Enhanced memory architecture for massively parallel vision chip
Chen, Zhe; Yang, Jie; Liu, Liyuan; Wu, Nanjian
2015-04-01
Local memory architecture plays an important role in high performance massively parallel vision chip. In this paper, we propose an enhanced memory architecture with compact circuit area designed in a full-custom flow. The memory consists of separate master-stage static latches and shared slave-stage dynamic latches. We use split transmission transistors on the input data path to enhance tolerance for charge sharing and to achieve random read/write capabilities. The memory is designed in a 0.18 μm CMOS process. The area overhead of the memory achieves 16.6 μm2/bit. Simulation results show that the maximum operating frequency reaches 410 MHz and the corresponding peak dynamic power consumption for a 64-bit memory unit is 190 μW under 1.8 V supply voltage.
International Nuclear Information System (INIS)
Soltz, R; Vranas, P; Blumrich, M; Chen, D; Gara, A; Giampap, M; Heidelberger, P; Salapura, V; Sexton, J; Bhanot, G
2007-01-01
The theory of the strong nuclear force, Quantum Chromodynamics (QCD), can be numerically simulated from first principles on massively-parallel supercomputers using the method of Lattice Gauge Theory. We describe the special programming requirements of lattice QCD (LQCD) as well as the optimal supercomputer hardware architectures that it suggests. We demonstrate these methods on the BlueGene massively-parallel supercomputer and argue that LQCD and the BlueGene architecture are a natural match. This can be traced to the simple fact that LQCD is a regular lattice discretization of space into lattice sites while the BlueGene supercomputer is a discretization of space into compute nodes, and that both are constrained by requirements of locality. This simple relation is both technologically important and theoretically intriguing. The main result of this paper is the speedup of LQCD using up to 131,072 CPUs on the largest BlueGene/L supercomputer. The speedup is perfect with sustained performance of about 20% of peak. This corresponds to a maximum of 70.5 sustained TFlop/s. At these speeds LQCD and BlueGene are poised to produce the next generation of strong interaction physics theoretical results
The 2nd Symposium on the Frontiers of Massively Parallel Computations
Mills, Ronnie (Editor)
1988-01-01
Programming languages, computer graphics, neural networks, massively parallel computers, SIMD architecture, algorithms, digital terrain models, sort computation, simulation of charged particle transport on the massively parallel processor and image processing are among the topics discussed.
Application of Raptor-M3G to reactor dosimetry problems on massively parallel architectures - 026
International Nuclear Information System (INIS)
Longoni, G.
2010-01-01
The solution of complex 3-D radiation transport problems requires significant resources both in terms of computation time and memory availability. Therefore, parallel algorithms and multi-processor architectures are required to solve efficiently large 3-D radiation transport problems. This paper presents the application of RAPTOR-M3G (Rapid Parallel Transport Of Radiation - Multiple 3D Geometries) to reactor dosimetry problems. RAPTOR-M3G is a newly developed parallel computer code designed to solve the discrete ordinates (SN) equations on multi-processor computer architectures. This paper presents the results for a reactor dosimetry problem using a 3-D model of a commercial 2-loop pressurized water reactor (PWR). The accuracy and performance of RAPTOR-M3G will be analyzed and the numerical results obtained from the calculation will be compared directly to measurements of the neutron field in the reactor cavity air gap. The parallel performance of RAPTOR-M3G on massively parallel architectures, where the number of computing nodes is in the order of hundreds, will be analyzed up to four hundred processors. The performance results will be presented based on two supercomputing architectures: the POPLE supercomputer operated by the Pittsburgh Supercomputing Center and the Westinghouse computer cluster. The Westinghouse computer cluster is equipped with a standard Ethernet network connection and an InfiniBand R interconnects capable of a bandwidth in excess of 20 GBit/sec. Therefore, the impact of the network architecture on RAPTOR-M3G performance will be analyzed as well. (authors)
Massively parallel mathematical sieves
Energy Technology Data Exchange (ETDEWEB)
Montry, G.R.
1989-01-01
The Sieve of Eratosthenes is a well-known algorithm for finding all prime numbers in a given subset of integers. A parallel version of the Sieve is described that produces computational speedups over 800 on a hypercube with 1,024 processing elements for problems of fixed size. Computational speedups as high as 980 are achieved when the problem size per processor is fixed. The method of parallelization generalizes to other sieves and will be efficient on any ensemble architecture. We investigate two highly parallel sieves using scattered decomposition and compare their performance on a hypercube multiprocessor. A comparison of different parallelization techniques for the sieve illustrates the trade-offs necessary in the design and implementation of massively parallel algorithms for large ensemble computers.
Massively parallel quantum computer simulator
De Raedt, K.; Michielsen, K.; De Raedt, H.; Trieu, B.; Arnold, G.; Richter, M.; Lippert, Th.; Watanabe, H.; Ito, N.
2007-01-01
We describe portable software to simulate universal quantum computers on massive parallel Computers. We illustrate the use of the simulation software by running various quantum algorithms on different computer architectures, such as a IBM BlueGene/L, a IBM Regatta p690+, a Hitachi SR11000/J1, a Cray
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.
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.
International Nuclear Information System (INIS)
Andrade, Xavier; Aspuru-Guzik, Alán; Alberdi-Rodriguez, Joseba; Rubio, Angel; Strubbe, David A; Louie, Steven G; Oliveira, Micael J T; Nogueira, Fernando; Castro, Alberto; Muguerza, Javier; Arruabarrena, Agustin; Marques, Miguel A L
2012-01-01
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. (topical review)
Programming massively parallel processors a hands-on approach
Kirk, David B
2010-01-01
Programming Massively Parallel Processors discusses basic concepts about parallel programming and GPU architecture. ""Massively parallel"" refers to the use of a large number of processors to perform a set of computations in a coordinated parallel way. The book details various techniques for constructing parallel programs. It also discusses the development process, performance level, floating-point format, parallel patterns, and dynamic parallelism. The book serves as a teaching guide where parallel programming is the main topic of the course. It builds on the basics of C programming for CUDA, a parallel programming environment that is supported on NVI- DIA GPUs. Composed of 12 chapters, the book begins with basic information about the GPU as a parallel computer source. It also explains the main concepts of CUDA, data parallelism, and the importance of memory access efficiency using CUDA. The target audience of the book is graduate and undergraduate students from all science and engineering disciplines who ...
