue for mesh partitioning. PART takes advantage of the following heterogeneous system features: (1) processor speed; (2) number of processors; (3) local network performance; and (4) wide area network performance. Further, different finite element applications under consideration may have different computational complexities, different communication patterns, and different element types, which also must be taken into consideration when partitioning. PART uses parallel simulated annealing to partition the domain, taking into consideration network and processor heterogeneity. The results of using PART for an explicit finite element application executing on two IBM SPs (located at Argonne National Laboratory and the San Diego Supercomputer Center) indicate an increase in efficiency by up to 36% as compared to METIS, a widely used mesh partitioning tool. The input to METIS was modified to take into consideration heterogeneous processor performance; METIS does not take into consideration heterogeneous networks. The execution times for these applications were reduced by up to 30% as compared to METIS. These results are given in Figure 1 for four irregular meshes with number of elements ranging from 30,269 elements for the Barth5 mesh to 11,451 elements for the Barth4 mesh. Future work with PART entails using the tool with an integrated application requiring distributed systems. In particular this application, illustrated in the document entails an integration of finite element and fluid dynamic simulations to address the cooling of turbine blades of a gas turbine engine design. It is not uncommon to encounter high-temperature, film-cooled turbine airfoils with 1,000,000s of degrees of freedom. This results because of the complexity of the various components of the airfoils, requiring fine-grain meshing for accuracy. Additional information is contained in the original.

Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis

DOE PAGES

Schulz, Martin; Galarowicz, Jim; Maghrak, Don; ...

2008-01-01

Over the last decades a large number of performance tools has been developed to analyze and optimize high performance applications. Their acceptance by end users, however, has been slow: each tool alone is often limited in scope and comes with widely varying interfaces and workflow constraints, requiring different changes in the often complex build and execution infrastructure of the target application. We started the Open | SpeedShop project about 3 years ago to overcome these limitations and provide efficient, easy to apply, and integrated performance analysis for parallel systems. Open | SpeedShop has two different faces: it provides an interoperable tool set covering themore » most common analysis steps as well as a comprehensive plugin infrastructure for building new tools. In both cases, the tools can be deployed to large scale parallel applications using DPCL/Dyninst for distributed binary instrumentation. Further, all tools developed within or on top of Open | SpeedShop are accessible through multiple fully equivalent interfaces including an easy-to-use GUI as well as an interactive command line interface reducing the usage threshold for those tools.« less

Empirical study of parallel LRU simulation algorithms

NASA Technical Reports Server (NTRS)

Carr, Eric; Nicol, David M.

1994-01-01

This paper reports on the performance of five parallel algorithms for simulating a fully associative cache operating under the LRU (Least-Recently-Used) replacement policy. Three of the algorithms are SIMD, and are implemented on the MasPar MP-2 architecture. Two other algorithms are parallelizations of an efficient serial algorithm on the Intel Paragon. One SIMD algorithm is quite simple, but its cost is linear in the cache size. The two other SIMD algorithm are more complex, but have costs that are independent on the cache size. Both the second and third SIMD algorithms compute all stack distances; the second SIMD algorithm is completely general, whereas the third SIMD algorithm presumes and takes advantage of bounds on the range of reference tags. Both MIMD algorithm implemented on the Paragon are general and compute all stack distances; they differ in one step that may affect their respective scalability. We assess the strengths and weaknesses of these algorithms as a function of problem size and characteristics, and compare their performance on traces derived from execution of three SPEC benchmark programs.

Parallel program debugging with flowback analysis

DOE Office of Scientific and Technical Information (OSTI.GOV)

Choi, Jongdeok.

1989-01-01

This thesis describes the design and implementation of an integrated debugging system for parallel programs running on shared memory multi-processors. The goal of the debugging system is to present to the programmer a graphical view of the dynamic program dependences while keeping the execution-time overhead low. The author first describes the use of flowback analysis to provide information on causal relationship between events in a programs' execution without re-executing the program for debugging. Execution time overhead is kept low by recording only a small amount of trace during a program's execution. He uses semantic analysis and a technique called incrementalmore » tracing to keep the time and space overhead low. As part of the semantic analysis, he uses a static program dependence graph structure that reduces the amount of work done at compile time and takes advantage of the dynamic information produced during execution time. The cornerstone of the incremental tracing concept is to generate a coarse trace during execution and fill incrementally, during the interactive portion of the debugging session, the gap between the information gathered in the coarse trace and the information needed to do the flowback analysis using the coarse trace. Then, he describes how to extend the flowback analysis to parallel programs. The flowback analysis can span process boundaries; i.e., the most recent modification to a shared variable might be traced to a different process than the one that contains the current reference. The static and dynamic program dependence graphs of the individual processes are tied together with synchronization and data dependence information to form complete graphs that represent the entire program.« less

Transferring ecosystem simulation codes to supercomputers

NASA Technical Reports Server (NTRS)

Skiles, J. W.; Schulbach, C. H.

1995-01-01

Many ecosystem simulation computer codes have been developed in the last twenty-five years. This development took place initially on main-frame computers, then mini-computers, and more recently, on micro-computers and workstations. Supercomputing platforms (both parallel and distributed systems) have been largely unused, however, because of the perceived difficulty in accessing and using the machines. Also, significant differences in the system architectures of sequential, scalar computers and parallel and/or vector supercomputers must be considered. We have transferred a grassland simulation model (developed on a VAX) to a Cray Y-MP/C90. We describe porting the model to the Cray and the changes we made to exploit the parallelism in the application and improve code execution. The Cray executed the model 30 times faster than the VAX and 10 times faster than a Unix workstation. We achieved an additional speedup of 30 percent by using the compiler's vectoring and 'in-line' capabilities. The code runs at only about 5 percent of the Cray's peak speed because it ineffectively uses the vector and parallel processing capabilities of the Cray. We expect that by restructuring the code, it could execute an additional six to ten times faster.

System, methods and apparatus for program optimization for multi-threaded processor architectures

DOEpatents

Bastoul, Cedric; Lethin, Richard A; Leung, Allen K; Meister, Benoit J; Szilagyi, Peter; Vasilache, Nicolas T; Wohlford, David E

2015-01-06

Methods, apparatus and computer software product for source code optimization are provided. In an exemplary embodiment, a first custom computing apparatus is used to optimize the execution of source code on a second computing apparatus. In this embodiment, the first custom computing apparatus contains a memory, a storage medium and at least one processor with at least one multi-stage execution unit. The second computing apparatus contains at least two multi-stage execution units that allow for parallel execution of tasks. The first custom computing apparatus optimizes the code for parallelism, locality of operations and contiguity of memory accesses on the second computing apparatus. This Abstract is provided for the sole purpose of complying with the Abstract requirement rules. This Abstract is submitted with the explicit understanding that it will not be used to interpret or to limit the scope or the meaning of the claims.

Power-Aware Compiler Controllable Chip Multiprocessor

NASA Astrophysics Data System (ADS)

Shikano, Hiroaki; Shirako, Jun; Wada, Yasutaka; Kimura, Keiji; Kasahara, Hironori

A power-aware compiler controllable chip multiprocessor (CMP) is presented and its performance and power consumption are evaluated with the optimally scheduled advanced multiprocessor (OSCAR) parallelizing compiler. The CMP is equipped with power control registers that change clock frequency and power supply voltage to functional units including processor cores, memories, and an interconnection network. The OSCAR compiler carries out coarse-grain task parallelization of programs and reduces power consumption using architectural power control support and the compiler's power saving scheme. The performance evaluation shows that MPEG-2 encoding on the proposed CMP with four CPUs results in 82.6% power reduction in real-time execution mode with a deadline constraint on its sequential execution time. Furthermore, MP3 encoding on a heterogeneous CMP with four CPUs and four accelerators results in 53.9% power reduction at 21.1-fold speed-up in performance against its sequential execution in the fastest execution mode.

Checkpoint-based forward recovery using lookahead execution and rollback validation in parallel and distributed systems. Ph.D. Thesis, 1992

NASA Technical Reports Server (NTRS)

Long, Junsheng

1994-01-01

This thesis studies a forward recovery strategy using checkpointing and optimistic execution in parallel and distributed systems. The approach uses replicated tasks executing on different processors for forwared recovery and checkpoint comparison for error detection. To reduce overall redundancy, this approach employs a lower static redundancy in the common error-free situation to detect error than the standard N Module Redundancy scheme (NMR) does to mask off errors. For the rare occurrence of an error, this approach uses some extra redundancy for recovery. To reduce the run-time recovery overhead, look-ahead processes are used to advance computation speculatively and a rollback process is used to produce a diagnosis for correct look-ahead processes without rollback of the whole system. Both analytical and experimental evaluation have shown that this strategy can provide a nearly error-free execution time even under faults with a lower average redundancy than NMR.

NiftySim: A GPU-based nonlinear finite element package for simulation of soft tissue biomechanics.

PubMed

Johnsen, Stian F; Taylor, Zeike A; Clarkson, Matthew J; Hipwell, John; Modat, Marc; Eiben, Bjoern; Han, Lianghao; Hu, Yipeng; Mertzanidou, Thomy; Hawkes, David J; Ourselin, Sebastien

2015-07-01

NiftySim, an open-source finite element toolkit, has been designed to allow incorporation of high-performance soft tissue simulation capabilities into biomedical applications. The toolkit provides the option of execution on fast graphics processing unit (GPU) hardware, numerous constitutive models and solid-element options, membrane and shell elements, and contact modelling facilities, in a simple to use library. The toolkit is founded on the total Lagrangian explicit dynamics (TLEDs) algorithm, which has been shown to be efficient and accurate for simulation of soft tissues. The base code is written in C[Formula: see text], and GPU execution is achieved using the nVidia CUDA framework. In most cases, interaction with the underlying solvers can be achieved through a single Simulator class, which may be embedded directly in third-party applications such as, surgical guidance systems. Advanced capabilities such as contact modelling and nonlinear constitutive models are also provided, as are more experimental technologies like reduced order modelling. A consistent description of the underlying solution algorithm, its implementation with a focus on GPU execution, and examples of the toolkit's usage in biomedical applications are provided. Efficient mapping of the TLED algorithm to parallel hardware results in very high computational performance, far exceeding that available in commercial packages. The NiftySim toolkit provides high-performance soft tissue simulation capabilities using GPU technology for biomechanical simulation research applications in medical image computing, surgical simulation, and surgical guidance applications.

Accelerating String Set Matching in FPGA Hardware for Bioinformatics Research

PubMed Central

Dandass, Yoginder S; Burgess, Shane C; Lawrence, Mark; Bridges, Susan M

2008-01-01

Background This paper describes techniques for accelerating the performance of the string set matching problem with particular emphasis on applications in computational proteomics. The process of matching peptide sequences against a genome translated in six reading frames is part of a proteogenomic mapping pipeline that is used as a case-study. The Aho-Corasick algorithm is adapted for execution in field programmable gate array (FPGA) devices in a manner that optimizes space and performance. In this approach, the traditional Aho-Corasick finite state machine (FSM) is split into smaller FSMs, operating in parallel, each of which matches up to 20 peptides in the input translated genome. Each of the smaller FSMs is further divided into five simpler FSMs such that each simple FSM operates on a single bit position in the input (five bits are sufficient for representing all amino acids and special symbols in protein sequences). Results This bit-split organization of the Aho-Corasick implementation enables efficient utilization of the limited random access memory (RAM) resources available in typical FPGAs. The use of on-chip RAM as opposed to FPGA logic resources for FSM implementation also enables rapid reconfiguration of the FPGA without the place and routing delays associated with complex digital designs. Conclusion Experimental results show storage efficiencies of over 80% for several data sets. Furthermore, the FPGA implementation executing at 100 MHz is nearly 20 times faster than an implementation of the traditional Aho-Corasick algorithm executing on a 2.67 GHz workstation. PMID:18412963

Design of object-oriented distributed simulation classes

NASA Technical Reports Server (NTRS)

Schoeffler, James D. (Principal Investigator)

1995-01-01

Distributed simulation of aircraft engines as part of a computer aided design package is being developed by NASA Lewis Research Center for the aircraft industry. The project is called NPSS, an acronym for 'Numerical Propulsion Simulation System'. NPSS is a flexible object-oriented simulation of aircraft engines requiring high computing speed. It is desirable to run the simulation on a distributed computer system with multiple processors executing portions of the simulation in parallel. The purpose of this research was to investigate object-oriented structures such that individual objects could be distributed. The set of classes used in the simulation must be designed to facilitate parallel computation. Since the portions of the simulation carried out in parallel are not independent of one another, there is the need for communication among the parallel executing processors which in turn implies need for their synchronization. Communication and synchronization can lead to decreased throughput as parallel processors wait for data or synchronization signals from other processors. As a result of this research, the following have been accomplished. The design and implementation of a set of simulation classes which result in a distributed simulation control program have been completed. The design is based upon MIT 'Actor' model of a concurrent object and uses 'connectors' to structure dynamic connections between simulation components. Connectors may be dynamically created according to the distribution of objects among machines at execution time without any programming changes. Measurements of the basic performance have been carried out with the result that communication overhead of the distributed design is swamped by the computation time of modules unless modules have very short execution times per iteration or time step. An analytical performance model based upon queuing network theory has been designed and implemented. Its application to realistic configurations has not been carried out.

Design of Object-Oriented Distributed Simulation Classes

NASA Technical Reports Server (NTRS)

Schoeffler, James D.

1995-01-01

Distributed simulation of aircraft engines as part of a computer aided design package being developed by NASA Lewis Research Center for the aircraft industry. The project is called NPSS, an acronym for "Numerical Propulsion Simulation System". NPSS is a flexible object-oriented simulation of aircraft engines requiring high computing speed. It is desirable to run the simulation on a distributed computer system with multiple processors executing portions of the simulation in parallel. The purpose of this research was to investigate object-oriented structures such that individual objects could be distributed. The set of classes used in the simulation must be designed to facilitate parallel computation. Since the portions of the simulation carried out in parallel are not independent of one another, there is the need for communication among the parallel executing processors which in turn implies need for their synchronization. Communication and synchronization can lead to decreased throughput as parallel processors wait for data or synchronization signals from other processors. As a result of this research, the following have been accomplished. The design and implementation of a set of simulation classes which result in a distributed simulation control program have been completed. The design is based upon MIT "Actor" model of a concurrent object and uses "connectors" to structure dynamic connections between simulation components. Connectors may be dynamically created according to the distribution of objects among machines at execution time without any programming changes. Measurements of the basic performance have been carried out with the result that communication overhead of the distributed design is swamped by the computation time of modules unless modules have very short execution times per iteration or time step. An analytical performance model based upon queuing network theory has been designed and implemented. Its application to realistic configurations has not been carried out.

Optimized Hypervisor Scheduler for Parallel Discrete Event Simulations on Virtual Machine Platforms

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yoginath, Srikanth B; Perumalla, Kalyan S

2013-01-01

With the advent of virtual machine (VM)-based platforms for parallel computing, it is now possible to execute parallel discrete event simulations (PDES) over multiple virtual machines, in contrast to executing in native mode directly over hardware as is traditionally done over the past decades. While mature VM-based parallel systems now offer new, compelling benefits such as serviceability, dynamic reconfigurability and overall cost effectiveness, the runtime performance of parallel applications can be significantly affected. In particular, most VM-based platforms are optimized for general workloads, but PDES execution exhibits unique dynamics significantly different from other workloads. Here we first present results frommore » experiments that highlight the gross deterioration of the runtime performance of VM-based PDES simulations when executed using traditional VM schedulers, quantitatively showing the bad scaling properties of the scheduler as the number of VMs is increased. The mismatch is fundamental in nature in the sense that any fairness-based VM scheduler implementation would exhibit this mismatch with PDES runs. We also present a new scheduler optimized specifically for PDES applications, and describe its design and implementation. Experimental results obtained from running PDES benchmarks (PHOLD and vehicular traffic simulations) over VMs show over an order of magnitude improvement in the run time of the PDES-optimized scheduler relative to the regular VM scheduler, with over 20 reduction in run time of simulations using up to 64 VMs. The observations and results are timely in the context of emerging systems such as cloud platforms and VM-based high performance computing installations, highlighting to the community the need for PDES-specific support, and the feasibility of significantly reducing the runtime overhead for scalable PDES on VM platforms.« less

Cloud-based large-scale air traffic flow optimization

NASA Astrophysics Data System (ADS)

Cao, Yi

The ever-increasing traffic demand makes the efficient use of airspace an imperative mission, and this paper presents an effort in response to this call. Firstly, a new aggregate model, called Link Transmission Model (LTM), is proposed, which models the nationwide traffic as a network of flight routes identified by origin-destination pairs. The traversal time of a flight route is assumed to be the mode of distribution of historical flight records, and the mode is estimated by using Kernel Density Estimation. As this simplification abstracts away physical trajectory details, the complexity of modeling is drastically decreased, resulting in efficient traffic forecasting. The predicative capability of LTM is validated against recorded traffic data. Secondly, a nationwide traffic flow optimization problem with airport and en route capacity constraints is formulated based on LTM. The optimization problem aims at alleviating traffic congestions with minimal global delays. This problem is intractable due to millions of variables. A dual decomposition method is applied to decompose the large-scale problem such that the subproblems are solvable. However, the whole problem is still computational expensive to solve since each subproblem is an smaller integer programming problem that pursues integer solutions. Solving an integer programing problem is known to be far more time-consuming than solving its linear relaxation. In addition, sequential execution on a standalone computer leads to linear runtime increase when the problem size increases. To address the computational efficiency problem, a parallel computing framework is designed which accommodates concurrent executions via multithreading programming. The multithreaded version is compared with its monolithic version to show decreased runtime. Finally, an open-source cloud computing framework, Hadoop MapReduce, is employed for better scalability and reliability. This framework is an "off-the-shelf" parallel computing model that can be used for both offline historical traffic data analysis and online traffic flow optimization. It provides an efficient and robust platform for easy deployment and implementation. A small cloud consisting of five workstations was configured and used to demonstrate the advantages of cloud computing in dealing with large-scale parallelizable traffic problems.

A Data Type for Efficient Representation of Other Data Types

NASA Technical Reports Server (NTRS)

James, Mark

2008-01-01

A self-organizing, monomorphic data type denoted a sequence has been conceived to address certain concerns that arise in programming parallel computers. A sequence in the present sense can be regarded abstractly as a vector, set, bag, queue, or other construct. Heretofore, in programming a parallel computer, it has been necessary for the programmer to state explicitly, at the outset, what parts of the program and the underlying data structures must be represented in parallel form. Not only is this requirement not optimal from the perspective of implementation; it entails an additional requirement that the programmer have intimate understanding of the underlying parallel structure. The present sequence data type overcomes both the implementation and parallel structure obstacles. In so doing, the sequence data type provides unified means by which the programmer can represent a data structure for natural and automatic decomposition to a parallel computing architecture. Sequences exhibit the behavioral and structural characteristics of vectors, but the underlying representations are automatically synthesized from combinations of programmers advice and execution use metrics. Sequences can vary bidirectionally between sparseness and density, making them excellent choices for many kinds of algorithms. The novelty and benefit of this behavior lies in the fact that it can relieve programmers of the details of implementations. The creation of a sequence enables decoupling of a conceptual representation from an implementation. The underlying representation of a sequence is a hybrid of representations composed of vectors, linked lists, connected blocks, and hash tables. The internal structure of a sequence can automatically change from time to time on the basis of how it is being used. Those portions of a sequence where elements have not been added or removed can be as efficient as vectors. As elements are inserted and removed in a given portion, then different methods are utilized to provide both an access and memory strategy that is optimized for that portion and the use to which it is put.

PARAMO: A Parallel Predictive Modeling Platform for Healthcare Analytic Research using Electronic Health Records

PubMed Central

Ng, Kenney; Ghoting, Amol; Steinhubl, Steven R.; Stewart, Walter F.; Malin, Bradley; Sun, Jimeng

2014-01-01

Objective Healthcare analytics research increasingly involves the construction of predictive models for disease targets across varying patient cohorts using electronic health records (EHRs). To facilitate this process, it is critical to support a pipeline of tasks: 1) cohort construction, 2) feature construction, 3) cross-validation, 4) feature selection, and 5) classification. To develop an appropriate model, it is necessary to compare and refine models derived from a diversity of cohorts, patient-specific features, and statistical frameworks. The goal of this work is to develop and evaluate a predictive modeling platform that can be used to simplify and expedite this process for health data. Methods To support this goal, we developed a PARAllel predictive MOdeling (PARAMO) platform which 1) constructs a dependency graph of tasks from specifications of predictive modeling pipelines, 2) schedules the tasks in a topological ordering of the graph, and 3) executes those tasks in parallel. We implemented this platform using Map-Reduce to enable independent tasks to run in parallel in a cluster computing environment. Different task scheduling preferences are also supported. Results We assess the performance of PARAMO on various workloads using three datasets derived from the EHR systems in place at Geisinger Health System and Vanderbilt University Medical Center and an anonymous longitudinal claims database. We demonstrate significant gains in computational efficiency against a standard approach. In particular, PARAMO can build 800 different models on a 300,000 patient data set in 3 hours in parallel compared to 9 days if running sequentially. Conclusion This work demonstrates that an efficient parallel predictive modeling platform can be developed for EHR data. This platform can facilitate large-scale modeling endeavors and speed-up the research workflow and reuse of health information. This platform is only a first step and provides the foundation for our ultimate goal of building analytic pipelines that are specialized for health data researchers. PMID:24370496

Implementation and performance of FDPS: a framework for developing parallel particle simulation codes

NASA Astrophysics Data System (ADS)

Iwasawa, Masaki; Tanikawa, Ataru; Hosono, Natsuki; Nitadori, Keigo; Muranushi, Takayuki; Makino, Junichiro

2016-08-01

We present the basic idea, implementation, measured performance, and performance model of FDPS (Framework for Developing Particle Simulators). FDPS is an application-development framework which helps researchers to develop simulation programs using particle methods for large-scale distributed-memory parallel supercomputers. A particle-based simulation program for distributed-memory parallel computers needs to perform domain decomposition, exchange of particles which are not in the domain of each computing node, and gathering of the particle information in other nodes which are necessary for interaction calculation. Also, even if distributed-memory parallel computers are not used, in order to reduce the amount of computation, algorithms such as the Barnes-Hut tree algorithm or the Fast Multipole Method should be used in the case of long-range interactions. For short-range interactions, some methods to limit the calculation to neighbor particles are required. FDPS provides all of these functions which are necessary for efficient parallel execution of particle-based simulations as "templates," which are independent of the actual data structure of particles and the functional form of the particle-particle interaction. By using FDPS, researchers can write their programs with the amount of work necessary to write a simple, sequential and unoptimized program of O(N2) calculation cost, and yet the program, once compiled with FDPS, will run efficiently on large-scale parallel supercomputers. A simple gravitational N-body program can be written in around 120 lines. We report the actual performance of these programs and the performance model. The weak scaling performance is very good, and almost linear speed-up was obtained for up to the full system of the K computer. The minimum calculation time per timestep is in the range of 30 ms (N = 107) to 300 ms (N = 109). These are currently limited by the time for the calculation of the domain decomposition and communication necessary for the interaction calculation. We discuss how we can overcome these bottlenecks.

PARAMO: a PARAllel predictive MOdeling platform for healthcare analytic research using electronic health records.

PubMed

Ng, Kenney; Ghoting, Amol; Steinhubl, Steven R; Stewart, Walter F; Malin, Bradley; Sun, Jimeng

2014-04-01

Healthcare analytics research increasingly involves the construction of predictive models for disease targets across varying patient cohorts using electronic health records (EHRs). To facilitate this process, it is critical to support a pipeline of tasks: (1) cohort construction, (2) feature construction, (3) cross-validation, (4) feature selection, and (5) classification. To develop an appropriate model, it is necessary to compare and refine models derived from a diversity of cohorts, patient-specific features, and statistical frameworks. The goal of this work is to develop and evaluate a predictive modeling platform that can be used to simplify and expedite this process for health data. To support this goal, we developed a PARAllel predictive MOdeling (PARAMO) platform which (1) constructs a dependency graph of tasks from specifications of predictive modeling pipelines, (2) schedules the tasks in a topological ordering of the graph, and (3) executes those tasks in parallel. We implemented this platform using Map-Reduce to enable independent tasks to run in parallel in a cluster computing environment. Different task scheduling preferences are also supported. We assess the performance of PARAMO on various workloads using three datasets derived from the EHR systems in place at Geisinger Health System and Vanderbilt University Medical Center and an anonymous longitudinal claims database. We demonstrate significant gains in computational efficiency against a standard approach. In particular, PARAMO can build 800 different models on a 300,000 patient data set in 3h in parallel compared to 9days if running sequentially. This work demonstrates that an efficient parallel predictive modeling platform can be developed for EHR data. This platform can facilitate large-scale modeling endeavors and speed-up the research workflow and reuse of health information. This platform is only a first step and provides the foundation for our ultimate goal of building analytic pipelines that are specialized for health data researchers. Copyright © 2013 Elsevier Inc. All rights reserved.

Parallel implementation of the particle simulation method with dynamic load balancing: Toward realistic geodynamical simulation

NASA Astrophysics Data System (ADS)

Furuichi, M.; Nishiura, D.

2015-12-01

Fully Lagrangian methods such as Smoothed Particle Hydrodynamics (SPH) and Discrete Element Method (DEM) have been widely used to solve the continuum and particles motions in the computational geodynamics field. These mesh-free methods are suitable for the problems with the complex geometry and boundary. In addition, their Lagrangian nature allows non-diffusive advection useful for tracking history dependent properties (e.g. rheology) of the material. These potential advantages over the mesh-based methods offer effective numerical applications to the geophysical flow and tectonic processes, which are for example, tsunami with free surface and floating body, magma intrusion with fracture of rock, and shear zone pattern generation of granular deformation. In order to investigate such geodynamical problems with the particle based methods, over millions to billion particles are required for the realistic simulation. Parallel computing is therefore important for handling such huge computational cost. An efficient parallel implementation of SPH and DEM methods is however known to be difficult especially for the distributed-memory architecture. Lagrangian methods inherently show workload imbalance problem for parallelization with the fixed domain in space, because particles move around and workloads change during the simulation. Therefore dynamic load balance is key technique to perform the large scale SPH and DEM simulation. In this work, we present the parallel implementation technique of SPH and DEM method utilizing dynamic load balancing algorithms toward the high resolution simulation over large domain using the massively parallel super computer system. Our method utilizes the imbalances of the executed time of each MPI process as the nonlinear term of parallel domain decomposition and minimizes them with the Newton like iteration method. In order to perform flexible domain decomposition in space, the slice-grid algorithm is used. Numerical tests show that our approach is suitable for solving the particles with different calculation costs (e.g. boundary particles) as well as the heterogeneous computer architecture. We analyze the parallel efficiency and scalability on the super computer systems (K-computer, Earth simulator 3, etc.).

Development of AN Innovative Three-Dimensional Complete Body Screening Device - 3D-CBS

NASA Astrophysics Data System (ADS)

Crosetto, D. B.

2004-07-01

This article describes an innovative technological approach that increases the efficiency with which a large number of particles (photons) can be detected and analyzed. The three-dimensional complete body screening (3D-CBS) combines the functional imaging capability of the Positron Emission Tomography (PET) with those of the anatomical imaging capability of Computed Tomography (CT). The novel techniques provide better images in a shorter time with less radiation to the patient. A primary means of accomplishing this is the use of a larger solid angle, but this requires a new electronic technique capable of handling the increased data rate. This technique, combined with an improved and simplified detector assembly, enables executing complex real-time algorithms and allows more efficiently use of economical crystals. These are the principal features of this invention. A good synergy of advanced techniques in particle detection, together with technological progress in industry (latest FPGA technology) and simple, but cost-effective ideas provide a revolutionary invention. This technology enables over 400 times PET efficiency improvement at once compared to two to three times improvements achieved every five years during the past decades. Details of the electronics are provided, including an IBM PC board with a parallel-processing architecture implemented in FPGA, enabling the execution of a programmable complex real-time algorithm for best detection of photons.

Sub-Second Parallel State Estimation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen, Yousu; Rice, Mark J.; Glaesemann, Kurt R.

This report describes the performance of Pacific Northwest National Laboratory (PNNL) sub-second parallel state estimation (PSE) tool using the utility data from the Bonneville Power Administrative (BPA) and discusses the benefits of the fast computational speed for power system applications. The test data were provided by BPA. They are two-days’ worth of hourly snapshots that include power system data and measurement sets in a commercial tool format. These data are extracted out from the commercial tool box and fed into the PSE tool. With the help of advanced solvers, the PSE tool is able to solve each BPA hourly statemore » estimation problem within one second, which is more than 10 times faster than today’s commercial tool. This improved computational performance can help increase the reliability value of state estimation in many aspects: (1) the shorter the time required for execution of state estimation, the more time remains for operators to take appropriate actions, and/or to apply automatic or manual corrective control actions. This increases the chances of arresting or mitigating the impact of cascading failures; (2) the SE can be executed multiple times within time allowance. Therefore, the robustness of SE can be enhanced by repeating the execution of the SE with adaptive adjustments, including removing bad data and/or adjusting different initial conditions to compute a better estimate within the same time as a traditional state estimator’s single estimate. There are other benefits with the sub-second SE, such as that the PSE results can potentially be used in local and/or wide-area automatic corrective control actions that are currently dependent on raw measurements to minimize the impact of bad measurements, and provides opportunities to enhance the power grid reliability and efficiency. PSE also can enable other advanced tools that rely on SE outputs and could be used to further improve operators’ actions and automated controls to mitigate effects of severe events on the grid. The power grid continues to grow and the number of measurements is increasing at an accelerated rate due to the variety of smart grid devices being introduced. A parallel state estimation implementation will have better performance than traditional, sequential state estimation by utilizing the power of high performance computing (HPC). This increased performance positions parallel state estimators as valuable tools for operating the increasingly more complex power grid.« less

The paradigm compiler: Mapping a functional language for the connection machine

NASA Technical Reports Server (NTRS)

Dennis, Jack B.

1989-01-01

The Paradigm Compiler implements a new approach to compiling programs written in high level languages for execution on highly parallel computers. The general approach is to identify the principal data structures constructed by the program and to map these structures onto the processing elements of the target machine. The mapping is chosen to maximize performance as determined through compile time global analysis of the source program. The source language is Sisal, a functional language designed for scientific computations, and the target language is Paris, the published low level interface to the Connection Machine. The data structures considered are multidimensional arrays whose dimensions are known at compile time. Computations that build such arrays usually offer opportunities for highly parallel execution; they are data parallel. The Connection Machine is an attractive target for these computations, and the parallel for construct of the Sisal language is a convenient high level notation for data parallel algorithms. The principles and organization of the Paradigm Compiler are discussed.

A path-level exact parallelization strategy for sequential simulation

NASA Astrophysics Data System (ADS)

Peredo, Oscar F.; Baeza, Daniel; Ortiz, Julián M.; Herrero, José R.

2018-01-01

Sequential Simulation is a well known method in geostatistical modelling. Following the Bayesian approach for simulation of conditionally dependent random events, Sequential Indicator Simulation (SIS) method draws simulated values for K categories (categorical case) or classes defined by K different thresholds (continuous case). Similarly, Sequential Gaussian Simulation (SGS) method draws simulated values from a multivariate Gaussian field. In this work, a path-level approach to parallelize SIS and SGS methods is presented. A first stage of re-arrangement of the simulation path is performed, followed by a second stage of parallel simulation for non-conflicting nodes. A key advantage of the proposed parallelization method is to generate identical realizations as with the original non-parallelized methods. Case studies are presented using two sequential simulation codes from GSLIB: SISIM and SGSIM. Execution time and speedup results are shown for large-scale domains, with many categories and maximum kriging neighbours in each case, achieving high speedup results in the best scenarios using 16 threads of execution in a single machine.

77 FR 47573 - Approval and Promulgation of Implementation Plans; Mississippi; 110(a)(2)(E)(ii) Infrastructure...

Federal Register 2010, 2011, 2012, 2013, 2014

2012-08-09

... Mississippi Department of Environmental Quality (MDEQ), on July 13, 2012, for parallel processing. This... of Contents I. What is parallel processing? II. Background III. What elements are required under... Executive Order Reviews I. What is parallel processing? Consistent with EPA regulations found at 40 CFR Part...

Parallelization of fine-scale computation in Agile Multiscale Modelling Methodology

NASA Astrophysics Data System (ADS)

Macioł, Piotr; Michalik, Kazimierz

2016-10-01

Nowadays, multiscale modelling of material behavior is an extensively developed area. An important obstacle against its wide application is high computational demands. Among others, the parallelization of multiscale computations is a promising solution. Heterogeneous multiscale models are good candidates for parallelization, since communication between sub-models is limited. In this paper, the possibility of parallelization of multiscale models based on Agile Multiscale Methodology framework is discussed. A sequential, FEM based macroscopic model has been combined with concurrently computed fine-scale models, employing a MatCalc thermodynamic simulator. The main issues, being investigated in this work are: (i) the speed-up of multiscale models with special focus on fine-scale computations and (ii) on decreasing the quality of computations enforced by parallel execution. Speed-up has been evaluated on the basis of Amdahl's law equations. The problem of `delay error', rising from the parallel execution of fine scale sub-models, controlled by the sequential macroscopic sub-model is discussed. Some technical aspects of combining third-party commercial modelling software with an in-house multiscale framework and a MPI library are also discussed.

Antecedent acute cycling exercise affects attention control: an ERP study using attention network test

PubMed Central

Chang, Yu-Kai; Pesce, Caterina; Chiang, Yi-Te; Kuo, Cheng-Yuh; Fong, Dong-Yang

2015-01-01

The purpose of this study was to investigate the after-effects of an acute bout of moderate intensity aerobic cycling exercise on neuroelectric and behavioral indices of efficiency of three attentional networks: alerting, orienting, and executive (conflict) control. Thirty young, highly fit amateur basketball players performed a multifunctional attentional reaction time task, the attention network test (ANT), with a two-group randomized experimental design after an acute bout of moderate intensity spinning wheel exercise or without antecedent exercise. The ANT combined warning signals prior to targets, spatial cueing of potential target locations and target stimuli surrounded by congruent or incongruent flankers, which were provided to assess three attentional networks. Event-related brain potentials and task performance were measured during the ANT. Exercise resulted in a larger P3 amplitude in the alerting and executive control subtasks across frontal, central and parietal midline sites that was paralleled by an enhanced reaction speed only on trials with incongruent flankers of the executive control network. The P3 latency and response accuracy were not affected by exercise. These findings suggest that after spinning, more resources are allocated to task-relevant stimuli in tasks that rely on the alerting and executive control networks. However, the improvement in performance was observed in only the executively challenging conflict condition, suggesting that whether the brain resources that are rendered available immediately after acute exercise translate into better attention performance depends on the cognitive task complexity. PMID:25914634

Energy-aware Thread and Data Management in Heterogeneous Multi-core, Multi-memory Systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Su, Chun-Yi

By 2004, microprocessor design focused on multicore scaling—increasing the number of cores per die in each generation—as the primary strategy for improving performance. These multicore processors typically equip multiple memory subsystems to improve data throughput. In addition, these systems employ heterogeneous processors such as GPUs and heterogeneous memories like non-volatile memory to improve performance, capacity, and energy efficiency. With the increasing volume of hardware resources and system complexity caused by heterogeneity, future systems will require intelligent ways to manage hardware resources. Early research to improve performance and energy efficiency on heterogeneous, multi-core, multi-memory systems focused on tuning a single primitivemore » or at best a few primitives in the systems. The key limitation of past efforts is their lack of a holistic approach to resource management that balances the tradeoff between performance and energy consumption. In addition, the shift from simple, homogeneous systems to these heterogeneous, multicore, multi-memory systems requires in-depth understanding of efficient resource management for scalable execution, including new models that capture the interchange between performance and energy, smarter resource management strategies, and novel low-level performance/energy tuning primitives and runtime systems. Tuning an application to control available resources efficiently has become a daunting challenge; managing resources in automation is still a dark art since the tradeoffs among programming, energy, and performance remain insufficiently understood. In this dissertation, I have developed theories, models, and resource management techniques to enable energy-efficient execution of parallel applications through thread and data management in these heterogeneous multi-core, multi-memory systems. I study the effect of dynamic concurrent throttling on the performance and energy of multi-core, non-uniform memory access (NUMA) systems. I use critical path analysis to quantify memory contention in the NUMA memory system and determine thread mappings. In addition, I implement a runtime system that combines concurrent throttling and a novel thread mapping algorithm to manage thread resources and improve energy efficient execution in multi-core, NUMA systems.« less

PEGASUS 5: An Automated Pre-Processor for Overset-Grid CFD

NASA Technical Reports Server (NTRS)

Suhs, Norman E.; Rogers, Stuart E.; Dietz, William E.; Kwak, Dochan (Technical Monitor)

2002-01-01

An all new, automated version of the PEGASUS software has been developed and tested. PEGASUS provides the hole-cutting and connectivity information between overlapping grids, and is used as the final part of the grid generation process for overset-grid computational fluid dynamics approaches. The new PEGASUS code (Version 5) has many new features: automated hole cutting; a projection scheme for fixing gaps in overset surfaces; more efficient interpolation search methods using an alternating digital tree; hole-size optimization based on adding additional layers of fringe points; and an automatic restart capability. The new code has also been parallelized using the Message Passing Interface standard. The parallelization performance provides efficient speed-up of the execution time by an order of magnitude, and up to a factor of 30 for very large problems. The results of three example cases are presented: a three-element high-lift airfoil, a generic business jet configuration, and a complete Boeing 777-200 aircraft in a high-lift landing configuration. Comparisons of the computed flow fields for the airfoil and 777 test cases between the old and new versions of the PEGASUS codes show excellent agreement with each other and with experimental results.

Medical image denoising via optimal implementation of non-local means on hybrid parallel architecture.

PubMed

Nguyen, Tuan-Anh; Nakib, Amir; Nguyen, Huy-Nam

2016-06-01

The Non-local means denoising filter has been established as gold standard for image denoising problem in general and particularly in medical imaging due to its efficiency. However, its computation time limited its applications in real world application, especially in medical imaging. In this paper, a distributed version on parallel hybrid architecture is proposed to solve the computation time problem and a new method to compute the filters' coefficients is also proposed, where we focused on the implementation and the enhancement of filters' parameters via taking the neighborhood of the current voxel more accurately into account. In terms of implementation, our key contribution consists in reducing the number of shared memory accesses. The different tests of the proposed method were performed on the brain-web database for different levels of noise. Performances and the sensitivity were quantified in terms of speedup, peak signal to noise ratio, execution time, the number of floating point operations. The obtained results demonstrate the efficiency of the proposed method. Moreover, the implementation is compared to that of other techniques, recently published in the literature. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

The force on the flex: Global parallelism and portability

NASA Technical Reports Server (NTRS)

Jordan, H. F.

1986-01-01

A parallel programming methodology, called the force, supports the construction of programs to be executed in parallel by an unspecified, but potentially large, number of processes. The methodology was originally developed on a pipelined, shared memory multiprocessor, the Denelcor HEP, and embodies the primitive operations of the force in a set of macros which expand into multiprocessor Fortran code. A small set of primitives is sufficient to write large parallel programs, and the system has been used to produce 10,000 line programs in computational fluid dynamics. The level of complexity of the force primitives is intermediate. It is high enough to mask detailed architectural differences between multiprocessors but low enough to give the user control over performance. The system is being ported to a medium scale multiprocessor, the Flex/32, which is a 20 processor system with a mixture of shared and local memory. Memory organization and the type of processor synchronization supported by the hardware on the two machines lead to some differences in efficient implementations of the force primitives, but the user interface remains the same. An initial implementation was done by retargeting the macros to Flexible Computer Corporation's ConCurrent C language. Subsequently, the macros were caused to directly produce the system calls which form the basis for ConCurrent C. The implementation of the Fortran based system is in step with Flexible Computer Corporations's implementation of a Fortran system in the parallel environment.

Developing a Collection of Composable Data Translation Software Units to Improve Efficiency and Reproducibility in Ecohydrologic Modeling Workflows

NASA Astrophysics Data System (ADS)

Olschanowsky, C.; Flores, A. N.; FitzGerald, K.; Masarik, M. T.; Rudisill, W. J.; Aguayo, M.