A Programming Model for Massive Data Parallelism with Data Dependencies
International Nuclear Information System (INIS)
Cui, Xiaohui; Mueller, Frank; Potok, Thomas E.; Zhang, Yongpeng
2009-01-01
Accelerating processors can often be more cost and energy effective for a wide range of data-parallel computing problems than general-purpose processors. For graphics processor units (GPUs), this is particularly the case when program development is aided by environments such as NVIDIA s Compute Unified Device Architecture (CUDA), which dramatically reduces the gap between domain-specific architectures and general purpose programming. Nonetheless, general-purpose GPU (GPGPU) programming remains subject to several restrictions. Most significantly, the separation of host (CPU) and accelerator (GPU) address spaces requires explicit management of GPU memory resources, especially for massive data parallelism that well exceeds the memory capacity of GPUs. One solution to this problem is to transfer data between the GPU and host memories frequently. In this work, we investigate another approach. We run massively data-parallel applications on GPU clusters. We further propose a programming model for massive data parallelism with data dependencies for this scenario. Experience from micro benchmarks and real-world applications shows that our model provides not only ease of programming but also significant performance gains
Massively parallel multicanonical simulations
Gross, Jonathan; Zierenberg, Johannes; Weigel, Martin; Janke, Wolfhard
2018-03-01
Generalized-ensemble Monte Carlo simulations such as the multicanonical method and similar techniques are among the most efficient approaches for simulations of systems undergoing discontinuous phase transitions or with rugged free-energy landscapes. As Markov chain methods, they are inherently serial computationally. It was demonstrated recently, however, that a combination of independent simulations that communicate weight updates at variable intervals allows for the efficient utilization of parallel computational resources for multicanonical simulations. Implementing this approach for the many-thread architecture provided by current generations of graphics processing units (GPUs), we show how it can be efficiently employed with of the order of 104 parallel walkers and beyond, thus constituting a versatile tool for Monte Carlo simulations in the era of massively parallel computing. We provide the fully documented source code for the approach applied to the paradigmatic example of the two-dimensional Ising model as starting point and reference for practitioners in the field.
The language parallel Pascal and other aspects of the massively parallel processor
Reeves, A. P.; Bruner, J. D.
1982-01-01
A high level language for the Massively Parallel Processor (MPP) was designed. This language, called Parallel Pascal, is described in detail. A description of the language design, a description of the intermediate language, Parallel P-Code, and details for the MPP implementation are included. Formal descriptions of Parallel Pascal and Parallel P-Code are given. A compiler was developed which converts programs in Parallel Pascal into the intermediate Parallel P-Code language. The code generator to complete the compiler for the MPP is being developed independently. A Parallel Pascal to Pascal translator was also developed. The architecture design for a VLSI version of the MPP was completed with a description of fault tolerant interconnection networks. The memory arrangement aspects of the MPP are discussed and a survey of other high level languages is given.
Mapping robust parallel multigrid algorithms to scalable memory architectures
Overman, Andrea; Vanrosendale, John
1993-01-01
The convergence rate of standard multigrid algorithms degenerates on problems with stretched grids or anisotropic operators. The usual cure for this is the use of line or plane relaxation. However, multigrid algorithms based on line and plane relaxation have limited and awkward parallelism and are quite difficult to map effectively to highly parallel architectures. Newer multigrid algorithms that overcome anisotropy through the use of multiple coarse grids rather than relaxation are better suited to massively parallel architectures because they require only simple point-relaxation smoothers. In this paper, we look at the parallel implementation of a V-cycle multiple semicoarsened grid (MSG) algorithm on distributed-memory architectures such as the Intel iPSC/860 and Paragon computers. The MSG algorithms provide two levels of parallelism: parallelism within the relaxation or interpolation on each grid and across the grids on each multigrid level. Both levels of parallelism must be exploited to map these algorithms effectively to parallel architectures. This paper describes a mapping of an MSG algorithm to distributed-memory architectures that demonstrates how both levels of parallelism can be exploited. The result is a robust and effective multigrid algorithm for distributed-memory machines.
Directory of Open Access Journals (Sweden)
Abdeslam Mehenni
2017-03-01
Full Text Available As our populations grow in a world of limited resources enterprise seek ways to lighten our load on the planet. The idea of modifying consumer behavior appears as a foundation for smart grids. Enterprise demonstrates the value available from deep analysis of electricity consummation histories, consumers’ messages, and outage alerts, etc. Enterprise mines massive structured and unstructured data. In a nutshell, smart grids result in a flood of data that needs to be analyzed, for better adjust to demand and give customers more ability to delve into their power consumption. Simply put, smart grids will increasingly have a flexible data warehouse attached to them. The key driver for the adoption of data management strategies is clearly the need to handle and analyze the large amounts of information utilities are now faced with. New approaches to data integration are nauseating moment; Hadoop is in fact now being used by the utility to help manage the huge growth in data whilst maintaining coherence of the Data Warehouse. In this paper we define a new Meter Data Management System Architecture repository that differ with three leaders MDMS, where we use MapReduce programming model for ETL and Parallel DBMS in Query statements(Massive Parallel Processing MPP.
Massive hybrid parallelism for fully implicit multiphysics
International Nuclear Information System (INIS)
Gaston, D. R.; Permann, C. J.; Andrs, D.; Peterson, J. W.
2013-01-01
As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided. (authors)
Massive hybrid parallelism for fully implicit multiphysics
Energy Technology Data Exchange (ETDEWEB)
Gaston, D. R.; Permann, C. J.; Andrs, D.; Peterson, J. W. [Idaho National Laboratory, 2525 N. Fremont Ave., Idaho Falls, ID 83415 (United States)
2013-07-01
As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided. (authors)
MASSIVE HYBRID PARALLELISM FOR FULLY IMPLICIT MULTIPHYSICS
Energy Technology Data Exchange (ETDEWEB)
Cody J. Permann; David Andrs; John W. Peterson; Derek R. Gaston
2013-05-01
As hardware advances continue to modify the supercomputing landscape, traditional scientific software development practices will become more outdated, ineffective, and inefficient. The process of rewriting/retooling existing software for new architectures is a Sisyphean task, and results in substantial hours of development time, effort, and money. Software libraries which provide an abstraction of the resources provided by such architectures are therefore essential if the computational engineering and science communities are to continue to flourish in this modern computing environment. The Multiphysics Object Oriented Simulation Environment (MOOSE) framework enables complex multiphysics analysis tools to be built rapidly by scientists, engineers, and domain specialists, while also allowing them to both take advantage of current HPC architectures, and efficiently prepare for future supercomputer designs. MOOSE employs a hybrid shared-memory and distributed-memory parallel model and provides a complete and consistent interface for creating multiphysics analysis tools. In this paper, a brief discussion of the mathematical algorithms underlying the framework and the internal object-oriented hybrid parallel design are given. Representative massively parallel results from several applications areas are presented, and a brief discussion of future areas of research for the framework are provided.
Analysis of multigrid methods on massively parallel computers: Architectural implications
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.
Solving the Stokes problem on a massively parallel computer
DEFF Research Database (Denmark)
Axelsson, Owe; Barker, Vincent A.; Neytcheva, Maya
2001-01-01
boundary value problem for each velocity component, are solved by the conjugate gradient method with a preconditioning based on the algebraic multi‐level iteration (AMLI) technique. The velocity is found from the computed pressure. The method is optimal in the sense that the computational work...... is proportional to the number of unknowns. Further, it is designed to exploit a massively parallel computer with distributed memory architecture. Numerical experiments on a Cray T3E computer illustrate the parallel performance of the method....
First massively parallel algorithm to be implemented in Apollo-II code
International Nuclear Information System (INIS)
Stankovski, Z.
1994-01-01
The collision probability (CP) method in neutron transport, as applied to arbitrary 2D XY geometries, like the TDT module in APOLLO-II, is very time consuming. Consequently RZ or 3D extensions became prohibitive. Fortunately, this method is very suitable for parallelization. Massively parallel computer architectures, especially MIMD machines, bring a new breath to this method. In this paper we present a CM5 implementation of the CP method. Parallelization is applied to the energy groups, using the CMMD message passing library. In our case we use 32 processors for the standard 99-group APOLLIB-II library. The real advantage of this algorithm will appear in the calculation of the future fine multigroup library (about 8000 groups) of the SAPHYR project with a massively parallel computer (to the order of hundreds of processors). (author). 3 tabs., 4 figs., 4 refs
First massively parallel algorithm to be implemented in APOLLO-II code
International Nuclear Information System (INIS)
Stankovski, Z.
1994-01-01
The collision probability method in neutron transport, as applied to arbitrary 2-dimensional geometries, like the two dimensional transport module in APOLLO-II is very time consuming. Consequently 3-dimensional extension became prohibitive. Fortunately, this method is very suitable for parallelization. Massively parallel computer architectures, especially MIMD machines, bring a new breath to this method. In this paper we present a CM5 implementation of the collision probability method. Parallelization is applied to the energy groups, using the CMMD massage passing library. In our case we used 32 processors for the standard 99-group APOLLIB-II library. The real advantage of this algorithm will appear in the calculation of the future multigroup library (about 8000 groups) of the SAPHYR project with a massively parallel computer (to the order of hundreds of processors). (author). 4 refs., 4 figs., 3 tabs
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1992-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1993-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well. (orig.)
Massively parallel Fokker-Planck calculations
International Nuclear Information System (INIS)
Mirin, A.A.
1990-01-01
This paper reports that the Fokker-Planck package FPPAC, which solves the complete nonlinear multispecies Fokker-Planck collision operator for a plasma in two-dimensional velocity space, has been rewritten for the Connection Machine 2. This has involved allocation of variables either to the front end or the CM2, minimization of data flow, and replacement of Cray-optimized algorithms with ones suitable for a massively parallel architecture. Calculations have been carried out on various Connection Machines throughout the country. Results and timings on these machines have been compared to each other and to those on the static memory Cray-2. For large problem size, the Connection Machine 2 is found to be cost-efficient
Parallel processing architecture for H.264 deblocking filter on multi-core platforms
Prasad, Durga P.; Sonachalam, Sekar; Kunchamwar, Mangesh K.; Gunupudi, Nageswara Rao
2012-03-01
Massively parallel computing (multi-core) chips offer outstanding new solutions that satisfy the increasing demand for high resolution and high quality video compression technologies such as H.264. Such solutions not only provide exceptional quality but also efficiency, low power, and low latency, previously unattainable in software based designs. While custom hardware and Application Specific Integrated Circuit (ASIC) technologies may achieve lowlatency, low power, and real-time performance in some consumer devices, many applications require a flexible and scalable software-defined solution. The deblocking filter in H.264 encoder/decoder poses difficult implementation challenges because of heavy data dependencies and the conditional nature of the computations. Deblocking filter implementations tend to be fixed and difficult to reconfigure for different needs. The ability to scale up for higher quality requirements such as 10-bit pixel depth or a 4:2:2 chroma format often reduces the throughput of a parallel architecture designed for lower feature set. A scalable architecture for deblocking filtering, created with a massively parallel processor based solution, means that the same encoder or decoder will be deployed in a variety of applications, at different video resolutions, for different power requirements, and at higher bit-depths and better color sub sampling patterns like YUV, 4:2:2, or 4:4:4 formats. Low power, software-defined encoders/decoders may be implemented using a massively parallel processor array, like that found in HyperX technology, with 100 or more cores and distributed memory. The large number of processor elements allows the silicon device to operate more efficiently than conventional DSP or CPU technology. This software programing model for massively parallel processors offers a flexible implementation and a power efficiency close to that of ASIC solutions. This work describes a scalable parallel architecture for an H.264 compliant deblocking
Scientific programming on massively parallel processor CP-PACS
International Nuclear Information System (INIS)
Boku, Taisuke
1998-01-01
The massively parallel processor CP-PACS takes various problems of calculation physics as the object, and it has been designed so that its architecture has been devised to do various numerical processings. In this report, the outline of the CP-PACS and the example of programming in the Kernel CG benchmark in NAS Parallel Benchmarks, version 1, are shown, and the pseudo vector processing mechanism and the parallel processing tuning of scientific and technical computation utilizing the three-dimensional hyper crossbar net, which are two great features of the architecture of the CP-PACS are described. As for the CP-PACS, the PUs based on RISC processor and added with pseudo vector processor are used. Pseudo vector processing is realized as the loop processing by scalar command. The features of the connection net of PUs are explained. The algorithm of the NPB version 1 Kernel CG is shown. The part that takes the time for processing most in the main loop is the product of matrix and vector (matvec), and the parallel processing of the matvec is explained. The time for the computation by the CPU is determined. As the evaluation of the performance, the evaluation of the time for execution, the short vector processing of pseudo vector processor based on slide window, and the comparison with other parallel computers are reported. (K.I.)
High-Efficient Parallel CAVLC Encoders on Heterogeneous Multicore Architectures
Directory of Open Access Journals (Sweden)
H. Y. Su
2012-04-01
Full Text Available This article presents two high-efficient parallel realizations of the context-based adaptive variable length coding (CAVLC based on heterogeneous multicore processors. By optimizing the architecture of the CAVLC encoder, three kinds of dependences are eliminated or weaken, including the context-based data dependence, the memory accessing dependence and the control dependence. The CAVLC pipeline is divided into three stages: two scans, coding, and lag packing, and be implemented on two typical heterogeneous multicore architectures. One is a block-based SIMD parallel CAVLC encoder on multicore stream processor STORM. The other is a component-oriented SIMT parallel encoder on massively parallel architecture GPU. Both of them exploited rich data-level parallelism. Experiments results show that compared with the CPU version, more than 70 times of speedup can be obtained for STORM and over 50 times for GPU. The implementation of encoder on STORM can make a real-time processing for 1080p @30fps and GPU-based version can satisfy the requirements for 720p real-time encoding. The throughput of the presented CAVLC encoders is more than 10 times higher than that of published software encoders on DSP and multicore platforms.
Parallel k-means++ for Multiple Shared-Memory Architectures
Energy Technology Data Exchange (ETDEWEB)
Mackey, Patrick S.; Lewis, Robert R.
2016-09-22
In recent years k-means++ has become a popular initialization technique for improved k-means clustering. To date, most of the work done to improve its performance has involved parallelizing algorithms that are only approximations of k-means++. In this paper we present a parallelization of the exact k-means++ algorithm, with a proof of its correctness. We develop implementations for three distinct shared-memory architectures: multicore CPU, high performance GPU, and the massively multithreaded Cray XMT platform. We demonstrate the scalability of the algorithm on each platform. In addition we present a visual approach for showing which platform performed k-means++ the fastest for varying data sizes.
Intelligent trigger by massively parallel processors for high energy physics experiments
International Nuclear Information System (INIS)
Rohrbach, F.; Vesztergombi, G.
1992-01-01
The CERN-MPPC collaboration concentrates its effort on the development of machines based on massive parallelism with thousands of integrated processing elements, arranged in a string. Seven applications are under detailed studies within the collaboration: three for LHC, one for SSC, two for fixed target high energy physics at CERN and one for HDTV. Preliminary results are presented. They show that the objectives should be reached with the use of the ASP architecture. (author)
Massively Parallel Computing: A Sandia Perspective
Energy Technology Data Exchange (ETDEWEB)
Dosanjh, Sudip S.; Greenberg, David S.; Hendrickson, Bruce; Heroux, Michael A.; Plimpton, Steve J.; Tomkins, James L.; Womble, David E.