2017-12-01

Dynamic models of the spatiotemporal evolution of water, energy, and nutrient cycling are important tools to assess impacts of climate and other environmental changes on ecohydrologic systems. These models require spatiotemporally varying environmental forcings like precipitation, temperature, humidity, windspeed, and solar radiation. These input data originate from a variety of sources, including global and regional weather and climate models, global and regional reanalysis products, and geostatistically interpolated surface observations. Data translation measures, often subsetting in space and/or time and transforming and converting variable units, represent a seemingly mundane, but critical step in the application workflows. Translation steps can introduce errors, misrepresentations of data, slow execution time, and interrupt data provenance. We leverage a workflow that subsets a large regional dataset derived from the Weather Research and Forecasting (WRF) model and prepares inputs to the Parflow integrated hydrologic model to demonstrate the impact translation tool software quality on scientific workflow results and performance. We propose that such workflows will benefit from a community approved collection of data transformation components. The components should be self-contained composable units of code. This design pattern enables automated parallelization and software verification, improving performance and reliability. Ensuring that individual translation components are self-contained and target minute tasks increases reliability. The small code size of each component enables effective unit and regression testing. The components can be automatically composed for efficient execution. An efficient data translation framework should be written to minimize data movement. Composing components within a single streaming process reduces data movement. Each component will typically have a low arithmetic intensity, meaning that it requires about the same number of bytes to be read as the number of computations it performs. When several components' executions are coordinated the overall arithmetic intensity increases, leading to increased efficiency.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Gooding, Thomas M.

Distributing an executable job load file to compute nodes in a parallel computer, the parallel computer comprising a plurality of compute nodes, including: determining, by a compute node in the parallel computer, whether the compute node is participating in a job; determining, by the compute node in the parallel computer, whether a descendant compute node is participating in the job; responsive to determining that the compute node is participating in the job or that the descendant compute node is participating in the job, communicating, by the compute node to a parent compute node, an identification of a data communications linkmore » over which the compute node receives data from the parent compute node; constructing a class route for the job, wherein the class route identifies all compute nodes participating in the job; and broadcasting the executable load file for the job along the class route for the job.« less

Automated Vectorization of Decision-Based Algorithms

NASA Technical Reports Server (NTRS)

James, Mark

2006-01-01

Virtually all existing vectorization algorithms are designed to only analyze the numeric properties of an algorithm and distribute those elements across multiple processors. This advances the state of the practice because it is the only known system, at the time of this reporting, that takes high-level statements and analyzes them for their decision properties and converts them to a form that allows them to automatically be executed in parallel. The software takes a high-level source program that describes a complex decision- based condition and rewrites it as a disjunctive set of component Boolean relations that can then be executed in parallel. This is important because parallel architectures are becoming more commonplace in conventional systems and they have always been present in NASA flight systems. This technology allows one to take existing condition-based code and automatically vectorize it so it naturally decomposes across parallel architectures.

75 FR 28555 - Executive Green ICT & Energy Efficiency Trade Mission to Mexico City, Mexico

Federal Register 2010, 2011, 2012, 2013, 2014

2010-05-21

... energy efficiency in data centers, smart grids, and green buildings will be discussed. Mission delegates... DEPARTMENT OF COMMERCE International Trade Administration Executive Green ICT & Energy Efficiency... Administration, and U.S. & Foreign Commercial Service are organizing an Executive Green ICT & Energy Efficiency...

Analysis and selection of optimal function implementations in massively parallel computer

DOEpatents

Archer, Charles Jens [Rochester, MN; Peters, Amanda [Rochester, MN; Ratterman, Joseph D [Rochester, MN

2011-05-31

An apparatus, program product and method optimize the operation of a parallel computer system by, in part, collecting performance data for a set of implementations of a function capable of being executed on the parallel computer system based upon the execution of the set of implementations under varying input parameters in a plurality of input dimensions. The collected performance data may be used to generate selection program code that is configured to call selected implementations of the function in response to a call to the function under varying input parameters. The collected performance data may be used to perform more detailed analysis to ascertain the comparative performance of the set of implementations of the function under the varying input parameters.

Reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application

DOEpatents

Archer, Charles J [Rochester, MN; Blocksome, Michael A [Rochester, MN; Peters, Amanda A [Rochester, MN; Ratterman, Joseph D [Rochester, MN; Smith, Brian E [Rochester, MN

2012-01-10

Methods, apparatus, and products are disclosed for reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application that include: beginning, by each compute node, performance of a blocking operation specified by the parallel application, each compute node beginning the blocking operation asynchronously with respect to the other compute nodes; reducing, for each compute node, power to one or more hardware components of that compute node in response to that compute node beginning the performance of the blocking operation; and restoring, for each compute node, the power to the hardware components having power reduced in response to all of the compute nodes beginning the performance of the blocking operation.

Reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application

DOEpatents

Archer, Charles J [Rochester, MN; Blocksome, Michael A [Rochester, MN; Peters, Amanda E [Cambridge, MA; Ratterman, Joseph D [Rochester, MN; Smith, Brian E [Rochester, MN

2012-04-17

Methods, apparatus, and products are disclosed for reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application that include: beginning, by each compute node, performance of a blocking operation specified by the parallel application, each compute node beginning the blocking operation asynchronously with respect to the other compute nodes; reducing, for each compute node, power to one or more hardware components of that compute node in response to that compute node beginning the performance of the blocking operation; and restoring, for each compute node, the power to the hardware components having power reduced in response to all of the compute nodes beginning the performance of the blocking operation.

Parallelization of a blind deconvolution algorithm

NASA Astrophysics Data System (ADS)

Matson, Charles L.; Borelli, Kathy J.

2006-09-01

Often it is of interest to deblur imagery in order to obtain higher-resolution images. Deblurring requires knowledge of the blurring function - information that is often not available separately from the blurred imagery. Blind deconvolution algorithms overcome this problem by jointly estimating both the high-resolution image and the blurring function from the blurred imagery. Because blind deconvolution algorithms are iterative in nature, they can take minutes to days to deblur an image depending how many frames of data are used for the deblurring and the platforms on which the algorithms are executed. Here we present our progress in parallelizing a blind deconvolution algorithm to increase its execution speed. This progress includes sub-frame parallelization and a code structure that is not specialized to a specific computer hardware architecture.

Algebraic multigrid preconditioning within parallel finite-element solvers for 3-D electromagnetic modelling problems in geophysics

NASA Astrophysics Data System (ADS)

Koldan, Jelena; Puzyrev, Vladimir; de la Puente, Josep; Houzeaux, Guillaume; Cela, José María

2014-06-01

We present an elaborate preconditioning scheme for Krylov subspace methods which has been developed to improve the performance and reduce the execution time of parallel node-based finite-element (FE) solvers for 3-D electromagnetic (EM) numerical modelling in exploration geophysics. This new preconditioner is based on algebraic multigrid (AMG) that uses different basic relaxation methods, such as Jacobi, symmetric successive over-relaxation (SSOR) and Gauss-Seidel, as smoothers and the wave front algorithm to create groups, which are used for a coarse-level generation. We have implemented and tested this new preconditioner within our parallel nodal FE solver for 3-D forward problems in EM induction geophysics. We have performed series of experiments for several models with different conductivity structures and characteristics to test the performance of our AMG preconditioning technique when combined with biconjugate gradient stabilized method. The results have shown that, the more challenging the problem is in terms of conductivity contrasts, ratio between the sizes of grid elements and/or frequency, the more benefit is obtained by using this preconditioner. Compared to other preconditioning schemes, such as diagonal, SSOR and truncated approximate inverse, the AMG preconditioner greatly improves the convergence of the iterative solver for all tested models. Also, when it comes to cases in which other preconditioners succeed to converge to a desired precision, AMG is able to considerably reduce the total execution time of the forward-problem code-up to an order of magnitude. Furthermore, the tests have confirmed that our AMG scheme ensures grid-independent rate of convergence, as well as improvement in convergence regardless of how big local mesh refinements are. In addition, AMG is designed to be a black-box preconditioner, which makes it easy to use and combine with different iterative methods. Finally, it has proved to be very practical and efficient in the parallel context.

Execution environment for intelligent real-time control systems

NASA Technical Reports Server (NTRS)

Sztipanovits, Janos

1987-01-01

Modern telerobot control technology requires the integration of symbolic and non-symbolic programming techniques, different models of parallel computations, and various programming paradigms. The Multigraph Architecture, which has been developed for the implementation of intelligent real-time control systems is described. The layered architecture includes specific computational models, integrated execution environment and various high-level tools. A special feature of the architecture is the tight coupling between the symbolic and non-symbolic computations. It supports not only a data interface, but also the integration of the control structures in a parallel computing environment.

CELES: CUDA-accelerated simulation of electromagnetic scattering by large ensembles of spheres

NASA Astrophysics Data System (ADS)

Egel, Amos; Pattelli, Lorenzo; Mazzamuto, Giacomo; Wiersma, Diederik S.; Lemmer, Uli

2017-09-01

CELES is a freely available MATLAB toolbox to simulate light scattering by many spherical particles. Aiming at high computational performance, CELES leverages block-diagonal preconditioning, a lookup-table approach to evaluate costly functions and massively parallel execution on NVIDIA graphics processing units using the CUDA computing platform. The combination of these techniques allows to efficiently address large electrodynamic problems (>104 scatterers) on inexpensive consumer hardware. In this paper, we validate near- and far-field distributions against the well-established multi-sphere T-matrix (MSTM) code and discuss the convergence behavior for ensembles of different sizes, including an exemplary system comprising 105 particles.

Parallel simulation of tsunami inundation on a large-scale supercomputer

NASA Astrophysics Data System (ADS)

Oishi, Y.; Imamura, F.; Sugawara, D.

2013-12-01

An accurate prediction of tsunami inundation is important for disaster mitigation purposes. One approach is to approximate the tsunami wave source through an instant inversion analysis using real-time observation data (e.g., Tsushima et al., 2009) and then use the resulting wave source data in an instant tsunami inundation simulation. However, a bottleneck of this approach is the large computational cost of the non-linear inundation simulation and the computational power of recent massively parallel supercomputers is helpful to enable faster than real-time execution of a tsunami inundation simulation. Parallel computers have become approximately 1000 times faster in 10 years (www.top500.org), and so it is expected that very fast parallel computers will be more and more prevalent in the near future. Therefore, it is important to investigate how to efficiently conduct a tsunami simulation on parallel computers. In this study, we are targeting very fast tsunami inundation simulations on the K computer, currently the fastest Japanese supercomputer, which has a theoretical peak performance of 11.2 PFLOPS. One computing node of the K computer consists of 1 CPU with 8 cores that share memory, and the nodes are connected through a high-performance torus-mesh network. The K computer is designed for distributed-memory parallel computation, so we have developed a parallel tsunami model. Our model is based on TUNAMI-N2 model of Tohoku University, which is based on a leap-frog finite difference method. A grid nesting scheme is employed to apply high-resolution grids only at the coastal regions. To balance the computation load of each CPU in the parallelization, CPUs are first allocated to each nested layer in proportion to the number of grid points of the nested layer. Using CPUs allocated to each layer, 1-D domain decomposition is performed on each layer. In the parallel computation, three types of communication are necessary: (1) communication to adjacent neighbours for the finite difference calculation, (2) communication between adjacent layers for the calculations to connect each layer, and (3) global communication to obtain the time step which satisfies the CFL condition in the whole domain. A preliminary test on the K computer showed the parallel efficiency on 1024 cores was 57% relative to 64 cores. We estimate that the parallel efficiency will be considerably improved by applying a 2-D domain decomposition instead of the present 1-D domain decomposition in future work. The present parallel tsunami model was applied to the 2011 Great Tohoku tsunami. The coarsest resolution layer covers a 758 km × 1155 km region with a 405 m grid spacing. A nesting of five layers was used with the resolution ratio of 1/3 between nested layers. The finest resolution region has 5 m resolution and covers most of the coastal region of Sendai city. To complete 2 hours of simulation time, the serial (non-parallel) computation took approximately 4 days on a workstation. To complete the same simulation on 1024 cores of the K computer, it took 45 minutes which is more than two times faster than real-time. This presentation discusses the updated parallel computational performance and the efficient use of the K computer when considering the characteristics of the tsunami inundation simulation model in relation to the characteristics and capabilities of the K computer.

RPYFMM: Parallel adaptive fast multipole method for Rotne-Prager-Yamakawa tensor in biomolecular hydrodynamics simulations

NASA Astrophysics Data System (ADS)

Guan, W.; Cheng, X.; Huang, J.; Huber, G.; Li, W.; McCammon, J. A.; Zhang, B.

2018-06-01

RPYFMM is a software package for the efficient evaluation of the potential field governed by the Rotne-Prager-Yamakawa (RPY) tensor interactions in biomolecular hydrodynamics simulations. In our algorithm, the RPY tensor is decomposed as a linear combination of four Laplace interactions, each of which is evaluated using the adaptive fast multipole method (FMM) (Greengard and Rokhlin, 1997) where the exponential expansions are applied to diagonalize the multipole-to-local translation operators. RPYFMM offers a unified execution on both shared and distributed memory computers by leveraging the DASHMM library (DeBuhr et al., 2016, 2018). Preliminary numerical results show that the interactions for a molecular system of 15 million particles (beads) can be computed within one second on a Cray XC30 cluster using 12,288 cores, while achieving approximately 54% strong-scaling efficiency.

FOX: A Fault-Oblivious Extreme-Scale Execution Environment Boston University Final Report Project Number: DE-SC0005365

DOE Office of Scientific and Technical Information (OSTI.GOV)

Appavoo, Jonathan

Exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today's machines. Systems software for exascale machines must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. The FOX project explored systems software and runtime support for a new approach to the data and work distribution for fault oblivious application execution. Our major OS work at Boston University focusedmore » on developing a new light-weight operating systems model that provides an appropriate context for both multi-core and multi-node application development. This work is discussed in section 1. Early on in the FOX project BU developed infrastructure for prototyping dynamic HPC environments in which the sets of nodes that an application is run on can be dynamically grown or shrunk. This work was an extension of the Kittyhawk project and is discussed in section 2. Section 3 documents the publications and software repositories that we have produced. To put our work in context of the complete FOX project contribution we include in section 4 an extended version of a paper that documents the complete work of the FOX team.« less

The curse of planning: dissecting multiple reinforcement-learning systems by taxing the central executive.

PubMed

Otto, A Ross; Gershman, Samuel J; Markman, Arthur B; Daw, Nathaniel D

2013-05-01

A number of accounts of human and animal behavior posit the operation of parallel and competing valuation systems in the control of choice behavior. In these accounts, a flexible but computationally expensive model-based reinforcement-learning system has been contrasted with a less flexible but more efficient model-free reinforcement-learning system. The factors governing which system controls behavior-and under what circumstances-are still unclear. Following the hypothesis that model-based reinforcement learning requires cognitive resources, we demonstrated that having human decision makers perform a demanding secondary task engenders increased reliance on a model-free reinforcement-learning strategy. Further, we showed that, across trials, people negotiate the trade-off between the two systems dynamically as a function of concurrent executive-function demands, and people's choice latencies reflect the computational expenses of the strategy they employ. These results demonstrate that competition between multiple learning systems can be controlled on a trial-by-trial basis by modulating the availability of cognitive resources.

The Curse of Planning: Dissecting multiple reinforcement learning systems by taxing the central executive

PubMed Central

Otto, A. Ross; Gershman, Samuel J.; Markman, Arthur B.; Daw, Nathaniel D.

2013-01-01

A number of accounts of human and animal behavior posit the operation of parallel and competing valuation systems in the control of choice behavior. Along these lines, a flexible but computationally expensive model-based reinforcement learning system has been contrasted with a less flexible but more efficient model-free reinforcement learning system. The factors governing which system controls behavior—and under what circumstances—are still unclear. Based on the hypothesis that model-based reinforcement learning requires cognitive resources, we demonstrate that having human decision-makers perform a demanding secondary task engenders increased reliance on a model-free reinforcement learning strategy. Further, we show that across trials, people negotiate this tradeoff dynamically as a function of concurrent executive function demands and their choice latencies reflect the computational expenses of the strategy employed. These results demonstrate that competition between multiple learning systems can be controlled on a trial-by-trial basis by modulating the availability of cognitive resources. PMID:23558545

Parallel Agent-Based Simulations on Clusters of GPUs and Multi-Core Processors

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aaby, Brandon G; Perumalla, Kalyan S; Seal, Sudip K

2010-01-01

An effective latency-hiding mechanism is presented in the parallelization of agent-based model simulations (ABMS) with millions of agents. The mechanism is designed to accommodate the hierarchical organization as well as heterogeneity of current state-of-the-art parallel computing platforms. We use it to explore the computation vs. communication trade-off continuum available with the deep computational and memory hierarchies of extant platforms and present a novel analytical model of the tradeoff. We describe our implementation and report preliminary performance results on two distinct parallel platforms suitable for ABMS: CUDA threads on multiple, networked graphical processing units (GPUs), and pthreads on multi-core processors. Messagemore » Passing Interface (MPI) is used for inter-GPU as well as inter-socket communication on a cluster of multiple GPUs and multi-core processors. Results indicate the benefits of our latency-hiding scheme, delivering as much as over 100-fold improvement in runtime for certain benchmark ABMS application scenarios with several million agents. This speed improvement is obtained on our system that is already two to three orders of magnitude faster on one GPU than an equivalent CPU-based execution in a popular simulator in Java. Thus, the overall execution of our current work is over four orders of magnitude faster when executed on multiple GPUs.« less

PWHATSHAP: efficient haplotyping for future generation sequencing.

PubMed

Bracciali, Andrea; Aldinucci, Marco; Patterson, Murray; Marschall, Tobias; Pisanti, Nadia; Merelli, Ivan; Torquati, Massimo

2016-09-22

Haplotype phasing is an important problem in the analysis of genomics information. Given a set of DNA fragments of an individual, it consists of determining which one of the possible alleles (alternative forms of a gene) each fragment comes from. Haplotype information is relevant to gene regulation, epigenetics, genome-wide association studies, evolutionary and population studies, and the study of mutations. Haplotyping is currently addressed as an optimisation problem aiming at solutions that minimise, for instance, error correction costs, where costs are a measure of the confidence in the accuracy of the information acquired from DNA sequencing. Solutions have typically an exponential computational complexity. WHATSHAP is a recent optimal approach which moves computational complexity from DNA fragment length to fragment overlap, i.e., coverage, and is hence of particular interest when considering sequencing technology's current trends that are producing longer fragments. Given the potential relevance of efficient haplotyping in several analysis pipelines, we have designed and engineered PWHATSHAP, a parallel, high-performance version of WHATSHAP. PWHATSHAP is embedded in a toolkit developed in Python and supports genomics datasets in standard file formats. Building on WHATSHAP, PWHATSHAP exhibits the same complexity exploring a number of possible solutions which is exponential in the coverage of the dataset. The parallel implementation on multi-core architectures allows for a relevant reduction of the execution time for haplotyping, while the provided results enjoy the same high accuracy as that provided by WHATSHAP, which increases with coverage. Due to its structure and management of the large datasets, the parallelisation of WHATSHAP posed demanding technical challenges, which have been addressed exploiting a high-level parallel programming framework. The result, PWHATSHAP, is a freely available toolkit that improves the efficiency of the analysis of genomics information.

Myria: Scalable Analytics as a Service

NASA Astrophysics Data System (ADS)

Howe, B.; Halperin, D.; Whitaker, A.

2014-12-01

At the UW eScience Institute, we're working to empower non-experts, especially in the sciences, to write and use data-parallel algorithms. To this end, we are building Myria, a web-based platform for scalable analytics and data-parallel programming. Myria's internal model of computation is the relational algebra extended with iteration, such that every program is inherently data-parallel, just as every query in a database is inherently data-parallel. But unlike databases, iteration is a first class concept, allowing us to express machine learning tasks, graph traversal tasks, and more. Programs can be expressed in a number of languages and can be executed on a number of execution environments, but we emphasize a particular language called MyriaL that supports both imperative and declarative styles and a particular execution engine called MyriaX that uses an in-memory column-oriented representation and asynchronous iteration. We deliver Myria over the web as a service, providing an editor, performance analysis tools, and catalog browsing features in a single environment. We find that this web-based "delivery vector" is critical in reaching non-experts: they are insulated from irrelevant effort technical work associated with installation, configuration, and resource management. The MyriaX backend, one of several execution runtimes we support, is a main-memory, column-oriented, RDBMS-on-the-worker system that supports cyclic data flows as a first-class citizen and has been shown to outperform competitive systems on 100-machine cluster sizes. I will describe the Myria system, give a demo, and present some new results in large-scale oceanographic microbiology.

Parallelisation study of a three-dimensional environmental flow model

NASA Astrophysics Data System (ADS)

O'Donncha, Fearghal; Ragnoli, Emanuele; Suits, Frank

2014-03-01

There are many simulation codes in the geosciences that are serial and cannot take advantage of the parallel computational resources commonly available today. One model important for our work in coastal ocean current modelling is EFDC, a Fortran 77 code configured for optimal deployment on vector computers. In order to take advantage of our cache-based, blade computing system we restructured EFDC from serial to parallel, thereby allowing us to run existing models more quickly, and to simulate larger and more detailed models that were previously impractical. Since the source code for EFDC is extensive and involves detailed computation, it is important to do such a port in a manner that limits changes to the files, while achieving the desired speedup. We describe a parallelisation strategy involving surgical changes to the source files to minimise error-prone alteration of the underlying computations, while allowing load-balanced domain decomposition for efficient execution on a commodity cluster. The use of conjugate gradient posed particular challenges due to implicit non-local communication posing a hindrance to standard domain partitioning schemes; a number of techniques are discussed to address this in a feasible, computationally efficient manner. The parallel implementation demonstrates good scalability in combination with a novel domain partitioning scheme that specifically handles mixed water/land regions commonly found in coastal simulations. The approach presented here represents a practical methodology to rejuvenate legacy code on a commodity blade cluster with reasonable effort; our solution has direct application to other similar codes in the geosciences.

Efficient iterative methods applied to the solution of transonic flows

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wissink, A.M.; Lyrintzis, A.S.; Chronopoulos, A.T.

1996-02-01

We investigate the use of an inexact Newton`s method to solve the potential equations in the transonic regime. As a test case, we solve the two-dimensional steady transonic small disturbance equation. Approximate factorization/ADI techniques have traditionally been employed for implicit solutions of this nonlinear equation. Instead, we apply Newton`s method using an exact analytical determination of the Jacobian with preconditioned conjugate gradient-like iterative solvers for solution of the linear systems in each Newton iteration. Two iterative solvers are tested; a block s-step version of the classical Orthomin(k) algorithm called orthogonal s-step Orthomin (OSOmin) and the well-known GIVIRES method. The preconditionermore » is a vectorizable and parallelizable version of incomplete LU (ILU) factorization. Efficiency of the Newton-Iterative method on vector and parallel computer architectures is the main issue addressed. In vectorized tests on a single processor of the Cray C-90, the performance of Newton-OSOmin is superior to Newton-GMRES and a more traditional monotone AF/ADI method (MAF) for a variety of transonic Mach numbers and mesh sizes. Newton- GIVIRES is superior to MAF for some cases. The parallel performance of the Newton method is also found to be very good on multiple processors of the Cray C-90 and on the massively parallel thinking machine CM-5, where very fast execution rates (up to 9 Gflops) are found for large problems. 38 refs., 14 figs., 7 tabs.« less

Locality Aware Concurrent Start for Stencil Applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Shrestha, Sunil; Gao, Guang R.; Manzano Franco, Joseph B.

Stencil computations are at the heart of many physical simulations used in scientific codes. Thus, there exists a plethora of optimization efforts for this family of computations. Among these techniques, tiling techniques that allow concurrent start have proven to be very efficient in providing better performance for these critical kernels. Nevertheless, with many core designs being the norm, these optimization techniques might not be able to fully exploit locality (both spatial and temporal) on multiple levels of the memory hierarchy without compromising parallelism. It is no longer true that the machine can be seen as a homogeneous collection of nodesmore » with caches, main memory and an interconnect network. New architectural designs exhibit complex grouping of nodes, cores, threads, caches and memory connected by an ever evolving network-on-chip design. These new designs may benefit greatly from carefully crafted schedules and groupings that encourage parallel actors (i.e. threads, cores or nodes) to be aware of the computational history of other actors in close proximity. In this paper, we provide an efficient tiling technique that allows hierarchical concurrent start for memory hierarchy aware tile groups. Each execution schedule and tile shape exploit the available parallelism, load balance and locality present in the given applications. We demonstrate our technique on the Intel Xeon Phi architecture with selected and representative stencil kernels. We show improvement ranging from 5.58% to 31.17% over existing state-of-the-art techniques.« less

Machine Learning Based Online Performance Prediction for Runtime Parallelization and Task Scheduling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Li, J; Ma, X; Singh, K

2008-10-09

With the emerging many-core paradigm, parallel programming must extend beyond its traditional realm of scientific applications. Converting existing sequential applications as well as developing next-generation software requires assistance from hardware, compilers and runtime systems to exploit parallelism transparently within applications. These systems must decompose applications into tasks that can be executed in parallel and then schedule those tasks to minimize load imbalance. However, many systems lack a priori knowledge about the execution time of all tasks to perform effective load balancing with low scheduling overhead. In this paper, we approach this fundamental problem using machine learning techniques first to generatemore » performance models for all tasks and then applying those models to perform automatic performance prediction across program executions. We also extend an existing scheduling algorithm to use generated task cost estimates for online task partitioning and scheduling. We implement the above techniques in the pR framework, which transparently parallelizes scripts in the popular R language, and evaluate their performance and overhead with both a real-world application and a large number of synthetic representative test scripts. Our experimental results show that our proposed approach significantly improves task partitioning and scheduling, with maximum improvements of 21.8%, 40.3% and 22.1% and average improvements of 15.9%, 16.9% and 4.2% for LMM (a real R application) and synthetic test cases with independent and dependent tasks, respectively.« less

Automatic recognition of vector and parallel operations in a higher level language

NASA Technical Reports Server (NTRS)

Schneck, P. B.

1971-01-01

A compiler for recognizing statements of a FORTRAN program which are suited for fast execution on a parallel or pipeline machine such as Illiac-4, Star or ASC is described. The technique employs interval analysis to provide flow information to the vector/parallel recognizer. Where profitable the compiler changes scalar variables to subscripted variables. The output of the compiler is an extension to FORTRAN which shows parallel and vector operations explicitly.

Prefetching in file systems for MIMD multiprocessors

NASA Technical Reports Server (NTRS)

Kotz, David F.; Ellis, Carla Schlatter

1990-01-01

The question of whether prefetching blocks on the file into the block cache can effectively reduce overall execution time of a parallel computation, even under favorable assumptions, is considered. Experiments have been conducted with an interleaved file system testbed on the Butterfly Plus multiprocessor. Results of these experiments suggest that (1) the hit ratio, the accepted measure in traditional caching studies, may not be an adequate measure of performance when the workload consists of parallel computations and parallel file access patterns, (2) caching with prefetching can significantly improve the hit ratio and the average time to perform an I/O (input/output) operation, and (3) an improvement in overall execution time has been observed in most cases. In spite of these gains, prefetching sometimes results in increased execution times (a negative result, given the optimistic nature of the study). The authors explore why it is not trivial to translate savings on individual I/O requests into consistently better overall performance and identify the key problems that need to be addressed in order to improve the potential of prefetching techniques in the environment.

Reconstruction for time-domain in vivo EPR 3D multigradient oximetric imaging--a parallel processing perspective.

PubMed

Dharmaraj, Christopher D; Thadikonda, Kishan; Fletcher, Anthony R; Doan, Phuc N; Devasahayam, Nallathamby; Matsumoto, Shingo; Johnson, Calvin A; Cook, John A; Mitchell, James B; Subramanian, Sankaran; Krishna, Murali C

2009-01-01

Three-dimensional Oximetric Electron Paramagnetic Resonance Imaging using the Single Point Imaging modality generates unpaired spin density and oxygen images that can readily distinguish between normal and tumor tissues in small animals. It is also possible with fast imaging to track the changes in tissue oxygenation in response to the oxygen content in the breathing air. However, this involves dealing with gigabytes of data for each 3D oximetric imaging experiment involving digital band pass filtering and background noise subtraction, followed by 3D Fourier reconstruction. This process is rather slow in a conventional uniprocessor system. This paper presents a parallelization framework using OpenMP runtime support and parallel MATLAB to execute such computationally intensive programs. The Intel compiler is used to develop a parallel C++ code based on OpenMP. The code is executed on four Dual-Core AMD Opteron shared memory processors, to reduce the computational burden of the filtration task significantly. The results show that the parallel code for filtration has achieved a speed up factor of 46.66 as against the equivalent serial MATLAB code. In addition, a parallel MATLAB code has been developed to perform 3D Fourier reconstruction. Speedup factors of 4.57 and 4.25 have been achieved during the reconstruction process and oximetry computation, for a data set with 23 x 23 x 23 gradient steps. The execution time has been computed for both the serial and parallel implementations using different dimensions of the data and presented for comparison. The reported system has been designed to be easily accessible even from low-cost personal computers through local internet (NIHnet). The experimental results demonstrate that the parallel computing provides a source of high computational power to obtain biophysical parameters from 3D EPR oximetric imaging, almost in real-time.

Run-time parallelization and scheduling of loops

NASA Technical Reports Server (NTRS)

Saltz, Joel H.; Mirchandaney, Ravi; Baxter, Doug

1988-01-01

The class of problems that can be effectively compiled by parallelizing compilers is discussed. This is accomplished with the doconsider construct which would allow these compilers to parallelize many problems in which substantial loop-level parallelism is available but cannot be detected by standard compile-time analysis. We describe and experimentally analyze mechanisms used to parallelize the work required for these types of loops. In each of these methods, a new loop structure is produced by modifying the loop to be parallelized. We also present the rules by which these loop transformations may be automated in order that they be included in language compilers. The main application area of the research involves problems in scientific computations and engineering. The workload used in our experiment includes a mixture of real problems as well as synthetically generated inputs. From our extensive tests on the Encore Multimax/320, we have reached the conclusion that for the types of workloads we have investigated, self-execution almost always performs better than pre-scheduling. Further, the improvement in performance that accrues as a result of global topological sorting of indices as opposed to the less expensive local sorting, is not very significant in the case of self-execution.

A Multiprocessor SoC Architecture with Efficient Communication Infrastructure and Advanced Compiler Support for Easy Application Development

NASA Astrophysics Data System (ADS)

Urfianto, Mohammad Zalfany; Isshiki, Tsuyoshi; Khan, Arif Ullah; Li, Dongju; Kunieda, Hiroaki

This paper presentss a Multiprocessor System-on-Chips (MPSoC) architecture used as an execution platform for the new C-language based MPSoC design framework we are currently developing. The MPSoC architecture is based on an existing SoC platform with a commercial RISC core acting as the host CPU. We extend the existing SoC with a multiprocessor-array block that is used as the main engine to run parallel applications modeled in our design framework. Utilizing several optimizations provided by our compiler, an efficient inter-communication between processing elements with minimum overhead is implemented. A host-interface is designed to integrate the existing RISC core to the multiprocessor-array. The experimental results show that an efficacious integration is achieved, proving that the designed communication module can be used to efficiently incorporate off-the-shelf processors as a processing element for MPSoC architectures designed using our framework.

Performing a global barrier operation in a parallel computer

DOEpatents

Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E

2014-12-09

Executing computing tasks on a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the single local barrier.

Bioinformatics algorithm based on a parallel implementation of a machine learning approach using transducers

NASA Astrophysics Data System (ADS)

Roche-Lima, Abiel; Thulasiram, Ruppa K.

2012-02-01

Finite automata, in which each transition is augmented with an output label in addition to the familiar input label, are considered finite-state transducers. Transducers have been used to analyze some fundamental issues in bioinformatics. Weighted finite-state transducers have been proposed to pairwise alignments of DNA and protein sequences; as well as to develop kernels for computational biology. Machine learning algorithms for conditional transducers have been implemented and used for DNA sequence analysis. Transducer learning algorithms are based on conditional probability computation. It is calculated by using techniques, such as pair-database creation, normalization (with Maximum-Likelihood normalization) and parameters optimization (with Expectation-Maximization - EM). These techniques are intrinsically costly for computation, even worse when are applied to bioinformatics, because the databases sizes are large. In this work, we describe a parallel implementation of an algorithm to learn conditional transducers using these techniques. The algorithm is oriented to bioinformatics applications, such as alignments, phylogenetic trees, and other genome evolution studies. Indeed, several experiences were developed using the parallel and sequential algorithm on Westgrid (specifically, on the Breeze cluster). As results, we obtain that our parallel algorithm is scalable, because execution times are reduced considerably when the data size parameter is increased. Another experience is developed by changing precision parameter. In this case, we obtain smaller execution times using the parallel algorithm. Finally, number of threads used to execute the parallel algorithm on the Breezy cluster is changed. In this last experience, we obtain as result that speedup is considerably increased when more threads are used; however there is a convergence for number of threads equal to or greater than 16.

Sixth- and eighth-order Hermite integrator for N-body simulations

NASA Astrophysics Data System (ADS)

Nitadori, Keigo; Makino, Junichiro

2008-10-01

We present sixth- and eighth-order Hermite integrators for astrophysical N-body simulations, which use the derivatives of accelerations up to second-order ( snap) and third-order ( crackle). These schemes do not require previous values for the corrector, and require only one previous value to construct the predictor. Thus, they are fairly easy to implement. The additional cost of the calculation of the higher-order derivatives is not very high. Even for the eighth-order scheme, the number of floating-point operations for force calculation is only about two times larger than that for traditional fourth-order Hermite scheme. The sixth-order scheme is better than the traditional fourth-order scheme for most cases. When the required accuracy is very high, the eighth-order one is the best. These high-order schemes have several practical advantages. For example, they allow a larger number of particles to be integrated in parallel than the fourth-order scheme does, resulting in higher execution efficiency in both general-purpose parallel computers and GRAPE systems.

Real-time simulation of large-scale neural architectures for visual features computation based on GPU.

PubMed

Chessa, Manuela; Bianchi, Valentina; Zampetti, Massimo; Sabatini, Silvio P; Solari, Fabio

2012-01-01

The intrinsic parallelism of visual neural architectures based on distributed hierarchical layers is well suited to be implemented on the multi-core architectures of modern graphics cards. The design strategies that allow us to optimally take advantage of such parallelism, in order to efficiently map on GPU the hierarchy of layers and the canonical neural computations, are proposed. Specifically, the advantages of a cortical map-like representation of the data are exploited. Moreover, a GPU implementation of a novel neural architecture for the computation of binocular disparity from stereo image pairs, based on populations of binocular energy neurons, is presented. The implemented neural model achieves good performances in terms of reliability of the disparity estimates and a near real-time execution speed, thus demonstrating the effectiveness of the devised design strategies. The proposed approach is valid in general, since the neural building blocks we implemented are a common basis for the modeling of visual neural functionalities.

Efficient irregular wavefront propagation algorithms on Intel® Xeon Phi™

PubMed Central

Gomes, Jeremias M.; Teodoro, George; de Melo, Alba; Kong, Jun; Kurc, Tahsin; Saltz, Joel H.

2016-01-01

We investigate the execution of the Irregular Wavefront Propagation Pattern (IWPP), a fundamental computing structure used in several image analysis operations, on the Intel® Xeon Phi™ co-processor. An efficient implementation of IWPP on the Xeon Phi is a challenging problem because of IWPP’s irregularity and the use of atomic instructions in the original IWPP algorithm to resolve race conditions. On the Xeon Phi, the use of SIMD and vectorization instructions is critical to attain high performance. However, SIMD atomic instructions are not supported. Therefore, we propose a new IWPP algorithm that can take advantage of the supported SIMD instruction set. We also evaluate an alternate storage container (priority queue) to track active elements in the wavefront in an effort to improve the parallel algorithm efficiency. The new IWPP algorithm is evaluated with Morphological Reconstruction and Imfill operations as use cases. Our results show performance improvements of up to 5.63× on top of the original IWPP due to vectorization. Moreover, the new IWPP achieves speedups of 45.7× and 1.62×, respectively, as compared to efficient CPU and GPU implementations. PMID:27298591

Efficient irregular wavefront propagation algorithms on Intel® Xeon Phi™.

PubMed

Gomes, Jeremias M; Teodoro, George; de Melo, Alba; Kong, Jun; Kurc, Tahsin; Saltz, Joel H

2015-10-01

We investigate the execution of the Irregular Wavefront Propagation Pattern (IWPP), a fundamental computing structure used in several image analysis operations, on the Intel ® Xeon Phi ™ co-processor. An efficient implementation of IWPP on the Xeon Phi is a challenging problem because of IWPP's irregularity and the use of atomic instructions in the original IWPP algorithm to resolve race conditions. On the Xeon Phi, the use of SIMD and vectorization instructions is critical to attain high performance. However, SIMD atomic instructions are not supported. Therefore, we propose a new IWPP algorithm that can take advantage of the supported SIMD instruction set. We also evaluate an alternate storage container (priority queue) to track active elements in the wavefront in an effort to improve the parallel algorithm efficiency. The new IWPP algorithm is evaluated with Morphological Reconstruction and Imfill operations as use cases. Our results show performance improvements of up to 5.63 × on top of the original IWPP due to vectorization. Moreover, the new IWPP achieves speedups of 45.7 × and 1.62 × , respectively, as compared to efficient CPU and GPU implementations.

BLESS 2: accurate, memory-efficient and fast error correction method.

PubMed

Heo, Yun; Ramachandran, Anand; Hwu, Wen-Mei; Ma, Jian; Chen, Deming

2016-08-01

The most important features of error correction tools for sequencing data are accuracy, memory efficiency and fast runtime. The previous version of BLESS was highly memory-efficient and accurate, but it was too slow to handle reads from large genomes. We have developed a new version of BLESS to improve runtime and accuracy while maintaining a small memory usage. The new version, called BLESS 2, has an error correction algorithm that is more accurate than BLESS, and the algorithm has been parallelized using hybrid MPI and OpenMP programming. BLESS 2 was compared with five top-performing tools, and it was found to be the fastest when it was executed on two computing nodes using MPI, with each node containing twelve cores. Also, BLESS 2 showed at least 11% higher gain while retaining the memory efficiency of the previous version for large genomes. Freely available at https://sourceforge.net/projects/bless-ec dchen@illinois.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Hierarchical Parallelization of Gene Differential Association Analysis

PubMed Central

2011-01-01

Background Microarray gene differential expression analysis is a widely used technique that deals with high dimensional data and is computationally intensive for permutation-based procedures. Microarray gene differential association analysis is even more computationally demanding and must take advantage of multicore computing technology, which is the driving force behind increasing compute power in recent years. In this paper, we present a two-layer hierarchical parallel implementation of gene differential association analysis. It takes advantage of both fine- and coarse-grain (with granularity defined by the frequency of communication) parallelism in order to effectively leverage the non-uniform nature of parallel processing available in the cutting-edge systems of today. Results Our results show that this hierarchical strategy matches data sharing behavior to the properties of the underlying hardware, thereby reducing the memory and bandwidth needs of the application. The resulting improved efficiency reduces computation time and allows the gene differential association analysis code to scale its execution with the number of processors. The code and biological data used in this study are downloadable from http://www.urmc.rochester.edu/biostat/people/faculty/hu.cfm. Conclusions The performance sweet spot occurs when using a number of threads per MPI process that allows the working sets of the corresponding MPI processes running on the multicore to fit within the machine cache. Hence, we suggest that practitioners follow this principle in selecting the appropriate number of MPI processes and threads within each MPI process for their cluster configurations. We believe that the principles of this hierarchical approach to parallelization can be utilized in the parallelization of other computationally demanding kernels. PMID:21936916

Hierarchical parallelization of gene differential association analysis.

PubMed

Needham, Mark; Hu, Rui; Dwarkadas, Sandhya; Qiu, Xing

2011-09-21

Microarray gene differential expression analysis is a widely used technique that deals with high dimensional data and is computationally intensive for permutation-based procedures. Microarray gene differential association analysis is even more computationally demanding and must take advantage of multicore computing technology, which is the driving force behind increasing compute power in recent years. In this paper, we present a two-layer hierarchical parallel implementation of gene differential association analysis. It takes advantage of both fine- and coarse-grain (with granularity defined by the frequency of communication) parallelism in order to effectively leverage the non-uniform nature of parallel processing available in the cutting-edge systems of today. Our results show that this hierarchical strategy matches data sharing behavior to the properties of the underlying hardware, thereby reducing the memory and bandwidth needs of the application. The resulting improved efficiency reduces computation time and allows the gene differential association analysis code to scale its execution with the number of processors. The code and biological data used in this study are downloadable from http://www.urmc.rochester.edu/biostat/people/faculty/hu.cfm. The performance sweet spot occurs when using a number of threads per MPI process that allows the working sets of the corresponding MPI processes running on the multicore to fit within the machine cache. Hence, we suggest that practitioners follow this principle in selecting the appropriate number of MPI processes and threads within each MPI process for their cluster configurations. We believe that the principles of this hierarchical approach to parallelization can be utilized in the parallelization of other computationally demanding kernels.