1999-05-06
The computing power available to scientists and engineers has increased dramatically in the past decade, due in part to progress in making massively parallel computing practical and available. The expectation for these machines has been great. The reality is that progress has been slower than expected. Nevertheless, massively parallel computing is beginning to realize its potential for enabling significant break-throughs in science and engineering. This paper provides a perspective on the state of the field, colored by the authors' experiences using large scale parallel machines at Sandia National Laboratories. We address trends in hardware, system software and algorithms, and we also offer our view of the forces shaping the parallel computing industry.
Micro-mechanical Simulations of Soils using Massively Parallel Supercomputers
Directory of Open Access Journals (Sweden)
David W. Washington
2004-06-01
Full Text Available In this research a computer program, Trubal version 1.51, based on the Discrete Element Method was converted to run on a Connection Machine (CM-5,a massively parallel supercomputer with 512 nodes, to expedite the computational times of simulating Geotechnical boundary value problems. The dynamic memory algorithm in Trubal program did not perform efficiently in CM-2 machine with the Single Instruction Multiple Data (SIMD architecture. This was due to the communication overhead involving global array reductions, global array broadcast and random data movement. Therefore, a dynamic memory algorithm in Trubal program was converted to a static memory arrangement and Trubal program was successfully converted to run on CM-5 machines. The converted program was called "TRUBAL for Parallel Machines (TPM." Simulating two physical triaxial experiments and comparing simulation results with Trubal simulations validated the TPM program. With a 512 nodes CM-5 machine TPM produced a nine-fold speedup demonstrating the inherent parallelism within algorithms based on the Discrete Element Method.
Massively Parallel Algorithms for Solution of Schrodinger Equation
Fijany, Amir; Barhen, Jacob; Toomerian, Nikzad
1994-01-01
In this paper massively parallel algorithms for solution of Schrodinger equation are developed. Our results clearly indicate that the Crank-Nicolson method, in addition to its excellent numerical properties, is also highly suitable for massively parallel computation.
Adapting algorithms to massively parallel hardware
Sioulas, Panagiotis
2016-01-01
In the recent years, the trend in computing has shifted from delivering processors with faster clock speeds to increasing the number of cores per processor. This marks a paradigm shift towards parallel programming in which applications are programmed to exploit the power provided by multi-cores. Usually there is gain in terms of the time-to-solution and the memory footprint. Specifically, this trend has sparked an interest towards massively parallel systems that can provide a large number of processors, and possibly computing nodes, as in the GPUs and MPPAs (Massively Parallel Processor Arrays). In this project, the focus was on two distinct computing problems: k-d tree searches and track seeding cellular automata. The goal was to adapt the algorithms to parallel systems and evaluate their performance in different cases.
A Massively Parallel Face Recognition System
Directory of Open Access Journals (Sweden)
Lahdenoja Olli
2007-01-01
Full Text Available We present methods for processing the LBPs (local binary patterns with a massively parallel hardware, especially with CNN-UM (cellular nonlinear network-universal machine. In particular, we present a framework for implementing a massively parallel face recognition system, including a dedicated highly accurate algorithm suitable for various types of platforms (e.g., CNN-UM and digital FPGA. We study in detail a dedicated mixed-mode implementation of the algorithm and estimate its implementation cost in the view of its performance and accuracy restrictions.
A Massively Parallel Face Recognition System
Directory of Open Access Journals (Sweden)
Ari Paasio
2006-12-01
Full Text Available We present methods for processing the LBPs (local binary patterns with a massively parallel hardware, especially with CNN-UM (cellular nonlinear network-universal machine. In particular, we present a framework for implementing a massively parallel face recognition system, including a dedicated highly accurate algorithm suitable for various types of platforms (e.g., CNN-UM and digital FPGA. We study in detail a dedicated mixed-mode implementation of the algorithm and estimate its implementation cost in the view of its performance and accuracy restrictions.
Designing Next Generation Massively Multithreaded Architectures for Irregular Applications
Energy Technology Data Exchange (ETDEWEB)
Tumeo, Antonino; Secchi, Simone; Villa, Oreste
2012-08-31
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 reference 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.
Massively parallel fabrication of repetitive nanostructures: nanolithography for nanoarrays
International Nuclear Information System (INIS)
Luttge, Regina
2009-01-01
This topical review provides an overview of nanolithographic techniques for nanoarrays. Using patterning techniques such as lithography, normally we aim for a higher order architecture similarly to functional systems in nature. Inspired by the wealth of complexity in nature, these architectures are translated into technical devices, for example, found in integrated circuitry or other systems in which structural elements work as discrete building blocks in microdevices. Ordered artificial nanostructures (arrays of pillars, holes and wires) have shown particular properties and bring about the opportunity to modify and tune the device operation. Moreover, these nanostructures deliver new applications, for example, the nanoscale control of spin direction within a nanomagnet. Subsequently, we can look for applications where this unique property of the smallest manufactured element is repetitively used such as, for example with respect to spin, in nanopatterned magnetic media for data storage. These nanostructures are generally called nanoarrays. Most of these applications require massively parallel produced nanopatterns which can be directly realized by laser interference (areas up to 4 cm 2 are easily achieved with a Lloyd's mirror set-up). In this topical review we will further highlight the application of laser interference as a tool for nanofabrication, its limitations and ultimate advantages towards a variety of devices including nanostructuring for photonic crystal devices, high resolution patterned media and surface modifications of medical implants. The unique properties of nanostructured surfaces have also found applications in biomedical nanoarrays used either for diagnostic or functional assays including catalytic reactions on chip. Bio-inspired templated nanoarrays will be presented in perspective to other massively parallel nanolithography techniques currently discussed in the scientific literature. (topical review)
Neural Parallel Engine: A toolbox for massively parallel neural signal processing.
Tam, Wing-Kin; Yang, Zhi
2018-05-01
Large-scale neural recordings provide detailed information on neuronal activities and can help elicit the underlying neural mechanisms of the brain. However, the computational burden is also formidable when we try to process the huge data stream generated by such recordings. In this study, we report the development of Neural Parallel Engine (NPE), a toolbox for massively parallel neural signal processing on graphical processing units (GPUs). It offers a selection of the most commonly used routines in neural signal processing such as spike detection and spike sorting, including advanced algorithms such as exponential-component-power-component (EC-PC) spike detection and binary pursuit spike sorting. We also propose a new method for detecting peaks in parallel through a parallel compact operation. Our toolbox is able to offer a 5× to 110× speedup compared with its CPU counterparts depending on the algorithms. A user-friendly MATLAB interface is provided to allow easy integration of the toolbox into existing workflows. Previous efforts on GPU neural signal processing only focus on a few rudimentary algorithms, are not well-optimized and often do not provide a user-friendly programming interface to fit into existing workflows. There is a strong need for a comprehensive toolbox for massively parallel neural signal processing. A new toolbox for massively parallel neural signal processing has been created. It can offer significant speedup in processing signals from large-scale recordings up to thousands of channels. Copyright © 2018 Elsevier B.V. All rights reserved.
PUMA: An Operating System for Massively Parallel Systems
Directory of Open Access Journals (Sweden)
Stephen R. Wheat
1994-01-01
Full Text Available This article presents an overview of PUMA (Performance-oriented, User-managed Messaging Architecture, a message-passing kernel for massively parallel systems. Message passing in PUMA is based on portals – an opening in the address space of an application process. Once an application process has established a portal, other processes can write values into the portal using a simple send operation. Because messages are written directly into the address space of the receiving process, there is no need to buffer messages in the PUMA kernel and later copy them into the applications address space. PUMA consists of two components: the quintessential kernel (Q-Kernel and the process control thread (PCT. Although the PCT provides management decisions, the Q-Kernel controls access and implements the policies specified by the PCT.
RAMA: A file system for massively parallel computers
Miller, Ethan L.; Katz, Randy H.
1993-01-01
This paper describes a file system design for massively parallel computers which makes very efficient use of a few disks per processor. This overcomes the traditional I/O bottleneck of massively parallel machines by storing the data on disks within the high-speed interconnection network. In addition, the file system, called RAMA, requires little inter-node synchronization, removing another common bottleneck in parallel processor file systems. Support for a large tertiary storage system can easily be integrated in lo the file system; in fact, RAMA runs most efficiently when tertiary storage is used.
Frontiers of massively parallel scientific computation
International Nuclear Information System (INIS)
Fischer, J.R.
1987-07-01
Practical applications using massively parallel computer hardware first appeared during the 1980s. Their development was motivated by the need for computing power orders of magnitude beyond that available today for tasks such as numerical simulation of complex physical and biological processes, generation of interactive visual displays, satellite image analysis, and knowledge based systems. Representative of the first generation of this new class of computers is the Massively Parallel Processor (MPP). A team of scientists was provided the opportunity to test and implement their algorithms on the MPP. The first results are presented. The research spans a broad variety of applications including Earth sciences, physics, signal and image processing, computer science, and graphics. The performance of the MPP was very good. Results obtained using the Connection Machine and the Distributed Array Processor (DAP) are presented
Massively parallel Fokker-Planck code ALLAp
International Nuclear Information System (INIS)
Batishcheva, A.A.; Krasheninnikov, S.I.; Craddock, G.G.; Djordjevic, V.
1996-01-01
The recently developed for workstations Fokker-Planck code ALLA simulates the temporal evolution of 1V, 2V and 1D2V collisional edge plasmas. In this work we present the results of code parallelization on the CRI T3D massively parallel platform (ALLAp version). Simultaneously we benchmark the 1D2V parallel vesion against an analytic self-similar solution of the collisional kinetic equation. This test is not trivial as it demands a very strong spatial temperature and density variation within the simulation domain. (orig.)
Multi-mode sensor processing on a dynamically reconfigurable massively parallel processor array
Chen, Paul; Butts, Mike; Budlong, Brad; Wasson, Paul
2008-04-01
This paper introduces a novel computing architecture that can be reconfigured in real time to adapt on demand to multi-mode sensor platforms' dynamic computational and functional requirements. This 1 teraOPS reconfigurable Massively Parallel Processor Array (MPPA) has 336 32-bit processors. The programmable 32-bit communication fabric provides streamlined inter-processor connections with deterministically high performance. Software programmability, scalability, ease of use, and fast reconfiguration time (ranging from microseconds to milliseconds) are the most significant advantages over FPGAs and DSPs. This paper introduces the MPPA architecture, its programming model, and methods of reconfigurability. An MPPA platform for reconfigurable computing is based on a structural object programming model. Objects are software programs running concurrently on hundreds of 32-bit RISC processors and memories. They exchange data and control through a network of self-synchronizing channels. A common application design pattern on this platform, called a work farm, is a parallel set of worker objects, with one input and one output stream. Statically configured work farms with homogeneous and heterogeneous sets of workers have been used in video compression and decompression, network processing, and graphics applications.
Impact analysis on a massively parallel computer
International Nuclear Information System (INIS)
Zacharia, T.; Aramayo, G.A.
1994-01-01
Advanced mathematical techniques and computer simulation play a major role in evaluating and enhancing the design of beverage cans, industrial, and transportation containers for improved performance. Numerical models are used to evaluate the impact requirements of containers used by the Department of Energy (DOE) for transporting radioactive materials. Many of these models are highly compute-intensive. An analysis may require several hours of computational time on current supercomputers despite the simplicity of the models being studied. As computer simulations and materials databases grow in complexity, massively parallel computers have become important tools. Massively parallel computational research at the Oak Ridge National Laboratory (ORNL) and its application to the impact analysis of shipping containers is briefly described in this paper
Introduction to parallel algorithms and architectures arrays, trees, hypercubes
Leighton, F Thomson
1991-01-01
Introduction to Parallel Algorithms and Architectures: Arrays Trees Hypercubes provides an introduction to the expanding field of parallel algorithms and architectures. This book focuses on parallel computation involving the most popular network architectures, namely, arrays, trees, hypercubes, and some closely related networks.Organized into three chapters, this book begins with an overview of the simplest architectures of arrays and trees. This text then presents the structures and relationships between the dominant network architectures, as well as the most efficient parallel algorithms for
Distributed Parallel Architecture for "Big Data"
Directory of Open Access Journals (Sweden)
Catalin BOJA
2012-01-01
Full Text Available This paper is an extension to the "Distributed Parallel Architecture for Storing and Processing Large Datasets" paper presented at the WSEAS SEPADS’12 conference in Cambridge. In its original version the paper went over the benefits of using a distributed parallel architecture to store and process large datasets. This paper analyzes the problem of storing, processing and retrieving meaningful insight from petabytes of data. It provides a survey on current distributed and parallel data processing technologies and, based on them, will propose an architecture that can be used to solve the analyzed problem. In this version there is more emphasis put on distributed files systems and the ETL processes involved in a distributed environment.
Massively parallel evolutionary computation on GPGPUs
Tsutsui, Shigeyoshi
2013-01-01
Evolutionary algorithms (EAs) are metaheuristics that learn from natural collective behavior and are applied to solve optimization problems in domains such as scheduling, engineering, bioinformatics, and finance. Such applications demand acceptable solutions with high-speed execution using finite computational resources. Therefore, there have been many attempts to develop platforms for running parallel EAs using multicore machines, massively parallel cluster machines, or grid computing environments. Recent advances in general-purpose computing on graphics processing units (GPGPU) have opened u
Introduction to massively-parallel computing in high-energy physics
AUTHOR|(CDS)2083520
1993-01-01
Ever since computers were first used for scientific and numerical work, there has existed an "arms race" between the technical development of faster computing hardware, and the desires of scientists to solve larger problems in shorter time-scales. However, the vast leaps in processor performance achieved through advances in semi-conductor science have reached a hiatus as the technology comes up against the physical limits of the speed of light and quantum effects. This has lead all high performance computer manufacturers to turn towards a parallel architecture for their new machines. In these lectures we will introduce the history and concepts behind parallel computing, and review the various parallel architectures and software environments currently available. We will then introduce programming methodologies that allow efficient exploitation of parallel machines, and present case studies of the parallelization of typical High Energy Physics codes for the two main classes of parallel computing architecture (S...
Mills, R. T.; Rupp, K.; Smith, B. F.; Brown, J.; Knepley, M.; Zhang, H.; Adams, M.; Hammond, G. E.