Parallel fuzzy connected image segmentation on GPU

PubMed Central

Zhuge, Ying; Cao, Yong; Udupa, Jayaram K.; Miller, Robert W.

2011-01-01

Purpose: Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm implementation on NVIDIA’s compute unified device Architecture (cuda) platform for segmenting medical image data sets. Methods: In the FC algorithm, there are two major computational tasks: (i) computing the fuzzy affinity relations and (ii) computing the fuzzy connectedness relations. These two tasks are implemented as cuda kernels and executed on GPU. A dramatic improvement in speed for both tasks is achieved as a result. Results: Our experiments based on three data sets of small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 24.4x, 18.1x, and 10.3x, correspondingly, for the three data sets on the NVIDIA Tesla C1060 over the implementation of the algorithm on CPU, and takes 0.25, 0.72, and 15.04 s, correspondingly, for the three data sets. Conclusions: The authors developed a parallel algorithm of the widely used fuzzy connected image segmentation method on the NVIDIA GPUs, which are far more cost- and speed-effective than both cluster of workstations and multiprocessing systems. A near-interactive speed of segmentation has been achieved, even for the large data set. PMID:21859037

Parallel fuzzy connected image segmentation on GPU.

PubMed

Zhuge, Ying; Cao, Yong; Udupa, Jayaram K; Miller, Robert W

2011-07-01

Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm implementation on NVIDIA's compute unified device Architecture (CUDA) platform for segmenting medical image data sets. In the FC algorithm, there are two major computational tasks: (i) computing the fuzzy affinity relations and (ii) computing the fuzzy connectedness relations. These two tasks are implemented as CUDA kernels and executed on GPU. A dramatic improvement in speed for both tasks is achieved as a result. Our experiments based on three data sets of small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 24.4x, 18.1x, and 10.3x, correspondingly, for the three data sets on the NVIDIA Tesla C1060 over the implementation of the algorithm on CPU, and takes 0.25, 0.72, and 15.04 s, correspondingly, for the three data sets. The authors developed a parallel algorithm of the widely used fuzzy connected image segmentation method on the NVIDIA GPUs, which are far more cost- and speed-effective than both cluster of workstations and multiprocessing systems. A near-interactive speed of segmentation has been achieved, even for the large data set.

Solution of a tridiagonal system of equations on the finite element machine

NASA Technical Reports Server (NTRS)

Bostic, S. W.

1984-01-01

Two parallel algorithms for the solution of tridiagonal systems of equations were implemented on the Finite Element Machine. The Accelerated Parallel Gauss method, an iterative method, and the Buneman algorithm, a direct method, are discussed and execution statistics are presented.

Bit-parallel arithmetic in a massively-parallel associative processor

NASA Technical Reports Server (NTRS)

Scherson, Isaac D.; Kramer, David A.; Alleyne, Brian D.

1992-01-01

A simple but powerful new architecture based on a classical associative processor model is presented. Algorithms for performing the four basic arithmetic operations both for integer and floating point operands are described. For m-bit operands, the proposed architecture makes it possible to execute complex operations in O(m) cycles as opposed to O(m exp 2) for bit-serial machines. A word-parallel, bit-parallel, massively-parallel computing system can be constructed using this architecture with VLSI technology. The operation of this system is demonstrated for the fast Fourier transform and matrix multiplication.

Block-Parallel Data Analysis with DIY2

DOE Office of Scientific and Technical Information (OSTI.GOV)

Morozov, Dmitriy; Peterka, Tom

DIY2 is a programming model and runtime for block-parallel analytics on distributed-memory machines. Its main abstraction is block-structured data parallelism: data are decomposed into blocks; blocks are assigned to processing elements (processes or threads); computation is described as iterations over these blocks, and communication between blocks is defined by reusable patterns. By expressing computation in this general form, the DIY2 runtime is free to optimize the movement of blocks between slow and fast memories (disk and flash vs. DRAM) and to concurrently execute blocks residing in memory with multiple threads. This enables the same program to execute in-core, out-of-core, serial,more » parallel, single-threaded, multithreaded, or combinations thereof. This paper describes the implementation of the main features of the DIY2 programming model and optimizations to improve performance. DIY2 is evaluated on benchmark test cases to establish baseline performance for several common patterns and on larger complete analysis codes running on large-scale HPC machines.« less

Threat facilitates subsequent executive control during anxious mood.

PubMed

Birk, Jeffrey L; Dennis, Tracy A; Shin, Lisa M; Urry, Heather L

2011-12-01

Dual competition framework (DCF) posits that low-level threat may facilitate behavioral performance by influencing executive control functions. Anxiety is thought to strengthen this effect by enhancing threat's affective significance. To test these ideas directly, we examined the effects of low-level threat and experimentally induced anxiety on one executive control function, the efficiency of response inhibition. In Study 1, briefly presented stimuli that were mildly threatening (i.e., fearful faces) relative to nonthreatening (i.e., neutral faces) led to facilitated executive control efficiency during experimentally induced anxiety. No such effect was observed during an equally arousing, experimentally induced happy mood state. In Study 2, we assessed the effects of low-level threat, experimentally induced anxiety, and individual differences in trait anxiety on executive control efficiency. Consistent with Study 1, fearful relative to neutral faces led to facilitated executive control efficiency during experimentally induced anxiety. No such effect was observed during an experimentally induced neutral mood state. Moreover, individual differences in trait anxiety did not moderate the effects of threat and anxiety on executive control efficiency. The findings are partially consistent with the predictions of DCF in that low-level threat improved executive control, at least during a state of anxiety. (c) 2011 APA, all rights reserved.

Rubus: A compiler for seamless and extensible parallelism.

PubMed

Adnan, Muhammad; Aslam, Faisal; Nawaz, Zubair; Sarwar, Syed Mansoor

2017-01-01

Nowadays, a typical processor may have multiple processing cores on a single chip. Furthermore, a special purpose processing unit called Graphic Processing Unit (GPU), originally designed for 2D/3D games, is now available for general purpose use in computers and mobile devices. However, the traditional programming languages which were designed to work with machines having single core CPUs, cannot utilize the parallelism available on multi-core processors efficiently. Therefore, to exploit the extraordinary processing power of multi-core processors, researchers are working on new tools and techniques to facilitate parallel programming. To this end, languages like CUDA and OpenCL have been introduced, which can be used to write code with parallelism. The main shortcoming of these languages is that programmer needs to specify all the complex details manually in order to parallelize the code across multiple cores. Therefore, the code written in these languages is difficult to understand, debug and maintain. Furthermore, to parallelize legacy code can require rewriting a significant portion of code in CUDA or OpenCL, which can consume significant time and resources. Thus, the amount of parallelism achieved is proportional to the skills of the programmer and the time spent in code optimizations. This paper proposes a new open source compiler, Rubus, to achieve seamless parallelism. The Rubus compiler relieves the programmer from manually specifying the low-level details. It analyses and transforms a sequential program into a parallel program automatically, without any user intervention. This achieves massive speedup and better utilization of the underlying hardware without a programmer's expertise in parallel programming. For five different benchmarks, on average a speedup of 34.54 times has been achieved by Rubus as compared to Java on a basic GPU having only 96 cores. Whereas, for a matrix multiplication benchmark the average execution speedup of 84 times has been achieved by Rubus on the same GPU. Moreover, Rubus achieves this performance without drastically increasing the memory footprint of a program.

Rubus: A compiler for seamless and extensible parallelism

PubMed Central

Adnan, Muhammad; Aslam, Faisal; Sarwar, Syed Mansoor

2017-01-01

Nowadays, a typical processor may have multiple processing cores on a single chip. Furthermore, a special purpose processing unit called Graphic Processing Unit (GPU), originally designed for 2D/3D games, is now available for general purpose use in computers and mobile devices. However, the traditional programming languages which were designed to work with machines having single core CPUs, cannot utilize the parallelism available on multi-core processors efficiently. Therefore, to exploit the extraordinary processing power of multi-core processors, researchers are working on new tools and techniques to facilitate parallel programming. To this end, languages like CUDA and OpenCL have been introduced, which can be used to write code with parallelism. The main shortcoming of these languages is that programmer needs to specify all the complex details manually in order to parallelize the code across multiple cores. Therefore, the code written in these languages is difficult to understand, debug and maintain. Furthermore, to parallelize legacy code can require rewriting a significant portion of code in CUDA or OpenCL, which can consume significant time and resources. Thus, the amount of parallelism achieved is proportional to the skills of the programmer and the time spent in code optimizations. This paper proposes a new open source compiler, Rubus, to achieve seamless parallelism. The Rubus compiler relieves the programmer from manually specifying the low-level details. It analyses and transforms a sequential program into a parallel program automatically, without any user intervention. This achieves massive speedup and better utilization of the underlying hardware without a programmer’s expertise in parallel programming. For five different benchmarks, on average a speedup of 34.54 times has been achieved by Rubus as compared to Java on a basic GPU having only 96 cores. Whereas, for a matrix multiplication benchmark the average execution speedup of 84 times has been achieved by Rubus on the same GPU. Moreover, Rubus achieves this performance without drastically increasing the memory footprint of a program. PMID:29211758

Large-Scale, Parallel, Multi-Sensor Atmospheric Data Fusion Using Cloud Computing

NASA Astrophysics Data System (ADS)

Wilson, B. D.; Manipon, G.; Hua, H.; Fetzer, E.

2013-05-01

NASA's Earth Observing System (EOS) is an ambitious facility for studying global climate change. The mandate now is to combine measurements from the instruments on the "A-Train" platforms (AIRS, AMSR-E, MODIS, MISR, MLS, and CloudSat) and other Earth probes to enable large-scale studies of climate change over decades. Moving to multi-sensor, long-duration analyses of important climate variables presents serious challenges for large-scale data mining and fusion. For example, one might want to compare temperature and water vapor retrievals from one instrument (AIRS) to another (MODIS), and to a model (ECMWF), stratify the comparisons using a classification of the "cloud scenes" from CloudSat, and repeat the entire analysis over 10 years of data. To efficiently assemble such datasets, we are utilizing Elastic Computing in the Cloud and parallel map/reduce-based algorithms. However, these problems are Data Intensive computing so the data transfer times and storage costs (for caching) are key issues. SciReduce is a Hadoop-like parallel analysis system, programmed in parallel python, that is designed from the ground up for Earth science. SciReduce executes inside VMWare images and scales to any number of nodes in the Cloud. Unlike Hadoop, SciReduce operates on bundles of named numeric arrays, which can be passed in memory or serialized to disk in netCDF4 or HDF5. Figure 1 shows the architecture of the full computational system, with SciReduce at the core. Multi-year datasets are automatically "sharded" by time and space across a cluster of nodes so that years of data (millions of files) can be processed in a massively parallel way. Input variables (arrays) are pulled on-demand into the Cloud using OPeNDAP URLs or other subsetting services, thereby minimizing the size of the cached input and intermediate datasets. We are using SciReduce to automate the production of multiple versions of a ten-year A-Train water vapor climatology under a NASA MEASURES grant. We will present the architecture of SciReduce, describe the achieved "clock time" speedups in fusing datasets on our own nodes and in the Cloud, and discuss the Cloud cost tradeoffs for storage, compute, and data transfer. We will also present a concept/prototype for staging NASA's A-Train Atmospheric datasets (Levels 2 & 3) in the Amazon Cloud so that any number of compute jobs can be executed "near" the multi-sensor data. Given such a system, multi-sensor climate studies over 10-20 years of data could be performed in an efficient way, with the researcher paying only his own Cloud compute bill.; Figure 1 -- Architecture.

Large-Scale, Parallel, Multi-Sensor Atmospheric Data Fusion Using Cloud Computing

NASA Astrophysics Data System (ADS)

Wilson, B. D.; Manipon, G.; Hua, H.; Fetzer, E. J.

2013-12-01

NASA's Earth Observing System (EOS) is an ambitious facility for studying global climate change. The mandate now is to combine measurements from the instruments on the 'A-Train' platforms (AIRS, AMSR-E, MODIS, MISR, MLS, and CloudSat) and other Earth probes to enable large-scale studies of climate change over decades. Moving to multi-sensor, long-duration analyses of important climate variables presents serious challenges for large-scale data mining and fusion. For example, one might want to compare temperature and water vapor retrievals from one instrument (AIRS) to another (MODIS), and to a model (MERRA), stratify the comparisons using a classification of the 'cloud scenes' from CloudSat, and repeat the entire analysis over 10 years of data. To efficiently assemble such datasets, we are utilizing Elastic Computing in the Cloud and parallel map/reduce-based algorithms. However, these problems are Data Intensive computing so the data transfer times and storage costs (for caching) are key issues. SciReduce is a Hadoop-like parallel analysis system, programmed in parallel python, that is designed from the ground up for Earth science. SciReduce executes inside VMWare images and scales to any number of nodes in the Cloud. Unlike Hadoop, SciReduce operates on bundles of named numeric arrays, which can be passed in memory or serialized to disk in netCDF4 or HDF5. Figure 1 shows the architecture of the full computational system, with SciReduce at the core. Multi-year datasets are automatically 'sharded' by time and space across a cluster of nodes so that years of data (millions of files) can be processed in a massively parallel way. Input variables (arrays) are pulled on-demand into the Cloud using OPeNDAP URLs or other subsetting services, thereby minimizing the size of the cached input and intermediate datasets. We are using SciReduce to automate the production of multiple versions of a ten-year A-Train water vapor climatology under a NASA MEASURES grant. We will present the architecture of SciReduce, describe the achieved 'clock time' speedups in fusing datasets on our own compute nodes and in the public Cloud, and discuss the Cloud cost tradeoffs for storage, compute, and data transfer. We will also present a concept/prototype for staging NASA's A-Train Atmospheric datasets (Levels 2 & 3) in the Amazon Cloud so that any number of compute jobs can be executed 'near' the multi-sensor data. Given such a system, multi-sensor climate studies over 10-20 years of data could be performed in an efficient way, with the researcher paying only his own Cloud compute bill. SciReduce Architecture

Putting time into proof outlines

NASA Technical Reports Server (NTRS)

Schneider, Fred B.; Bloom, Bard; Marzullo, Keith

1991-01-01

A logic for reasoning about timing of concurrent programs is presented. The logic is based on proof outlines and can handle maximal parallelism as well as resource-constrained execution environments. The correctness proof for a mutual exclusion protocol that uses execution timings in a subtle way illustrates the logic in action.

Adaptive multi-GPU Exchange Monte Carlo for the 3D Random Field Ising Model

NASA Astrophysics Data System (ADS)

Navarro, Cristóbal A.; Huang, Wei; Deng, Youjin

2016-08-01

This work presents an adaptive multi-GPU Exchange Monte Carlo approach for the simulation of the 3D Random Field Ising Model (RFIM). The design is based on a two-level parallelization. The first level, spin-level parallelism, maps the parallel computation as optimal 3D thread-blocks that simulate blocks of spins in shared memory with minimal halo surface, assuming a constant block volume. The second level, replica-level parallelism, uses multi-GPU computation to handle the simulation of an ensemble of replicas. CUDA's concurrent kernel execution feature is used in order to fill the occupancy of each GPU with many replicas, providing a performance boost that is more notorious at the smallest values of L. In addition to the two-level parallel design, the work proposes an adaptive multi-GPU approach that dynamically builds a proper temperature set free of exchange bottlenecks. The strategy is based on mid-point insertions at the temperature gaps where the exchange rate is most compromised. The extra work generated by the insertions is balanced across the GPUs independently of where the mid-point insertions were performed. Performance results show that spin-level performance is approximately two orders of magnitude faster than a single-core CPU version and one order of magnitude faster than a parallel multi-core CPU version running on 16-cores. Multi-GPU performance is highly convenient under a weak scaling setting, reaching up to 99 % efficiency as long as the number of GPUs and L increase together. The combination of the adaptive approach with the parallel multi-GPU design has extended our possibilities of simulation to sizes of L = 32 , 64 for a workstation with two GPUs. Sizes beyond L = 64 can eventually be studied using larger multi-GPU systems.

Graphical Representation of Parallel Algorithmic Processes

DTIC Science & Technology

1990-12-01

interface with the AAARF main process . The source code for the AAARF class-common library is in the common subdi- rectory and consists of the following files... for public release; distribution unlimited AFIT/GCE/ENG/90D-07 Graphical Representation of Parallel Algorithmic Processes THESIS Presented to the...goal of this study is to develop an algorithm animation facility for parallel processes executing on different architectures, from multiprocessor

Effective Vectorization with OpenMP 4.5

DOE Office of Scientific and Technical Information (OSTI.GOV)

Huber, Joseph N.; Hernandez, Oscar R.; Lopez, Matthew Graham

This paper describes how the Single Instruction Multiple Data (SIMD) model and its extensions in OpenMP work, and how these are implemented in different compilers. Modern processors are highly parallel computational machines which often include multiple processors capable of executing several instructions in parallel. Understanding SIMD and executing instructions in parallel allows the processor to achieve higher performance without increasing the power required to run it. SIMD instructions can significantly reduce the runtime of code by executing a single operation on large groups of data. The SIMD model is so integral to the processor s potential performance that, if SIMDmore » is not utilized, less than half of the processor is ever actually used. Unfortunately, using SIMD instructions is a challenge in higher level languages because most programming languages do not have a way to describe them. Most compilers are capable of vectorizing code by using the SIMD instructions, but there are many code features important for SIMD vectorization that the compiler cannot determine at compile time. OpenMP attempts to solve this by extending the C++/C and Fortran programming languages with compiler directives that express SIMD parallelism. OpenMP is used to pass hints to the compiler about the code to be executed in SIMD. This is a key resource for making optimized code, but it does not change whether or not the code can use SIMD operations. However, in many cases critical functions are limited by a poor understanding of how SIMD instructions are actually implemented, as SIMD can be implemented through vector instructions or simultaneous multi-threading (SMT). We have found that it is often the case that code cannot be vectorized, or is vectorized poorly, because the programmer does not have sufficient knowledge of how SIMD instructions work.« less

Contingency Analysis Post-Processing With Advanced Computing and Visualization

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen, Yousu; Glaesemann, Kurt; Fitzhenry, Erin

Contingency analysis is a critical function widely used in energy management systems to assess the impact of power system component failures. Its outputs are important for power system operation for improved situational awareness, power system planning studies, and power market operations. With the increased complexity of power system modeling and simulation caused by increased energy production and demand, the penetration of renewable energy and fast deployment of smart grid devices, and the trend of operating grids closer to their capacity for better efficiency, more and more contingencies must be executed and analyzed quickly in order to ensure grid reliability andmore » accuracy for the power market. Currently, many researchers have proposed different techniques to accelerate the computational speed of contingency analysis, but not much work has been published on how to post-process the large amount of contingency outputs quickly. This paper proposes a parallel post-processing function that can analyze contingency analysis outputs faster and display them in a web-based visualization tool to help power engineers improve their work efficiency by fast information digestion. Case studies using an ESCA-60 bus system and a WECC planning system are presented to demonstrate the functionality of the parallel post-processing technique and the web-based visualization tool.« less

MrBayes tgMC3++: A High Performance and Resource-Efficient GPU-Oriented Phylogenetic Analysis Method.

PubMed

Ling, Cheng; Hamada, Tsuyoshi; Gao, Jingyang; Zhao, Guoguang; Sun, Donghong; Shi, Weifeng

2016-01-01

MrBayes is a widespread phylogenetic inference tool harnessing empirical evolutionary models and Bayesian statistics. However, the computational cost on the likelihood estimation is very expensive, resulting in undesirably long execution time. Although a number of multi-threaded optimizations have been proposed to speed up MrBayes, there are bottlenecks that severely limit the GPU thread-level parallelism of likelihood estimations. This study proposes a high performance and resource-efficient method for GPU-oriented parallelization of likelihood estimations. Instead of having to rely on empirical programming, the proposed novel decomposition storage model implements high performance data transfers implicitly. In terms of performance improvement, a speedup factor of up to 178 can be achieved on the analysis of simulated datasets by four Tesla K40 cards. In comparison to the other publicly available GPU-oriented MrBayes, the tgMC 3 ++ method (proposed herein) outperforms the tgMC 3 (v1.0), nMC 3 (v2.1.1) and oMC 3 (v1.00) methods by speedup factors of up to 1.6, 1.9 and 2.9, respectively. Moreover, tgMC 3 ++ supports more evolutionary models and gamma categories, which previous GPU-oriented methods fail to take into analysis.

Computational Particle Dynamic Simulations on Multicore Processors (CPDMu) Final Report Phase I

DOE Office of Scientific and Technical Information (OSTI.GOV)

Schmalz, Mark S

2011-07-24

Statement of Problem - Department of Energy has many legacy codes for simulation of computational particle dynamics and computational fluid dynamics applications that are designed to run on sequential processors and are not easily parallelized. Emerging high-performance computing architectures employ massively parallel multicore architectures (e.g., graphics processing units) to increase throughput. Parallelization of legacy simulation codes is a high priority, to achieve compatibility, efficiency, accuracy, and extensibility. General Statement of Solution - A legacy simulation application designed for implementation on mainly-sequential processors has been represented as a graph G. Mathematical transformations, applied to G, produce a graph representation {und G}more » for a high-performance architecture. Key computational and data movement kernels of the application were analyzed/optimized for parallel execution using the mapping G {yields} {und G}, which can be performed semi-automatically. This approach is widely applicable to many types of high-performance computing systems, such as graphics processing units or clusters comprised of nodes that contain one or more such units. Phase I Accomplishments - Phase I research decomposed/profiled computational particle dynamics simulation code for rocket fuel combustion into low and high computational cost regions (respectively, mainly sequential and mainly parallel kernels), with analysis of space and time complexity. Using the research team's expertise in algorithm-to-architecture mappings, the high-cost kernels were transformed, parallelized, and implemented on Nvidia Fermi GPUs. Measured speedups (GPU with respect to single-core CPU) were approximately 20-32X for realistic model parameters, without final optimization. Error analysis showed no loss of computational accuracy. Commercial Applications and Other Benefits - The proposed research will constitute a breakthrough in solution of problems related to efficient parallel computation of particle and fluid dynamics simulations. These problems occur throughout DOE, military and commercial sectors: the potential payoff is high. We plan to license or sell the solution to contractors for military and domestic applications such as disaster simulation (aerodynamic and hydrodynamic), Government agencies (hydrological and environmental simulations), and medical applications (e.g., in tomographic image reconstruction). Keywords - High-performance Computing, Graphic Processing Unit, Fluid/Particle Simulation. Summary for Members of Congress - Department of Energy has many simulation codes that must compute faster, to be effective. The Phase I research parallelized particle/fluid simulations for rocket combustion, for high-performance computing systems.« less

Performance Analysis and Scaling Behavior of the Terrestrial Systems Modeling Platform TerrSysMP in Large-Scale Supercomputing Environments

NASA Astrophysics Data System (ADS)

Kollet, S. J.; Goergen, K.; Gasper, F.; Shresta, P.; Sulis, M.; Rihani, J.; Simmer, C.; Vereecken, H.

2013-12-01

In studies of the terrestrial hydrologic, energy and biogeochemical cycles, integrated multi-physics simulation platforms take a central role in characterizing non-linear interactions, variances and uncertainties of system states and fluxes in reciprocity with observations. Recently developed integrated simulation platforms attempt to honor the complexity of the terrestrial system across multiple time and space scales from the deeper subsurface including groundwater dynamics into the atmosphere. Technically, this requires the coupling of atmospheric, land surface, and subsurface-surface flow models in supercomputing environments, while ensuring a high-degree of efficiency in the utilization of e.g., standard Linux clusters and massively parallel resources. A systematic performance analysis including profiling and tracing in such an application is crucial in the understanding of the runtime behavior, to identify optimum model settings, and is an efficient way to distinguish potential parallel deficiencies. On sophisticated leadership-class supercomputers, such as the 28-rack 5.9 petaFLOP IBM Blue Gene/Q 'JUQUEEN' of the Jülich Supercomputing Centre (JSC), this is a challenging task, but even more so important, when complex coupled component models are to be analysed. Here we want to present our experience from coupling, application tuning (e.g. 5-times speedup through compiler optimizations), parallel scaling and performance monitoring of the parallel Terrestrial Systems Modeling Platform TerrSysMP. The modeling platform consists of the weather prediction system COSMO of the German Weather Service; the Community Land Model, CLM of NCAR; and the variably saturated surface-subsurface flow code ParFlow. The model system relies on the Multiple Program Multiple Data (MPMD) execution model where the external Ocean-Atmosphere-Sea-Ice-Soil coupler (OASIS3) links the component models. TerrSysMP has been instrumented with the performance analysis tool Scalasca and analyzed on JUQUEEN with processor counts on the order of 10,000. The instrumentation is used in weak and strong scaling studies with real data cases and hypothetical idealized numerical experiments for detailed profiling and tracing analysis. The profiling is not only useful in identifying wait states that are due to the MPMD execution model, but also in fine-tuning resource allocation to the component models in search of the most suitable load balancing. This is especially necessary, as with numerical experiments that cover multiple (high resolution) spatial scales, the time stepping, coupling frequencies, and communication overheads are constantly shifting, which makes it necessary to re-determine the model setup with each new experimental design.

Evolution of CMS workload management towards multicore job support

NASA Astrophysics Data System (ADS)

Pérez-Calero Yzquierdo, A.; Hernández, J. M.; Khan, F. A.; Letts, J.; Majewski, K.; Rodrigues, A. M.; McCrea, A.; Vaandering, E.

2015-12-01

The successful exploitation of multicore processor architectures is a key element of the LHC distributed computing system in the coming era of the LHC Run 2. High-pileup complex-collision events represent a challenge for the traditional sequential programming in terms of memory and processing time budget. The CMS data production and processing framework is introducing the parallel execution of the reconstruction and simulation algorithms to overcome these limitations. CMS plans to execute multicore jobs while still supporting singlecore processing for other tasks difficult to parallelize, such as user analysis. The CMS strategy for job management thus aims at integrating single and multicore job scheduling across the Grid. This is accomplished by employing multicore pilots with internal dynamic partitioning of the allocated resources, capable of running payloads of various core counts simultaneously. An extensive test programme has been conducted to enable multicore scheduling with the various local batch systems available at CMS sites, with the focus on the Tier-0 and Tier-1s, responsible during 2015 of the prompt data reconstruction. Scale tests have been run to analyse the performance of this scheduling strategy and ensure an efficient use of the distributed resources. This paper presents the evolution of the CMS job management and resource provisioning systems in order to support this hybrid scheduling model, as well as its deployment and performance tests, which will enable CMS to transition to a multicore production model for the second LHC run.

Evolution of CMS Workload Management Towards Multicore Job Support

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perez-Calero Yzquierdo, A.; Hernández, J. M.; Khan, F. A.

The successful exploitation of multicore processor architectures is a key element of the LHC distributed computing system in the coming era of the LHC Run 2. High-pileup complex-collision events represent a challenge for the traditional sequential programming in terms of memory and processing time budget. The CMS data production and processing framework is introducing the parallel execution of the reconstruction and simulation algorithms to overcome these limitations. CMS plans to execute multicore jobs while still supporting singlecore processing for other tasks difficult to parallelize, such as user analysis. The CMS strategy for job management thus aims at integrating single andmore » multicore job scheduling across the Grid. This is accomplished by employing multicore pilots with internal dynamic partitioning of the allocated resources, capable of running payloads of various core counts simultaneously. An extensive test programme has been conducted to enable multicore scheduling with the various local batch systems available at CMS sites, with the focus on the Tier-0 and Tier-1s, responsible during 2015 of the prompt data reconstruction. Scale tests have been run to analyse the performance of this scheduling strategy and ensure an efficient use of the distributed resources. This paper presents the evolution of the CMS job management and resource provisioning systems in order to support this hybrid scheduling model, as well as its deployment and performance tests, which will enable CMS to transition to a multicore production model for the second LHC run.« less

Energy-efficient fault tolerance in multiprocessor real-time systems

NASA Astrophysics Data System (ADS)

Guo, Yifeng

The recent progress in the multiprocessor/multicore systems has important implications for real-time system design and operation. From vehicle navigation to space applications as well as industrial control systems, the trend is to deploy multiple processors in real-time systems: systems with 4 -- 8 processors are common, and it is expected that many-core systems with dozens of processing cores will be available in near future. For such systems, in addition to general temporal requirement common for all real-time systems, two additional operational objectives are seen as critical: energy efficiency and fault tolerance. An intriguing dimension of the problem is that energy efficiency and fault tolerance are typically conflicting objectives, due to the fact that tolerating faults (e.g., permanent/transient) often requires extra resources with high energy consumption potential. In this dissertation, various techniques for energy-efficient fault tolerance in multiprocessor real-time systems have been investigated. First, the Reliability-Aware Power Management (RAPM) framework, which can preserve the system reliability with respect to transient faults when Dynamic Voltage Scaling (DVS) is applied for energy savings, is extended to support parallel real-time applications with precedence constraints. Next, the traditional Standby-Sparing (SS) technique for dual processor systems, which takes both transient and permanent faults into consideration while saving energy, is generalized to support multiprocessor systems with arbitrary number of identical processors. Observing the inefficient usage of slack time in the SS technique, a Preference-Oriented Scheduling Framework is designed to address the problem where tasks are given preferences for being executed as soon as possible (ASAP) or as late as possible (ALAP). A preference-oriented earliest deadline (POED) scheduler is proposed and its application in multiprocessor systems for energy-efficient fault tolerance is investigated, where tasks' main copies are executed ASAP while backup copies ALAP to reduce the overlapped execution of main and backup copies of the same task and thus reduce energy consumption. All proposed techniques are evaluated through extensive simulations and compared with other state-of-the-art approaches. The simulation results confirm that the proposed schemes can preserve the system reliability while still achieving substantial energy savings. Finally, for both SS and POED based Energy-Efficient Fault-Tolerant (EEFT) schemes, a series of recovery strategies are designed when more than one (transient and permanent) faults need to be tolerated.

GPU based cloud system for high-performance arrhythmia detection with parallel k-NN algorithm.

PubMed

Tae Joon Jun; Hyun Ji Park; Hyuk Yoo; Young-Hak Kim; Daeyoung Kim

2016-08-01

In this paper, we propose an GPU based Cloud system for high-performance arrhythmia detection. Pan-Tompkins algorithm is used for QRS detection and we optimized beat classification algorithm with K-Nearest Neighbor (K-NN). To support high performance beat classification on the system, we parallelized beat classification algorithm with CUDA to execute the algorithm on virtualized GPU devices on the Cloud system. MIT-BIH Arrhythmia database is used for validation of the algorithm. The system achieved about 93.5% of detection rate which is comparable to previous researches while our algorithm shows 2.5 times faster execution time compared to CPU only detection algorithm.

Parallel Execution of Functional Mock-up Units in Buildings Modeling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ozmen, Ozgur; Nutaro, James J.; New, Joshua Ryan

2016-06-30

A Functional Mock-up Interface (FMI) defines a standardized interface to be used in computer simulations to develop complex cyber-physical systems. FMI implementation by a software modeling tool enables the creation of a simulation model that can be interconnected, or the creation of a software library called a Functional Mock-up Unit (FMU). This report describes an FMU wrapper implementation that imports FMUs into a C++ environment and uses an Euler solver that executes FMUs in parallel using Open Multi-Processing (OpenMP). The purpose of this report is to elucidate the runtime performance of the solver when a multi-component system is imported asmore » a single FMU (for the whole system) or as multiple FMUs (for different groups of components as sub-systems). This performance comparison is conducted using two test cases: (1) a simple, multi-tank problem; and (2) a more realistic use case based on the Modelica Buildings Library. In both test cases, the performance gains are promising when each FMU consists of a large number of states and state events that are wrapped in a single FMU. Load balancing is demonstrated to be a critical factor in speeding up parallel execution of multiple FMUs.« less

Mining on Big Data Using Hadoop MapReduce Model

NASA Astrophysics Data System (ADS)

Salman Ahmed, G.; Bhattacharya, Sweta

2017-11-01

Customary parallel calculations for mining nonstop item create opportunity to adjust stack of similar data among hubs. The paper aims to review this process by analyzing the critical execution downside of the common parallel recurrent item-set mining calculations. Given a larger than average dataset, data apportioning strategies inside the current arrangements endure high correspondence and mining overhead evoked by repetitive exchanges transmitted among registering hubs. We tend to address this downside by building up a learning apportioning approach referred as Hadoop abuse using the map-reduce programming model. All objectives of Hadoop are to zest up the execution of parallel recurrent item-set mining on Hadoop bunches. Fusing the comparability metric and furthermore the locality-sensitive hashing procedure, Hadoop puts to a great degree comparative exchanges into an information segment to lift neighborhood while not making AN exorbitant assortment of excess exchanges. We tend to execute Hadoop on a 34-hub Hadoop bunch, driven by a decent change of datasets made by IBM quest market-basket manufactured data generator. Trial uncovers the fact that Hadoop contributes towards lessening system and processing masses by the uprightness of dispensing with excess exchanges on Hadoop hubs. Hadoop impressively outperforms and enhances the other models considerably.

A Parallel Relational Database Management System Approach to Relevance Feedback in Information Retrieval.

ERIC Educational Resources Information Center

Lundquist, Carol; Frieder, Ophir; Holmes, David O.; Grossman, David

1999-01-01

Describes a scalable, parallel, relational database-drive information retrieval engine. To support portability across a wide range of execution environments, all algorithms adhere to the SQL-92 standard. By incorporating relevance feedback algorithms, accuracy is enhanced over prior database-driven information retrieval efforts. Presents…

The Tera Multithreaded Architecture and Unstructured Meshes

NASA Technical Reports Server (NTRS)

Bokhari, Shahid H.; Mavriplis, Dimitri J.

1998-01-01

The Tera Multithreaded Architecture (MTA) is a new parallel supercomputer currently being installed at San Diego Supercomputing Center (SDSC). This machine has an architecture quite different from contemporary parallel machines. The computational processor is a custom design and the machine uses hardware to support very fine grained multithreading. The main memory is shared, hardware randomized and flat. These features make the machine highly suited to the execution of unstructured mesh problems, which are difficult to parallelize on other architectures. We report the results of a study carried out during July-August 1998 to evaluate the execution of EUL3D, a code that solves the Euler equations on an unstructured mesh, on the 2 processor Tera MTA at SDSC. Our investigation shows that parallelization of an unstructured code is extremely easy on the Tera. We were able to get an existing parallel code (designed for a shared memory machine), running on the Tera by changing only the compiler directives. Furthermore, a serial version of this code was compiled to run in parallel on the Tera by judicious use of directives to invoke the "full/empty" tag bits of the machine to obtain synchronization. This version achieves 212 and 406 Mflop/s on one and two processors respectively, and requires no attention to partitioning or placement of data issues that would be of paramount importance in other parallel architectures.

Extending molecular simulation time scales: Parallel in time integrations for high-level quantum chemistry and complex force representations

NASA Astrophysics Data System (ADS)

Bylaska, Eric J.; Weare, Jonathan Q.; Weare, John H.

2013-08-01

Parallel in time simulation algorithms are presented and applied to conventional molecular dynamics (MD) and ab initio molecular dynamics (AIMD) models of realistic complexity. Assuming that a forward time integrator, f (e.g., Verlet algorithm), is available to propagate the system from time ti (trajectory positions and velocities xi = (ri, vi)) to time ti + 1 (xi + 1) by xi + 1 = fi(xi), the dynamics problem spanning an interval from t0…tM can be transformed into a root finding problem, F(X) = [xi - f(x(i - 1)]i = 1, M = 0, for the trajectory variables. The root finding problem is solved using a variety of root finding techniques, including quasi-Newton and preconditioned quasi-Newton schemes that are all unconditionally convergent. The algorithms are parallelized by assigning a processor to each time-step entry in the columns of F(X). The relation of this approach to other recently proposed parallel in time methods is discussed, and the effectiveness of various approaches to solving the root finding problem is tested. We demonstrate that more efficient dynamical models based on simplified interactions or coarsening time-steps provide preconditioners for the root finding problem. However, for MD and AIMD simulations, such preconditioners are not required to obtain reasonable convergence and their cost must be considered in the performance of the algorithm. The parallel in time algorithms developed are tested by applying them to MD and AIMD simulations of size and complexity similar to those encountered in present day applications. These include a 1000 Si atom MD simulation using Stillinger-Weber potentials, and a HCl + 4H2O AIMD simulation at the MP2 level. The maximum speedup (serial execution time/parallel execution time) obtained by parallelizing the Stillinger-Weber MD simulation was nearly 3.0. For the AIMD MP2 simulations, the algorithms achieved speedups of up to 14.3. The parallel in time algorithms can be implemented in a distributed computing environment using very slow transmission control protocol/Internet protocol networks. Scripts written in Python that make calls to a precompiled quantum chemistry package (NWChem) are demonstrated to provide an actual speedup of 8.2 for a 2.5 ps AIMD simulation of HCl + 4H2O at the MP2/6-31G* level. Implemented in this way these algorithms can be used for long time high-level AIMD simulations at a modest cost using machines connected by very slow networks such as WiFi, or in different time zones connected by the Internet. The algorithms can also be used with programs that are already parallel. Using these algorithms, we are able to reduce the cost of a MP2/6-311++G(2d,2p) simulation that had reached its maximum possible speedup in the parallelization of the electronic structure calculation from 32 s/time step to 6.9 s/time step.

cljam: a library for handling DNA sequence alignment/map (SAM) with parallel processing.

PubMed

Takeuchi, Toshiki; Yamada, Atsuo; Aoki, Takashi; Nishimura, Kunihiro

2016-01-01

Next-generation sequencing can determine DNA bases and the results of sequence alignments are generally stored in files in the Sequence Alignment/Map (SAM) format and the compressed binary version (BAM) of it. SAMtools is a typical tool for dealing with files in the SAM/BAM format. SAMtools has various functions, including detection of variants, visualization of alignments, indexing, extraction of parts of the data and loci, and conversion of file formats. It is written in C and can execute fast. However, SAMtools requires an additional implementation to be used in parallel with, for example, OpenMP (Open Multi-Processing) libraries. For the accumulation of next-generation sequencing data, a simple parallelization program, which can support cloud and PC cluster environments, is required. We have developed cljam using the Clojure programming language, which simplifies parallel programming, to handle SAM/BAM data. Cljam can run in a Java runtime environment (e.g., Windows, Linux, Mac OS X) with Clojure. Cljam can process and analyze SAM/BAM files in parallel and at high speed. The execution time with cljam is almost the same as with SAMtools. The cljam code is written in Clojure and has fewer lines than other similar tools.

A sweep algorithm for massively parallel simulation of circuit-switched networks

NASA Technical Reports Server (NTRS)

Gaujal, Bruno; Greenberg, Albert G.; Nicol, David M.

1992-01-01

A new massively parallel algorithm is presented for simulating large asymmetric circuit-switched networks, controlled by a randomized-routing policy that includes trunk-reservation. A single instruction multiple data (SIMD) implementation is described, and corresponding experiments on a 16384 processor MasPar parallel computer are reported. A multiple instruction multiple data (MIMD) implementation is also described, and corresponding experiments on an Intel IPSC/860 parallel computer, using 16 processors, are reported. By exploiting parallelism, our algorithm increases the possible execution rate of such complex simulations by as much as an order of magnitude.

Dependability analysis of parallel systems using a simulation-based approach. M.S. Thesis

NASA Technical Reports Server (NTRS)

Sawyer, Darren Charles

1994-01-01

The analysis of dependability in large, complex, parallel systems executing real applications or workloads is examined in this thesis. To effectively demonstrate the wide range of dependability problems that can be analyzed through simulation, the analysis of three case studies is presented. For each case, the organization of the simulation model used is outlined, and the results from simulated fault injection experiments are explained, showing the usefulness of this method in dependability modeling of large parallel systems. The simulation models are constructed using DEPEND and C++. Where possible, methods to increase dependability are derived from the experimental results. Another interesting facet of all three cases is the presence of some kind of workload of application executing in the simulation while faults are injected. This provides a completely new dimension to this type of study, not possible to model accurately with analytical approaches.

Potential Application of a Graphical Processing Unit to Parallel Computations in the NUBEAM Code

NASA Astrophysics Data System (ADS)

Payne, J.; McCune, D.; Prater, R.

2010-11-01

NUBEAM is a comprehensive computational Monte Carlo based model for neutral beam injection (NBI) in tokamaks. NUBEAM computes NBI-relevant profiles in tokamak plasmas by tracking the deposition and the slowing of fast ions. At the core of NUBEAM are vector calculations used to track fast ions. These calculations have recently been parallelized to run on MPI clusters. However, cost and interlink bandwidth limit the ability to fully parallelize NUBEAM on an MPI cluster. Recent implementation of double precision capabilities for Graphical Processing Units (GPUs) presents a cost effective and high performance alternative or complement to MPI computation. Commercially available graphics cards can achieve up to 672 GFLOPS double precision and can handle hundreds of thousands of threads. The ability to execute at least one thread per particle simultaneously could significantly reduce the execution time and the statistical noise of NUBEAM. Progress on implementation on a GPU will be presented.