2017-12-01
As the high-performance computing community pushes towards the exascale horizon, power and heat considerations have driven the increasing importance and prevalence of fine-grained parallelism in new computer architectures. High-performance computing centers have become increasingly reliant on GPGPU accelerators and "manycore" processors such as the Intel Xeon Phi line, and 512-bit SIMD registers have even been introduced in the latest generation of Intel's mainstream Xeon server processors. The high degree of fine-grained parallelism and more complicated memory hierarchy considerations of such "manycore" processors present several challenges to existing scientific software. Here, we consider how the massively parallel, open-source hydrologic flow and reactive transport code PFLOTRAN - and the underlying Portable, Extensible Toolkit for Scientific Computation (PETSc) library on which it is built - can best take advantage of such architectures. We will discuss some key features of these novel architectures and our code optimizations and algorithmic developments targeted at them, and present experiences drawn from working with a wide range of PFLOTRAN benchmark problems on these architectures.
Gunnels, John; Lee, Jon; Margulies, Susan
2010-01-01
We provide a first demonstration of the idea that matrix-based algorithms for nonlinear combinatorial optimization problems can be efficiently implemented. Such algorithms were mainly conceived by theoretical computer scientists for proving efficiency. We are able to demonstrate the practicality of our approach by developing an implementation on a massively parallel architecture, and exploiting scalable and efficient parallel implementations of algorithms for ultra high-precision linear algebra. Additionally, we have delineated and implemented the necessary algorithmic and coding changes required in order to address problems several orders of magnitude larger, dealing with the limits of scalability from memory footprint, computational efficiency, reliability, and interconnect perspectives. © Springer and Mathematical Programming Society 2010.
Gunnels, John
2010-06-01
We provide a first demonstration of the idea that matrix-based algorithms for nonlinear combinatorial optimization problems can be efficiently implemented. Such algorithms were mainly conceived by theoretical computer scientists for proving efficiency. We are able to demonstrate the practicality of our approach by developing an implementation on a massively parallel architecture, and exploiting scalable and efficient parallel implementations of algorithms for ultra high-precision linear algebra. Additionally, we have delineated and implemented the necessary algorithmic and coding changes required in order to address problems several orders of magnitude larger, dealing with the limits of scalability from memory footprint, computational efficiency, reliability, and interconnect perspectives. © Springer and Mathematical Programming Society 2010.
Massively parallel sequencing of forensic STRs
DEFF Research Database (Denmark)
Parson, Walther; Ballard, David; Budowle, Bruce
2016-01-01
The DNA Commission of the International Society for Forensic Genetics (ISFG) is reviewing factors that need to be considered ahead of the adoption by the forensic community of short tandem repeat (STR) genotyping by massively parallel sequencing (MPS) technologies. MPS produces sequence data that...
A discrete ordinate response matrix method for massively parallel computers
International Nuclear Information System (INIS)
Hanebutte, U.R.; Lewis, E.E.
1991-01-01
A discrete ordinate response matrix method is formulated for the solution of neutron transport problems on massively parallel computers. The response matrix formulation eliminates iteration on the scattering source. The nodal matrices which result from the diamond-differenced equations are utilized in a factored form which minimizes memory requirements and significantly reduces the required number of algorithm utilizes massive parallelism by assigning each spatial node to a processor. The algorithm is accelerated effectively by a synthetic method in which the low-order diffusion equations are also solved by massively parallel red/black iterations. The method has been implemented on a 16k Connection Machine-2, and S 8 and S 16 solutions have been obtained for fixed-source benchmark problems in X--Y geometry
Advanced parallel processing with supercomputer architectures
International Nuclear Information System (INIS)
Hwang, K.
1987-01-01
This paper investigates advanced parallel processing techniques and innovative hardware/software architectures that can be applied to boost the performance of supercomputers. Critical issues on architectural choices, parallel languages, compiling techniques, resource management, concurrency control, programming environment, parallel algorithms, and performance enhancement methods are examined and the best answers are presented. The authors cover advanced processing techniques suitable for supercomputers, high-end mainframes, minisupers, and array processors. The coverage emphasizes vectorization, multitasking, multiprocessing, and distributed computing. In order to achieve these operation modes, parallel languages, smart compilers, synchronization mechanisms, load balancing methods, mapping parallel algorithms, operating system functions, application library, and multidiscipline interactions are investigated to ensure high performance. At the end, they assess the potentials of optical and neural technologies for developing future supercomputers
Energy Technology Data Exchange (ETDEWEB)
1991-10-23
An account of the Caltech Concurrent Computation Program (C{sup 3}P), a five year project that focused on answering the question: Can parallel computers be used to do large-scale scientific computations '' As the title indicates, the question is answered in the affirmative, by implementing numerous scientific applications on real parallel computers and doing computations that produced new scientific results. In the process of doing so, C{sup 3}P helped design and build several new computers, designed and implemented basic system software, developed algorithms for frequently used mathematical computations on massively parallel machines, devised performance models and measured the performance of many computers, and created a high performance computing facility based exclusively on parallel computers. While the initial focus of C{sup 3}P was the hypercube architecture developed by C. Seitz, many of the methods developed and lessons learned have been applied successfully on other massively parallel architectures.
Template based parallel checkpointing in a massively parallel computer system
Archer, Charles Jens [Rochester, MN; Inglett, Todd Alan [Rochester, MN
2009-01-13
A method and apparatus for a template based parallel checkpoint save for a massively parallel super computer system using a parallel variation of the rsync protocol, and network broadcast. In preferred embodiments, the checkpoint data for each node is compared to a template checkpoint file that resides in the storage and that was previously produced. Embodiments herein greatly decrease the amount of data that must be transmitted and stored for faster checkpointing and increased efficiency of the computer system. Embodiments are directed to a parallel computer system with nodes arranged in a cluster with a high speed interconnect that can perform broadcast communication. The checkpoint contains a set of actual small data blocks with their corresponding checksums from all nodes in the system. The data blocks may be compressed using conventional non-lossy data compression algorithms to further reduce the overall checkpoint size.
Parallel Architectures and Parallel Algorithms for Integrated Vision Systems. Ph.D. Thesis
Choudhary, Alok Nidhi
1989-01-01
Computer vision is regarded as one of the most complex and computationally intensive problems. An integrated vision system (IVS) is a system that uses vision algorithms from all levels of processing to perform for a high level application (e.g., object recognition). An IVS normally involves algorithms from low level, intermediate level, and high level vision. Designing parallel architectures for vision systems is of tremendous interest to researchers. Several issues are addressed in parallel architectures and parallel algorithms for integrated vision systems.
International Nuclear Information System (INIS)
Michel, J.
1993-02-01
This doctorate thesis studies an integrated architecture designed to a parallel massive treatment of analogue signals supplied by silicon detectors of very high spatial resolution. The first chapter is an introduction presenting the general outline and the triggering conditions of the spectrometer. Chapter two describes the operational structure of a microvertex detector made of Si micro-plates associated to the measuring chains. Information preconditioning is related to the pre-amplification stage, to the pile-up effects and to the reduction in the time characteristic due to the high counting rates. The chapter three describes the architecture of the analogue delay buffer, makes an analysis of the intrinsic noise and presents the operational testings and input/output control operations. The fourth chapter is devoted to the description of the analogue pulse shape processor and gives also the testings and the corresponding measurements on the circuit. Finally, the chapter five deals with the simplest modeling of the entire conditioning chain. Also, the testings and measuring procedures are here discussed. In conclusion the author presents some prospects for improving the signal-to-noise ratio by summation of the de-convoluted micro-paths. 78 refs., 78 figs., 1 annexe
CHOLLA: A NEW MASSIVELY PARALLEL HYDRODYNAMICS CODE FOR ASTROPHYSICAL SIMULATION
International Nuclear Information System (INIS)
Schneider, Evan E.; Robertson, Brant E.