Parallel file system with metadata distributed across partitioned key-value store c

DOEpatents

Bent, John M.; Faibish, Sorin; Grider, Gary; Torres, Aaron

2017-09-19

Improved techniques are provided for storing metadata associated with a plurality of sub-files associated with a single shared file in a parallel file system. The shared file is generated by a plurality of applications executing on a plurality of compute nodes. A compute node implements a Parallel Log Structured File System (PLFS) library to store at least one portion of the shared file generated by an application executing on the compute node and metadata for the at least one portion of the shared file on one or more object storage servers. The compute node is also configured to implement a partitioned data store for storing a partition of the metadata for the shared file, wherein the partitioned data store communicates with partitioned data stores on other compute nodes using a message passing interface. The partitioned data store can be implemented, for example, using Multidimensional Data Hashing Indexing Middleware (MDHIM).

The R package "sperrorest" : Parallelized spatial error estimation and variable importance assessment for geospatial machine learning

NASA Astrophysics Data System (ADS)

Schratz, Patrick; Herrmann, Tobias; Brenning, Alexander

2017-04-01

Computational and statistical prediction methods such as the support vector machine have gained popularity in remote-sensing applications in recent years and are often compared to more traditional approaches like maximum-likelihood classification. However, the accuracy assessment of such predictive models in a spatial context needs to account for the presence of spatial autocorrelation in geospatial data by using spatial cross-validation and bootstrap strategies instead of their now more widely used non-spatial equivalent. The R package sperrorest by A. Brenning [IEEE International Geoscience and Remote Sensing Symposium, 1, 374 (2012)] provides a generic interface for performing (spatial) cross-validation of any statistical or machine-learning technique available in R. Since spatial statistical models as well as flexible machine-learning algorithms can be computationally expensive, parallel computing strategies are required to perform cross-validation efficiently. The most recent major release of sperrorest therefore comes with two new features (aside from improved documentation): The first one is the parallelized version of sperrorest(), parsperrorest(). This function features two parallel modes to greatly speed up cross-validation runs. Both parallel modes are platform independent and provide progress information. par.mode = 1 relies on the pbapply package and calls interactively (depending on the platform) parallel::mclapply() or parallel::parApply() in the background. While forking is used on Unix-Systems, Windows systems use a cluster approach for parallel execution. par.mode = 2 uses the foreach package to perform parallelization. This method uses a different way of cluster parallelization than the parallel package does. In summary, the robustness of parsperrorest() is increased with the implementation of two independent parallel modes. A new way of partitioning the data in sperrorest is provided by partition.factor.cv(). This function gives the user the possibility to perform cross-validation at the level of some grouping structure. As an example, in remote sensing of agricultural land uses, pixels from the same field contain nearly identical information and will thus be jointly placed in either the test set or the training set. Other spatial sampling resampling strategies are already available and can be extended by the user.

Incremental Parallelization of Non-Data-Parallel Programs Using the Charon Message-Passing Library

NASA Technical Reports Server (NTRS)

VanderWijngaart, Rob F.

2000-01-01

Message passing is among the most popular techniques for parallelizing scientific programs on distributed-memory architectures. The reasons for its success are wide availability (MPI), efficiency, and full tuning control provided to the programmer. A major drawback, however, is that incremental parallelization, as offered by compiler directives, is not generally possible, because all data structures have to be changed throughout the program simultaneously. Charon remedies this situation through mappings between distributed and non-distributed data. It allows breaking up the parallelization into small steps, guaranteeing correctness at every stage. Several tools are available to help convert legacy codes into high-performance message-passing programs. They usually target data-parallel applications, whose loops carrying most of the work can be distributed among all processors without much dependency analysis. Others do a full dependency analysis and then convert the code virtually automatically. Even more toolkits are available that aid construction from scratch of message passing programs. None, however, allows piecemeal translation of codes with complex data dependencies (i.e. non-data-parallel programs) into message passing codes. The Charon library (available in both C and Fortran) provides incremental parallelization capabilities by linking legacy code arrays with distributed arrays. During the conversion process, non-distributed and distributed arrays exist side by side, and simple mapping functions allow the programmer to switch between the two in any location in the program. Charon also provides wrapper functions that leave the structure of the legacy code intact, but that allow execution on truly distributed data. Finally, the library provides a rich set of communication functions that support virtually all patterns of remote data demands in realistic structured grid scientific programs, including transposition, nearest-neighbor communication, pipelining, gather/scatter, and redistribution. At the end of the conversion process most intermediate Charon function calls will have been removed, the non-distributed arrays will have been deleted, and virtually the only remaining Charon functions calls are the high-level, highly optimized communications. Distribution of the data is under complete control of the programmer, although a wide range of useful distributions is easily available through predefined functions. A crucial aspect of the library is that it does not allocate space for distributed arrays, but accepts programmer-specified memory. This has two major consequences. First, codes parallelized using Charon do not suffer from encapsulation; user data is always directly accessible. This provides high efficiency, and also retains the possibility of using message passing directly for highly irregular communications. Second, non-distributed arrays can be interpreted as (trivial) distributions in the Charon sense, which allows them to be mapped to truly distributed arrays, and vice versa. This is the mechanism that enables incremental parallelization. In this paper we provide a brief introduction of the library and then focus on the actual steps in the parallelization process, using some representative examples from, among others, the NAS Parallel Benchmarks. We show how a complicated two-dimensional pipeline-the prototypical non-data-parallel algorithm- can be constructed with ease. To demonstrate the flexibility of the library, we give examples of the stepwise, efficient parallel implementation of nonlocal boundary conditions common in aircraft simulations, as well as the construction of the sequence of grids required for multigrid.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sadayappan, Ponnuswamy

Exascale computing systems will provide a thousand-fold increase in parallelism and a proportional increase in failure rate relative to today's machines. Systems software for exascale machines must provide the infrastructure to support existing applications while simultaneously enabling efficient execution of new programming models that naturally express dynamic, adaptive, irregular computation; coupled simulations; and massive data analysis in a highly unreliable hardware environment with billions of threads of execution. We propose a new approach to the data and work distribution model provided by system software based on the unifying formalism of an abstract file system. The proposed hierarchical data model providesmore » simple, familiar visibility and access to data structures through the file system hierarchy, while providing fault tolerance through selective redundancy. The hierarchical task model features work queues whose form and organization are represented as file system objects. Data and work are both first class entities. By exposing the relationships between data and work to the runtime system, information is available to optimize execution time and provide fault tolerance. The data distribution scheme provides replication (where desirable and possible) for fault tolerance and efficiency, and it is hierarchical to make it possible to take advantage of locality. The user, tools, and applications, including legacy applications, can interface with the data, work queues, and one another through the abstract file model. This runtime environment will provide multiple interfaces to support traditional Message Passing Interface applications, languages developed under DARPA's High Productivity Computing Systems program, as well as other, experimental programming models. We will validate our runtime system with pilot codes on existing platforms and will use simulation to validate for exascale-class platforms. In this final report, we summarize research results from the work done at the Ohio State University towards the larger goals of the project listed above.« less

Individual differences in control of language interference in late bilinguals are mainly related to general executive abilities

PubMed Central

2010-01-01

Background Recent research based on comparisons between bilinguals and monolinguals postulates that bilingualism enhances cognitive control functions, because the parallel activation of languages necessitates control of interference. In a novel approach we investigated two groups of bilinguals, distinguished by their susceptibility to cross-language interference, asking whether bilinguals with strong language control abilities ("non-switchers") have an advantage in executive functions (inhibition of irrelevant information, problem solving, planning efficiency, generative fluency and self-monitoring) compared to those bilinguals showing weaker language control abilities ("switchers"). Methods 29 late bilinguals (21 women) were evaluated using various cognitive control neuropsychological tests [e.g., Tower of Hanoi, Ruff Figural Fluency Task, Divided Attention, Go/noGo] tapping executive functions as well as four subtests of the Wechsler Adult Intelligence Scale. The analysis involved t-tests (two independent samples). Non-switchers (n = 16) were distinguished from switchers (n = 13) by their performance observed in a bilingual picture-naming task. Results The non-switcher group demonstrated a better performance on the Tower of Hanoi and Ruff Figural Fluency task, faster reaction time in a Go/noGo and Divided Attention task, and produced significantly fewer errors in the Tower of Hanoi, Go/noGo, and Divided Attention tasks when compared to the switchers. Non-switchers performed significantly better on two verbal subtests of the Wechsler Adult Intelligence Scale (Information and Similarity), but not on the Performance subtests (Picture Completion, Block Design). Conclusions The present results suggest that bilinguals with stronger language control have indeed a cognitive advantage in the administered tests involving executive functions, in particular inhibition, self-monitoring, problem solving, and generative fluency, and in two of the intelligence tests. What remains unclear is the direction of the relationship between executive functions and language control abilities. PMID:20180956

The procedure execution manager and its application to Advanced Photon Source operation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Borland, M.

1997-06-01

The Procedure Execution Manager (PEM) combines a complete scripting environment for coding accelerator operation procedures with a manager application for executing and monitoring the procedures. PEM is based on Tcl/Tk, a supporting widget library, and the dp-tcl extension for distributed processing. The scripting environment provides support for distributed, parallel execution of procedures along with join and abort operations. Nesting of procedures is supported, permitting the same code to run as a top-level procedure under operator control or as a subroutine under control of another procedure. The manager application allows an operator to execute one or more procedures in automatic, semi-automatic,more » or manual modes. It also provides a standard way for operators to interact with procedures. A number of successful applications of PEM to accelerator operations have been made to date. These include start-up, shutdown, and other control of the positron accumulator ring (PAR), low-energy transport (LET) lines, and the booster rf systems. The PAR/LET procedures make nested use of PEM`s ability to run parallel procedures. There are also a number of procedures to guide and assist tune-up operations, to make accelerator physics measurements, and to diagnose equipment. Because of the success of the existing procedures, expanded use of PEM is planned.« less

Accelerating next generation sequencing data analysis with system level optimizations.

PubMed

Kathiresan, Nagarajan; Temanni, Ramzi; Almabrazi, Hakeem; Syed, Najeeb; Jithesh, Puthen V; Al-Ali, Rashid

2017-08-22

Next generation sequencing (NGS) data analysis is highly compute intensive. In-memory computing, vectorization, bulk data transfer, CPU frequency scaling are some of the hardware features in the modern computing architectures. To get the best execution time and utilize these hardware features, it is necessary to tune the system level parameters before running the application. We studied the GATK-HaplotypeCaller which is part of common NGS workflows, that consume more than 43% of the total execution time. Multiple GATK 3.x versions were benchmarked and the execution time of HaplotypeCaller was optimized by various system level parameters which included: (i) tuning the parallel garbage collection and kernel shared memory to simulate in-memory computing, (ii) architecture-specific tuning in the PairHMM library for vectorization, (iii) including Java 1.8 features through GATK source code compilation and building a runtime environment for parallel sorting and bulk data transfer (iv) the default 'on-demand' mode of CPU frequency is over-clocked by using 'performance-mode' to accelerate the Java multi-threads. As a result, the HaplotypeCaller execution time was reduced by 82.66% in GATK 3.3 and 42.61% in GATK 3.7. Overall, the execution time of NGS pipeline was reduced to 70.60% and 34.14% for GATK 3.3 and GATK 3.7 respectively.

Designing Next Generation Massively Multithreaded Architectures for Irregular Applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tumeo, Antonino; Secchi, Simone; Villa, Oreste

Irregular applications, such as data mining or graph-based computations, show unpredictable memory/network access patterns and control structures. Massively multi-threaded architectures with large node count, like the Cray XMT, have been shown to address their requirements better than commodity clusters. In this paper we present the approaches that we are currently pursuing to design future generations of these architectures. First, we introduce the Cray XMT and compare it to other multithreaded architectures. We then propose an evolution of the architecture, integrating multiple cores per node and next generation network interconnect. We advocate the use of hardware support for remote memory referencemore » aggregation to optimize network utilization. For this evaluation we developed a highly parallel, custom simulation infrastructure for multi-threaded systems. Our simulator executes unmodified XMT binaries with very large datasets, capturing effects due to contention and hot-spotting, while predicting execution times with greater than 90% accuracy. We also discuss the FPGA prototyping approach that we are employing to study efficient support for irregular applications in next generation manycore processors.« less

The FORCE - A highly portable parallel programming language

NASA Technical Reports Server (NTRS)

Jordan, Harry F.; Benten, Muhammad S.; Alaghband, Gita; Jakob, Ruediger

1989-01-01

This paper explains why the FORCE parallel programming language is easily portable among six different shared-memory multiprocessors, and how a two-level macro preprocessor makes it possible to hide low-level machine dependencies and to build machine-independent high-level constructs on top of them. These FORCE constructs make it possible to write portable parallel programs largely independent of the number of processes and the specific shared-memory multiprocessor executing them.

The FORCE: A highly portable parallel programming language

NASA Technical Reports Server (NTRS)

Jordan, Harry F.; Benten, Muhammad S.; Alaghband, Gita; Jakob, Ruediger

1989-01-01

Here, it is explained why the FORCE parallel programming language is easily portable among six different shared-memory microprocessors, and how a two-level macro preprocessor makes it possible to hide low level machine dependencies and to build machine-independent high level constructs on top of them. These FORCE constructs make it possible to write portable parallel programs largely independent of the number of processes and the specific shared memory multiprocessor executing them.

Quantitative Image Feature Engine (QIFE): an Open-Source, Modular Engine for 3D Quantitative Feature Extraction from Volumetric Medical Images.

PubMed

Echegaray, Sebastian; Bakr, Shaimaa; Rubin, Daniel L; Napel, Sandy

2017-10-06

The aim of this study was to develop an open-source, modular, locally run or server-based system for 3D radiomics feature computation that can be used on any computer system and included in existing workflows for understanding associations and building predictive models between image features and clinical data, such as survival. The QIFE exploits various levels of parallelization for use on multiprocessor systems. It consists of a managing framework and four stages: input, pre-processing, feature computation, and output. Each stage contains one or more swappable components, allowing run-time customization. We benchmarked the engine using various levels of parallelization on a cohort of CT scans presenting 108 lung tumors. Two versions of the QIFE have been released: (1) the open-source MATLAB code posted to Github, (2) a compiled version loaded in a Docker container, posted to DockerHub, which can be easily deployed on any computer. The QIFE processed 108 objects (tumors) in 2:12 (h/mm) using 1 core, and 1:04 (h/mm) hours using four cores with object-level parallelization. We developed the Quantitative Image Feature Engine (QIFE), an open-source feature-extraction framework that focuses on modularity, standards, parallelism, provenance, and integration. Researchers can easily integrate it with their existing segmentation and imaging workflows by creating input and output components that implement their existing interfaces. Computational efficiency can be improved by parallelizing execution at the cost of memory usage. Different parallelization levels provide different trade-offs, and the optimal setting will depend on the size and composition of the dataset to be processed.

Development of a Dynamic Time Sharing Scheduled Environment Final Report CRADA No. TC-824-94E

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jette, M.; Caliga, D.

Massively parallel computers, such as the Cray T3D, have historically supported resource sharing solely with space sharing. In that method, multiple problems are solved by executing them on distinct processors. This project developed a dynamic time- and space-sharing scheduler to achieve greater interactivity and throughput than could be achieved with space-sharing alone. CRI and LLNL worked together on the design, testing, and review aspects of this project. There were separate software deliverables. CFU implemented a general purpose scheduling system as per the design specifications. LLNL ported the local gang scheduler software to the LLNL Cray T3D. In this approach, processorsmore » are allocated simultaneously to aU components of a parallel program (in a “gang”). Program execution is preempted as needed to provide for interactivity. Programs are also reIocated to different processors as needed to efficiently pack the computer’s torus of processors. In phase one, CRI developed an interface specification after discussions with LLNL for systemlevel software supporting a time- and space-sharing environment on the LLNL T3D. The two parties also discussed interface specifications for external control tools (such as scheduling policy tools, system administration tools) and applications programs. CRI assumed responsibility for the writing and implementation of all the necessary system software in this phase. In phase two, CRI implemented job-rolling on the Cray T3D, a mechanism for preempting a program, saving its state to disk, and later restoring its state to memory for continued execution. LLNL ported its gang scheduler to the LLNL T3D utilizing the CRI interface implemented in phases one and two. During phase three, the functionality and effectiveness of the LLNL gang scheduler was assessed to provide input to CRI time- and space-sharing, efforts. CRI will utilize this information in the development of general schedulers suitable for other sites and future architectures.« less

Automated Instrumentation, Monitoring and Visualization of PVM Programs Using AIMS

NASA Technical Reports Server (NTRS)

Mehra, Pankaj; VanVoorst, Brian; Yan, Jerry; Tucker, Deanne (Technical Monitor)

1994-01-01

We present views and analysis of the execution of several PVM codes for Computational Fluid Dynamics on a network of Sparcstations, including (a) NAS Parallel benchmarks CG and MG (White, Alund and Sunderam 1993); (b) a multi-partitioning algorithm for NAS Parallel Benchmark SP (Wijngaart 1993); and (c) an overset grid flowsolver (Smith 1993). These views and analysis were obtained using our Automated Instrumentation and Monitoring System (AIMS) version 3.0, a toolkit for debugging the performance of PVM programs. We will describe the architecture, operation and application of AIMS. The AIMS toolkit contains (a) Xinstrument, which can automatically instrument various computational and communication constructs in message-passing parallel programs; (b) Monitor, a library of run-time trace-collection routines; (c) VK (Visual Kernel), an execution-animation tool with source-code clickback; and (d) Tally, a tool for statistical analysis of execution profiles. Currently, Xinstrument can handle C and Fortran77 programs using PVM 3.2.x; Monitor has been implemented and tested on Sun 4 systems running SunOS 4.1.2; and VK uses X11R5 and Motif 1.2. Data and views obtained using AIMS clearly illustrate several characteristic features of executing parallel programs on networked workstations: (a) the impact of long message latencies; (b) the impact of multiprogramming overheads and associated load imbalance; (c) cache and virtual-memory effects; and (4significant skews between workstation clocks. Interestingly, AIMS can compensate for constant skew (zero drift) by calibrating the skew between a parent and its spawned children. In addition, AIMS' skew-compensation algorithm can adjust timestamps in a way that eliminates physically impossible communications (e.g., messages going backwards in time). Our current efforts are directed toward creating new views to explain the observed performance of PVM programs. Some of the features planned for the near future include: (a) ConfigView, showing the physical topology of the virtual machine, inferred using specially formatted IP (Internet Protocol) packets; and (b) LoadView, synchronous animation of PVM-program execution and resource-utilization patterns.

Development of gallium arsenide high-speed, low-power serial parallel interface modules: Executive summary

NASA Technical Reports Server (NTRS)

1988-01-01

Final report to NASA LeRC on the development of gallium arsenide (GaAS) high-speed, low power serial/parallel interface modules. The report discusses the development and test of a family of 16, 32 and 64 bit parallel to serial and serial to parallel integrated circuits using a self aligned gate MESFET technology developed at the Honeywell Sensors and Signal Processing Laboratory. Lab testing demonstrated 1.3 GHz clock rates at a power of 300 mW. This work was accomplished under contract number NAS3-24676.

Verification and Planning Based on Coinductive Logic Programming

NASA Technical Reports Server (NTRS)

Bansal, Ajay; Min, Richard; Simon, Luke; Mallya, Ajay; Gupta, Gopal

2008-01-01

Coinduction is a powerful technique for reasoning about unfounded sets, unbounded structures, infinite automata, and interactive computations [6]. Where induction corresponds to least fixed point's semantics, coinduction corresponds to greatest fixed point semantics. Recently coinduction has been incorporated into logic programming and an elegant operational semantics developed for it [11, 12]. This operational semantics is the greatest fix point counterpart of SLD resolution (SLD resolution imparts operational semantics to least fix point based computations) and is termed co- SLD resolution. In co-SLD resolution, a predicate goal p( t) succeeds if it unifies with one of its ancestor calls. In addition, rational infinite terms are allowed as arguments of predicates. Infinite terms are represented as solutions to unification equations and the occurs check is omitted during the unification process. Coinductive Logic Programming (Co-LP) and Co-SLD resolution can be used to elegantly perform model checking and planning. A combined SLD and Co-SLD resolution based LP system forms the common basis for planning, scheduling, verification, model checking, and constraint solving [9, 4]. This is achieved by amalgamating SLD resolution, co-SLD resolution, and constraint logic programming [13] in a single logic programming system. Given that parallelism in logic programs can be implicitly exploited [8], complex, compute-intensive applications (planning, scheduling, model checking, etc.) can be executed in parallel on multi-core machines. Parallel execution can result in speed-ups as well as in larger instances of the problems being solved. In the remainder we elaborate on (i) how planning can be elegantly and efficiently performed under real-time constraints, (ii) how real-time systems can be elegantly and efficiently model- checked, as well as (iii) how hybrid systems can be verified in a combined system with both co-SLD and SLD resolution. Implementations of co-SLD resolution as well as preliminary implementations of the planning and verification applications have been developed [4]. Co-LP and Model Checking: The vast majority of properties that are to be verified can be classified into safety properties and liveness properties. It is well known within model checking that safety properties can be verified by reachability analysis, i.e, if a counter-example to the property exists, it can be finitely determined by enumerating all the reachable states of the Kripke structure.

Parallel Performance of a Combustion Chemistry Simulation

DOE PAGES

Skinner, Gregg; Eigenmann, Rudolf

1995-01-01

We used a description of a combustion simulation's mathematical and computational methods to develop a version for parallel execution. The result was a reasonable performance improvement on small numbers of processors. We applied several important programming techniques, which we describe, in optimizing the application. This work has implications for programming languages, compiler design, and software engineering.

Towards Energy-Performance Trade-off Analysis of Parallel Applications

ERIC Educational Resources Information Center

Korthikanti, Vijay Anand Reddy

2011-01-01

Energy consumption by computer systems has emerged as an important concern, both at the level of individual devices (limited battery capacity in mobile systems) and at the societal level (the production of Green House Gases). In parallel architectures, applications may be executed on a variable number of cores and these cores may operate at…

Graph Partitioning for Parallel Applications in Heterogeneous Grid Environments

NASA Technical Reports Server (NTRS)

Bisws, Rupak; Kumar, Shailendra; Das, Sajal K.; Biegel, Bryan (Technical Monitor)

2002-01-01

The problem of partitioning irregular graphs and meshes for parallel computations on homogeneous systems has been extensively studied. However, these partitioning schemes fail when the target system architecture exhibits heterogeneity in resource characteristics. With the emergence of technologies such as the Grid, it is imperative to study the partitioning problem taking into consideration the differing capabilities of such distributed heterogeneous systems. In our model, the heterogeneous system consists of processors with varying processing power and an underlying non-uniform communication network. We present in this paper a novel multilevel partitioning scheme for irregular graphs and meshes, that takes into account issues pertinent to Grid computing environments. Our partitioning algorithm, called MiniMax, generates and maps partitions onto a heterogeneous system with the objective of minimizing the maximum execution time of the parallel distributed application. For experimental performance study, we have considered both a realistic mesh problem from NASA as well as synthetic workloads. Simulation results demonstrate that MiniMax generates high quality partitions for various classes of applications targeted for parallel execution in a distributed heterogeneous environment.

Multitasking scheduler works without OS

DOE Office of Scientific and Technical Information (OSTI.GOV)

Howard, D.M.

1982-09-15

Z80 control applications requiring parallel execution of multiple software tasks can use the executive routine described and listed in this article when multitasking is not available via an operating system (OS). Although the routine is not as capable or as transparent to software as the multitasking in a full-scale OS, it is simple to understand and use.

Tensor contraction engine: Abstraction and automated parallel implementation of configuration-interaction, coupled-cluster, and many-body perturbation theories

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hirata, So

2003-11-20

We develop a symbolic manipulation program and program generator (Tensor Contraction Engine or TCE) that automatically derives the working equations of a well-defined model of second-quantized many-electron theories and synthesizes efficient parallel computer programs on the basis of these equations. Provided an ansatz of a many-electron theory model, TCE performs valid contractions of creation and annihilation operators according to Wick's theorem, consolidates identical terms, and reduces the expressions into the form of multiple tensor contractions acted by permutation operators. Subsequently, it determines the binary contraction order for each multiple tensor contraction with the minimal operation and memory cost, factorizes commonmore » binary contractions (defines intermediate tensors), and identifies reusable intermediates. The resulting ordered list of binary tensor contractions, additions, and index permutations is translated into an optimized program that is combined with the NWChem and UTChem computational chemistry software packages. The programs synthesized by TCE take advantage of spin symmetry, Abelian point-group symmetry, and index permutation symmetry at every stage of calculations to minimize the number of arithmetic operations and storage requirement, adjust the peak local memory usage by index range tiling, and support parallel I/O interfaces and dynamic load balancing for parallel executions. We demonstrate the utility of TCE through automatic derivation and implementation of parallel programs for various models of configuration-interaction theory (CISD, CISDT, CISDTQ), many-body perturbation theory [MBPT(2), MBPT(3), MBPT(4)], and coupled-cluster theory (LCCD, CCD, LCCSD, CCSD, QCISD, CCSDT, and CCSDTQ).« less

Runtime Detection of C-Style Errors in UPC Code

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pirkelbauer, P; Liao, C; Panas, T

2011-09-29

Unified Parallel C (UPC) extends the C programming language (ISO C 99) with explicit parallel programming support for the partitioned global address space (PGAS), which provides a global memory space with localized partitions to each thread. Like its ancestor C, UPC is a low-level language that emphasizes code efficiency over safety. The absence of dynamic (and static) safety checks allows programmer oversights and software flaws that can be hard to spot. In this paper, we present an extension of a dynamic analysis tool, ROSE-Code Instrumentation and Runtime Monitor (ROSECIRM), for UPC to help programmers find C-style errors involving the globalmore » address space. Built on top of the ROSE source-to-source compiler infrastructure, the tool instruments source files with code that monitors operations and keeps track of changes to the system state. The resulting code is linked to a runtime monitor that observes the program execution and finds software defects. We describe the extensions to ROSE-CIRM that were necessary to support UPC. We discuss complications that arise from parallel code and our solutions. We test ROSE-CIRM against a runtime error detection test suite, and present performance results obtained from running error-free codes. ROSE-CIRM is released as part of the ROSE compiler under a BSD-style open source license.« less

A parallel and sensitive software tool for methylation analysis on multicore platforms.

PubMed

Tárraga, Joaquín; Pérez, Mariano; Orduña, Juan M; Duato, José; Medina, Ignacio; Dopazo, Joaquín

2015-10-01

DNA methylation analysis suffers from very long processing time, as the advent of Next-Generation Sequencers has shifted the bottleneck of genomic studies from the sequencers that obtain the DNA samples to the software that performs the analysis of these samples. The existing software for methylation analysis does not seem to scale efficiently neither with the size of the dataset nor with the length of the reads to be analyzed. As it is expected that the sequencers will provide longer and longer reads in the near future, efficient and scalable methylation software should be developed. We present a new software tool, called HPG-Methyl, which efficiently maps bisulphite sequencing reads on DNA, analyzing DNA methylation. The strategy used by this software consists of leveraging the speed of the Burrows-Wheeler Transform to map a large number of DNA fragments (reads) rapidly, as well as the accuracy of the Smith-Waterman algorithm, which is exclusively employed to deal with the most ambiguous and shortest reads. Experimental results on platforms with Intel multicore processors show that HPG-Methyl significantly outperforms in both execution time and sensitivity state-of-the-art software such as Bismark, BS-Seeker or BSMAP, particularly for long bisulphite reads. Software in the form of C libraries and functions, together with instructions to compile and execute this software. Available by sftp to anonymous@clariano.uv.es (password 'anonymous'). juan.orduna@uv.es or jdopazo@cipf.es. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

A distributed version of the NASA Engine Performance Program

NASA Technical Reports Server (NTRS)

Cours, Jeffrey T.; Curlett, Brian P.

1993-01-01

Distributed NEPP, a version of the NASA Engine Performance Program, uses the original NEPP code but executes it in a distributed computer environment. Multiple workstations connected by a network increase the program's speed and, more importantly, the complexity of the cases it can handle in a reasonable time. Distributed NEPP uses the public domain software package, called Parallel Virtual Machine, allowing it to execute on clusters of machines containing many different architectures. It includes the capability to link with other computers, allowing them to process NEPP jobs in parallel. This paper discusses the design issues and granularity considerations that entered into programming Distributed NEPP and presents the results of timing runs.

Vectorization for Molecular Dynamics on Intel Xeon Phi Corpocessors

NASA Astrophysics Data System (ADS)

Yi, Hongsuk

2014-03-01

Many modern processors are capable of exploiting data-level parallelism through the use of single instruction multiple data (SIMD) execution. The new Intel Xeon Phi coprocessor supports 512 bit vector registers for the high performance computing. In this paper, we have developed a hierarchical parallelization scheme for accelerated molecular dynamics simulations with the Terfoff potentials for covalent bond solid crystals on Intel Xeon Phi coprocessor systems. The scheme exploits multi-level parallelism computing. We combine thread-level parallelism using a tightly coupled thread-level and task-level parallelism with 512-bit vector register. The simulation results show that the parallel performance of SIMD implementations on Xeon Phi is apparently superior to their x86 CPU architecture.

Concurrent approach for evolving compact decision rule sets

NASA Astrophysics Data System (ADS)

Marmelstein, Robert E.; Hammack, Lonnie P.; Lamont, Gary B.

1999-02-01

The induction of decision rules from data is important to many disciplines, including artificial intelligence and pattern recognition. To improve the state of the art in this area, we introduced the genetic rule and classifier construction environment (GRaCCE). It was previously shown that GRaCCE consistently evolved decision rule sets from data, which were significantly more compact than those produced by other methods (such as decision tree algorithms). The primary disadvantage of GRaCCe, however, is its relatively poor run-time execution performance. In this paper, a concurrent version of the GRaCCE architecture is introduced, which improves the efficiency of the original algorithm. A prototype of the algorithm is tested on an in- house parallel processor configuration and the results are discussed.

Heterogeneous Distributed Computing for Computational Aerosciences

NASA Technical Reports Server (NTRS)

Sunderam, Vaidy S.

1998-01-01

The research supported under this award focuses on heterogeneous distributed computing for high-performance applications, with particular emphasis on computational aerosciences. The overall goal of this project was to and investigate issues in, and develop solutions to, efficient execution of computational aeroscience codes in heterogeneous concurrent computing environments. In particular, we worked in the context of the PVM[1] system and, subsequent to detailed conversion efforts and performance benchmarking, devising novel techniques to increase the efficacy of heterogeneous networked environments for computational aerosciences. Our work has been based upon the NAS Parallel Benchmark suite, but has also recently expanded in scope to include the NAS I/O benchmarks as specified in the NHT-1 document. In this report we summarize our research accomplishments under the auspices of the grant.

FPGA-based real-time phase measuring profilometry algorithm design and implementation

NASA Astrophysics Data System (ADS)

Zhan, Guomin; Tang, Hongwei; Zhong, Kai; Li, Zhongwei; Shi, Yusheng

2016-11-01

Phase measuring profilometry (PMP) has been widely used in many fields, like Computer Aided Verification (CAV), Flexible Manufacturing System (FMS) et al. High frame-rate (HFR) real-time vision-based feedback control will be a common demands in near future. However, the instruction time delay in the computer caused by numerous repetitive operations greatly limit the efficiency of data processing. FPGA has the advantages of pipeline architecture and parallel execution, and it fit for handling PMP algorithm. In this paper, we design a fully pipelined hardware architecture for PMP. The functions of hardware architecture includes rectification, phase calculation, phase shifting, and stereo matching. The experiment verified the performance of this method, and the factors that may influence the computation accuracy was analyzed.

APINetworks Java. A Java approach to the efficient treatment of large-scale complex networks

NASA Astrophysics Data System (ADS)

Muñoz-Caro, Camelia; Niño, Alfonso; Reyes, Sebastián; Castillo, Miriam

2016-10-01

We present a new version of the core structural package of our Application Programming Interface, APINetworks, for the treatment of complex networks in arbitrary computational environments. The new version is written in Java and presents several advantages over the previous C++ version: the portability of the Java code, the easiness of object-oriented design implementations, and the simplicity of memory management. In addition, some additional data structures are introduced for storing the sets of nodes and edges. Also, by resorting to the different garbage collectors currently available in the JVM the Java version is much more efficient than the C++ one with respect to memory management. In particular, the G1 collector is the most efficient one because of the parallel execution of G1 and the Java application. Using G1, APINetworks Java outperforms the C++ version and the well-known NetworkX and JGraphT packages in the building and BFS traversal of linear and complete networks. The better memory management of the present version allows for the modeling of much larger networks.

Grid Task Execution

NASA Technical Reports Server (NTRS)

Hu, Chaumin

2007-01-01

IPG Execution Service is a framework that reliably executes complex jobs on a computational grid, and is part of the IPG service architecture designed to support location-independent computing. The new grid service enables users to describe the platform on which they need a job to run, which allows the service to locate the desired platform, configure it for the required application, and execute the job. After a job is submitted, users can monitor it through periodic notifications, or through queries. Each job consists of a set of tasks that performs actions such as executing applications and managing data. Each task is executed based on a starting condition that is an expression of the states of other tasks. This formulation allows tasks to be executed in parallel, and also allows a user to specify tasks to execute when other tasks succeed, fail, or are canceled. The two core components of the Execution Service are the Task Database, which stores tasks that have been submitted for execution, and the Task Manager, which executes tasks in the proper order, based on the user-specified starting conditions, and avoids overloading local and remote resources while executing tasks.

A hybrid parallel architecture for electrostatic interactions in the simulation of dissipative particle dynamics

NASA Astrophysics Data System (ADS)

Yang, Sheng-Chun; Lu, Zhong-Yuan; Qian, Hu-Jun; Wang, Yong-Lei; Han, Jie-Ping

2017-11-01

In this work, we upgraded the electrostatic interaction method of CU-ENUF (Yang, et al., 2016) which first applied CUNFFT (nonequispaced Fourier transforms based on CUDA) to the reciprocal-space electrostatic computation and made the computation of electrostatic interaction done thoroughly in GPU. The upgraded edition of CU-ENUF runs concurrently in a hybrid parallel way that enables the computation parallelizing on multiple computer nodes firstly, then further on the installed GPU in each computer. By this parallel strategy, the size of simulation system will be never restricted to the throughput of a single CPU or GPU. The most critical technical problem is how to parallelize a CUNFFT in the parallel strategy, which is conquered effectively by deep-seated research of basic principles and some algorithm skills. Furthermore, the upgraded method is capable of computing electrostatic interactions for both the atomistic molecular dynamics (MD) and the dissipative particle dynamics (DPD). Finally, the benchmarks conducted for validation and performance indicate that the upgraded method is able to not only present a good precision when setting suitable parameters, but also give an efficient way to compute electrostatic interactions for huge simulation systems. Program Files doi:http://dx.doi.org/10.17632/zncf24fhpv.1 Licensing provisions: GNU General Public License 3 (GPL) Programming language: C, C++, and CUDA C Supplementary material: The program is designed for effective electrostatic interactions of large-scale simulation systems, which runs on particular computers equipped with NVIDIA GPUs. It has been tested on (a) single computer node with Intel(R) Core(TM) i7-3770@ 3.40 GHz (CPU) and GTX 980 Ti (GPU), and (b) MPI parallel computer nodes with the same configurations. Nature of problem: For molecular dynamics simulation, the electrostatic interaction is the most time-consuming computation because of its long-range feature and slow convergence in simulation space, which approximately take up most of the total simulation time. Although the parallel method CU-ENUF (Yang et al., 2016) based on GPU has achieved a qualitative leap compared with previous methods in electrostatic interactions computation, the computation capability is limited to the throughput capacity of a single GPU for super-scale simulation system. Therefore, we should look for an effective method to handle the calculation of electrostatic interactions efficiently for a simulation system with super-scale size. Solution method: We constructed a hybrid parallel architecture, in which CPU and GPU are combined to accelerate the electrostatic computation effectively. Firstly, the simulation system is divided into many subtasks via domain-decomposition method. Then MPI (Message Passing Interface) is used to implement the CPU-parallel computation with each computer node corresponding to a particular subtask, and furthermore each subtask in one computer node will be executed in GPU in parallel efficiently. In this hybrid parallel method, the most critical technical problem is how to parallelize a CUNFFT (nonequispaced fast Fourier transform based on CUDA) in the parallel strategy, which is conquered effectively by deep-seated research of basic principles and some algorithm skills. Restrictions: The HP-ENUF is mainly oriented to super-scale system simulations, in which the performance superiority is shown adequately. However, for a small simulation system containing less than 106 particles, the mode of multiple computer nodes has no apparent efficiency advantage or even lower efficiency due to the serious network delay among computer nodes, than the mode of single computer node. References: (1) S.-C. Yang, H.-J. Qian, Z.-Y. Lu, Appl. Comput. Harmon. Anal. 2016, http://dx.doi.org/10.1016/j.acha.2016.04.009. (2) S.-C. Yang, Y.-L. Wang, G.-S. Jiao, H.-J. Qian, Z.-Y. Lu, J. Comput. Chem. 37 (2016) 378. (3) S.-C. Yang, Y.-L. Zhu, H.-J. Qian, Z.-Y. Lu, Appl. Chem. Res. Chin. Univ., 2017, http://dx.doi.org/10.1007/s40242-016-6354-5. (4) Y.-L. Zhu, H. Liu, Z.-W. Li, H.-J. Qian, G. Milano, Z.-Y. Lu, J. Comput. Chem. 34 (2013) 2197.

Model-Based Systems Engineering in the Execution of Search and Rescue Operations

DTIC Science & Technology

2015-09-01

OSC can fulfill the duties of an ACO but it may make sense to split the duties if there are no communication links between the OSC and participating...parallel mode. This mode is the most powerful option because it 35 creates sequence diagrams that generate parallel “ swim lanes” for each asset...greater flexibility is desired, sequence mode generates diagrams based purely on sequential action and activity diagrams without the parallel “ swim lanes

Parallel computation with the force

NASA Technical Reports Server (NTRS)

Jordan, H. F.

1985-01-01

A methodology, called the force, supports the construction of programs to be executed in parallel by a force of processes. The number of processes in the force is unspecified, but potentially very large. The force idea is embodied in a set of macros which produce multiproceossor FORTRAN code and has been studied on two shared memory multiprocessors of fairly different character. The method has simplified the writing of highly parallel programs within a limited class of parallel algorithms and is being extended to cover a broader class. The individual parallel constructs which comprise the force methodology are discussed. Of central concern are their semantics, implementation on different architectures and performance implications.

Application configuration selection for energy-efficient execution on multicore systems

DOE PAGES

Wang, Shinan; Luo, Bing; Shi, Weisong; ...

2015-09-21

Balanced performance and energy consumption are incorporated in the design of modern computer systems. Several runtime factors, such as concurrency levels, thread mapping strategies, and dynamic voltage and frequency scaling (DVFS) should be considered in order to achieve optimal energy efficiency fora workload. Selecting appropriate run-time factors, however, is one of the most challenging tasks because the run-time factors are architecture-specific and workload-specific. And while most existing works concentrate on either static analysis of the workload or run-time prediction results, we present a hybrid two-step method that utilizes concurrency levels and DVFS settings to achieve the energy efficiency configuration formore » a worldoad. The experimental results based on a Xeon E5620 server with NPB and PARSEC benchmark suites show that the model is able to predict the energy efficient configuration accurately. On average, an additional 10% EDP (Energy Delay Product) saving is obtained by using run-time DVFS for the entire system. An off-line optimal solution is used to compare with the proposed scheme. Finally, the experimental results show that the average extra EDP saved by the optimal solution is within 5% on selective parallel benchmarks.« less

F3D Image Processing and Analysis for Many - and Multi-core Platforms

DOE Office of Scientific and Technical Information (OSTI.GOV)

F3D is written in OpenCL, so it achieve[sic] platform-portable parallelism on modern mutli-core CPUs and many-core GPUs. The interface and mechanims to access F3D core are written in Java as a plugin for Fiji/ImageJ to deliver several key image-processing algorithms necessary to remove artifacts from micro-tomography data. The algorithms consist of data parallel aware filters that can efficiently utilizes[sic] resources and can work on out of core datasets and scale efficiently across multiple accelerators. Optimizing for data parallel filters, streaming out of core datasets, and efficient resource and memory and data managements over complex execution sequence of filters greatly expeditesmore » any scientific workflow with image processing requirements. F3D performs several different types of 3D image processing operations, such as non-linear filtering using bilateral filtering and/or median filtering and/or morphological operators (MM). F3D gray-level MM operators are one-pass constant time methods that can perform morphological transformations with a line-structuring element oriented in discrete directions. Additionally, MM operators can be applied to gray-scale images, and consist of two parts: (a) a reference shape or structuring element, which is translated over the image, and (b) a mechanism, or operation, that defines the comparisons to be performed between the image and the structuring element. This tool provides a critical component within many complex pipelines such as those for performing automated segmentation of image stacks. F3D is also called a "descendent" of Quant-CT, another software we developed in the past. These two modules are to be integrated in a next version. Further details were reported in: D.M. Ushizima, T. Perciano, H. Krishnan, B. Loring, H. Bale, D. Parkinson, and J. Sethian. Structure recognition from high-resolution images of ceramic composites. IEEE International Conference on Big Data, October 2014.« less

Application of the Linux cluster for exhaustive window haplotype analysis using the FBAT and Unphased programs.

PubMed

Mishima, Hiroyuki; Lidral, Andrew C; Ni, Jun

2008-05-28

Genetic association studies have been used to map disease-causing genes. A newly introduced statistical method, called exhaustive haplotype association study, analyzes genetic information consisting of different numbers and combinations of DNA sequence variations along a chromosome. Such studies involve a large number of statistical calculations and subsequently high computing power. It is possible to develop parallel algorithms and codes to perform the calculations on a high performance computing (HPC) system. However, most existing commonly-used statistic packages for genetic studies are non-parallel versions. Alternatively, one may use the cutting-edge technology of grid computing and its packages to conduct non-parallel genetic statistical packages on a centralized HPC system or distributed computing systems. In this paper, we report the utilization of a queuing scheduler built on the Grid Engine and run on a Rocks Linux cluster for our genetic statistical studies. Analysis of both consecutive and combinational window haplotypes was conducted by the FBAT (Laird et al., 2000) and Unphased (Dudbridge, 2003) programs. The dataset consisted of 26 loci from 277 extended families (1484 persons). Using the Rocks Linux cluster with 22 compute-nodes, FBAT jobs performed about 14.4-15.9 times faster, while Unphased jobs performed 1.1-18.6 times faster compared to the accumulated computation duration. Execution of exhaustive haplotype analysis using non-parallel software packages on a Linux-based system is an effective and efficient approach in terms of cost and performance.

Application of the Linux cluster for exhaustive window haplotype analysis using the FBAT and Unphased programs

PubMed Central

Mishima, Hiroyuki; Lidral, Andrew C; Ni, Jun

2008-01-01

Background Genetic association studies have been used to map disease-causing genes. A newly introduced statistical method, called exhaustive haplotype association study, analyzes genetic information consisting of different numbers and combinations of DNA sequence variations along a chromosome. Such studies involve a large number of statistical calculations and subsequently high computing power. It is possible to develop parallel algorithms and codes to perform the calculations on a high performance computing (HPC) system. However, most existing commonly-used statistic packages for genetic studies are non-parallel versions. Alternatively, one may use the cutting-edge technology of grid computing and its packages to conduct non-parallel genetic statistical packages on a centralized HPC system or distributed computing systems. In this paper, we report the utilization of a queuing scheduler built on the Grid Engine and run on a Rocks Linux cluster for our genetic statistical studies. Results Analysis of both consecutive and combinational window haplotypes was conducted by the FBAT (Laird et al., 2000) and Unphased (Dudbridge, 2003) programs. The dataset consisted of 26 loci from 277 extended families (1484 persons). Using the Rocks Linux cluster with 22 compute-nodes, FBAT jobs performed about 14.4–15.9 times faster, while Unphased jobs performed 1.1–18.6 times faster compared to the accumulated computation duration. Conclusion Execution of exhaustive haplotype analysis using non-parallel software packages on a Linux-based system is an effective and efficient approach in terms of cost and performance. PMID:18541045

Metascalable molecular dynamics simulation of nano-mechano-chemistry

NASA Astrophysics Data System (ADS)

Shimojo, F.; Kalia, R. K.; Nakano, A.; Nomura, K.; Vashishta, P.

2008-07-01

We have developed a metascalable (or 'design once, scale on new architectures') parallel application-development framework for first-principles based simulations of nano-mechano-chemical processes on emerging petaflops architectures based on spatiotemporal data locality principles. The framework consists of (1) an embedded divide-and-conquer (EDC) algorithmic framework based on spatial locality to design linear-scaling algorithms, (2) a space-time-ensemble parallel (STEP) approach based on temporal locality to predict long-time dynamics, and (3) a tunable hierarchical cellular decomposition (HCD) parallelization framework to map these scalable algorithms onto hardware. The EDC-STEP-HCD framework exposes and expresses maximal concurrency and data locality, thereby achieving parallel efficiency as high as 0.99 for 1.59-billion-atom reactive force field molecular dynamics (MD) and 17.7-million-atom (1.56 trillion electronic degrees of freedom) quantum mechanical (QM) MD in the framework of the density functional theory (DFT) on adaptive multigrids, in addition to 201-billion-atom nonreactive MD, on 196 608 IBM BlueGene/L processors. We have also used the framework for automated execution of adaptive hybrid DFT/MD simulation on a grid of six supercomputers in the US and Japan, in which the number of processors changed dynamically on demand and tasks were migrated according to unexpected faults. The paper presents the application of the framework to the study of nanoenergetic materials: (1) combustion of an Al/Fe2O3 thermite and (2) shock initiation and reactive nanojets at a void in an energetic crystal.

Some Problems and Solutions in Transferring Ecosystem Simulation Codes to Supercomputers

NASA Technical Reports Server (NTRS)

Skiles, J. W.; Schulbach, C. H.

1994-01-01

Many computer codes for the simulation of ecological systems have been developed in the last twenty-five years. This development took place initially on main-frame computers, then mini-computers, and more recently, on micro-computers and workstations. Recent recognition of ecosystem science as a High Performance Computing and Communications Program Grand Challenge area emphasizes supercomputers (both parallel and distributed systems) as the next set of tools for ecological simulation. Transferring ecosystem simulation codes to such systems is not a matter of simply compiling and executing existing code on the supercomputer since there are significant differences in the system architectures of sequential, scalar computers and parallel and/or vector supercomputers. To more appropriately match the application to the architecture (necessary to achieve reasonable performance), the parallelism (if it exists) of the original application must be exploited. We discuss our work in transferring a general grassland simulation model (developed on a VAX in the FORTRAN computer programming language) to a Cray Y-MP. We show the Cray shared-memory vector-architecture, and discuss our rationale for selecting the Cray. We describe porting the model to the Cray and executing and verifying a baseline version, and we discuss the changes we made to exploit the parallelism in the application and to improve code execution. As a result, the Cray executed the model 30 times faster than the VAX 11/785 and 10 times faster than a Sun 4 workstation. We achieved an additional speed-up of approximately 30 percent over the original Cray run by using the compiler's vectorizing capabilities and the machine's ability to put subroutines and functions "in-line" in the code. With the modifications, the code still runs at only about 5% of the Cray's peak speed because it makes ineffective use of the vector processing capabilities of the Cray. We conclude with a discussion and future plans.

Parallel Logic Programming Architecture

DTIC Science & Technology

1990-04-01

Section 3.1. 3.1. A STATIC ALLOCATION SCHEME (SAS) Methods that have been used for decomposing distributed problems in artificial intelligence...multiple agents, knowledge organization and allocation, and cooperative parallel execution. These difficulties are common to distributed artificial ...for the following reasons. First, intellegent backtracking requires much more bookkeeping and is therefore more costly during consult-time and during

Efficient Synthesis of Graph Methods: a Dynamically Scheduled Architecture

DOE Office of Scientific and Technical Information (OSTI.GOV)

Minutoli, Marco; Castellana, Vito G.; Tumeo, Antonino

RDF databases naturally map to a graph representation and employ languages, such as SPARQL, that implements queries as graph pattern matching routines. Graph methods exhibit an irregular behavior: they present unpredictable, fine-grained data accesses, and are synchronization inten- sive. Graph data structures expose large amounts of dy- namic parallelism, but are difficult to partition without gen- erating load unbalance. In this paper, we present a novel ar- chitecture to improve the synthesis of graph methods. Our design addresses the issues of these algorithms with two com- ponents: a Dynamic Task Scheduler (DTS), which reduces load unbalance and maximize resource utilization,more » and a Hi- erarchical Memory Interface controller (HMI), which pro- vides support for concurrent memory operations on multi- ported/multi-banked shared memories. We evaluate our ap- proach by generating the accelerators for a set of SPARQL queries from the Lehigh University Benchmark (LUBM). We first analyze the load unbalance of these queries, showing that execution time among tasks can differ even of order of magnitudes. We then synthesize the queries and com- pare the performance of the resulting accelerators against the current state of the art. Experimental results show that our solution provides a speedup over the serial implementa- tion close to the theoretical maximum and a speedup up to 3.45 over a baseline parallel implementation. We conclude our study by exploring the design space to achieve maximum memory channels utilization. The best design used at least three of the four memory channels for more than 90% of the execution time.« less

Decaf: Decoupled Dataflows for In Situ High-Performance Workflows

DOE Office of Scientific and Technical Information (OSTI.GOV)

Dreher, M.; Peterka, T.

Decaf is a dataflow system for the parallel communication of coupled tasks in an HPC workflow. The dataflow can perform arbitrary data transformations ranging from simply forwarding data to complex data redistribution. Decaf does this by allowing the user to allocate resources and execute custom code in the dataflow. All communication through the dataflow is efficient parallel message passing over MPI. The runtime for calling tasks is entirely message-driven; Decaf executes a task when all messages for the task have been received. Such a messagedriven runtime allows cyclic task dependencies in the workflow graph, for example, to enact computational steeringmore » based on the result of downstream tasks. Decaf includes a simple Python API for describing the workflow graph. This allows Decaf to stand alone as a complete workflow system, but Decaf can also be used as the dataflow layer by one or more other workflow systems to form a heterogeneous task-based computing environment. In one experiment, we couple a molecular dynamics code with a visualization tool using the FlowVR and Damaris workflow systems and Decaf for the dataflow. In another experiment, we test the coupling of a cosmology code with Voronoi tessellation and density estimation codes using MPI for the simulation, the DIY programming model for the two analysis codes, and Decaf for the dataflow. Such workflows consisting of heterogeneous software infrastructures exist because components are developed separately with different programming models and runtimes, and this is the first time that such heterogeneous coupling of diverse components was demonstrated in situ on HPC systems.« less

FPGA implementation of a biological neural network based on the Hodgkin-Huxley neuron model.

PubMed

Yaghini Bonabi, Safa; Asgharian, Hassan; Safari, Saeed; Nili Ahmadabadi, Majid

2014-01-01

A set of techniques for efficient implementation of Hodgkin-Huxley-based (H-H) model of a neural network on FPGA (Field Programmable Gate Array) is presented. The central implementation challenge is H-H model complexity that puts limits on the network size and on the execution speed. However, basics of the original model cannot be compromised when effect of synaptic specifications on the network behavior is the subject of study. To solve the problem, we used computational techniques such as CORDIC (Coordinate Rotation Digital Computer) algorithm and step-by-step integration in the implementation of arithmetic circuits. In addition, we employed different techniques such as sharing resources to preserve the details of model as well as increasing the network size in addition to keeping the network execution speed close to real time while having high precision. Implementation of a two mini-columns network with 120/30 excitatory/inhibitory neurons is provided to investigate the characteristic of our method in practice. The implementation techniques provide an opportunity to construct large FPGA-based network models to investigate the effect of different neurophysiological mechanisms, like voltage-gated channels and synaptic activities, on the behavior of a neural network in an appropriate execution time. Additional to inherent properties of FPGA, like parallelism and re-configurability, our approach makes the FPGA-based system a proper candidate for study on neural control of cognitive robots and systems as well.

A framework for accelerated phototrophic bioprocess development: integration of parallelized microscale cultivation, laboratory automation and Kriging-assisted experimental design.

PubMed

Morschett, Holger; Freier, Lars; Rohde, Jannis; Wiechert, Wolfgang; von Lieres, Eric; Oldiges, Marco

2017-01-01

Even though microalgae-derived biodiesel has regained interest within the last decade, industrial production is still challenging for economic reasons. Besides reactor design, as well as value chain and strain engineering, laborious and slow early-stage parameter optimization represents a major drawback. The present study introduces a framework for the accelerated development of phototrophic bioprocesses. A state-of-the-art micro-photobioreactor supported by a liquid-handling robot for automated medium preparation and product quantification was used. To take full advantage of the technology's experimental capacity, Kriging-assisted experimental design was integrated to enable highly efficient execution of screening applications. The resulting platform was used for medium optimization of a lipid production process using Chlorella vulgaris toward maximum volumetric productivity. Within only four experimental rounds, lipid production was increased approximately threefold to 212 ± 11 mg L -1  d -1 . Besides nitrogen availability as a key parameter, magnesium, calcium and various trace elements were shown to be of crucial importance. Here, synergistic multi-parameter interactions as revealed by the experimental design introduced significant further optimization potential. The integration of parallelized microscale cultivation, laboratory automation and Kriging-assisted experimental design proved to be a fruitful tool for the accelerated development of phototrophic bioprocesses. By means of the proposed technology, the targeted optimization task was conducted in a very timely and material-efficient manner.

A Hybrid Procedural/Deductive Executive for Autonomous Spacecraft

NASA Technical Reports Server (NTRS)

Pell, Barney; Gamble, Edward B.; Gat, Erann; Kessing, Ron; Kurien, James; Millar, William; Nayak, P. Pandurang; Plaunt, Christian; Williams, Brian C.; Lau, Sonie (Technical Monitor)

1998-01-01

The New Millennium Remote Agent (NMRA) will be the first AI system to control an actual spacecraft. The spacecraft domain places a strong premium on autonomy and requires dynamic recoveries and robust concurrent execution, all in the presence of tight real-time deadlines, changing goals, scarce resource constraints, and a wide variety of possible failures. To achieve this level of execution robustness, we have integrated a procedural executive based on generic procedures with a deductive model-based executive. A procedural executive provides sophisticated control constructs such as loops, parallel activity, locks, and synchronization which are used for robust schedule execution, hierarchical task decomposition, and routine configuration management. A deductive executive provides algorithms for sophisticated state inference and optimal failure recover), planning. The integrated executive enables designers to code knowledge via a combination of procedures and declarative models, yielding a rich modeling capability suitable to the challenges of real spacecraft control. The interface between the two executives ensures both that recovery sequences are smoothly merged into high-level schedule execution and that a high degree of reactivity is retained to effectively handle additional failures during recovery.

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

DOE Office of Scientific and Technical Information (OSTI.GOV)

Arumugam, Kamesh

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore,more » these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.« less

Concurrent simulation of a parallel jaw end effector

NASA Technical Reports Server (NTRS)

Bynum, Bill

1985-01-01

A system of programs developed to aid in the design and development of the command/response protocol between a parallel jaw end effector and the strategic planner program controlling it are presented. The system executes concurrently with the LISP controlling program to generate a graphical image of the end effector that moves in approximately real time in response to commands sent from the controlling program. Concurrent execution of the simulation program is useful for revealing flaws in the communication command structure arising from the asynchronous nature of the message traffic between the end effector and the strategic planner. Software simulation helps to minimize the number of hardware changes necessary to the microprocessor driving the end effector because of changes in the communication protocol. The simulation of other actuator devices can be easily incorporated into the system of programs by using the underlying support that was developed for the concurrent execution of the simulation process and the communication between it and the controlling program.

A conservative approach to parallelizing the Sharks World simulation

NASA Technical Reports Server (NTRS)

Nicol, David M.; Riffe, Scott E.

1990-01-01

Parallelizing a benchmark problem for parallel simulation, the Sharks World, is described. The described solution is conservative, in the sense that no state information is saved, and no 'rollbacks' occur. The used approach illustrates both the principal advantage and principal disadvantage of conservative parallel simulation. The advantage is that by exploiting lookahead an approach was found that dramatically improves the serial execution time, and also achieves excellent speedups. The disadvantage is that if the model rules are changed in such a way that the lookahead is destroyed, it is difficult to modify the solution to accommodate the changes.

Endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface of a parallel computer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Archer, Charles J; Blocksome, Michael A; Cernohous, Bob R

Methods, apparatuses, and computer program products for endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface (`PAMI`) of a parallel computer are provided. Embodiments include establishing by a parallel application a data communications geometry, the geometry specifying a set of endpoints that are used in collective operations of the PAMI, including associating with the geometry a list of collective algorithms valid for use with the endpoints of the geometry. Embodiments also include registering in each endpoint in the geometry a dispatch callback function for a collective operation and executing without blocking, through a single onemore » of the endpoints in the geometry, an instruction for the collective operation.« less

Ffuzz: Towards full system high coverage fuzz testing on binary executables.

PubMed

Zhang, Bin; Ye, Jiaxi; Bi, Xing; Feng, Chao; Tang, Chaojing

2018-01-01

Bugs and vulnerabilities in binary executables threaten cyber security. Current discovery methods, like fuzz testing, symbolic execution and manual analysis, both have advantages and disadvantages when exercising the deeper code area in binary executables to find more bugs. In this paper, we designed and implemented a hybrid automatic bug finding tool-Ffuzz-on top of fuzz testing and selective symbolic execution. It targets full system software stack testing including both the user space and kernel space. Combining these two mainstream techniques enables us to achieve higher coverage and avoid getting stuck both in fuzz testing and symbolic execution. We also proposed two key optimizations to improve the efficiency of full system testing. We evaluated the efficiency and effectiveness of our method on real-world binary software and 844 memory corruption vulnerable programs in the Juliet test suite. The results show that Ffuzz can discover software bugs in the full system software stack effectively and efficiently.

Semantics-based distributed I/O with the ParaMEDIC framework.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Balaji, P.; Feng, W.; Lin, H.

2008-01-01

Many large-scale applications simultaneously rely on multiple resources for efficient execution. For example, such applications may require both large compute and storage resources; however, very few supercomputing centers can provide large quantities of both. Thus, data generated at the compute site oftentimes has to be moved to a remote storage site for either storage or visualization and analysis. Clearly, this is not an efficient model, especially when the two sites are distributed over a wide-area network. Thus, we present a framework called 'ParaMEDIC: Parallel Metadata Environment for Distributed I/O and Computing' which uses application-specific semantic information to convert the generatedmore » data to orders-of-magnitude smaller metadata at the compute site, transfer the metadata to the storage site, and re-process the metadata at the storage site to regenerate the output. Specifically, ParaMEDIC trades a small amount of additional computation (in the form of data post-processing) for a potentially significant reduction in data that needs to be transferred in distributed environments.« less

A Novel Hybrid Firefly Algorithm for Global Optimization.

PubMed

Zhang, Lina; Liu, Liqiang; Yang, Xin-She; Dai, Yuntao

Global optimization is challenging to solve due to its nonlinearity and multimodality. Traditional algorithms such as the gradient-based methods often struggle to deal with such problems and one of the current trends is to use metaheuristic algorithms. In this paper, a novel hybrid population-based global optimization algorithm, called hybrid firefly algorithm (HFA), is proposed by combining the advantages of both the firefly algorithm (FA) and differential evolution (DE). FA and DE are executed in parallel to promote information sharing among the population and thus enhance searching efficiency. In order to evaluate the performance and efficiency of the proposed algorithm, a diverse set of selected benchmark functions are employed and these functions fall into two groups: unimodal and multimodal. The experimental results show better performance of the proposed algorithm compared to the original version of the firefly algorithm (FA), differential evolution (DE) and particle swarm optimization (PSO) in the sense of avoiding local minima and increasing the convergence rate.

A Novel Hybrid Firefly Algorithm for Global Optimization

PubMed Central

Zhang, Lina; Liu, Liqiang; Yang, Xin-She; Dai, Yuntao

2016-01-01

Global optimization is challenging to solve due to its nonlinearity and multimodality. Traditional algorithms such as the gradient-based methods often struggle to deal with such problems and one of the current trends is to use metaheuristic algorithms. In this paper, a novel hybrid population-based global optimization algorithm, called hybrid firefly algorithm (HFA), is proposed by combining the advantages of both the firefly algorithm (FA) and differential evolution (DE). FA and DE are executed in parallel to promote information sharing among the population and thus enhance searching efficiency. In order to evaluate the performance and efficiency of the proposed algorithm, a diverse set of selected benchmark functions are employed and these functions fall into two groups: unimodal and multimodal. The experimental results show better performance of the proposed algorithm compared to the original version of the firefly algorithm (FA), differential evolution (DE) and particle swarm optimization (PSO) in the sense of avoiding local minima and increasing the convergence rate. PMID:27685869

Multitasking a three-dimensional Navier-Stokes algorithm on the Cray-2

NASA Technical Reports Server (NTRS)

Swisshelm, Julie M.

1989-01-01

A three-dimensional computational aerodynamics algorithm has been multitasked for efficient parallel execution on the Cray-2. It provides a means for examining the multitasking performance of a complete CFD application code. An embedded zonal multigrid scheme is used to solve the Reynolds-averaged Navier-Stokes equations for an internal flow model problem. The explicit nature of each component of the method allows a spatial partitioning of the computational domain to achieve a well-balanced task load for MIMD computers with vector-processing capability. Experiments have been conducted with both two- and three-dimensional multitasked cases. The best speedup attained by an individual task group was 3.54 on four processors of the Cray-2, while the entire solver yielded a speedup of 2.67 on four processors for the three-dimensional case. The multiprocessing efficiency of various types of computational tasks is examined, performance on two Cray-2s with different memory access speeds is compared, and extrapolation to larger problems is discussed.

Application Performance Analysis and Efficient Execution on Systems with multi-core CPUs, GPUs and MICs: A Case Study with Microscopy Image Analysis

PubMed Central

Teodoro, George; Kurc, Tahsin; Andrade, Guilherme; Kong, Jun; Ferreira, Renato; Saltz, Joel

2015-01-01

We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core-MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core operations of the application. We correlate the observed performance with the characteristics of computing devices and data access patterns, computation complexities, and parallelization forms of the operations. The results show a significant variability in the performance of operations with respect to the device used. The performances of operations with regular data access are comparable or sometimes better on a MIC than that on a GPU. GPUs are more efficient than MICs for operations that access data irregularly, because of the lower bandwidth of the MIC for random data accesses. We propose new performance-aware scheduling strategies that consider variabilities in operation speedups. Our scheduling strategies significantly improve application performance compared to classic strategies in hybrid configurations. PMID:28239253

Extending molecular simulation time scales: Parallel in time integrations for high-level quantum chemistry and complex force representations

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bylaska, Eric J., E-mail: Eric.Bylaska@pnnl.gov; Weare, Jonathan Q., E-mail: weare@uchicago.edu; Weare, John H., E-mail: jweare@ucsd.edu

2013-08-21

Parallel in time simulation algorithms are presented and applied to conventional molecular dynamics (MD) and ab initio molecular dynamics (AIMD) models of realistic complexity. Assuming that a forward time integrator, f (e.g., Verlet algorithm), is available to propagate the system from time t{sub i} (trajectory positions and velocities x{sub i} = (r{sub i}, v{sub i})) to time t{sub i+1} (x{sub i+1}) by x{sub i+1} = f{sub i}(x{sub i}), the dynamics problem spanning an interval from t{sub 0}…t{sub M} can be transformed into a root finding problem, F(X) = [x{sub i} − f(x{sub (i−1})]{sub i} {sub =1,M} = 0, for themore » trajectory variables. The root finding problem is solved using a variety of root finding techniques, including quasi-Newton and preconditioned quasi-Newton schemes that are all unconditionally convergent. The algorithms are parallelized by assigning a processor to each time-step entry in the columns of F(X). The relation of this approach to other recently proposed parallel in time methods is discussed, and the effectiveness of various approaches to solving the root finding problem is tested. We demonstrate that more efficient dynamical models based on simplified interactions or coarsening time-steps provide preconditioners for the root finding problem. However, for MD and AIMD simulations, such preconditioners are not required to obtain reasonable convergence and their cost must be considered in the performance of the algorithm. The parallel in time algorithms developed are tested by applying them to MD and AIMD simulations of size and complexity similar to those encountered in present day applications. These include a 1000 Si atom MD simulation using Stillinger-Weber potentials, and a HCl + 4H{sub 2}O AIMD simulation at the MP2 level. The maximum speedup ((serial execution time)/(parallel execution time) ) obtained by parallelizing the Stillinger-Weber MD simulation was nearly 3.0. For the AIMD MP2 simulations, the algorithms achieved speedups of up to 14.3. The parallel in time algorithms can be implemented in a distributed computing environment using very slow transmission control protocol/Internet protocol networks. Scripts written in Python that make calls to a precompiled quantum chemistry package (NWChem) are demonstrated to provide an actual speedup of 8.2 for a 2.5 ps AIMD simulation of HCl + 4H{sub 2}O at the MP2/6-31G* level. Implemented in this way these algorithms can be used for long time high-level AIMD simulations at a modest cost using machines connected by very slow networks such as WiFi, or in different time zones connected by the Internet. The algorithms can also be used with programs that are already parallel. Using these algorithms, we are able to reduce the cost of a MP2/6-311++G(2d,2p) simulation that had reached its maximum possible speedup in the parallelization of the electronic structure calculation from 32 s/time step to 6.9 s/time step.« less

Array processor architecture

NASA Technical Reports Server (NTRS)

Barnes, George H. (Inventor); Lundstrom, Stephen F. (Inventor); Shafer, Philip E. (Inventor)

1983-01-01

A high speed parallel array data processing architecture fashioned under a computational envelope approach includes a data base memory for secondary storage of programs and data, and a plurality of memory modules interconnected to a plurality of processing modules by a connection network of the Omega gender. Programs and data are fed from the data base memory to the plurality of memory modules and from hence the programs are fed through the connection network to the array of processors (one copy of each program for each processor). Execution of the programs occur with the processors operating normally quite independently of each other in a multiprocessing fashion. For data dependent operations and other suitable operations, all processors are instructed to finish one given task or program branch before all are instructed to proceed in parallel processing fashion on the next instruction. Even when functioning in the parallel processing mode however, the processors are not locked-step but execute their own copy of the program individually unless or until another overall processor array synchronization instruction is issued.

Automated Performance Prediction of Message-Passing Parallel Programs

NASA Technical Reports Server (NTRS)

Block, Robert J.; Sarukkai, Sekhar; Mehra, Pankaj; Woodrow, Thomas S. (Technical Monitor)

1995-01-01

The increasing use of massively parallel supercomputers to solve large-scale scientific problems has generated a need for tools that can predict scalability trends of applications written for these machines. Much work has been done to create simple models that represent important characteristics of parallel programs, such as latency, network contention, and communication volume. But many of these methods still require substantial manual effort to represent an application in the model's format. The NIK toolkit described in this paper is the result of an on-going effort to automate the formation of analytic expressions of program execution time, with a minimum of programmer assistance. In this paper we demonstrate the feasibility of our approach, by extending previous work to detect and model communication patterns automatically, with and without overlapped computations. The predictions derived from these models agree, within reasonable limits, with execution times of programs measured on the Intel iPSC/860 and Paragon. Further, we demonstrate the use of MK in selecting optimal computational grain size and studying various scalability metrics.

Application of a hybrid MPI/OpenMP approach for parallel groundwater model calibration using multi-core computers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tang, Guoping; D'Azevedo, Ed F; Zhang, Fan

2010-01-01

Calibration of groundwater models involves hundreds to thousands of forward solutions, each of which may solve many transient coupled nonlinear partial differential equations, resulting in a computationally intensive problem. We describe a hybrid MPI/OpenMP approach to exploit two levels of parallelisms in software and hardware to reduce calibration time on multi-core computers. HydroGeoChem 5.0 (HGC5) is parallelized using OpenMP for direct solutions for a reactive transport model application, and a field-scale coupled flow and transport model application. In the reactive transport model, a single parallelizable loop is identified to account for over 97% of the total computational time using GPROF.more » Addition of a few lines of OpenMP compiler directives to the loop yields a speedup of about 10 on a 16-core compute node. For the field-scale model, parallelizable loops in 14 of 174 HGC5 subroutines that require 99% of the execution time are identified. As these loops are parallelized incrementally, the scalability is found to be limited by a loop where Cray PAT detects over 90% cache missing rates. With this loop rewritten, similar speedup as the first application is achieved. The OpenMP-parallelized code can be run efficiently on multiple workstations in a network or multiple compute nodes on a cluster as slaves using parallel PEST to speedup model calibration. To run calibration on clusters as a single task, the Levenberg Marquardt algorithm is added to HGC5 with the Jacobian calculation and lambda search parallelized using MPI. With this hybrid approach, 100 200 compute cores are used to reduce the calibration time from weeks to a few hours for these two applications. This approach is applicable to most of the existing groundwater model codes for many applications.« less

A Hybrid MPI/OpenMP Approach for Parallel Groundwater Model Calibration on Multicore Computers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tang, Guoping; D'Azevedo, Ed F; Zhang, Fan

2010-01-01

Groundwater model calibration is becoming increasingly computationally time intensive. We describe a hybrid MPI/OpenMP approach to exploit two levels of parallelism in software and hardware to reduce calibration time on multicore computers with minimal parallelization effort. At first, HydroGeoChem 5.0 (HGC5) is parallelized using OpenMP for a uranium transport model with over a hundred species involving nearly a hundred reactions, and a field scale coupled flow and transport model. In the first application, a single parallelizable loop is identified to consume over 97% of the total computational time. With a few lines of OpenMP compiler directives inserted into the code,more » the computational time reduces about ten times on a compute node with 16 cores. The performance is further improved by selectively parallelizing a few more loops. For the field scale application, parallelizable loops in 15 of the 174 subroutines in HGC5 are identified to take more than 99% of the execution time. By adding the preconditioned conjugate gradient solver and BICGSTAB, and using a coloring scheme to separate the elements, nodes, and boundary sides, the subroutines for finite element assembly, soil property update, and boundary condition application are parallelized, resulting in a speedup of about 10 on a 16-core compute node. The Levenberg-Marquardt (LM) algorithm is added into HGC5 with the Jacobian calculation and lambda search parallelized using MPI. With this hybrid approach, compute nodes at the number of adjustable parameters (when the forward difference is used for Jacobian approximation), or twice that number (if the center difference is used), are used to reduce the calibration time from days and weeks to a few hours for the two applications. This approach can be extended to global optimization scheme and Monte Carol analysis where thousands of compute nodes can be efficiently utilized.« less

Putting time into proof outlines

NASA Technical Reports Server (NTRS)

Schneider, Fred B.; Bloom, Bard; Marzullo, Keith

1993-01-01

A logic for reasoning about timing properties of concurrent programs is presented. The logic is based on Hoare-style proof outlines and can handle maximal parallelism as well as certain resource-constrained execution environments. The correctness proof for a mutual exclusion protocol that uses execution timings in a subtle way illustrates the logic in action. A soundness proof using structural operational semantics is outlined in the appendix.

Impact of Elevated Core Body Temperature on Attention Networks.

PubMed

Liu, Kai; Jiang, Qingjun; Li, Li; Li, Bo; Yang, Zhen; Qian, Shaowen; Li, Min; Sun, Gang

2015-12-01

Cognitive function can be impaired after passive heat exposure and with an elevation in core body temperature (Tcore). This study examined the dynamic correlation among passive heat exposure, Tcore, and cognition. We gave the Attention Network Test of alerting, orienting, and executive control to five groups of five young men who were being exposed to a hyperthermic condition (50°C, 40% relative humidity) for 0, 10, 20, 30, or 40 minutes. We used the participants' reaction time, accuracy (correct responses), efficiency (accuracy÷reaction time), and Tcore to estimate optimal curve models for best fit of data. We could not estimate an appropriate curve model for either alerting or orienting with Tcore, change in Tcore, or duration of passive heat exposure. We estimated quadratic models for Tcore and duration (adjusted R=0.752), change in Tcore and duration (0.906), executive control score and duration (0.509), and efficiency of executive control and duration (0.293). We estimated linear models for executive control score and Tcore (0.479), efficiency of executive control and Tcore (0.261), executive control score and change in Tcore (0.279), and efficiency of executive control and change in Tcore (0.262). Different attentional abilities had different sensitivities to thermal stress. Executive control of attention deteriorated linearly with a rise in Tcore within the normal physiologic range, but deteriorated nonlinearly with longer passive heat exposure.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Haghighat, A.; Sjoden, G.E.; Wagner, J.C.

In the past 10 yr, the Penn State Transport Theory Group (PSTTG) has concentrated its efforts on developing accurate and efficient particle transport codes to address increasing needs for efficient and accurate simulation of nuclear systems. The PSTTG's efforts have primarily focused on shielding applications that are generally treated using multigroup, multidimensional, discrete ordinates (S{sub n}) deterministic and/or statistical Monte Carlo methods. The difficulty with the existing public codes is that they require significant (impractical) computation time for simulation of complex three-dimensional (3-D) problems. For the S{sub n} codes, the large memory requirements are handled through the use of scratchmore » files (i.e., read-from and write-to-disk) that significantly increases the necessary execution time. Further, the lack of flexible features and/or utilities for preparing input and processing output makes these codes difficult to use. The Monte Carlo method becomes impractical because variance reduction (VR) methods have to be used, and normally determination of the necessary parameters for the VR methods is very difficult and time consuming for a complex 3-D problem. For the deterministic method, the authors have developed the 3-D parallel PENTRAN (Parallel Environment Neutral-particle TRANsport) code system that, in addition to a parallel 3-D S{sub n} solver, includes pre- and postprocessing utilities. PENTRAN provides for full phase-space decomposition, memory partitioning, and parallel input/output to provide the capability of solving large problems in a relatively short time. Besides having a modular parallel structure, PENTRAN has several unique new formulations and features that are necessary for achieving high parallel performance. For the Monte Carlo method, the major difficulty currently facing most users is the selection of an effective VR method and its associated parameters. For complex problems, generally, this process is very time consuming and may be complicated due to the possibility of biasing the results. In an attempt to eliminate this problem, the authors have developed the A{sup 3}MCNP (automated adjoint accelerated MCNP) code that automatically prepares parameters for source and transport biasing within a weight-window VR approach based on the S{sub n} adjoint function. A{sup 3}MCNP prepares the necessary input files for performing multigroup, 3-D adjoint S{sub n} calculations using TORT.« less

A Multi-Level Parallelization Concept for High-Fidelity Multi-Block Solvers

NASA Technical Reports Server (NTRS)

Hatay, Ferhat F.; Jespersen, Dennis C.; Guruswamy, Guru P.; Rizk, Yehia M.; Byun, Chansup; Gee, Ken; VanDalsem, William R. (Technical Monitor)

1997-01-01

The integration of high-fidelity Computational Fluid Dynamics (CFD) analysis tools with the industrial design process benefits greatly from the robust implementations that are transportable across a wide range of computer architectures. In the present work, a hybrid domain-decomposition and parallelization concept was developed and implemented into the widely-used NASA multi-block Computational Fluid Dynamics (CFD) packages implemented in ENSAERO and OVERFLOW. The new parallel solver concept, PENS (Parallel Euler Navier-Stokes Solver), employs both fine and coarse granularity in data partitioning as well as data coalescing to obtain the desired load-balance characteristics on the available computer platforms. This multi-level parallelism implementation itself introduces no changes to the numerical results, hence the original fidelity of the packages are identically preserved. The present implementation uses the Message Passing Interface (MPI) library for interprocessor message passing and memory accessing. By choosing an appropriate combination of the available partitioning and coalescing capabilities only during the execution stage, the PENS solver becomes adaptable to different computer architectures from shared-memory to distributed-memory platforms with varying degrees of parallelism. The PENS implementation on the IBM SP2 distributed memory environment at the NASA Ames Research Center obtains 85 percent scalable parallel performance using fine-grain partitioning of single-block CFD domains using up to 128 wide computational nodes. Multi-block CFD simulations of complete aircraft simulations achieve 75 percent perfect load-balanced executions using data coalescing and the two levels of parallelism. SGI PowerChallenge, SGI Origin 2000, and a cluster of workstations are the other platforms where the robustness of the implementation is tested. The performance behavior on the other computer platforms with a variety of realistic problems will be included as this on-going study progresses.

Decision-Tree Formulation With Order-1 Lateral Execution

NASA Technical Reports Server (NTRS)

James, Mark

2007-01-01

A compact symbolic formulation enables mapping of an arbitrarily complex decision tree of a certain type into a highly computationally efficient multidimensional software object. The type of decision trees to which this formulation applies is that known in the art as the Boolean class of balanced decision trees. Parallel lateral slices of an object created by means of this formulation can be executed in constant time considerably less time than would otherwise be required. Decision trees of various forms are incorporated into almost all large software systems. A decision tree is a way of hierarchically solving a problem, proceeding through a set of true/false responses to a conclusion. By definition, a decision tree has a tree-like structure, wherein each internal node denotes a test on an attribute, each branch from an internal node represents an outcome of a test, and leaf nodes represent classes or class distributions that, in turn represent possible conclusions. The drawback of decision trees is that execution of them can be computationally expensive (and, hence, time-consuming) because each non-leaf node must be examined to determine whether to progress deeper into a tree structure or to examine an alternative. The present formulation was conceived as an efficient means of representing a decision tree and executing it in as little time as possible. The formulation involves the use of a set of symbolic algorithms to transform a decision tree into a multi-dimensional object, the rank of which equals the number of lateral non-leaf nodes. The tree can then be executed in constant time by means of an order-one table lookup. The sequence of operations performed by the algorithms is summarized as follows: 1. Determination of whether the tree under consideration can be encoded by means of this formulation. 2. Extraction of decision variables. 3. Symbolic optimization of the decision tree to minimize its form. 4. Expansion and transformation of all nested conjunctive-disjunctive paths to a flattened conjunctive form composed only of equality checks when possible. If each reduced conjunctive form contains only equality checks and all of these forms use the same variables, then the decision tree can be reduced to an order-one operation through a table lookup. The speedup to order one is accomplished by distributing each decision variable over a surface of a multidimensional object by mapping the equality constant to an index

Vectorized and multitasked solution of the few-group neutron diffusion equations

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zee, S.K.; Turinsky, P.J.; Shayer, Z.

1989-03-01

A numerical algorithm with parallelism was used to solve the two-group, multidimensional neutron diffusion equations on computers characterized by shared memory, vector pipeline, and multi-CPU architecture features. Specifically, solutions were obtained on the Cray X/MP-48, the IBM-3090 with vector facilities, and the FPS-164. The material-centered mesh finite difference method approximation and outer-inner iteration method were employed. Parallelism was introduced in the inner iterations using the cyclic line successive overrelaxation iterative method and solving in parallel across lines. The outer iterations were completed using the Chebyshev semi-iterative method that allows parallelism to be introduced in both space and energy groups. Formore » the three-dimensional model, power, soluble boron, and transient fission product feedbacks were included. Concentrating on the pressurized water reactor (PWR), the thermal-hydraulic calculation of moderator density assumed single-phase flow and a closed flow channel, allowing parallelism to be introduced in the solution across the radial plane. Using a pinwise detail, quarter-core model of a typical PWR in cycle 1, for the two-dimensional model without feedback the measured million floating point operations per second (MFLOPS)/vector speedups were 83/11.7. 18/2.2, and 2.4/5.6 on the Cray, IBM, and FPS without multitasking, respectively. Lower performance was observed with a coarser mesh, i.e., shorter vector length, due to vector pipeline start-up. For an 18 x 18 x 30 (x-y-z) three-dimensional model with feedback of the same core, MFLOPS/vector speedups of --61/6.7 and an execution time of 0.8 CPU seconds on the Cray without multitasking were measured. Finally, using two CPUs and the vector pipelines of the Cray, a multitasking efficiency of 81% was noted for the three-dimensional model.« less

Accelerating Wright–Fisher Forward Simulations on the Graphics Processing Unit

PubMed Central

Lawrie, David S.