2015-01-01
We present Computational Hydrodynamics On ParaLLel Architectures (Cholla ), a new three-dimensional hydrodynamics code that harnesses the power of graphics processing units (GPUs) to accelerate astrophysical simulations. Cholla models the Euler equations on a static mesh using state-of-the-art techniques, including the unsplit Corner Transport Upwind algorithm, a variety of exact and approximate Riemann solvers, and multiple spatial reconstruction techniques including the piecewise parabolic method (PPM). Using GPUs, Cholla evolves the fluid properties of thousands of cells simultaneously and can update over 10 million cells per GPU-second while using an exact Riemann solver and PPM reconstruction. Owing to the massively parallel architecture of GPUs and the design of the Cholla code, astrophysical simulations with physically interesting grid resolutions (≳256 3 ) can easily be computed on a single device. We use the Message Passing Interface library to extend calculations onto multiple devices and demonstrate nearly ideal scaling beyond 64 GPUs. A suite of test problems highlights the physical accuracy of our modeling and provides a useful comparison to other codes. We then use Cholla to simulate the interaction of a shock wave with a gas cloud in the interstellar medium, showing that the evolution of the cloud is highly dependent on its density structure. We reconcile the computed mixing time of a turbulent cloud with a realistic density distribution destroyed by a strong shock with the existing analytic theory for spherical cloud destruction by describing the system in terms of its median gas density
CHOLLA: A NEW MASSIVELY PARALLEL HYDRODYNAMICS CODE FOR ASTROPHYSICAL SIMULATION
Energy Technology Data Exchange (ETDEWEB)
Schneider, Evan E.; Robertson, Brant E. [Steward Observatory, University of Arizona, 933 North Cherry Avenue, Tucson, AZ 85721 (United States)
2015-04-15
We present Computational Hydrodynamics On ParaLLel Architectures (Cholla ), a new three-dimensional hydrodynamics code that harnesses the power of graphics processing units (GPUs) to accelerate astrophysical simulations. Cholla models the Euler equations on a static mesh using state-of-the-art techniques, including the unsplit Corner Transport Upwind algorithm, a variety of exact and approximate Riemann solvers, and multiple spatial reconstruction techniques including the piecewise parabolic method (PPM). Using GPUs, Cholla evolves the fluid properties of thousands of cells simultaneously and can update over 10 million cells per GPU-second while using an exact Riemann solver and PPM reconstruction. Owing to the massively parallel architecture of GPUs and the design of the Cholla code, astrophysical simulations with physically interesting grid resolutions (≳256{sup 3}) can easily be computed on a single device. We use the Message Passing Interface library to extend calculations onto multiple devices and demonstrate nearly ideal scaling beyond 64 GPUs. A suite of test problems highlights the physical accuracy of our modeling and provides a useful comparison to other codes. We then use Cholla to simulate the interaction of a shock wave with a gas cloud in the interstellar medium, showing that the evolution of the cloud is highly dependent on its density structure. We reconcile the computed mixing time of a turbulent cloud with a realistic density distribution destroyed by a strong shock with the existing analytic theory for spherical cloud destruction by describing the system in terms of its median gas density.
High Efficiency EBCOT with Parallel Coding Architecture for JPEG2000
Directory of Open Access Journals (Sweden)
Chiang Jen-Shiun
2006-01-01
Full Text Available This work presents a parallel context-modeling coding architecture and a matching arithmetic coder (MQ-coder for the embedded block coding (EBCOT unit of the JPEG2000 encoder. Tier-1 of the EBCOT consumes most of the computation time in a JPEG2000 encoding system. The proposed parallel architecture can increase the throughput rate of the context modeling. To match the high throughput rate of the parallel context-modeling architecture, an efficient pipelined architecture for context-based adaptive arithmetic encoder is proposed. This encoder of JPEG2000 can work at 180 MHz to encode one symbol each cycle. Compared with the previous context-modeling architectures, our parallel architectures can improve the throughput rate up to 25%.
Programming parallel architectures: The BLAZE family of languages
Mehrotra, Piyush
1988-01-01
Programming multiprocessor architectures is a critical research issue. An overview is given of the various approaches to programming these architectures that are currently being explored. It is argued that two of these approaches, interactive programming environments and functional parallel languages, are particularly attractive since they remove much of the burden of exploiting parallel architectures from the user. Also described is recent work by the author in the design of parallel languages. Research on languages for both shared and nonshared memory multiprocessors is described, as well as the relations of this work to other current language research projects.
Massively parallel red-black algorithms for x-y-z response matrix equations
International Nuclear Information System (INIS)
Hanebutte, U.R.; Laurin-Kovitz, K.; Lewis, E.E.
1992-01-01
Recently, both discrete ordinates and spherical harmonic (S n and P n ) methods have been cast in the form of response matrices. In x-y geometry, massively parallel algorithms have been developed to solve the resulting response matrix equations on the Connection Machine family of parallel computers, the CM-2, CM-200, and CM-5. These algorithms utilize two-cycle iteration on a red-black checkerboard. In this work we examine the use of massively parallel red-black algorithms to solve response matric equations in three dimensions. This longer term objective is to utilize massively parallel algorithms to solve S n and/or P n response matrix problems. In this exploratory examination, however, we consider the simple 6 x 6 response matrices that are derivable from fine-mesh diffusion approximations in three dimensions
International Nuclear Information System (INIS)
Pandya, Tara M.; Johnson, Seth R.; Evans, Thomas M.; Davidson, Gregory G.; Hamilton, Steven P.; Godfrey, Andrew T.
2015-01-01
This paper discusses the implementation, capabilities, and validation of Shift, a massively parallel Monte Carlo radiation transport package developed and maintained at Oak Ridge National Laboratory. It has been developed to scale well from laptop to small computing clusters to advanced supercomputers. Special features of Shift include hybrid capabilities for variance reduction such as CADIS and FW-CADIS, and advanced parallel decomposition and tally methods optimized for scalability on supercomputing architectures. Shift has been validated and verified against various reactor physics benchmarks and compares well to other state-of-the-art Monte Carlo radiation transport codes such as MCNP5, CE KENO-VI, and OpenMC. Some specific benchmarks used for verification and validation include the CASL VERA criticality test suite and several Westinghouse AP1000 ® problems. These benchmark and scaling studies show promising results
An FPGA-Based Massively Parallel Neuromorphic Cortex Simulator.
Wang, Runchun M; Thakur, Chetan S; van Schaik, André
2018-01-01
This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of this work is the abstraction of a neuromorphic architecture into clusters represented by minicolumns and hypercolumns, analogously to the fundamental structural units observed in neurobiology. Without this approach, simulating large-scale fully connected networks needs prohibitively large memory to store look-up tables for point-to-point connections. Instead, we use a novel architecture, based on the structural connectivity in the neocortex, such that all the required parameters and connections can be stored in on-chip memory. The cortex simulator can be easily reconfigured for simulating different neural networks without any change in hardware structure by programming the memory. A hierarchical communication scheme allows one neuron to have a fan-out of up to 200 k neurons. As a proof-of-concept, an implementation on one Altera Stratix V FPGA was able to simulate 20 million to 2.6 billion leaky-integrate-and-fire (LIF) neurons in real time. We verified the system by emulating a simplified auditory cortex (with 100 million neurons). This cortex simulator achieved a low power dissipation of 1.62 μW per neuron. With the advent of commercially available FPGA boards, our system offers an accessible and scalable tool for the design, real-time simulation, and analysis of large-scale spiking neural networks.