2017-01-01

Forward Wright–Fisher simulations are powerful in their ability to model complex demography and selection scenarios, but suffer from slow execution on the Central Processor Unit (CPU), thus limiting their usefulness. However, the single-locus Wright–Fisher forward algorithm is exceedingly parallelizable, with many steps that are so-called “embarrassingly parallel,” consisting of a vast number of individual computations that are all independent of each other and thus capable of being performed concurrently. The rise of modern Graphics Processing Units (GPUs) and programming languages designed to leverage the inherent parallel nature of these processors have allowed researchers to dramatically speed up many programs that have such high arithmetic intensity and intrinsic concurrency. The presented GPU Optimized Wright–Fisher simulation, or “GO Fish” for short, can be used to simulate arbitrary selection and demographic scenarios while running over 250-fold faster than its serial counterpart on the CPU. Even modest GPU hardware can achieve an impressive speedup of over two orders of magnitude. With simulations so accelerated, one can not only do quick parametric bootstrapping of previously estimated parameters, but also use simulated results to calculate the likelihoods and summary statistics of demographic and selection models against real polymorphism data, all without restricting the demographic and selection scenarios that can be modeled or requiring approximations to the single-locus forward algorithm for efficiency. Further, as many of the parallel programming techniques used in this simulation can be applied to other computationally intensive algorithms important in population genetics, GO Fish serves as an exciting template for future research into accelerating computation in evolution. GO Fish is part of the Parallel PopGen Package available at: http://dl42.github.io/ParallelPopGen/. PMID:28768689

An Integrated Approach to Locality-Conscious Processor Allocation and Scheduling of Mixed-Parallel Applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Vydyanathan, Naga; Krishnamoorthy, Sriram; Sabin, Gerald M.

2009-08-01

Complex parallel applications can often be modeled as directed acyclic graphs of coarse-grained application-tasks with dependences. These applications exhibit both task- and data-parallelism, and combining these two (also called mixedparallelism), has been shown to be an effective model for their execution. In this paper, we present an algorithm to compute the appropriate mix of task- and data-parallelism required to minimize the parallel completion time (makespan) of these applications. In other words, our algorithm determines the set of tasks that should be run concurrently and the number of processors to be allocated to each task. The processor allocation and scheduling decisionsmore » are made in an integrated manner and are based on several factors such as the structure of the taskgraph, the runtime estimates and scalability characteristics of the tasks and the inter-task data communication volumes. A locality conscious scheduling strategy is used to improve inter-task data reuse. Evaluation through simulations and actual executions of task graphs derived from real applications as well as synthetic graphs shows that our algorithm consistently generates schedules with lower makespan as compared to CPR and CPA, two previously proposed scheduling algorithms. Our algorithm also produces schedules that have lower makespan than pure taskand data-parallel schedules. For task graphs with known optimal schedules or lower bounds on the makespan, our algorithm generates schedules that are closer to the optima than other scheduling approaches.« less

76 FR 57956 - Renewable Energy and Energy Efficiency Executive Business Development Mission; Clarification and...

Federal Register 2010, 2011, 2012, 2013, 2014

2011-09-19

... DEPARTMENT OF COMMERCE International Trade Administration Renewable Energy and Energy Efficiency... the Notice of the Renewable Energy and Energy Efficiency Executive Business Development Mission, 76 FR... U.S. renewable energy firms and trade organizations which have not already submitted an application...

Large-Scale Distributed Computational Fluid Dynamics on the Information Power Grid Using Globus

NASA Technical Reports Server (NTRS)

Barnard, Stephen; Biswas, Rupak; Saini, Subhash; VanderWijngaart, Robertus; Yarrow, Maurice; Zechtzer, Lou; Foster, Ian; Larsson, Olle

1999-01-01

This paper describes an experiment in which a large-scale scientific application development for tightly-coupled parallel machines is adapted to the distributed execution environment of the Information Power Grid (IPG). A brief overview of the IPG and a description of the computational fluid dynamics (CFD) algorithm are given. The Globus metacomputing toolkit is used as the enabling device for the geographically-distributed computation. Modifications related to latency hiding and Load balancing were required for an efficient implementation of the CFD application in the IPG environment. Performance results on a pair of SGI Origin 2000 machines indicate that real scientific applications can be effectively implemented on the IPG; however, a significant amount of continued effort is required to make such an environment useful and accessible to scientists and engineers.

Advancements in RNASeqGUI towards a Reproducible Analysis of RNA-Seq Experiments

PubMed Central

Russo, Francesco; Righelli, Dario

2016-01-01

We present the advancements and novelties recently introduced in RNASeqGUI, a graphical user interface that helps biologists to handle and analyse large data collected in RNA-Seq experiments. This work focuses on the concept of reproducible research and shows how it has been incorporated in RNASeqGUI to provide reproducible (computational) results. The novel version of RNASeqGUI combines graphical interfaces with tools for reproducible research, such as literate statistical programming, human readable report, parallel executions, caching, and interactive and web-explorable tables of results. These features allow the user to analyse big datasets in a fast, efficient, and reproducible way. Moreover, this paper represents a proof of concept, showing a simple way to develop computational tools for Life Science in the spirit of reproducible research. PMID:26977414

The BLAZE language: A parallel language for scientific programming

NASA Technical Reports Server (NTRS)

Mehrotra, P.; Vanrosendale, J.

1985-01-01

A Pascal-like scientific programming language, Blaze, is described. Blaze contains array arithmetic, forall loops, and APL-style accumulation operators, which allow natural expression of fine grained parallelism. It also employs an applicative or functional procedure invocation mechanism, which makes it easy for compilers to extract coarse grained parallelism using machine specific program restructuring. Thus Blaze should allow one to achieve highly parallel execution on multiprocessor architectures, while still providing the user with onceptually sequential control flow. A central goal in the design of Blaze is portability across a broad range of parallel architectures. The multiple levels of parallelism present in Blaze code, in principle, allow a compiler to extract the types of parallelism appropriate for the given architecture while neglecting the remainder. The features of Blaze are described and shows how this language would be used in typical scientific programming.

Detecting opportunities for parallel observations on the Hubble Space Telescope

NASA Technical Reports Server (NTRS)

Lucks, Michael

1992-01-01

The presence of multiple scientific instruments aboard the Hubble Space Telescope provides opportunities for parallel science, i.e., the simultaneous use of different instruments for different observations. Determining whether candidate observations are suitable for parallel execution depends on numerous criteria (some involving quantitative tradeoffs) that may change frequently. A knowledge based approach is presented for constructing a scoring function to rank candidate pairs of observations for parallel science. In the Parallel Observation Matching System (POMS), spacecraft knowledge and schedulers' preferences are represented using a uniform set of mappings, or knowledge functions. Assessment of parallel science opportunities is achieved via composition of the knowledge functions in a prescribed manner. The knowledge acquisition, and explanation facilities of the system are presented. The methodology is applicable to many other multiple criteria assessment problems.

Communications oriented programming of parallel iterative solutions of sparse linear systems

NASA Technical Reports Server (NTRS)

Patrick, M. L.; Pratt, T. W.

1986-01-01

Parallel algorithms are developed for a class of scientific computational problems by partitioning the problems into smaller problems which may be solved concurrently. The effectiveness of the resulting parallel solutions is determined by the amount and frequency of communication and synchronization and the extent to which communication can be overlapped with computation. Three different parallel algorithms for solving the same class of problems are presented, and their effectiveness is analyzed from this point of view. The algorithms are programmed using a new programming environment. Run-time statistics and experience obtained from the execution of these programs assist in measuring the effectiveness of these algorithms.

An Adaptive Memory Interface Controller for Improving Bandwidth Utilization of Hybrid and Reconfigurable Systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Castellana, Vito G.; Tumeo, Antonino; Ferrandi, Fabrizio

Emerging applications such as data mining, bioinformatics, knowledge discovery, social network analysis are irregular. They use data structures based on pointers or linked lists, such as graphs, unbalanced trees or unstructures grids, which generates unpredictable memory accesses. These data structures usually are large, but difficult to partition. These applications mostly are memory bandwidth bounded and have high synchronization intensity. However, they also have large amounts of inherent dynamic parallelism, because they potentially perform a task for each one of the element they are exploring. Several efforts are looking at accelerating these applications on hybrid architectures, which integrate general purpose processorsmore » with reconfigurable devices. Some solutions, which demonstrated significant speedups, include custom-hand tuned accelerators or even full processor architectures on the reconfigurable logic. In this paper we present an approach for the automatic synthesis of accelerators from C, targeted at irregular applications. In contrast to typical High Level Synthesis paradigms, which construct a centralized Finite State Machine, our approach generates dynamically scheduled hardware components. While parallelism exploitation in typical HLS-generated accelerators is usually bound within a single execution flow, our solution allows concurrently running multiple execution flow, thus also exploiting the coarser grain task parallelism of irregular applications. Our approach supports multiple, multi-ported and distributed memories, and atomic memory operations. Its main objective is parallelizing as many memory operations as possible, independently from their execution time, to maximize the memory bandwidth utilization. This significantly differs from current HLS flows, which usually consider a single memory port and require precise scheduling of memory operations. A key innovation of our approach is the generation of a memory interface controller, which dynamically maps concurrent memory accesses to multiple ports. We present a case study on a typical irregular kernel, Graph Breadth First search (BFS), exploring different tradeoffs in terms of parallelism and number of memories.« less

Scalable Triadic Analysis of Large-Scale Graphs: Multi-Core vs. Multi-Processor vs. Multi-Threaded Shared Memory Architectures

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chin, George; Marquez, Andres; Choudhury, Sutanay

2012-09-01

Triadic analysis encompasses a useful set of graph mining methods that is centered on the concept of a triad, which is a subgraph of three nodes and the configuration of directed edges across the nodes. Such methods are often applied in the social sciences as well as many other diverse fields. Triadic methods commonly operate on a triad census that counts the number of triads of every possible edge configuration in a graph. Like other graph algorithms, triadic census algorithms do not scale well when graphs reach tens of millions to billions of nodes. To enable the triadic analysis ofmore » large-scale graphs, we developed and optimized a triad census algorithm to efficiently execute on shared memory architectures. We will retrace the development and evolution of a parallel triad census algorithm. Over the course of several versions, we continually adapted the code’s data structures and program logic to expose more opportunities to exploit parallelism on shared memory that would translate into improved computational performance. We will recall the critical steps and modifications that occurred during code development and optimization. Furthermore, we will compare the performances of triad census algorithm versions on three specific systems: Cray XMT, HP Superdome, and AMD multi-core NUMA machine. These three systems have shared memory architectures but with markedly different hardware capabilities to manage parallelism.« less

The novel implicit LU-SGS parallel iterative method based on the diffusion equation of a nuclear reactor on a GPU cluster

NASA Astrophysics Data System (ADS)

Zhang, Jilin; Sha, Chaoqun; Wu, Yusen; Wan, Jian; Zhou, Li; Ren, Yongjian; Si, Huayou; Yin, Yuyu; Jing, Ya

2017-02-01

GPU not only is used in the field of graphic technology but also has been widely used in areas needing a large number of numerical calculations. In the energy industry, because of low carbon, high energy density, high duration and other characteristics, the development of nuclear energy cannot easily be replaced by other energy sources. Management of core fuel is one of the major areas of concern in a nuclear power plant, and it is directly related to the economic benefits and cost of nuclear power. The large-scale reactor core expansion equation is large and complicated, so the calculation of the diffusion equation is crucial in the core fuel management process. In this paper, we use CUDA programming technology on a GPU cluster to run the LU-SGS parallel iterative calculation against the background of the diffusion equation of the reactor. We divide one-dimensional and two-dimensional mesh into a plurality of domains, with each domain evenly distributed on the GPU blocks. A parallel collision scheme is put forward that defines the virtual boundary of the grid exchange information and data transmission by non-stop collision. Compared with the serial program, the experiment shows that GPU greatly improves the efficiency of program execution and verifies that GPU is playing a much more important role in the field of numerical calculations.

Porting Ordinary Applications to Blue Gene/Q Supercomputers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Maheshwari, Ketan C.; Wozniak, Justin M.; Armstrong, Timothy

2015-08-31

Efficiently porting ordinary applications to Blue Gene/Q supercomputers is a significant challenge. Codes are often originally developed without considering advanced architectures and related tool chains. Science needs frequently lead users to want to run large numbers of relatively small jobs (often called many-task computing, an ensemble, or a workflow), which can conflict with supercomputer configurations. In this paper, we discuss techniques developed to execute ordinary applications over leadership class supercomputers. We use the high-performance Swift parallel scripting framework and build two workflow execution techniques-sub-jobs and main-wrap. The sub-jobs technique, built on top of the IBM Blue Gene/Q resource manager Cobalt'smore » sub-block jobs, lets users submit multiple, independent, repeated smaller jobs within a single larger resource block. The main-wrap technique is a scheme that enables C/C++ programs to be defined as functions that are wrapped by a high-performance Swift wrapper and that are invoked as a Swift script. We discuss the needs, benefits, technicalities, and current limitations of these techniques. We further discuss the real-world science enabled by these techniques and the results obtained.« less

CMS Readiness for Multi-Core Workload Scheduling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perez-Calero Yzquierdo, A.; Balcas, J.; Hernandez, J.

In the present run of the LHC, CMS data reconstruction and simulation algorithms benefit greatly from being executed as multiple threads running on several processor cores. The complexity of the Run 2 events requires parallelization of the code to reduce the memory-per- core footprint constraining serial execution programs, thus optimizing the exploitation of present multi-core processor architectures. The allocation of computing resources for multi-core tasks, however, becomes a complex problem in itself. The CMS workload submission infrastructure employs multi-slot partitionable pilots, built on HTCondor and GlideinWMS native features, to enable scheduling of single and multi-core jobs simultaneously. This provides amore » solution for the scheduling problem in a uniform way across grid sites running a diversity of gateways to compute resources and batch system technologies. This paper presents this strategy and the tools on which it has been implemented. The experience of managing multi-core resources at the Tier-0 and Tier-1 sites during 2015, along with the deployment phase to Tier-2 sites during early 2016 is reported. The process of performance monitoring and optimization to achieve efficient and flexible use of the resources is also described.« less

CMS readiness for multi-core workload scheduling

NASA Astrophysics Data System (ADS)

Perez-Calero Yzquierdo, A.; Balcas, J.; Hernandez, J.; Aftab Khan, F.; Letts, J.; Mason, D.; Verguilov, V.

2017-10-01

In the present run of the LHC, CMS data reconstruction and simulation algorithms benefit greatly from being executed as multiple threads running on several processor cores. The complexity of the Run 2 events requires parallelization of the code to reduce the memory-per- core footprint constraining serial execution programs, thus optimizing the exploitation of present multi-core processor architectures. The allocation of computing resources for multi-core tasks, however, becomes a complex problem in itself. The CMS workload submission infrastructure employs multi-slot partitionable pilots, built on HTCondor and GlideinWMS native features, to enable scheduling of single and multi-core jobs simultaneously. This provides a solution for the scheduling problem in a uniform way across grid sites running a diversity of gateways to compute resources and batch system technologies. This paper presents this strategy and the tools on which it has been implemented. The experience of managing multi-core resources at the Tier-0 and Tier-1 sites during 2015, along with the deployment phase to Tier-2 sites during early 2016 is reported. The process of performance monitoring and optimization to achieve efficient and flexible use of the resources is also described.

Ffuzz: Towards full system high coverage fuzz testing on binary executables

PubMed Central

2018-01-01

Bugs and vulnerabilities in binary executables threaten cyber security. Current discovery methods, like fuzz testing, symbolic execution and manual analysis, both have advantages and disadvantages when exercising the deeper code area in binary executables to find more bugs. In this paper, we designed and implemented a hybrid automatic bug finding tool—Ffuzz—on top of fuzz testing and selective symbolic execution. It targets full system software stack testing including both the user space and kernel space. Combining these two mainstream techniques enables us to achieve higher coverage and avoid getting stuck both in fuzz testing and symbolic execution. We also proposed two key optimizations to improve the efficiency of full system testing. We evaluated the efficiency and effectiveness of our method on real-world binary software and 844 memory corruption vulnerable programs in the Juliet test suite. The results show that Ffuzz can discover software bugs in the full system software stack effectively and efficiently. PMID:29791469

spammpack, Version 2013-06-18

DOE Office of Scientific and Technical Information (OSTI.GOV)

2014-01-17

This library is an implementation of the Sparse Approximate Matrix Multiplication (SpAMM) algorithm introduced. It provides a matrix data type, and an approximate matrix product, which exhibits linear scaling computational complexity for matrices with decay. The product error and the performance of the multiply can be tuned by choosing an appropriate tolerance. The library can be compiled for serial execution or parallel execution on shared memory systems with an OpenMP capable compiler

FX-87 performance measurements: data-flow implementation. Technical report

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hammel, R.T.; Gifford, D.K.

1988-11-01

This report documents a series of experiments performed to explore the thesis that the FX-87 effect system permits a compiler to schedule imperative programs (i.e., programs that may contain side-effects) for execution on a parallel computer. The authors analyze how much the FX-87 static effect system can improve the execution times of five benchmark programs on a parallel graph interpreter. Three of their benchmark programs do not use side-effects (factorial, fibonacci, and polynomial division) and thus did not have any effect-induced constraints. Their FX-87 performance was comparable to their performance in a purely functional language. Two of the benchmark programsmore » use side effects (DNA sequence matching and Scheme interpretation) and the compiler was able to use effect information to reduce their execution times by factors of 1.7 to 5.4 when compared with sequential execution times. These results support the thesis that a static effect system is a powerful tool for compilation to multiprocessor computers. However, the graph interpreter we used was based on unrealistic assumptions, and thus our results may not accurately reflect the performance of a practical FX-87 implementation. The results also suggest that conventional loop analysis would complement the FX-87 effect system« less

Concepts of Concurrent Programming

DTIC Science & Technology

1990-04-01

to the material presented. Carriero89 Carriero, N., and Gelernter, D. " How to Write Parallel Programs : A Guide to the Perplexed." ACM...between the architectures on which programs can be executed and the application domains from which problems are drawn. Our goal is to show how programs ...Sept. 1989), 251-510. Abstract: There are four papers: 1. Programming Languages for Distributed Computing Systems (52); 2. How to Write Parallel

Automatic Adaptation of Tunable Distributed Applications

DTIC Science & Technology

2001-01-01

size, weight, and battery life, with a single CPU, less memory, smaller hard disk, and lower bandwidth network connectivity. The power of PDAs is...wireless, and bluetooth [32] facilities; thus achieving different rates of data transmission. 1 With the trend of “write once, run everywhere...applications, a single component can execute on multiple processors (or machines) in parallel. These parallel applications, written in a specialized language

Collective communications apparatus and method for parallel systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Knies, Allan D.; Keppel, David Pardo; Woo, Dong Hyuk

A collective communication apparatus and method for parallel computing systems. For example, one embodiment of an apparatus comprises a plurality of processor elements (PEs); collective interconnect logic to dynamically form a virtual collective interconnect (VCI) between the PEs at runtime without global communication among all of the PEs, the VCI defining a logical topology between the PEs in which each PE is directly communicatively coupled to a only a subset of the remaining PEs; and execution logic to execute collective operations across the PEs, wherein one or more of the PEs receive first results from a first portion of themore » subset of the remaining PEs, perform a portion of the collective operations, and provide second results to a second portion of the subset of the remaining PEs.« less

Chip architecture - A revolution brewing

NASA Astrophysics Data System (ADS)

Guterl, F.

1983-07-01

Techniques being explored by microchip designers and manufacturers to both speed up memory access and instruction execution while protecting memory are discussed. Attention is given to hardwiring control logic, pipelining for parallel processing, devising orthogonal instruction sets for interchangeable instruction fields, and the development of hardware for implementation of virtual memory and multiuser systems to provide memory management and protection. The inclusion of microcode in mainframes eliminated logic circuits that control timing and gating of the CPU. However, improvements in memory architecture have reduced access time to below that needed for instruction execution. Hardwiring the functions as a virtual memory enhances memory protection. Parallelism involves a redundant architecture, which allows identical operations to be performed simultaneously, and can be directed with microcode to avoid abortion of intermediate instructions once on set of instructions has been completed.

Japanese project aims at supercomputer that executes 10 gflops

DOE Office of Scientific and Technical Information (OSTI.GOV)

Burskey, D.

1984-05-03

Dubbed supercom by its multicompany design team, the decade-long project's goal is an engineering supercomputer that can execute 10 billion floating-point operations/s-about 20 times faster than today's supercomputers. The project, guided by Japan's Ministry of International Trade and Industry (MITI) and the Agency of Industrial Science and Technology encompasses three parallel research programs, all aimed at some angle of the superconductor. One program should lead to superfast logic and memory circuits, another to a system architecture that will afford the best performance, and the last to the software that will ultimately control the computer. The work on logic and memorymore » chips is based on: GAAS circuit; Josephson junction devices; and high electron mobility transistor structures. The architecture will involve parallel processing.« less

PRAIS: Distributed, real-time knowledge-based systems made easy

NASA Technical Reports Server (NTRS)

Goldstein, David G.

1990-01-01

This paper discusses an architecture for real-time, distributed (parallel) knowledge-based systems called the Parallel Real-time Artificial Intelligence System (PRAIS). PRAIS strives for transparently parallelizing production (rule-based) systems, even when under real-time constraints. PRAIS accomplishes these goals by incorporating a dynamic task scheduler, operating system extensions for fact handling, and message-passing among multiple copies of CLIPS executing on a virtual blackboard. This distributed knowledge-based system tool uses the portability of CLIPS and common message-passing protocols to operate over a heterogeneous network of processors.

Trace-Driven Debugging of Message Passing Programs

NASA Technical Reports Server (NTRS)

Frumkin, Michael; Hood, Robert; Lopez, Louis; Bailey, David (Technical Monitor)

1998-01-01

In this paper we report on features added to a parallel debugger to simplify the debugging of parallel message passing programs. These features include replay, setting consistent breakpoints based on interprocess event causality, a parallel undo operation, and communication supervision. These features all use trace information collected during the execution of the program being debugged. We used a number of different instrumentation techniques to collect traces. We also implemented trace displays using two different trace visualization systems. The implementation was tested on an SGI Power Challenge cluster and a network of SGI workstations.

Execution of parallel algorithms on a heterogeneous multicomputer

NASA Astrophysics Data System (ADS)

Isenstein, Barry S.; Greene, Jonathon

1995-04-01

Many aerospace/defense sensing and dual-use applications require high-performance computing, extensive high-bandwidth interconnect and realtime deterministic operation. This paper will describe the architecture of a scalable multicomputer that includes DSP and RISC processors. A single chassis implementation is capable of delivering in excess of 10 GFLOPS of DSP processing power with 2 Gbytes/s of realtime sensor I/O. A software approach to implementing parallel algorithms called the Parallel Application System (PAS) is also presented. An example of applying PAS to a DSP application is shown.

A new scheduling algorithm for parallel sparse LU factorization with static pivoting

DOE Office of Scientific and Technical Information (OSTI.GOV)

Grigori, Laura; Li, Xiaoye S.

2002-08-20

In this paper we present a static scheduling algorithm for parallel sparse LU factorization with static pivoting. The algorithm is divided into mapping and scheduling phases, using the symmetric pruned graphs of L' and U to represent dependencies. The scheduling algorithm is designed for driving the parallel execution of the factorization on a distributed-memory architecture. Experimental results and comparisons with SuperLU{_}DIST are reported after applying this algorithm on real world application matrices on an IBM SP RS/6000 distributed memory machine.

Parallel Alterations of Functional Connectivity during Execution and Imagination after Motor Imagery Learning

PubMed Central

Zhang, Rushao; Hui, Mingqi; Long, Zhiying; Zhao, Xiaojie; Yao, Li

2012-01-01

Background Neural substrates underlying motor learning have been widely investigated with neuroimaging technologies. Investigations have illustrated the critical regions of motor learning and further revealed parallel alterations of functional activation during imagination and execution after learning. However, little is known about the functional connectivity associated with motor learning, especially motor imagery learning, although benefits from functional connectivity analysis attract more attention to the related explorations. We explored whether motor imagery (MI) and motor execution (ME) shared parallel alterations of functional connectivity after MI learning. Methodology/Principal Findings Graph theory analysis, which is widely used in functional connectivity exploration, was performed on the functional magnetic resonance imaging (fMRI) data of MI and ME tasks before and after 14 days of consecutive MI learning. The control group had no learning. Two measures, connectivity degree and interregional connectivity, were calculated and further assessed at a statistical level. Two interesting results were obtained: (1) The connectivity degree of the right posterior parietal lobe decreased in both MI and ME tasks after MI learning in the experimental group; (2) The parallel alterations of interregional connectivity related to the right posterior parietal lobe occurred in the supplementary motor area for both tasks. Conclusions/Significance These computational results may provide the following insights: (1) The establishment of motor schema through MI learning may induce the significant decrease of connectivity degree in the posterior parietal lobe; (2) The decreased interregional connectivity between the supplementary motor area and the right posterior parietal lobe in post-test implicates the dissociation between motor learning and task performing. These findings and explanations further revealed the neural substrates underpinning MI learning and supported that the potential value of MI learning in motor function rehabilitation and motor skill learning deserves more attention and further investigation. PMID:22629308

Parallel CE/SE Computations via Domain Decomposition

NASA Technical Reports Server (NTRS)

Himansu, Ananda; Jorgenson, Philip C. E.; Wang, Xiao-Yen; Chang, Sin-Chung

2000-01-01

This paper describes the parallelization strategy and achieved parallel efficiency of an explicit time-marching algorithm for solving conservation laws. The Space-Time Conservation Element and Solution Element (CE/SE) algorithm for solving the 2D and 3D Euler equations is parallelized with the aid of domain decomposition. The parallel efficiency of the resultant algorithm on a Silicon Graphics Origin 2000 parallel computer is checked.

Use of general purpose graphics processing units with MODFLOW

USGS Publications Warehouse

Hughes, Joseph D.; White, Jeremy T.

2013-01-01

To evaluate the use of general-purpose graphics processing units (GPGPUs) to improve the performance of MODFLOW, an unstructured preconditioned conjugate gradient (UPCG) solver has been developed. The UPCG solver uses a compressed sparse row storage scheme and includes Jacobi, zero fill-in incomplete, and modified-incomplete lower-upper (LU) factorization, and generalized least-squares polynomial preconditioners. The UPCG solver also includes options for sequential and parallel solution on the central processing unit (CPU) using OpenMP. For simulations utilizing the GPGPU, all basic linear algebra operations are performed on the GPGPU; memory copies between the central processing unit CPU and GPCPU occur prior to the first iteration of the UPCG solver and after satisfying head and flow criteria or exceeding a maximum number of iterations. The efficiency of the UPCG solver for GPGPU and CPU solutions is benchmarked using simulations of a synthetic, heterogeneous unconfined aquifer with tens of thousands to millions of active grid cells. Testing indicates GPGPU speedups on the order of 2 to 8, relative to the standard MODFLOW preconditioned conjugate gradient (PCG) solver, can be achieved when (1) memory copies between the CPU and GPGPU are optimized, (2) the percentage of time performing memory copies between the CPU and GPGPU is small relative to the calculation time, (3) high-performance GPGPU cards are utilized, and (4) CPU-GPGPU combinations are used to execute sequential operations that are difficult to parallelize. Furthermore, UPCG solver testing indicates GPGPU speedups exceed parallel CPU speedups achieved using OpenMP on multicore CPUs for preconditioners that can be easily parallelized.

Ensemble Smoother implemented in parallel for groundwater problems applications

NASA Astrophysics Data System (ADS)

Leyva, E.; Herrera, G. S.; de la Cruz, L. M.

2013-05-01

Data assimilation is a process that links forecasting models and measurements using the benefits from both sources. The Ensemble Kalman Filter (EnKF) is a data-assimilation sequential-method that was designed to address two of the main problems related to the use of the Extended Kalman Filter (EKF) with nonlinear models in large state spaces, i-e the use of a closure problem and massive computational requirements associated with the storage and subsequent integration of the error covariance matrix. The EnKF has gained popularity because of its simple conceptual formulation and relative ease of implementation. It has been used successfully in various applications of meteorology and oceanography and more recently in petroleum engineering and hydrogeology. The Ensemble Smoother (ES) is a method similar to EnKF, it was proposed by Van Leeuwen and Evensen (1996). Herrera (1998) proposed a version of the ES which we call Ensemble Smoother of Herrera (ESH) to distinguish it from the former. It was introduced for space-time optimization of groundwater monitoring networks. In recent years, this method has been used for data assimilation and parameter estimation in groundwater flow and transport models. The ES method uses Monte Carlo simulation, which consists of generating repeated realizations of the random variable considered, using a flow and transport model. However, often a large number of model runs are required for the moments of the variable to converge. Therefore, depending on the complexity of problem a serial computer may require many hours of continuous use to apply the ES. For this reason, it is required to parallelize the process in order to do it in a reasonable time. In this work we present the results of a parallelization strategy to reduce the execution time for doing a high number of realizations. The software GWQMonitor by Herrera (1998), implements all the algorithms required for the ESH in Fortran 90. We develop a script in Python using mpi4py, in order to execute GWQMonitor in parallel, applying the MPI library. Our approach is to calculate the initial inputs for each realization, and run groups of these realizations in separate processors. The only modification to the GWQMonitor was the final calculation of the covariance matrix. This strategy was applied to the study of a simplified aquifer in a rectangular domain of a single layer. We show the speedup and efficiency for different number of processors.

Batched matrix computations on hardware accelerators based on GPUs

DOE PAGES

Haidar, Azzam; Dong, Tingxing; Luszczek, Piotr; ...

2015-02-09

Scientific applications require solvers that work on many small size problems that are independent from each other. At the same time, the high-end hardware evolves rapidly and becomes ever more throughput-oriented and thus there is an increasing need for an effective approach to develop energy-efficient, high-performance codes for these small matrix problems that we call batched factorizations. The many applications that need this functionality could especially benefit from the use of GPUs, which currently are four to five times more energy efficient than multicore CPUs on important scientific workloads. This study, consequently, describes the development of the most common, one-sidedmore » factorizations, Cholesky, LU, and QR, for a set of small dense matrices. The algorithms we present together with their implementations are, by design, inherently parallel. In particular, our approach is based on representing the process as a sequence of batched BLAS routines that are executed entirely on a GPU. Importantly, this is unlike the LAPACK and the hybrid MAGMA factorization algorithms that work under drastically different assumptions of hardware design and efficiency of execution of the various computational kernels involved in the implementation. Thus, our approach is more efficient than what works for a combination of multicore CPUs and GPUs for the problems sizes of interest of the application use cases. The paradigm where upon a single chip (a GPU or a CPU) factorizes a single problem at a time is not at all efficient in our applications’ context. We illustrate all of these claims through a detailed performance analysis. With the help of profiling and tracing tools, we guide our development of batched factorizations to achieve up to two-fold speedup and three-fold better energy efficiency as compared against our highly optimized batched CPU implementations based on MKL library. Finally, the tested system featured two sockets of Intel Sandy Bridge CPUs and we compared with a batched LU factorizations featured in the CUBLAS library for GPUs, we achieve as high as 2.5× speedup on the NVIDIA K40 GPU.« less

An empirical analysis of executive behaviour with hospital executive information systems in Taiwan.

PubMed

Huang, Wei-Min

2013-01-01

Existing health information systems largely only support the daily operations of a medical centre, and are unable to generate the information required by executives for decision-making. Building on past research concerning information retrieval behaviour and learning through mental models, this study examines the use of information systems by hospital executives in medical centres. It uses a structural equation model to help find ways hospital executives might use information systems more effectively. The results show that computer self-efficacy directly affects the maintenance of mental models, and that system characteristics directly impact learning styles and information retrieval behaviour. Other results include the significant impact of perceived environmental uncertainty on scan searches; information retrieval behaviour and focused searches on mental models and perceived efficiency; scan searches on mental model building; learning styles and model building on perceived efficiency; and finally the impact of mental model maintenance on perceived efficiency and effectiveness.

Scalable geocomputation: evolving an environmental model building platform from single-core to supercomputers

NASA Astrophysics Data System (ADS)

Schmitz, Oliver; de Jong, Kor; Karssenberg, Derek

2017-04-01

There is an increasing demand to run environmental models on a big scale: simulations over large areas at high resolution. The heterogeneity of available computing hardware such as multi-core CPUs, GPUs or supercomputer potentially provides significant computing power to fulfil this demand. However, this requires detailed knowledge of the underlying hardware, parallel algorithm design and the implementation thereof in an efficient system programming language. Domain scientists such as hydrologists or ecologists often lack this specific software engineering knowledge, their emphasis is (and should be) on exploratory building and analysis of simulation models. As a result, models constructed by domain specialists mostly do not take full advantage of the available hardware. A promising solution is to separate the model building activity from software engineering by offering domain specialists a model building framework with pre-programmed building blocks that they combine to construct a model. The model building framework, consequently, needs to have built-in capabilities to make full usage of the available hardware. Developing such a framework providing understandable code for domain scientists and being runtime efficient at the same time poses several challenges on developers of such a framework. For example, optimisations can be performed on individual operations or the whole model, or tasks need to be generated for a well-balanced execution without explicitly knowing the complexity of the domain problem provided by the modeller. Ideally, a modelling framework supports the optimal use of available hardware whichsoever combination of model building blocks scientists use. We demonstrate our ongoing work on developing parallel algorithms for spatio-temporal modelling and demonstrate 1) PCRaster, an environmental software framework (http://www.pcraster.eu) providing spatio-temporal model building blocks and 2) parallelisation of about 50 of these building blocks using the new Fern library (https://github.com/geoneric/fern/), an independent generic raster processing library. Fern is a highly generic software library and its algorithms can be configured according to the configuration of a modelling framework. With manageable programming effort (e.g. matching data types between programming and domain language) we created a binding between Fern and PCRaster. The resulting PCRaster Python multicore module can be used to execute existing PCRaster models without having to make any changes to the model code. We show initial results on synthetic and geoscientific models indicating significant runtime improvements provided by parallel local and focal operations. We further outline challenges in improving remaining algorithms such as flow operations over digital elevation maps and further potential improvements like enhancing disk I/O.

FPGA implementation of a biological neural network based on the Hodgkin-Huxley neuron model

PubMed Central

Yaghini Bonabi, Safa; Asgharian, Hassan; Safari, Saeed; Nili Ahmadabadi, Majid

2014-01-01

A set of techniques for efficient implementation of Hodgkin-Huxley-based (H-H) model of a neural network on FPGA (Field Programmable Gate Array) is presented. The central implementation challenge is H-H model complexity that puts limits on the network size and on the execution speed. However, basics of the original model cannot be compromised when effect of synaptic specifications on the network behavior is the subject of study. To solve the problem, we used computational techniques such as CORDIC (Coordinate Rotation Digital Computer) algorithm and step-by-step integration in the implementation of arithmetic circuits. In addition, we employed different techniques such as sharing resources to preserve the details of model as well as increasing the network size in addition to keeping the network execution speed close to real time while having high precision. Implementation of a two mini-columns network with 120/30 excitatory/inhibitory neurons is provided to investigate the characteristic of our method in practice. The implementation techniques provide an opportunity to construct large FPGA-based network models to investigate the effect of different neurophysiological mechanisms, like voltage-gated channels and synaptic activities, on the behavior of a neural network in an appropriate execution time. Additional to inherent properties of FPGA, like parallelism and re-configurability, our approach makes the FPGA-based system a proper candidate for study on neural control of cognitive robots and systems as well. PMID:25484854

Photo-z-SQL: Integrated, flexible photometric redshift computation in a database

NASA Astrophysics Data System (ADS)

Beck, R.; Dobos, L.; Budavári, T.; Szalay, A. S.; Csabai, I.

2017-04-01

We present a flexible template-based photometric redshift estimation framework, implemented in C#, that can be seamlessly integrated into a SQL database (or DB) server and executed on-demand in SQL. The DB integration eliminates the need to move large photometric datasets outside a database for redshift estimation, and utilizes the computational capabilities of DB hardware. The code is able to perform both maximum likelihood and Bayesian estimation, and can handle inputs of variable photometric filter sets and corresponding broad-band magnitudes. It is possible to take into account the full covariance matrix between filters, and filter zero points can be empirically calibrated using measurements with given redshifts. The list of spectral templates and the prior can be specified flexibly, and the expensive synthetic magnitude computations are done via lazy evaluation, coupled with a caching of results. Parallel execution is fully supported. For large upcoming photometric surveys such as the LSST, the ability to perform in-place photo-z calculation would be a significant advantage. Also, the efficient handling of variable filter sets is a necessity for heterogeneous databases, for example the Hubble Source Catalog, and for cross-match services such as SkyQuery. We illustrate the performance of our code on two reference photo-z estimation testing datasets, and provide an analysis of execution time and scalability with respect to different configurations. The code is available for download at https://github.com/beckrob/Photo-z-SQL.

The BLAZE language - A parallel language for scientific programming

NASA Technical Reports Server (NTRS)

Mehrotra, Piyush; Van Rosendale, John

1987-01-01

A Pascal-like scientific programming language, BLAZE, is described. BLAZE contains array arithmetic, forall loops, and APL-style accumulation operators, which allow natural expression of fine grained parallelism. It also employs an applicative or functional procedure invocation mechanism, which makes it easy for compilers to extract coarse grained parallelism using machine specific program restructuring. Thus BLAZE should allow one to achieve highly parallel execution on multiprocessor architectures, while still providing the user with conceptually sequential control flow. A central goal in the design of BLAZE is portability across a broad range of parallel architectures. The multiple levels of parallelism present in BLAZE code, in principle, allow a compiler to extract the types of parallelism appropriate for the given architecture while neglecting the remainder. The features of BLAZE are described and it is shown how this language would be used in typical scientific programming.

NDL-v2.0: A new version of the numerical differentiation library for parallel architectures

NASA Astrophysics Data System (ADS)

Hadjidoukas, P. E.; Angelikopoulos, P.; Voglis, C.; Papageorgiou, D. G.; Lagaris, I. E.

2014-07-01

We present a new version of the numerical differentiation library (NDL) used for the numerical estimation of first and second order partial derivatives of a function by finite differencing. In this version we have restructured the serial implementation of the code so as to achieve optimal task-based parallelization. The pure shared-memory parallelization of the library has been based on the lightweight OpenMP tasking model allowing for the full extraction of the available parallelism and efficient scheduling of multiple concurrent library calls. On multicore clusters, parallelism is exploited by means of TORC, an MPI-based multi-threaded tasking library. The new MPI implementation of NDL provides optimal performance in terms of function calls and, furthermore, supports asynchronous execution of multiple library calls within legacy MPI programs. In addition, a Python interface has been implemented for all cases, exporting the functionality of our library to sequential Python codes. Catalog identifier: AEDG_v2_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEDG_v2_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.html No. of lines in distributed program, including test data, etc.: 63036 No. of bytes in distributed program, including test data, etc.: 801872 Distribution format: tar.gz Programming language: ANSI Fortran-77, ANSI C, Python. Computer: Distributed systems (clusters), shared memory systems. Operating system: Linux, Unix. Has the code been vectorized or parallelized?: Yes. RAM: The library uses O(N) internal storage, N being the dimension of the problem. It can use up to O(N2) internal storage for Hessian calculations, if a task throttling factor has not been set by the user. Classification: 4.9, 4.14, 6.5. Catalog identifier of previous version: AEDG_v1_0 Journal reference of previous version: Comput. Phys. Comm. 180(2009)1404 Does the new version supersede the previous version?: Yes Nature of problem: The numerical estimation of derivatives at several accuracy levels is a common requirement in many computational tasks, such as optimization, solution of nonlinear systems, and sensitivity analysis. For a large number of scientific and engineering applications, the underlying functions correspond to simulation codes for which analytical estimation of derivatives is difficult or almost impossible. A parallel implementation that exploits systems with multiple CPUs is very important for large scale and computationally expensive problems. Solution method: Finite differencing is used with a carefully chosen step that minimizes the sum of the truncation and round-off errors. The parallel versions employ both OpenMP and MPI libraries. Reasons for new version: The updated version was motivated by our endeavors to extend a parallel Bayesian uncertainty quantification framework [1], by incorporating higher order derivative information as in most state-of-the-art stochastic simulation methods such as Stochastic Newton MCMC [2] and Riemannian Manifold Hamiltonian MC [3]. The function evaluations are simulations with significant time-to-solution, which also varies with the input parameters such as in [1, 4]. The runtime of the N-body-type of problem changes considerably with the introduction of a longer cut-off between the bodies. In the first version of the library, the OpenMP-parallel subroutines spawn a new team of threads and distribute the function evaluations with a PARALLEL DO directive. This limits the functionality of the library as multiple concurrent calls require nested parallelism support from the OpenMP environment. Therefore, either their function evaluations will be serialized or processor oversubscription is likely to occur due to the increased number of OpenMP threads. In addition, the Hessian calculations include two explicit parallel regions that compute first the diagonal and then the off-diagonal elements of the array. Due to the barrier between the two regions, the parallelism of the calculations is not fully exploited. These issues have been addressed in the new version by first restructuring the serial code and then running the function evaluations in parallel using OpenMP tasks. Although the MPI-parallel implementation of the first version is capable of fully exploiting the task parallelism of the PNDL routines, it does not utilize the caching mechanism of the serial code and, therefore, performs some redundant function evaluations in the Hessian and Jacobian calculations. This can lead to: (a) higher execution times if the number of available processors is lower than the total number of tasks, and (b) significant energy consumption due to wasted processor cycles. Overcoming these drawbacks, which become critical as the time of a single function evaluation increases, was the primary goal of this new version. Due to the code restructure, the MPI-parallel implementation (and the OpenMP-parallel in accordance) avoids redundant calls, providing optimal performance in terms of the number of function evaluations. Another limitation of the library was that the library subroutines were collective and synchronous calls. In the new version, each MPI process can issue any number of subroutines for asynchronous execution. We introduce two library calls that provide global and local task synchronizations, similarly to the BARRIER and TASKWAIT directives of OpenMP. The new MPI-implementation is based on TORC, a new tasking library for multicore clusters [5-7]. TORC improves the portability of the software, as it relies exclusively on the POSIX-Threads and MPI programming interfaces. It allows MPI processes to utilize multiple worker threads, offering a hybrid programming and execution environment similar to MPI+OpenMP, in a completely transparent way. Finally, to further improve the usability of our software, a Python interface has been implemented on top of both the OpenMP and MPI versions of the library. This allows sequential Python codes to exploit shared and distributed memory systems. Summary of revisions: The revised code improves the performance of both parallel (OpenMP and MPI) implementations. The functionality and the user-interface of the MPI-parallel version have been extended to support the asynchronous execution of multiple PNDL calls, issued by one or multiple MPI processes. A new underlying tasking library increases portability and allows MPI processes to have multiple worker threads. For both implementations, an interface to the Python programming language has been added. Restrictions: The library uses only double precision arithmetic. The MPI implementation assumes the homogeneity of the execution environment provided by the operating system. Specifically, the processes of a single MPI application must have identical address space and a user function resides at the same virtual address. In addition, address space layout randomization should not be used for the application. Unusual features: The software takes into account bound constraints, in the sense that only feasible points are used to evaluate the derivatives, and given the level of the desired accuracy, the proper formula is automatically employed. Running time: Running time depends on the function's complexity. The test run took 23 ms for the serial distribution, 25 ms for the OpenMP with 2 threads, 53 ms and 1.01 s for the MPI parallel distribution using 2 threads and 2 processes respectively and yield-time for idle workers equal to 10 ms. References: [1] P. Angelikopoulos, C. Paradimitriou, P. Koumoutsakos, Bayesian uncertainty quantification and propagation in molecular dynamics simulations: a high performance computing framework, J. Chem. Phys 137 (14). [2] H.P. Flath, L.C. Wilcox, V. Akcelik, J. Hill, B. van Bloemen Waanders, O. Ghattas, Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations, SIAM J. Sci. Comput. 33 (1) (2011) 407-432. [3] M. Girolami, B. Calderhead, Riemann manifold Langevin and Hamiltonian Monte Carlo methods, J. R. Stat. Soc. Ser. B (Stat. Methodol.) 73 (2) (2011) 123-214. [4] P. Angelikopoulos, C. Paradimitriou, P. Koumoutsakos, Data driven, predictive molecular dynamics for nanoscale flow simulations under uncertainty, J. Phys. Chem. B 117 (47) (2013) 14808-14816. [5] P.E. Hadjidoukas, E. Lappas, V.V. Dimakopoulos, A runtime library for platform-independent task parallelism, in: PDP, IEEE, 2012, pp. 229-236. [6] C. Voglis, P.E. Hadjidoukas, D.G. Papageorgiou, I. Lagaris, A parallel hybrid optimization algorithm for fitting interatomic potentials, Appl. Soft Comput. 13 (12) (2013) 4481-4492. [7] P.E. Hadjidoukas, C. Voglis, V.V. Dimakopoulos, I. Lagaris, D.G. Papageorgiou, Supporting adaptive and irregular parallelism for non-linear numerical optimization, Appl. Math. Comput. 231 (2014) 544-559.

Overview of the NASA Glenn Flux Reconstruction Based High-Order Unstructured Grid Code

NASA Technical Reports Server (NTRS)

Spiegel, Seth C.; DeBonis, James R.; Huynh, H. T.

2016-01-01

A computational fluid dynamics code based on the flux reconstruction (FR) method is currently being developed at NASA Glenn Research Center to ultimately provide a large- eddy simulation capability that is both accurate and efficient for complex aeropropulsion flows. The FR approach offers a simple and efficient method that is easy to implement and accurate to an arbitrary order on common grid cell geometries. The governing compressible Navier-Stokes equations are discretized in time using various explicit Runge-Kutta schemes, with the default being the 3-stage/3rd-order strong stability preserving scheme. The code is written in modern Fortran (i.e., Fortran 2008) and parallelization is attained through MPI for execution on distributed-memory high-performance computing systems. An h- refinement study of the isentropic Euler vortex problem is able to empirically demonstrate the capability of the FR method to achieve super-accuracy for inviscid flows. Additionally, the code is applied to the Taylor-Green vortex problem, performing numerous implicit large-eddy simulations across a range of grid resolutions and solution orders. The solution found by a pseudo-spectral code is commonly used as a reference solution to this problem, and the FR code is able to reproduce this solution using approximately the same grid resolution. Finally, an examination of the code's performance demonstrates good parallel scaling, as well as an implementation of the FR method with a computational cost/degree- of-freedom/time-step that is essentially independent of the solution order of accuracy for structured geometries.

Augmenting The HST Pure Parallel Observations

NASA Astrophysics Data System (ADS)

Patterson, Alan; Soutchkova, G.; Workman, W.

2012-05-01

Pure Parallel (PP) programs, designated GO/PAR, are a subgroup of General Observer (GO) programs. PP execute simultaneously with prime GO observations to which they are "attached". The PP observations can be performed with ACS/WFC, WFC3/UVIS or WFC3/IR and can be attached only to GO visits in which the instruments are either COS or STIS. The current HST Parallel Observation Processing System (POPS) was introduced after the Servicing Mission 4. It increased the HST productivity by 10% in terms of the utilization of HST prime orbits and was highly appreciated by the HST observers, allowing them to design efficient, multi-orbit survey projects for collecting large amounts of data on identifiable targets. The results of the WFC3 Infrared Spectroscopic Parallel Survey (WISP), Hubble Infrared Pure Parallel Imaging Extragalactic Survey (HIPPIES), and The Brightest-of-Reionizing Galaxies Pure Parallel Survey (BoRG) exemplify this benefit. In Cycle 19, however, the full advantage of GO/PARs came under risk. Whereas each of the previous cycles provided over one million seconds of exposure time for PP, in Cycle 19 that number reduced to 680,000 seconds. This dramatic decline occurred because of fundamental changes in the construction of COS prime observations. To preserve the science output of PP, the PP Working Group was tasked to find a way to recover the lost time and maximize the total time available for PP observing. The solution was to expand the definition of a PP opportunity to allow PP exposures to span one or more primary exposure readouts. So starting in HST Cycle 20, PP opportunities will no longer be limited to GO visits with a single uninterrupted exposure in an orbit. The resulting enhancements in HST Cycle 20 to the PP opportunity identification and matching process are expected to restore the PP time to previously achieved and possibly even greater levels.

The Modeling, Simulation and Comparison of Interconnection Networks for Parallel Processing.

DTIC Science & Technology

1987-12-01

performs better at a lower hardware cost than do the single stage cube and mesh networks. As a result, the designer of a paralll pro- cessing system is...attempted, and in most cases succeeded, in designing and implementing faster. more powerful systems. Due to design innovations and technological advances...largely to the computational complexity of the algorithms executed. In the von Neumann machine, instructions must be executed in a sequential manner. Design

A Parallel Framework with Block Matrices of a Discrete Fourier Transform for Vector-Valued Discrete-Time Signals.

PubMed

Soto-Quiros, Pablo

2015-01-01

This paper presents a parallel implementation of a kind of discrete Fourier transform (DFT): the vector-valued DFT. The vector-valued DFT is a novel tool to analyze the spectra of vector-valued discrete-time signals. This parallel implementation is developed in terms of a mathematical framework with a set of block matrix operations. These block matrix operations contribute to analysis, design, and implementation of parallel algorithms in multicore processors. In this work, an implementation and experimental investigation of the mathematical framework are performed using MATLAB with the Parallel Computing Toolbox. We found that there is advantage to use multicore processors and a parallel computing environment to minimize the high execution time. Additionally, speedup increases when the number of logical processors and length of the signal increase.

Implementation and Performance of Factorized Back projection on Low-Cost Commercial-Off-the-Shelf Hardware

DTIC Science & Technology

performance on a low cost, low size, weight, and power (SWAP) computer : a Raspberry Pi Model B. For a comparison of performance, a baseline implementation...improvement factor of 2-3 compared to filtered backprojection. Execution on a single Raspberry Pi is too slow for real-time imaging. However, factorized...backprojection is easily parallelized, and we include a discussion of parallel implementation across multiple Pis .

Reverse time migration: A seismic processing application on the connection machine

NASA Technical Reports Server (NTRS)

Fiebrich, Rolf-Dieter

1987-01-01

The implementation of a reverse time migration algorithm on the Connection Machine, a massively parallel computer is described. Essential architectural features of this machine as well as programming concepts are presented. The data structures and parallel operations for the implementation of the reverse time migration algorithm are described. The algorithm matches the Connection Machine architecture closely and executes almost at the peak performance of this machine.

Force user's manual, revised

NASA Technical Reports Server (NTRS)

Jordan, Harry F.; Benten, Muhammad S.; Arenstorf, Norbert S.; Ramanan, Aruna V.

1987-01-01

A methodology for writing parallel programs for shared memory multiprocessors has been formalized as an extension to the Fortran language and implemented as a macro preprocessor. The extended language is known as the Force, and this manual describes how to write Force programs and execute them on the Flexible Computer Corporation Flex/32, the Encore Multimax and the Sequent Balance computers. The parallel extension macros are described in detail, but knowledge of Fortran is assumed.

Parallel task processing of very large datasets

NASA Astrophysics Data System (ADS)

Romig, Phillip Richardson, III

This research concerns the use of distributed computer technologies for the analysis and management of very large datasets. Improvements in sensor technology, an emphasis on global change research, and greater access to data warehouses all are increase the number of non-traditional users of remotely sensed data. We present a framework for distributed solutions to the challenges of datasets which exceed the online storage capacity of individual workstations. This framework, called parallel task processing (PTP), incorporates both the task- and data-level parallelism exemplified by many image processing operations. An implementation based on the principles of PTP, called Tricky, is also presented. Additionally, we describe the challenges and practical issues in modeling the performance of parallel task processing with large datasets. We present a mechanism for estimating the running time of each unit of work within a system and an algorithm that uses these estimates to simulate the execution environment and produce estimated runtimes. Finally, we describe and discuss experimental results which validate the design. Specifically, the system (a) is able to perform computation on datasets which exceed the capacity of any one disk, (b) provides reduction of overall computation time as a result of the task distribution even with the additional cost of data transfer and management, and (c) in the simulation mode accurately predicts the performance of the real execution environment.

On program restructuring, scheduling, and communication for parallel processor systems

DOE Office of Scientific and Technical Information (OSTI.GOV)

Polychronopoulos, Constantine D.

1986-08-01

This dissertation discusses several software and hardware aspects of program execution on large-scale, high-performance parallel processor systems. The issues covered are program restructuring, partitioning, scheduling and interprocessor communication, synchronization, and hardware design issues of specialized units. All this work was performed focusing on a single goal: to maximize program speedup, or equivalently, to minimize parallel execution time. Parafrase, a Fortran restructuring compiler was used to transform programs in a parallel form and conduct experiments. Two new program restructuring techniques are presented, loop coalescing and subscript blocking. Compile-time and run-time scheduling schemes are covered extensively. Depending on the program construct, thesemore » algorithms generate optimal or near-optimal schedules. For the case of arbitrarily nested hybrid loops, two optimal scheduling algorithms for dynamic and static scheduling are presented. Simulation results are given for a new dynamic scheduling algorithm. The performance of this algorithm is compared to that of self-scheduling. Techniques for program partitioning and minimization of interprocessor communication for idealized program models and for real Fortran programs are also discussed. The close relationship between scheduling, interprocessor communication, and synchronization becomes apparent at several points in this work. Finally, the impact of various types of overhead on program speedup and experimental results are presented.« less

Parallel Processing of Images in Mobile Devices using BOINC

NASA Astrophysics Data System (ADS)

Curiel, Mariela; Calle, David F.; Santamaría, Alfredo S.; Suarez, David F.; Flórez, Leonardo

2018-04-01

Medical image processing helps health professionals make decisions for the diagnosis and treatment of patients. Since some algorithms for processing images require substantial amounts of resources, one could take advantage of distributed or parallel computing. A mobile grid can be an adequate computing infrastructure for this problem. A mobile grid is a grid that includes mobile devices as resource providers. In a previous step of this research, we selected BOINC as the infrastructure to build our mobile grid. However, parallel processing of images in mobile devices poses at least two important challenges: the execution of standard libraries for processing images and obtaining adequate performance when compared to desktop computers grids. By the time we started our research, the use of BOINC in mobile devices also involved two issues: a) the execution of programs in mobile devices required to modify the code to insert calls to the BOINC API, and b) the division of the image among the mobile devices as well as its merging required additional code in some BOINC components. This article presents answers to these four challenges.

Runtime verification of embedded real-time systems.

PubMed

Reinbacher, Thomas; Függer, Matthias; Brauer, Jörg

We present a runtime verification framework that allows on-line monitoring of past-time Metric Temporal Logic (ptMTL) specifications in a discrete time setting. We design observer algorithms for the time-bounded modalities of ptMTL, which take advantage of the highly parallel nature of hardware designs. The algorithms can be translated into efficient hardware blocks, which are designed for reconfigurability, thus, facilitate applications of the framework in both a prototyping and a post-deployment phase of embedded real-time systems. We provide formal correctness proofs for all presented observer algorithms and analyze their time and space complexity. For example, for the most general operator considered, the time-bounded Since operator, we obtain a time complexity that is doubly logarithmic both in the point in time the operator is executed and the operator's time bounds. This result is promising with respect to a self-contained, non-interfering monitoring approach that evaluates real-time specifications in parallel to the system-under-test. We implement our framework on a Field Programmable Gate Array platform and use extensive simulation and logic synthesis runs to assess the benefits of the approach in terms of resource usage and operating frequency.

A Framework to Analyze the Performance of Load Balancing Schemes for Ensembles of Stochastic Simulations

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ahn, Tae-Hyuk; Sandu, Adrian; Watson, Layne T.

2015-08-01

Ensembles of simulations are employed to estimate the statistics of possible future states of a system, and are widely used in important applications such as climate change and biological modeling. Ensembles of runs can naturally be executed in parallel. However, when the CPU times of individual simulations vary considerably, a simple strategy of assigning an equal number of tasks per processor can lead to serious work imbalances and low parallel efficiency. This paper presents a new probabilistic framework to analyze the performance of dynamic load balancing algorithms for ensembles of simulations where many tasks are mapped onto each processor, andmore » where the individual compute times vary considerably among tasks. Four load balancing strategies are discussed: most-dividing, all-redistribution, random-polling, and neighbor-redistribution. Simulation results with a stochastic budding yeast cell cycle model are consistent with the theoretical analysis. It is especially significant that there is a provable global decrease in load imbalance for the local rebalancing algorithms due to scalability concerns for the global rebalancing algorithms. The overall simulation time is reduced by up to 25 %, and the total processor idle time by 85 %.« less

Fast MPEG-CDVS Encoder With GPU-CPU Hybrid Computing

NASA Astrophysics Data System (ADS)

Duan, Ling-Yu; Sun, Wei; Zhang, Xinfeng; Wang, Shiqi; Chen, Jie; Yin, Jianxiong; See, Simon; Huang, Tiejun; Kot, Alex C.; Gao, Wen

2018-05-01

The compact descriptors for visual search (CDVS) standard from ISO/IEC moving pictures experts group (MPEG) has succeeded in enabling the interoperability for efficient and effective image retrieval by standardizing the bitstream syntax of compact feature descriptors. However, the intensive computation of CDVS encoder unfortunately hinders its widely deployment in industry for large-scale visual search. In this paper, we revisit the merits of low complexity design of CDVS core techniques and present a very fast CDVS encoder by leveraging the massive parallel execution resources of GPU. We elegantly shift the computation-intensive and parallel-friendly modules to the state-of-the-arts GPU platforms, in which the thread block allocation and the memory access are jointly optimized to eliminate performance loss. In addition, those operations with heavy data dependence are allocated to CPU to resolve the extra but non-necessary computation burden for GPU. Furthermore, we have demonstrated the proposed fast CDVS encoder can work well with those convolution neural network approaches which has harmoniously leveraged the advantages of GPU platforms, and yielded significant performance improvements. Comprehensive experimental results over benchmarks are evaluated, which has shown that the fast CDVS encoder using GPU-CPU hybrid computing is promising for scalable visual search.

Iterative load-balancing method with multigrid level relaxation for particle simulation with short-range interactions

NASA Astrophysics Data System (ADS)

Furuichi, Mikito; Nishiura, Daisuke

2017-10-01

We developed dynamic load-balancing algorithms for Particle Simulation Methods (PSM) involving short-range interactions, such as Smoothed Particle Hydrodynamics (SPH), Moving Particle Semi-implicit method (MPS), and Discrete Element method (DEM). These are needed to handle billions of particles modeled in large distributed-memory computer systems. Our method utilizes flexible orthogonal domain decomposition, allowing the sub-domain boundaries in the column to be different for each row. The imbalances in the execution time between parallel logical processes are treated as a nonlinear residual. Load-balancing is achieved by minimizing the residual within the framework of an iterative nonlinear solver, combined with a multigrid technique in the local smoother. Our iterative method is suitable for adjusting the sub-domain frequently by monitoring the performance of each computational process because it is computationally cheaper in terms of communication and memory costs than non-iterative methods. Numerical tests demonstrated the ability of our approach to handle workload imbalances arising from a non-uniform particle distribution, differences in particle types, or heterogeneous computer architecture which was difficult with previously proposed methods. We analyzed the parallel efficiency and scalability of our method using Earth simulator and K-computer supercomputer systems.

Magnetohydrodynamics with GAMER

NASA Astrophysics Data System (ADS)

Zhang, Ui-Han; Schive, Hsi-Yu; Chiueh, Tzihong

2018-06-01

GAMER, a parallel Graphic-processing-unit-accelerated Adaptive-MEsh-Refinement (AMR) hydrodynamic code, has been extended to support magnetohydrodynamics (MHD) with both the corner-transport-upwind and MUSCL-Hancock schemes and the constraint transport technique. The divergent preserving operator for AMR has been applied to reinforce the divergence-free constraint on the magnetic field. GAMER-MHD has fully exploited the concurrent executions between the graphic process unit (GPU) MHD solver and other central processing unit computation pertinent to AMR. We perform various standard tests to demonstrate that GAMER-MHD is both second-order accurate and robust, producing results as accurate as those given by high-resolution uniform-grid runs. We also explore a new 3D MHD test, where the magnetic field assumes the Arnold–Beltrami–Childress configuration, temporarily becomes turbulent with current sheets, and finally settles to a lowest-energy equilibrium state. This 3D problem is adopted for the performance test of GAMER-MHD. The single-GPU performance reaches 1.2 × 108 and 5.5 × 107 cell updates per second for the single- and double-precision calculations, respectively, on Tesla P100. We also demonstrate a parallel efficiency of ∼70% for both weak and strong scaling using 1024 XK nodes on the Blue Waters supercomputers.

Performance of GeantV EM Physics Models

NASA Astrophysics Data System (ADS)

Amadio, G.; Ananya, A.; Apostolakis, J.; Aurora, A.; Bandieramonte, M.; Bhattacharyya, A.; Bianchini, C.; Brun, R.; Canal, P.; Carminati, F.; Cosmo, G.; Duhem, L.; Elvira, D.; Folger, G.; Gheata, A.; Gheata, M.; Goulas, I.; Iope, R.; Jun, S. Y.; Lima, G.; Mohanty, A.; Nikitina, T.; Novak, M.; Pokorski, W.; Ribon, A.; Seghal, R.; Shadura, O.; Vallecorsa, S.; Wenzel, S.; Zhang, Y.

2017-10-01

The recent progress in parallel hardware architectures with deeper vector pipelines or many-cores technologies brings opportunities for HEP experiments to take advantage of SIMD and SIMT computing models. Launched in 2013, the GeantV project studies performance gains in propagating multiple particles in parallel, improving instruction throughput and data locality in HEP event simulation on modern parallel hardware architecture. Due to the complexity of geometry description and physics algorithms of a typical HEP application, performance analysis is indispensable in identifying factors limiting parallel execution. In this report, we will present design considerations and preliminary computing performance of GeantV physics models on coprocessors (Intel Xeon Phi and NVidia GPUs) as well as on mainstream CPUs.

Implementing and analyzing the multi-threaded LP-inference

NASA Astrophysics Data System (ADS)

Bolotova, S. Yu; Trofimenko, E. V.; Leschinskaya, M. V.

2018-03-01

The logical production equations provide new possibilities for the backward inference optimization in intelligent production-type systems. The strategy of a relevant backward inference is aimed at minimization of a number of queries to external information source (either to a database or an interactive user). The idea of the method is based on the computing of initial preimages set and searching for the true preimage. The execution of each stage can be organized independently and in parallel and the actual work at a given stage can also be distributed between parallel computers. This paper is devoted to the parallel algorithms of the relevant inference based on the advanced scheme of the parallel computations “pipeline” which allows to increase the degree of parallelism. The author also provides some details of the LP-structures implementation.

A man-made object detection for underwater TV

NASA Astrophysics Data System (ADS)

Cheng, Binbin; Wang, Wenwu; Chen, Yao

2018-03-01

It is a great challenging task to complete an automatic search of objects underwater. Usually the forward looking sonar is used to find the target, and then the initial identification of the target is completed by the side-scan sonar, and finally the confirmation of the target is accomplished by underwater TV. This paper presents an efficient method for automatic extraction of man-made sensitive targets in underwater TV. Firstly, the image of underwater TV is simplified with taking full advantage of the prior knowledge of the target and the background; then template matching technology is used for target detection; finally the target is confirmed by extracting parallel lines on the target contour. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detection objects in underwater TV.

Evaluating Multi-core Architectures through Accelerating the Three-Dimensional Lax–Wendroff Correction

DOE Office of Scientific and Technical Information (OSTI.GOV)

You, Yang; Fu, Haohuan; Song, Shuaiwen

2014-07-18

Wave propagation forward modeling is a widely used computational method in oil and gas exploration. The iterative stencil loops in such problems have broad applications in scientific computing. However, executing such loops can be highly time time-consuming, which greatly limits application’s performance and power efficiency. In this paper, we accelerate the forward modeling technique on the latest multi-core and many-core architectures such as Intel Sandy Bridge CPUs, NVIDIA Fermi C2070 GPU, NVIDIA Kepler K20x GPU, and the Intel Xeon Phi Co-processor. For the GPU platforms, we propose two parallel strategies to explore the performance optimization opportunities for our stencil kernels.more » For Sandy Bridge CPUs and MIC, we also employ various optimization techniques in order to achieve the best.« less

Design of high-performance parallelized gene predictors in MATLAB.

PubMed

Rivard, Sylvain Robert; Mailloux, Jean-Gabriel; Beguenane, Rachid; Bui, Hung Tien

2012-04-10

This paper proposes a method of implementing parallel gene prediction algorithms in MATLAB. The proposed designs are based on either Goertzel's algorithm or on FFTs and have been implemented using varying amounts of parallelism on a central processing unit (CPU) and on a graphics processing unit (GPU). Results show that an implementation using a straightforward approach can require over 4.5 h to process 15 million base pairs (bps) whereas a properly designed one could perform the same task in less than five minutes. In the best case, a GPU implementation can yield these results in 57 s. The present work shows how parallelism can be used in MATLAB for gene prediction in very large DNA sequences to produce results that are over 270 times faster than a conventional approach. This is significant as MATLAB is typically overlooked due to its apparent slow processing time even though it offers a convenient environment for bioinformatics. From a practical standpoint, this work proposes two strategies for accelerating genome data processing which rely on different parallelization mechanisms. Using a CPU, the work shows that direct access to the MEX function increases execution speed and that the PARFOR construct should be used in order to take full advantage of the parallelizable Goertzel implementation. When the target is a GPU, the work shows that data needs to be segmented into manageable sizes within the GFOR construct before processing in order to minimize execution time.

76 FR 57947 - Senior Executive Service Performance Review Board Membership

Federal Register 2010, 2011, 2012, 2013, 2014

2011-09-19

... AND EFFICIENCY Senior Executive Service Performance Review Board Membership AGENCY: Council of the... of Personnel Management, each agency is required to establish one or more Senior Executive Service... appraisal of a senior executive's performance by the supervisor, along with any recommendations to the...

Research of the effectiveness of parallel multithreaded realizations of interpolation methods for scaling raster images

NASA Astrophysics Data System (ADS)

Vnukov, A. A.; Shershnev, M. B.

2018-01-01

The aim of this work is the software implementation of three image scaling algorithms using parallel computations, as well as the development of an application with a graphical user interface for the Windows operating system to demonstrate the operation of algorithms and to study the relationship between system performance, algorithm execution time and the degree of parallelization of computations. Three methods of interpolation were studied, formalized and adapted to scale images. The result of the work is a program for scaling images by different methods. Comparison of the quality of scaling by different methods is given.

Data decomposition method for parallel polygon rasterization considering load balancing

NASA Astrophysics Data System (ADS)

Zhou, Chen; Chen, Zhenjie; Liu, Yongxue; Li, Feixue; Cheng, Liang; Zhu, A.-xing; Li, Manchun

2015-12-01

It is essential to adopt parallel computing technology to rapidly rasterize massive polygon data. In parallel rasterization, it is difficult to design an effective data decomposition method. Conventional methods ignore load balancing of polygon complexity in parallel rasterization and thus fail to achieve high parallel efficiency. In this paper, a novel data decomposition method based on polygon complexity (DMPC) is proposed. First, four factors that possibly affect the rasterization efficiency were investigated. Then, a metric represented by the boundary number and raster pixel number in the minimum bounding rectangle was developed to calculate the complexity of each polygon. Using this metric, polygons were rationally allocated according to the polygon complexity, and each process could achieve balanced loads of polygon complexity. To validate the efficiency of DMPC, it was used to parallelize different polygon rasterization algorithms and tested on different datasets. Experimental results showed that DMPC could effectively parallelize polygon rasterization algorithms. Furthermore, the implemented parallel algorithms with DMPC could achieve good speedup ratios of at least 15.69 and generally outperformed conventional decomposition methods in terms of parallel efficiency and load balancing. In addition, the results showed that DMPC exhibited consistently better performance for different spatial distributions of polygons.

A DAG Scheduling Scheme on Heterogeneous Computing Systems Using Tuple-Based Chemical Reaction Optimization

PubMed Central

Jiang, Yuyi; Shao, Zhiqing; Guo, Yi

2014-01-01

A complex computing problem can be solved efficiently on a system with multiple computing nodes by dividing its implementation code into several parallel processing modules or tasks that can be formulated as directed acyclic graph (DAG) problems. The DAG jobs may be mapped to and scheduled on the computing nodes to minimize the total execution time. Searching an optimal DAG scheduling solution is considered to be NP-complete. This paper proposed a tuple molecular structure-based chemical reaction optimization (TMSCRO) method for DAG scheduling on heterogeneous computing systems, based on a very recently proposed metaheuristic method, chemical reaction optimization (CRO). Comparing with other CRO-based algorithms for DAG scheduling, the design of tuple reaction molecular structure and four elementary reaction operators of TMSCRO is more reasonable. TMSCRO also applies the concept of constrained critical paths (CCPs), constrained-critical-path directed acyclic graph (CCPDAG) and super molecule for accelerating convergence. In this paper, we have also conducted simulation experiments to verify the effectiveness and efficiency of TMSCRO upon a large set of randomly generated graphs and the graphs for real world problems. PMID:25143977

A DAG scheduling scheme on heterogeneous computing systems using tuple-based chemical reaction optimization.

PubMed

Jiang, Yuyi; Shao, Zhiqing; Guo, Yi

2014-01-01

A complex computing problem can be solved efficiently on a system with multiple computing nodes by dividing its implementation code into several parallel processing modules or tasks that can be formulated as directed acyclic graph (DAG) problems. The DAG jobs may be mapped to and scheduled on the computing nodes to minimize the total execution time. Searching an optimal DAG scheduling solution is considered to be NP-complete. This paper proposed a tuple molecular structure-based chemical reaction optimization (TMSCRO) method for DAG scheduling on heterogeneous computing systems, based on a very recently proposed metaheuristic method, chemical reaction optimization (CRO). Comparing with other CRO-based algorithms for DAG scheduling, the design of tuple reaction molecular structure and four elementary reaction operators of TMSCRO is more reasonable. TMSCRO also applies the concept of constrained critical paths (CCPs), constrained-critical-path directed acyclic graph (CCPDAG) and super molecule for accelerating convergence. In this paper, we have also conducted simulation experiments to verify the effectiveness and efficiency of TMSCRO upon a large set of randomly generated graphs and the graphs for real world problems.

Real-time software receiver

NASA Technical Reports Server (NTRS)

Psiaki, Mark L. (Inventor); Kintner, Jr., Paul M. (Inventor); Ledvina, Brent M. (Inventor); Powell, Steven P. (Inventor)

2007-01-01

A real-time software receiver that executes on a general purpose processor. The software receiver includes data acquisition and correlator modules that perform, in place of hardware correlation, baseband mixing and PRN code correlation using bit-wise parallelism.

Real-time software receiver

NASA Technical Reports Server (NTRS)

Psiaki, Mark L. (Inventor); Ledvina, Brent M. (Inventor); Powell, Steven P. (Inventor); Kintner, Jr., Paul M. (Inventor)

2006-01-01

A real-time software receiver that executes on a general purpose processor. The software receiver includes data acquisition and correlator modules that perform, in place of hardware correlation, baseband mixing and PRN code correlation using bit-wise parallelism.

High-speed parallel implementation of a modified PBR algorithm on DSP-based EH topology

NASA Astrophysics Data System (ADS)

Rajan, K.; Patnaik, L. M.; Ramakrishna, J.

1997-08-01

Algebraic Reconstruction Technique (ART) is an age-old method used for solving the problem of three-dimensional (3-D) reconstruction from projections in electron microscopy and radiology. In medical applications, direct 3-D reconstruction is at the forefront of investigation. The simultaneous iterative reconstruction technique (SIRT) is an ART-type algorithm with the potential of generating in a few iterations tomographic images of a quality comparable to that of convolution backprojection (CBP) methods. Pixel-based reconstruction (PBR) is similar to SIRT reconstruction, and it has been shown that PBR algorithms give better quality pictures compared to those produced by SIRT algorithms. In this work, we propose a few modifications to the PBR algorithms. The modified algorithms are shown to give better quality pictures compared to PBR algorithms. The PBR algorithm and the modified PBR algorithms are highly compute intensive, Not many attempts have been made to reconstruct objects in the true 3-D sense because of the high computational overhead. In this study, we have developed parallel two-dimensional (2-D) and 3-D reconstruction algorithms based on modified PBR. We attempt to solve the two problems encountered by the PBR and modified PBR algorithms, i.e., the long computational time and the large memory requirements, by parallelizing the algorithm on a multiprocessor system. We investigate the possible task and data partitioning schemes by exploiting the potential parallelism in the PBR algorithm subject to minimizing the memory requirement. We have implemented an extended hypercube (EH) architecture for the high-speed execution of the 3-D reconstruction algorithm using the commercially available fast floating point digital signal processor (DSP) chips as the processing elements (PEs) and dual-port random access memories (DPR) as channels between the PEs. We discuss and compare the performances of the PBR algorithm on an IBM 6000 RISC workstation, on a Silicon Graphics Indigo 2 workstation, and on an EH system. The results show that an EH(3,1) using DSP chips as PEs executes the modified PBR algorithm about 100 times faster than an LBM 6000 RISC workstation. We have executed the algorithms on a 4-node IBM SP2 parallel computer. The results show that execution time of the algorithm on an EH(3,1) is better than that of a 4-node IBM SP2 system. The speed-up of an EH(3,1) system with eight PEs and one network controller is approximately 7.85.

77 FR 51523 - Senior Executive Service Performance Review Board Membership

Federal Register 2010, 2011, 2012, 2013, 2014

2012-08-24

... COUNCIL OF THE INSPECTORS GENERAL ON INTEGRITY AND EFFICIENCY Senior Executive Service Performance... required to establish one or more Senior Executive Service (SES) performance review boards. The purpose of these boards is to review and evaluate the initial appraisal of a senior executive's performance by the...

Genetic algorithm based task reordering to improve the performance of batch scheduled massively parallel scientific applications

DOE PAGES

Sankaran, Ramanan; Angel, Jordan; Brown, W. Michael

2015-04-08

The growth in size of networked high performance computers along with novel accelerator-based node architectures has further emphasized the importance of communication efficiency in high performance computing. The world's largest high performance computers are usually operated as shared user facilities due to the costs of acquisition and operation. Applications are scheduled for execution in a shared environment and are placed on nodes that are not necessarily contiguous on the interconnect. Furthermore, the placement of tasks on the nodes allocated by the scheduler is sub-optimal, leading to performance loss and variability. Here, we investigate the impact of task placement on themore » performance of two massively parallel application codes on the Titan supercomputer, a turbulent combustion flow solver (S3D) and a molecular dynamics code (LAMMPS). Benchmark studies show a significant deviation from ideal weak scaling and variability in performance. The inter-task communication distance was determined to be one of the significant contributors to the performance degradation and variability. A genetic algorithm-based parallel optimization technique was used to optimize the task ordering. This technique provides an improved placement of the tasks on the nodes, taking into account the application's communication topology and the system interconnect topology. As a result, application benchmarks after task reordering through genetic algorithm show a significant improvement in performance and reduction in variability, therefore enabling the applications to achieve better time to solution and scalability on Titan during production.« less

HARP: A Dynamic Inertial Spectral Partitioner

NASA Technical Reports Server (NTRS)

Simon, Horst D.; Sohn, Andrew; Biswas, Rupak

1997-01-01

Partitioning unstructured graphs is central to the parallel solution of computational science and engineering problems. Spectral partitioners, such recursive spectral bisection (RSB), have proven effecfive in generating high-quality partitions of realistically-sized meshes. The major problem which hindered their wide-spread use was their long execution times. This paper presents a new inertial spectral partitioner, called HARP. The main objective of the proposed approach is to quickly partition the meshes at runtime in a manner that works efficiently for real applications in the context of distributed-memory machines. The underlying principle of HARP is to find the eigenvectors of the unpartitioned vertices and then project them onto the eigerivectors of the original mesh. Results for various meshes ranging in size from 1000 to 100,000 vertices indicate that HARP can indeed partition meshes rapidly at runtime. Experimental results show that our largest mesh can be partitioned sequentially in only a few seconds on an SP2 which is several times faster than other spectral partitioners while maintaining the solution quality of the proven RSB method. A parallel WI version of HARP has also been implemented on IBM SP2 and Cray T3E. Parallel HARP, running on 64 processors SP2 and T3E, can partition a mesh containing more than 100,000 vertices into 64 subgrids in about half a second. These results indicate that graph partitioning can now be truly embedded in dynamically-changing real-world applications.

BPELPower—A BPEL execution engine for geospatial web services

NASA Astrophysics Data System (ADS)

Yu, Genong (Eugene); Zhao, Peisheng; Di, Liping; Chen, Aijun; Deng, Meixia; Bai, Yuqi

2012-10-01

The Business Process Execution Language (BPEL) has become a popular choice for orchestrating and executing workflows in the Web environment. As one special kind of scientific workflow, geospatial Web processing workflows are data-intensive, deal with complex structures in data and geographic features, and execute automatically with limited human intervention. To enable the proper execution and coordination of geospatial workflows, a specially enhanced BPEL execution engine is required. BPELPower was designed, developed, and implemented as a generic BPEL execution engine with enhancements for executing geospatial workflows. The enhancements are especially in its capabilities in handling Geography Markup Language (GML) and standard geospatial Web services, such as the Web Processing Service (WPS) and the Web Feature Service (WFS). BPELPower has been used in several demonstrations over the decade. Two scenarios were discussed in detail to demonstrate the capabilities of BPELPower. That study showed a standard-compliant, Web-based approach for properly supporting geospatial processing, with the only enhancement at the implementation level. Pattern-based evaluation and performance improvement of the engine are discussed: BPELPower directly supports 22 workflow control patterns and 17 workflow data patterns. In the future, the engine will be enhanced with high performance parallel processing and broad Web paradigms.

Revisiting Molecular Dynamics on a CPU/GPU system: Water Kernel and SHAKE Parallelization.

PubMed

Ruymgaart, A Peter; Elber, Ron

2012-11-13

We report Graphics Processing Unit (GPU) and Open-MP parallel implementations of water-specific force calculations and of bond constraints for use in Molecular Dynamics simulations. We focus on a typical laboratory computing-environment in which a CPU with a few cores is attached to a GPU. We discuss in detail the design of the code and we illustrate performance comparable to highly optimized codes such as GROMACS. Beside speed our code shows excellent energy conservation. Utilization of water-specific lists allows the efficient calculations of non-bonded interactions that include water molecules and results in a speed-up factor of more than 40 on the GPU compared to code optimized on a single CPU core for systems larger than 20,000 atoms. This is up four-fold from a factor of 10 reported in our initial GPU implementation that did not include a water-specific code. Another optimization is the implementation of constrained dynamics entirely on the GPU. The routine, which enforces constraints of all bonds, runs in parallel on multiple Open-MP cores or entirely on the GPU. It is based on Conjugate Gradient solution of the Lagrange multipliers (CG SHAKE). The GPU implementation is partially in double precision and requires no communication with the CPU during the execution of the SHAKE algorithm. The (parallel) implementation of SHAKE allows an increase of the time step to 2.0fs while maintaining excellent energy conservation. Interestingly, CG SHAKE is faster than the usual bond relaxation algorithm even on a single core if high accuracy is expected. The significant speedup of the optimized components transfers the computational bottleneck of the MD calculation to the reciprocal part of Particle Mesh Ewald (PME).

Performance Comparison of a Set of Periodic and Non-Periodic Tridiagonal Solvers on SP2 and Paragon Parallel Computers

NASA Technical Reports Server (NTRS)

Sun, Xian-He; Moitra, Stuti

1996-01-01

Various tridiagonal solvers have been proposed in recent years for different parallel platforms. In this paper, the performance of three tridiagonal solvers, namely, the parallel partition LU algorithm, the parallel diagonal dominant algorithm, and the reduced diagonal dominant algorithm, is studied. These algorithms are designed for distributed-memory machines and are tested on an Intel Paragon and an IBM SP2 machines. Measured results are reported in terms of execution time and speedup. Analytical study are conducted for different communication topologies and for different tridiagonal systems. The measured results match the analytical results closely. In addition to address implementation issues, performance considerations such as problem sizes and models of speedup are also discussed.

An intelligent allocation algorithm for parallel processing

NASA Technical Reports Server (NTRS)

Carroll, Chester C.; Homaifar, Abdollah; Ananthram, Kishan G.

1988-01-01

The problem of allocating nodes of a program graph to processors in a parallel processing architecture is considered. The algorithm is based on critical path analysis, some allocation heuristics, and the execution granularity of nodes in a program graph. These factors, and the structure of interprocessor communication network, influence the allocation. To achieve realistic estimations of the executive durations of allocations, the algorithm considers the fact that nodes in a program graph have to communicate through varying numbers of tokens. Coarse and fine granularities have been implemented, with interprocessor token-communication duration, varying from zero up to values comparable to the execution durations of individual nodes. The effect on allocation of communication network structures is demonstrated by performing allocations for crossbar (non-blocking) and star (blocking) networks. The algorithm assumes the availability of as many processors as it needs for the optimal allocation of any program graph. Hence, the focus of allocation has been on varying token-communication durations rather than varying the number of processors. The algorithm always utilizes as many processors as necessary for the optimal allocation of any program graph, depending upon granularity and characteristics of the interprocessor communication network.

Validating the simulation of large-scale parallel applications using statistical characteristics

DOE PAGES

Zhang, Deli; Wilke, Jeremiah; Hendry, Gilbert; ...

2016-03-01

Simulation is a widely adopted method to analyze and predict the performance of large-scale parallel applications. Validating the hardware model is highly important for complex simulations with a large number of parameters. Common practice involves calculating the percent error between the projected and the real execution time of a benchmark program. However, in a high-dimensional parameter space, this coarse-grained approach often suffers from parameter insensitivity, which may not be known a priori. Moreover, the traditional approach cannot be applied to the validation of software models, such as application skeletons used in online simulations. In this work, we present a methodologymore » and a toolset for validating both hardware and software models by quantitatively comparing fine-grained statistical characteristics obtained from execution traces. Although statistical information has been used in tasks like performance optimization, this is the first attempt to apply it to simulation validation. Lastly, our experimental results show that the proposed evaluation approach offers significant improvement in fidelity when compared to evaluation using total execution time, and the proposed metrics serve as reliable criteria that progress toward automating the simulation tuning process.« less

Subsidized then scrutinized. Reform will bring billions of dollars to the industry, but it could also deliver added examination of executive pay.

PubMed

Galloro, Vince; Vesely, Rebecca; Zigmond, Jessica

2010-08-16

With more government involvement comes more government attention. That's the lesson about executive pay healthcare CEOs could learn as the reform law and its ramifications settle into place. "It's important for the people who are scraping together the dollars to pay their health insurance premiums to know what luxurious lives these CEOs are leading. They're living in a parallel universe", says U.S. Rep. Jan Schakowsky, left.

Executing scatter operation to parallel computer nodes by repeatedly broadcasting content of send buffer partition corresponding to each node upon bitwise OR operation

DOEpatents

Archer, Charles J [Rochester, MN; Ratterman, Joseph D [Rochester, MN

2009-11-06

Executing a scatter operation on a parallel computer includes: configuring a send buffer on a logical root, the send buffer having positions, each position corresponding to a ranked node in an operational group of compute nodes and for storing contents scattered to that ranked node; and repeatedly for each position in the send buffer: broadcasting, by the logical root to each of the other compute nodes on a global combining network, the contents of the current position of the send buffer using a bitwise OR operation, determining, by each compute node, whether the current position in the send buffer corresponds with the rank of that compute node, if the current position corresponds with the rank, receiving the contents and storing the contents in a reception buffer of that compute node, and if the current position does not correspond with the rank, discarding the contents.

Interconnect-free parallel logic circuits in a single mechanical resonator

PubMed Central

Mahboob, I.; Flurin, E.; Nishiguchi, K.; Fujiwara, A.; Yamaguchi, H.

2011-01-01

In conventional computers, wiring between transistors is required to enable the execution of Boolean logic functions. This has resulted in processors in which billions of transistors are physically interconnected, which limits integration densities, gives rise to huge power consumption and restricts processing speeds. A method to eliminate wiring amongst transistors by condensing Boolean logic into a single active element is thus highly desirable. Here, we demonstrate a novel logic architecture using only a single electromechanical parametric resonator into which multiple channels of binary information are encoded as mechanical oscillations at different frequencies. The parametric resonator can mix these channels, resulting in new mechanical oscillation states that enable the construction of AND, OR and XOR logic gates as well as multibit logic circuits. Moreover, the mechanical logic gates and circuits can be executed simultaneously, giving rise to the prospect of a parallel logic processor in just a single mechanical resonator. PMID:21326230

Interconnect-free parallel logic circuits in a single mechanical resonator.

PubMed

Mahboob, I; Flurin, E; Nishiguchi, K; Fujiwara, A; Yamaguchi, H

2011-02-15

In conventional computers, wiring between transistors is required to enable the execution of Boolean logic functions. This has resulted in processors in which billions of transistors are physically interconnected, which limits integration densities, gives rise to huge power consumption and restricts processing speeds. A method to eliminate wiring amongst transistors by condensing Boolean logic into a single active element is thus highly desirable. Here, we demonstrate a novel logic architecture using only a single electromechanical parametric resonator into which multiple channels of binary information are encoded as mechanical oscillations at different frequencies. The parametric resonator can mix these channels, resulting in new mechanical oscillation states that enable the construction of AND, OR and XOR logic gates as well as multibit logic circuits. Moreover, the mechanical logic gates and circuits can be executed simultaneously, giving rise to the prospect of a parallel logic processor in just a single mechanical resonator.

Cognitive Neural Prosthetics

PubMed Central

Andersen, Richard A.; Hwang, Eun Jung; Mulliken, Grant H.

2010-01-01

The cognitive neural prosthetic (CNP) is a very versatile method for assisting paralyzed patients and patients with amputations. The CNP records the cognitive state of the subject, rather than signals strictly related to motor execution or sensation. We review a number of high-level cortical signals and their application for CNPs, including intention, motor imagery, decision making, forward estimation, executive function, attention, learning, and multi-effector movement planning. CNPs are defined by the cognitive function they extract, not the cortical region from which the signals are recorded. However, some cortical areas may be better than others for particular applications. Signals can also be extracted in parallel from multiple cortical areas using multiple implants, which in many circumstances can increase the range of applications of CNPs. The CNP approach relies on scientific understanding of the neural processes involved in cognition, and many of the decoding algorithms it uses also have parallels to underlying neural circuit functions. PMID:19575625

Gilgamesh: A Multithreaded Processor-In-Memory Architecture for Petaflops Computing

NASA Technical Reports Server (NTRS)

Sterling, T. L.; Zima, H. P.

2002-01-01

Processor-in-Memory (PIM) architectures avoid the von Neumann bottleneck in conventional machines by integrating high-density DRAM and CMOS logic on the same chip. Parallel systems based on this new technology are expected to provide higher scalability, adaptability, robustness, fault tolerance and lower power consumption than current MPPs or commodity clusters. In this paper we describe the design of Gilgamesh, a PIM-based massively parallel architecture, and elements of its execution model. Gilgamesh extends existing PIM capabilities by incorporating advanced mechanisms for virtualizing tasks and data and providing adaptive resource management for load balancing and latency tolerance. The Gilgamesh execution model is based on macroservers, a middleware layer which supports object-based runtime management of data and threads allowing explicit and dynamic control of locality and load balancing. The paper concludes with a discussion of related research activities and an outlook to future work.

GPU-based Parallel Application Design for Emerging Mobile Devices

NASA Astrophysics Data System (ADS)

Gupta, Kshitij

A revolution is underway in the computing world that is causing a fundamental paradigm shift in device capabilities and form-factor, with a move from well-established legacy desktop/laptop computers to mobile devices in varying sizes and shapes. Amongst all the tasks these devices must support, graphics has emerged as the 'killer app' for providing a fluid user interface and high-fidelity game rendering, effectively making the graphics processor (GPU) one of the key components in (present and future) mobile systems. By utilizing the GPU as a general-purpose parallel processor, this dissertation explores the GPU computing design space from an applications standpoint, in the mobile context, by focusing on key challenges presented by these devices---limited compute, memory bandwidth, and stringent power consumption requirements---while improving the overall application efficiency of the increasingly important speech recognition workload for mobile user interaction. We broadly partition trends in GPU computing into four major categories. We analyze hardware and programming model limitations in current-generation GPUs and detail an alternate programming style called Persistent Threads, identify four use case patterns, and propose minimal modifications that would be required for extending native support. We show how by manually extracting data locality and altering the speech recognition pipeline, we are able to achieve significant savings in memory bandwidth while simultaneously reducing the compute burden on GPU-like parallel processors. As we foresee GPU computing to evolve from its current 'co-processor' model into an independent 'applications processor' that is capable of executing complex work independently, we create an alternate application framework that enables the GPU to handle all control-flow dependencies autonomously at run-time while minimizing host involvement to just issuing commands, that facilitates an efficient application implementation. Finally, as compute and communication capabilities of mobile devices improve, we analyze energy implications of processing speech recognition locally (on-chip) and offloading it to servers (in-cloud).

DNA Assembly with De Bruijn Graphs Using an FPGA Platform.

PubMed

Poirier, Carl; Gosselin, Benoit; Fortier, Paul

2018-01-01

This paper presents an FPGA implementation of a DNA assembly algorithm, called Ray, initially developed to run on parallel CPUs. The OpenCL language is used and the focus is placed on modifying and optimizing the original algorithm to better suit the new parallelization tool and the radically different hardware architecture. The results show that the execution time is roughly one fourth that of the CPU and factoring energy consumption yields a tenfold savings.

Parallel processing implementations of a contextual classifier for multispectral remote sensing data

NASA Technical Reports Server (NTRS)

Siegel, H. J.; Swain, P. H.; Smith, B. W.

1980-01-01

Contextual classifiers are being developed as a method to exploit the spatial/spectral context of a pixel to achieve accurate classification. Classification algorithms such as the contextual classifier typically require large amounts of computation time. One way to reduce the execution time of these tasks is through the use of parallelism. The applicability of the CDC flexible processor system and of a proposed multimicroprocessor system (PASM) for implementing contextual classifiers is examined.

An Evaluation of Database Solutions to Spatial Object Association

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kumar, V S; Kurc, T; Saltz, J

2008-06-24

Object association is a common problem encountered in many applications. Spatial object association, also referred to as crossmatch of spatial datasets, is the problem of identifying and comparing objects in two datasets based on their positions in a common spatial coordinate system--one of the datasets may correspond to a catalog of objects observed over time in a multi-dimensional domain; the other dataset may consist of objects observed in a snapshot of the domain at a time point. The use of database management systems to the solve the object association problem provides portability across different platforms and also greater flexibility. Increasingmore » dataset sizes in today's applications, however, have made object association a data/compute-intensive problem that requires targeted optimizations for efficient execution. In this work, we investigate how database-based crossmatch algorithms can be deployed on different database system architectures and evaluate the deployments to understand the impact of architectural choices on crossmatch performance and associated trade-offs. We investigate the execution of two crossmatch algorithms on (1) a parallel database system with active disk style processing capabilities, (2) a high-throughput network database (MySQL Cluster), and (3) shared-nothing databases with replication. We have conducted our study in the context of a large-scale astronomy application with real use-case scenarios.« less

Distributed spatial information integration based on web service

NASA Astrophysics Data System (ADS)

Tong, Hengjian; Zhang, Yun; Shao, Zhenfeng

2008-10-01

Spatial information systems and spatial information in different geographic locations usually belong to different organizations. They are distributed and often heterogeneous and independent from each other. This leads to the fact that many isolated spatial information islands are formed, reducing the efficiency of information utilization. In order to address this issue, we present a method for effective spatial information integration based on web service. The method applies asynchronous invocation of web service and dynamic invocation of web service to implement distributed, parallel execution of web map services. All isolated information islands are connected by the dispatcher of web service and its registration database to form a uniform collaborative system. According to the web service registration database, the dispatcher of web services can dynamically invoke each web map service through an asynchronous delegating mechanism. All of the web map services can be executed at the same time. When each web map service is done, an image will be returned to the dispatcher. After all of the web services are done, all images are transparently overlaid together in the dispatcher. Thus, users can browse and analyze the integrated spatial information. Experiments demonstrate that the utilization rate of spatial information resources is significantly raised thought the proposed method of distributed spatial information integration.

Distributed spatial information integration based on web service

NASA Astrophysics Data System (ADS)

Tong, Hengjian; Zhang, Yun; Shao, Zhenfeng

2009-10-01

Spatial information systems and spatial information in different geographic locations usually belong to different organizations. They are distributed and often heterogeneous and independent from each other. This leads to the fact that many isolated spatial information islands are formed, reducing the efficiency of information utilization. In order to address this issue, we present a method for effective spatial information integration based on web service. The method applies asynchronous invocation of web service and dynamic invocation of web service to implement distributed, parallel execution of web map services. All isolated information islands are connected by the dispatcher of web service and its registration database to form a uniform collaborative system. According to the web service registration database, the dispatcher of web services can dynamically invoke each web map service through an asynchronous delegating mechanism. All of the web map services can be executed at the same time. When each web map service is done, an image will be returned to the dispatcher. After all of the web services are done, all images are transparently overlaid together in the dispatcher. Thus, users can browse and analyze the integrated spatial information. Experiments demonstrate that the utilization rate of spatial information resources is significantly raised thought the proposed method of distributed spatial information integration.

Executive Functions and Motor Ability Contribute to Children's Participation in Daily Activities

ERIC Educational Resources Information Center

Rosenberg, Limor; Jacobi, Shani; Bart, Orit

2017-01-01

Executive functions are crucial for efficient daily functioning. However, the contribution of executive functions to the participation in daily life activities of children, have been inadequately studied. The study aimed to examine the unique contribution of executive functions, beyond motor ability, to the diversity and independence of children's…

A Survey of New Trends in Symbolic Execution for Software Testing and Analysis

NASA Technical Reports Server (NTRS)

Pasareanu, Corina S.; Visser, Willem

2009-01-01

Symbolic execution is a well-known program analysis technique which represents values of program inputs with symbolic values instead of concrete (initialized) data and executes the program by manipulating program expressions involving the symbolic values. Symbolic execution has been proposed over three decades ago but recently it has found renewed interest in the research community, due in part to the progress in decision procedures, availability of powerful computers and new algorithmic developments. We provide a survey of some of the new research trends in symbolic execution, with particular emphasis on applications to test generation and program analysis. We first describe an approach that handles complex programming constructs such as input data structures, arrays, as well as multi-threading. We follow with a discussion of abstraction techniques that can be used to limit the (possibly infinite) number of symbolic configurations that need to be analyzed for the symbolic execution of looping programs. Furthermore, we describe recent hybrid techniques that combine concrete and symbolic execution to overcome some of the inherent limitations of symbolic execution, such as handling native code or availability of decision procedures for the application domain. Finally, we give a short survey of interesting new applications, such as predictive testing, invariant inference, program repair, analysis of parallel numerical programs and differential symbolic execution.

A parallelized three-dimensional cellular automaton model for grain growth during additive manufacturing

NASA Astrophysics Data System (ADS)

Lian, Yanping; Lin, Stephen; Yan, Wentao; Liu, Wing Kam; Wagner, Gregory J.

2018-05-01

In this paper, a parallelized 3D cellular automaton computational model is developed to predict grain morphology for solidification of metal during the additive manufacturing process. Solidification phenomena are characterized by highly localized events, such as the nucleation and growth of multiple grains. As a result, parallelization requires careful treatment of load balancing between processors as well as interprocess communication in order to maintain a high parallel efficiency. We give a detailed summary of the formulation of the model, as well as a description of the communication strategies implemented to ensure parallel efficiency. Scaling tests on a representative problem with about half a billion cells demonstrate parallel efficiency of more than 80% on 8 processors and around 50% on 64; loss of efficiency is attributable to load imbalance due to near-surface grain nucleation in this test problem. The model is further demonstrated through an additive manufacturing simulation with resulting grain structures showing reasonable agreement with those observed in experiments.

A parallelized three-dimensional cellular automaton model for grain growth during additive manufacturing

NASA Astrophysics Data System (ADS)

Lian, Yanping; Lin, Stephen; Yan, Wentao; Liu, Wing Kam; Wagner, Gregory J.

2018-01-01

In this paper, a parallelized 3D cellular automaton computational model is developed to predict grain morphology for solidification of metal during the additive manufacturing process. Solidification phenomena are characterized by highly localized events, such as the nucleation and growth of multiple grains. As a result, parallelization requires careful treatment of load balancing between processors as well as interprocess communication in order to maintain a high parallel efficiency. We give a detailed summary of the formulation of the model, as well as a description of the communication strategies implemented to ensure parallel efficiency. Scaling tests on a representative problem with about half a billion cells demonstrate parallel efficiency of more than 80% on 8 processors and around 50% on 64; loss of efficiency is attributable to load imbalance due to near-surface grain nucleation in this test problem. The model is further demonstrated through an additive manufacturing simulation with resulting grain structures showing reasonable agreement with those observed in experiments.

ATDM LANL FleCSI: Topology and Execution Framework

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bergen, Benjamin Karl

FleCSI is a compile-time configurable C++ framework designed to support multi-physics application development. As such, FleCSI attempts to provide a very general set of infrastructure design patterns that can be specialized and extended to suit the needs of a broad variety of solver and data requirements. This means that FleCSI is potentially useful to many different ECP projects. Current support includes multidimensional mesh topology, mesh geometry, and mesh adjacency information, n-dimensional hashed-tree data structures, graph partitioning interfaces, and dependency closures (to identify data dependencies between distributed-memory address spaces). FleCSI introduces a functional programming model with control, execution, and data abstractionsmore » that are consistent with state-of-the-art task-based runtimes such as Legion and Charm++. The model also provides support for fine-grained, data-parallel execution with backend support for runtimes such as OpenMP and C++17. The FleCSI abstraction layer provides the developer with insulation from the underlying runtimes, while allowing support for multiple runtime systems, including conventional models like asynchronous MPI. The intent is to give developers a concrete set of user-friendly programming tools that can be used now, while allowing flexibility in choosing runtime implementations and optimizations that can be applied to architectures and runtimes that arise in the future. This project is essential to the ECP Ristra Next-Generation Code project, part of ASC ATDM, because it provides a hierarchically parallel programming model that is consistent with the design of modern system architectures, but which allows for the straightforward expression of algorithmic parallelism in a portably performant manner.« less

Multiprogramming performance degradation - Case study on a shared memory multiprocessor

NASA Technical Reports Server (NTRS)

Dimpsey, R. T.; Iyer, R. K.

1989-01-01

The performance degradation due to multiprogramming overhead is quantified for a parallel-processing machine. Measurements of real workloads were taken, and it was found that there is a moderate correlation between the completion time of a program and the amount of system overhead measured during program execution. Experiments in controlled environments were then conducted to calculate a lower bound on the performance degradation of parallel jobs caused by multiprogramming overhead. The results show that the multiprogramming overhead of parallel jobs consumes at least 4 percent of the processor time. When two or more serial jobs are introduced into the system, this amount increases to 5.3 percent

Fine-grained parallelization of fitness functions in bioinformatics optimization problems: gene selection for cancer classification and biclustering of gene expression data.

PubMed

Gomez-Pulido, Juan A; Cerrada-Barrios, Jose L; Trinidad-Amado, Sebastian; Lanza-Gutierrez, Jose M; Fernandez-Diaz, Ramon A; Crawford, Broderick; Soto, Ricardo

2016-08-31

Metaheuristics are widely used to solve large combinatorial optimization problems in bioinformatics because of the huge set of possible solutions. Two representative problems are gene selection for cancer classification and biclustering of gene expression data. In most cases, these metaheuristics, as well as other non-linear techniques, apply a fitness function to each possible solution with a size-limited population, and that step involves higher latencies than other parts of the algorithms, which is the reason why the execution time of the applications will mainly depend on the execution time of the fitness function. In addition, it is usual to find floating-point arithmetic formulations for the fitness functions. This way, a careful parallelization of these functions using the reconfigurable hardware technology will accelerate the computation, specially if they are applied in parallel to several solutions of the population. A fine-grained parallelization of two floating-point fitness functions of different complexities and features involved in biclustering of gene expression data and gene selection for cancer classification allowed for obtaining higher speedups and power-reduced computation with regard to usual microprocessors. The results show better performances using reconfigurable hardware technology instead of usual microprocessors, in computing time and power consumption terms, not only because of the parallelization of the arithmetic operations, but also thanks to the concurrent fitness evaluation for several individuals of the population in the metaheuristic. This is a good basis for building accelerated and low-energy solutions for intensive computing scenarios.

FPGA accelerator for protein secondary structure prediction based on the GOR algorithm

PubMed Central

2011-01-01

Background Protein is an important molecule that performs a wide range of functions in biological systems. Recently, the protein folding attracts much more attention since the function of protein can be generally derived from its molecular structure. The GOR algorithm is one of the most successful computational methods and has been widely used as an efficient analysis tool to predict secondary structure from protein sequence. However, the execution time is still intolerable with the steep growth in protein database. Recently, FPGA chips have emerged as one promising application accelerator to accelerate bioinformatics algorithms by exploiting fine-grained custom design. Results In this paper, we propose a complete fine-grained parallel hardware implementation on FPGA to accelerate the GOR-IV package for 2D protein structure prediction. To improve computing efficiency, we partition the parameter table into small segments and access them in parallel. We aggressively exploit data reuse schemes to minimize the need for loading data from external memory. The whole computation structure is carefully pipelined to overlap the sequence loading, computing and back-writing operations as much as possible. We implemented a complete GOR desktop system based on an FPGA chip XC5VLX330. Conclusions The experimental results show a speedup factor of more than 430x over the original GOR-IV version and 110x speedup over the optimized version with multi-thread SIMD implementation running on a PC platform with AMD Phenom 9650 Quad CPU for 2D protein structure prediction. However, the power consumption is only about 30% of that of current general-propose CPUs. PMID:21342582

Hadoop-GIS: A High Performance Spatial Data Warehousing System over MapReduce.

PubMed

Aji, Ablimit; Wang, Fusheng; Vo, Hoang; Lee, Rubao; Liu, Qiaoling; Zhang, Xiaodong; Saltz, Joel

2013-08-01

Support of high performance queries on large volumes of spatial data becomes increasingly important in many application domains, including geospatial problems in numerous fields, location based services, and emerging scientific applications that are increasingly data- and compute-intensive. The emergence of massive scale spatial data is due to the proliferation of cost effective and ubiquitous positioning technologies, development of high resolution imaging technologies, and contribution from a large number of community users. There are two major challenges for managing and querying massive spatial data to support spatial queries: the explosion of spatial data, and the high computational complexity of spatial queries. In this paper, we present Hadoop-GIS - a scalable and high performance spatial data warehousing system for running large scale spatial queries on Hadoop. Hadoop-GIS supports multiple types of spatial queries on MapReduce through spatial partitioning, customizable spatial query engine RESQUE, implicit parallel spatial query execution on MapReduce, and effective methods for amending query results through handling boundary objects. Hadoop-GIS utilizes global partition indexing and customizable on demand local spatial indexing to achieve efficient query processing. Hadoop-GIS is integrated into Hive to support declarative spatial queries with an integrated architecture. Our experiments have demonstrated the high efficiency of Hadoop-GIS on query response and high scalability to run on commodity clusters. Our comparative experiments have showed that performance of Hadoop-GIS is on par with parallel SDBMS and outperforms SDBMS for compute-intensive queries. Hadoop-GIS is available as a set of library for processing spatial queries, and as an integrated software package in Hive.

Hadoop-GIS: A High Performance Spatial Data Warehousing System over MapReduce

PubMed Central

Aji, Ablimit; Wang, Fusheng; Vo, Hoang; Lee, Rubao; Liu, Qiaoling; Zhang, Xiaodong; Saltz, Joel

2013-01-01

Support of high performance queries on large volumes of spatial data becomes increasingly important in many application domains, including geospatial problems in numerous fields, location based services, and emerging scientific applications that are increasingly data- and compute-intensive. The emergence of massive scale spatial data is due to the proliferation of cost effective and ubiquitous positioning technologies, development of high resolution imaging technologies, and contribution from a large number of community users. There are two major challenges for managing and querying massive spatial data to support spatial queries: the explosion of spatial data, and the high computational complexity of spatial queries. In this paper, we present Hadoop-GIS – a scalable and high performance spatial data warehousing system for running large scale spatial queries on Hadoop. Hadoop-GIS supports multiple types of spatial queries on MapReduce through spatial partitioning, customizable spatial query engine RESQUE, implicit parallel spatial query execution on MapReduce, and effective methods for amending query results through handling boundary objects. Hadoop-GIS utilizes global partition indexing and customizable on demand local spatial indexing to achieve efficient query processing. Hadoop-GIS is integrated into Hive to support declarative spatial queries with an integrated architecture. Our experiments have demonstrated the high efficiency of Hadoop-GIS on query response and high scalability to run on commodity clusters. Our comparative experiments have showed that performance of Hadoop-GIS is on par with parallel SDBMS and outperforms SDBMS for compute-intensive queries. Hadoop-GIS is available as a set of library for processing spatial queries, and as an integrated software package in Hive. PMID:24187650

a Novel Approach of Indexing and Retrieving Spatial Polygons for Efficient Spatial Region Queries

NASA Astrophysics Data System (ADS)

Zhao, J. H.; Wang, X. Z.; Wang, F. Y.; Shen, Z. H.; Zhou, Y. C.; Wang, Y. L.

2017-10-01

Spatial region queries are more and more widely used in web-based applications. Mechanisms to provide efficient query processing over geospatial data are essential. However, due to the massive geospatial data volume, heavy geometric computation, and high access concurrency, it is difficult to get response in real time. Spatial indexes are usually used in this situation. In this paper, based on k-d tree, we introduce a distributed KD-Tree (DKD-Tree) suitbable for polygon data, and a two-step query algorithm. The spatial index construction is recursive and iterative, and the query is an in memory process. Both the index and query methods can be processed in parallel, and are implemented based on HDFS, Spark and Redis. Experiments on a large volume of Remote Sensing images metadata have been carried out, and the advantages of our method are investigated by comparing with spatial region queries executed on PostgreSQL and PostGIS. Results show that our approach not only greatly improves the efficiency of spatial region query, but also has good scalability, Moreover, the two-step spatial range query algorithm can also save cluster resources to support a large number of concurrent queries. Therefore, this method is very useful when building large geographic information systems.

Image processing for a tactile/vision substitution system using digital CNN.

PubMed

Lin, Chien-Nan; Yu, Sung-Nien; Hu, Jin-Cheng

2006-01-01

In view of the parallel processing and easy implementation properties of CNN, we propose to use digital CNN as the image processor of a tactile/vision substitution system (TVSS). The digital CNN processor is used to execute the wavelet down-sampling filtering and the half-toning operations, aiming to extract important features from the images. A template combination method is used to embed the two image processing functions into a single CNN processor. The digital CNN processor is implemented on an intellectual property (IP) and is implemented on a XILINX VIRTEX II 2000 FPGA board. Experiments are designated to test the capability of the CNN processor in the recognition of characters and human subjects in different environments. The experiments demonstrates impressive results, which proves the proposed digital CNN processor a powerful component in the design of efficient tactile/vision substitution systems for the visually impaired people.

Wave scheduling - Decentralized scheduling of task forces in multicomputers

NASA Technical Reports Server (NTRS)

Van Tilborg, A. M.; Wittie, L. D.

1984-01-01

Decentralized operating systems that control large multicomputers need techniques to schedule competing parallel programs called task forces. Wave scheduling is a probabilistic technique that uses a hierarchical distributed virtual machine to schedule task forces by recursively subdividing and issuing wavefront-like commands to processing elements capable of executing individual tasks. Wave scheduling is highly resistant to processing element failures because it uses many distributed schedulers that dynamically assign scheduling responsibilities among themselves. The scheduling technique is trivially extensible as more processing elements join the host multicomputer. A simple model of scheduling cost is used by every scheduler node to distribute scheduling activity and minimize wasted processing capacity by using perceived workload to vary decentralized scheduling rules. At low to moderate levels of network activity, wave scheduling is only slightly less efficient than a central scheduler in its ability to direct processing elements to accomplish useful work.

A Gateway for Phylogenetic Analysis Powered by Grid Computing Featuring GARLI 2.0

PubMed Central

Bazinet, Adam L.; Zwickl, Derrick J.; Cummings, Michael P.

2014-01-01

We introduce molecularevolution.org, a publicly available gateway for high-throughput, maximum-likelihood phylogenetic analysis powered by grid computing. The gateway features a garli 2.0 web service that enables a user to quickly and easily submit thousands of maximum likelihood tree searches or bootstrap searches that are executed in parallel on distributed computing resources. The garli web service allows one to easily specify partitioned substitution models using a graphical interface, and it performs sophisticated post-processing of phylogenetic results. Although the garli web service has been used by the research community for over three years, here we formally announce the availability of the service, describe its capabilities, highlight new features and recent improvements, and provide details about how the grid system efficiently delivers high-quality phylogenetic results. [garli, gateway, grid computing, maximum likelihood, molecular evolution portal, phylogenetics, web service.] PMID:24789072

A gateway for phylogenetic analysis powered by grid computing featuring GARLI 2.0.

PubMed

Bazinet, Adam L; Zwickl, Derrick J; Cummings, Michael P

2014-09-01

We introduce molecularevolution.org, a publicly available gateway for high-throughput, maximum-likelihood phylogenetic analysis powered by grid computing. The gateway features a garli 2.0 web service that enables a user to quickly and easily submit thousands of maximum likelihood tree searches or bootstrap searches that are executed in parallel on distributed computing resources. The garli web service allows one to easily specify partitioned substitution models using a graphical interface, and it performs sophisticated post-processing of phylogenetic results. Although the garli web service has been used by the research community for over three years, here we formally announce the availability of the service, describe its capabilities, highlight new features and recent improvements, and provide details about how the grid system efficiently delivers high-quality phylogenetic results. © The Author(s) 2014. Published by Oxford University Press, on behalf of the Society of Systematic Biologists.

ClusCo: clustering and comparison of protein models.

PubMed

Jamroz, Michal; Kolinski, Andrzej

2013-02-22

The development, optimization and validation of protein modeling methods require efficient tools for structural comparison. Frequently, a large number of models need to be compared with the target native structure. The main reason for the development of Clusco software was to create a high-throughput tool for all-versus-all comparison, because calculating similarity matrix is the one of the bottlenecks in the protein modeling pipeline. Clusco is fast and easy-to-use software for high-throughput comparison of protein models with different similarity measures (cRMSD, dRMSD, GDT_TS, TM-Score, MaxSub, Contact Map Overlap) and clustering of the comparison results with standard methods: K-means Clustering or Hierarchical Agglomerative Clustering. The application was highly optimized and written in C/C++, including the code for parallel execution on CPU and GPU, which resulted in a significant speedup over similar clustering and scoring computation programs.

A high-speed linear algebra library with automatic parallelism

NASA Technical Reports Server (NTRS)

Boucher, Michael L.

1994-01-01

Parallel or distributed processing is key to getting highest performance workstations. However, designing and implementing efficient parallel algorithms is difficult and error-prone. It is even more difficult to write code that is both portable to and efficient on many different computers. Finally, it is harder still to satisfy the above requirements and include the reliability and ease of use required of commercial software intended for use in a production environment. As a result, the application of parallel processing technology to commercial software has been extremely small even though there are numerous computationally demanding programs that would significantly benefit from application of parallel processing. This paper describes DSSLIB, which is a library of subroutines that perform many of the time-consuming computations in engineering and scientific software. DSSLIB combines the high efficiency and speed of parallel computation with a serial programming model that eliminates many undesirable side-effects of typical parallel code. The result is a simple way to incorporate the power of parallel processing into commercial software without compromising maintainability, reliability, or ease of use. This gives significant advantages over less powerful non-parallel entries in the market.

Parallel Domain Decomposition Formulation and Software for Large-Scale Sparse Symmetrical/Unsymmetrical Aeroacoustic Applications

NASA Technical Reports Server (NTRS)

Nguyen, D. T.; Watson, Willie R. (Technical Monitor)

2005-01-01

The overall objectives of this research work are to formulate and validate efficient parallel algorithms, and to efficiently design/implement computer software for solving large-scale acoustic problems, arised from the unified frameworks of the finite element procedures. The adopted parallel Finite Element (FE) Domain Decomposition (DD) procedures should fully take advantages of multiple processing capabilities offered by most modern high performance computing platforms for efficient parallel computation. To achieve this objective. the formulation needs to integrate efficient sparse (and dense) assembly techniques, hybrid (or mixed) direct and iterative equation solvers, proper pre-conditioned strategies, unrolling strategies, and effective processors' communicating schemes. Finally, the numerical performance of the developed parallel finite element procedures will be evaluated by solving series of structural, and acoustic (symmetrical and un-symmetrical) problems (in different computing platforms). Comparisons with existing "commercialized" and/or "public domain" software are also included, whenever possible.

Parallel algorithm for computation of second-order sequential best rotations

NASA Astrophysics Data System (ADS)

Redif, Soydan; Kasap, Server

2013-12-01

Algorithms for computing an approximate polynomial matrix eigenvalue decomposition of para-Hermitian systems have emerged as a powerful, generic signal processing tool. A technique that has shown much success in this regard is the sequential best rotation (SBR2) algorithm. Proposed is a scheme for parallelising SBR2 with a view to exploiting the modern architectural features and inherent parallelism of field-programmable gate array (FPGA) technology. Experiments show that the proposed scheme can achieve low execution times while requiring minimal FPGA resources.

Connectionist Models: Proceedings of the Summer School Held in San Diego, California on 1990

DTIC Science & Technology

1990-01-01

modes: control network continues activation spreading based There is the sequential version and the parallel version on the actual inputs instead of...ent). 2. Execute all motoric actions based on activations of r a ent.The parallel version of the algorithm is local in time, units in A. Update the...a- movements that help o recognize an entering person.) tions like ’move focus left’, ’rotate focus’ are based on the activations of the C’s output

An Expert System for Automating Nuclear Strike Aircraft Replacement, Aircraft Beddown, and Logistics Movement for the Theater Warfare Exercise.

DTIC Science & Technology

1989-12-01

that can be easily understood. (9) Parallelism. Several system components may need to execute in parallel. For example, the processing of sensor data...knowledge base are not accessible for processing by the database. Also in the likely case that the expert system poses a series of related queries, the...hiharken nxpfilcs’Iog - Knowledge base for the automation of loCgistics rr-ovenet T’he Ii rectorY containing the strike aircraft replacement knowledge base

A class of parallel algorithms for computation of the manipulator inertia matrix

NASA Technical Reports Server (NTRS)

Fijany, Amir; Bejczy, Antal K.

1989-01-01

Parallel and parallel/pipeline algorithms for computation of the manipulator inertia matrix are presented. An algorithm based on composite rigid-body spatial inertia method, which provides better features for parallelization, is used for the computation of the inertia matrix. Two parallel algorithms are developed which achieve the time lower bound in computation. Also described is the mapping of these algorithms with topological variation on a two-dimensional processor array, with nearest-neighbor connection, and with cardinality variation on a linear processor array. An efficient parallel/pipeline algorithm for the linear array was also developed, but at significantly higher efficiency.

On the Optimality of Serial and Parallel Processing in the Psychological Refractory Period Paradigm: Effects of the Distribution of Stimulus Onset Asynchronies

ERIC Educational Resources Information Center

Miller, Jeff; Ulrich, Rolf; Rolke, Bettina

2009-01-01

Within the context of the psychological refractory period (PRP) paradigm, we developed a general theoretical framework for deciding when it is more efficient to process two tasks in serial and when it is more efficient to process them in parallel. This analysis suggests that a serial mode is more efficient than a parallel mode under a wide variety…

Large-Scale, Multi-Sensor Atmospheric Data Fusion Using Hybrid Cloud Computing

NASA Astrophysics Data System (ADS)

Wilson, Brian; Manipon, Gerald; Hua, Hook; Fetzer, Eric

2014-05-01

NASA's Earth Observing System (EOS) is an ambitious facility for studying global climate change. The mandate now is to combine measurements from the instruments on the "A-Train" platforms (AIRS, AMSR-E, MODIS, MISR, MLS, and CloudSat) and other Earth probes to enable large-scale studies of climate change over decades. Moving to multi-sensor, long-duration analyses of important climate variables presents serious challenges for large-scale data mining and fusion. For example, one might want to compare temperature and water vapor retrievals from one instrument (AIRS) to another (MODIS), and to a model (ECMWF), stratify the comparisons using a classification of the "cloud scenes" from CloudSat, and repeat the entire analysis over 10 years of data. To efficiently assemble such datasets, we are utilizing Elastic Computing in the Cloud and parallel map-reduce-based algorithms. However, these problems are Data Intensive computing so the data transfer times and storage costs (for caching) are key issues. SciReduce is a Hadoop-like parallel analysis system, programmed in parallel python, that is designed from the ground up for Earth science. SciReduce executes inside VMWare images and scales to any number of nodes in a hybrid Cloud (private eucalyptus & public Amazon). Unlike Hadoop, SciReduce operates on bundles of named numeric arrays, which can be passed in memory or serialized to disk in netCDF4 or HDF5. Multi-year datasets are automatically "sharded" by time and space across a cluster of nodes so that years of data (millions of files) can be processed in a massively parallel way. Input variables (arrays) are pulled on-demand into the Cloud using OPeNDAP URLs or other subsetting services, thereby minimizing the size of the cached input and intermediate datasets. We are using SciReduce to automate the production of multiple versions of a ten-year A-Train water vapor climatology under a NASA MEASURES grant. We will present the architecture of SciReduce, describe the achieved "clock time" speedups in fusing datasets on our own nodes and in the Cloud, and discuss the Cloud cost tradeoffs for storage, compute, and data transfer. We will also present a concept and prototype for staging NASA's A-Train Atmospheric datasets (Levels 2 & 3) in the Amazon Cloud so that any number of compute jobs can be executed "near" the multi-sensor data. Given such a system, multi-sensor climate studies over 10-20 years of data could be perform

Accelerating Dust Storm Simulation by Balancing Task Allocation in Parallel Computing Environment

NASA Astrophysics Data System (ADS)

Gui, Z.; Yang, C.; XIA, J.; Huang, Q.; YU, M.

2013-12-01

Dust storm has serious negative impacts on environment, human health, and assets. The continuing global climate change has increased the frequency and intensity of dust storm in the past decades. To better understand and predict the distribution, intensity and structure of dust storm, a series of dust storm models have been developed, such as Dust Regional Atmospheric Model (DREAM), the NMM meteorological module (NMM-dust) and Chinese Unified Atmospheric Chemistry Environment for Dust (CUACE/Dust). The developments and applications of these models have contributed significantly to both scientific research and our daily life. However, dust storm simulation is a data and computing intensive process. Normally, a simulation for a single dust storm event may take several days or hours to run. It seriously impacts the timeliness of prediction and potential applications. To speed up the process, high performance computing is widely adopted. By partitioning a large study area into small subdomains according to their geographic location and executing them on different computing nodes in a parallel fashion, the computing performance can be significantly improved. Since spatiotemporal correlations exist in the geophysical process of dust storm simulation, each subdomain allocated to a node need to communicate with other geographically adjacent subdomains to exchange data. Inappropriate allocations may introduce imbalance task loads and unnecessary communications among computing nodes. Therefore, task allocation method is the key factor, which may impact the feasibility of the paralleling. The allocation algorithm needs to carefully leverage the computing cost and communication cost for each computing node to minimize total execution time and reduce overall communication cost for the entire system. This presentation introduces two algorithms for such allocation and compares them with evenly distributed allocation method. Specifically, 1) In order to get optimized solutions, a quadratic programming based modeling method is proposed. This algorithm performs well with small amount of computing tasks. However, its efficiency decreases significantly as the subdomain number and computing node number increase. 2) To compensate performance decreasing for large scale tasks, a K-Means clustering based algorithm is introduced. Instead of dedicating to get optimized solutions, this method can get relatively good feasible solutions within acceptable time. However, it may introduce imbalance communication for nodes or node-isolated subdomains. This research shows both two algorithms have their own strength and weakness for task allocation. A combination of the two algorithms is under study to obtain a better performance. Keywords: Scheduling; Parallel Computing; Load Balance; Optimization; Cost Model

Parallel family trees for transfer matrices in the Potts model

NASA Astrophysics Data System (ADS)

Navarro, Cristobal A.; Canfora, Fabrizio; Hitschfeld, Nancy; Navarro, Gonzalo

2015-02-01

The computational cost of transfer matrix methods for the Potts model is related to the question in how many ways can two layers of a lattice be connected? Answering the question leads to the generation of a combinatorial set of lattice configurations. This set defines the configuration space of the problem, and the smaller it is, the faster the transfer matrix can be computed. The configuration space of generic (q , v) transfer matrix methods for strips is in the order of the Catalan numbers, which grows asymptotically as O(4m) where m is the width of the strip. Other transfer matrix methods with a smaller configuration space indeed exist but they make assumptions on the temperature, number of spin states, or restrict the structure of the lattice. In this paper we propose a parallel algorithm that uses a sub-Catalan configuration space of O(3m) to build the generic (q , v) transfer matrix in a compressed form. The improvement is achieved by grouping the original set of Catalan configurations into a forest of family trees, in such a way that the solution to the problem is now computed by solving the root node of each family. As a result, the algorithm becomes exponentially faster than the Catalan approach while still highly parallel. The resulting matrix is stored in a compressed form using O(3m ×4m) of space, making numerical evaluation and decompression to be faster than evaluating the matrix in its O(4m ×4m) uncompressed form. Experimental results for different sizes of strip lattices show that the parallel family trees (PFT) strategy indeed runs exponentially faster than the Catalan Parallel Method (CPM), especially when dealing with dense transfer matrices. In terms of parallel performance, we report strong-scaling speedups of up to 5.7 × when running on an 8-core shared memory machine and 28 × for a 32-core cluster. The best balance of speedup and efficiency for the multi-core machine was achieved when using p = 4 processors, while for the cluster scenario it was in the range p ∈ [ 8 , 10 ] . Because of the parallel capabilities of the algorithm, a large-scale execution of the parallel family trees strategy in a supercomputer could contribute to the study of wider strip lattices.