An FPGA-Based Massively Parallel Neuromorphic Cortex Simulator
Directory of Open Access Journals (Sweden)
Runchun M. Wang
2018-04-01
Full Text Available This paper presents a massively parallel and scalable neuromorphic cortex simulator designed for simulating large and structurally connected spiking neural networks, such as complex models of various areas of the cortex. The main novelty of this work is the abstraction of a neuromorphic architecture into clusters represented by minicolumns and hypercolumns, analogously to the fundamental structural units observed in neurobiology. Without this approach, simulating large-scale fully connected networks needs prohibitively large memory to store look-up tables for point-to-point connections. Instead, we use a novel architecture, based on the structural connectivity in the neocortex, such that all the required parameters and connections can be stored in on-chip memory. The cortex simulator can be easily reconfigured for simulating different neural networks without any change in hardware structure by programming the memory. A hierarchical communication scheme allows one neuron to have a fan-out of up to 200 k neurons. As a proof-of-concept, an implementation on one Altera Stratix V FPGA was able to simulate 20 million to 2.6 billion leaky-integrate-and-fire (LIF neurons in real time. We verified the system by emulating a simplified auditory cortex (with 100 million neurons. This cortex simulator achieved a low power dissipation of 1.62 μW per neuron. With the advent of commercially available FPGA boards, our system offers an accessible and scalable tool for the design, real-time simulation, and analysis of large-scale spiking neural networks.
Electromagnetic Physics Models for Parallel Computing Architectures
Amadio, G.; Ananya, A.; Apostolakis, J.; Aurora, A.; Bandieramonte, M.; Bhattacharyya, A.; Bianchini, C.; Brun, R.; Canal, P.; Carminati, F.; Duhem, L.; Elvira, D.; 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.
2016-10-01
The recent emergence of hardware architectures characterized by many-core or accelerated processors has opened new opportunities for concurrent programming models taking advantage of both SIMD and SIMT architectures. GeantV, a next generation detector simulation, has been designed to exploit both the vector capability of mainstream CPUs and multi-threading capabilities of coprocessors including NVidia GPUs and Intel Xeon Phi. The characteristics of these architectures are very different in terms of the vectorization depth and type of parallelization needed to achieve optimal performance. In this paper we describe implementation of electromagnetic physics models developed for parallel computing architectures as a part of the GeantV project. Results of preliminary performance evaluation and physics validation are presented as well.
A massively parallel discrete ordinates response matrix method for neutron transport
International Nuclear Information System (INIS)
Hanebutte, U.R.; Lewis, E.E.
1992-01-01
In this paper a discrete ordinates response matrix method is formulated with anisotropic scattering for the solution of neutron transport problems on massively parallel computers. The response matrix formulation eliminates iteration on the scattering source. The nodal matrices that result from the diamond-differenced equations are utilized in a factored form that minimizes memory requirements and significantly reduces the number of arithmetic operations required per node. The red-black solution algorithm utilizes massive parallelism by assigning each spatial node to one or more processors. The algorithm is accelerated by a synthetic method in which the low-order diffusion equations are also solved by massively parallel red-black iterations. The method is implemented on a 16K Connection Machine-2, and S 8 and S 16 solutions are obtained for fixed-source benchmark problems in x-y geometry
Morse, H Stephen
1994-01-01
Practical Parallel Computing provides information pertinent to the fundamental aspects of high-performance parallel processing. This book discusses the development of parallel applications on a variety of equipment.Organized into three parts encompassing 12 chapters, this book begins with an overview of the technology trends that converge to favor massively parallel hardware over traditional mainframes and vector machines. This text then gives a tutorial introduction to parallel hardware architectures. Other chapters provide worked-out examples of programs using several parallel languages. Thi
Programming parallel architectures - The BLAZE family of languages
Mehrotra, Piyush
1989-01-01
This paper gives an overview of the various approaches to programming multiprocessor architectures that are currently being explored. It is argued that two of these approaches, interactive programming environments and functional parallel languages, are particularly attractive, since they remove much of the burden of exploiting parallel architectures from the user. This paper also describes recent work in the design of parallel languages. Research on languages for both shared and nonshared memory multiprocessors is described.
Electromagnetic Physics Models for Parallel Computing Architectures
International Nuclear Information System (INIS)
Amadio, G; Bianchini, C; Iope, R; Ananya, A; Apostolakis, J; Aurora, A; Bandieramonte, M; Brun, R; Carminati, F; Gheata, A; Gheata, M; Goulas, I; Nikitina, T; Bhattacharyya, A; Mohanty, A; Canal, P; Elvira, D; Jun, S Y; Lima, G; Duhem, L
2016-01-01
The recent emergence of hardware architectures characterized by many-core or accelerated processors has opened new opportunities for concurrent programming models taking advantage of both SIMD and SIMT architectures. GeantV, a next generation detector simulation, has been designed to exploit both the vector capability of mainstream CPUs and multi-threading capabilities of coprocessors including NVidia GPUs and Intel Xeon Phi. The characteristics of these architectures are very different in terms of the vectorization depth and type of parallelization needed to achieve optimal performance. In this paper we describe implementation of electromagnetic physics models developed for parallel computing architectures as a part of the GeantV project. Results of preliminary performance evaluation and physics validation are presented as well. (paper)
Fox, Geoffrey C; Messina, Guiseppe C
2014-01-01
A clear illustration of how parallel computers can be successfully appliedto large-scale scientific computations. This book demonstrates how avariety of applications in physics, biology, mathematics and other scienceswere implemented on real parallel computers to produce new scientificresults. It investigates issues of fine-grained parallelism relevant forfuture supercomputers with particular emphasis on hypercube architecture. The authors describe how they used an experimental approach to configuredifferent massively parallel machines, design and implement basic systemsoftware, and develop
Acoustic simulation in architecture with parallel algorithm
Li, Xiaohong; Zhang, Xinrong; Li, Dan
2004-03-01
In allusion to complexity of architecture environment and Real-time simulation of architecture acoustics, a parallel radiosity algorithm was developed. The distribution of sound energy in scene is solved with this method. And then the impulse response between sources and receivers at frequency segment, which are calculated with multi-process, are combined into whole frequency response. The numerical experiment shows that parallel arithmetic can improve the acoustic simulating efficiency of complex scene.
Increasing the reach of forensic genetics with massively parallel sequencing.
Budowle, Bruce; Schmedes, Sarah E; Wendt, Frank R
2017-09-01
The field of forensic genetics has made great strides in the analysis of biological evidence related to criminal and civil matters. More so, the discipline has set a standard of performance and quality in the forensic sciences. The advent of massively parallel sequencing will allow the field to expand its capabilities substantially. This review describes the salient features of massively parallel sequencing and how it can impact forensic genetics. The features of this technology offer increased number and types of genetic markers that can be analyzed, higher throughput of samples, and the capability of targeting different organisms, all by one unifying methodology. While there are many applications, three are described where massively parallel sequencing will have immediate impact: molecular autopsy, microbial forensics and differentiation of monozygotic twins. The intent of this review is to expose the forensic science community to the potential enhancements that have or are soon to arrive and demonstrate the continued expansion the field of forensic genetics and its service in the investigation of legal matters.
Neural nets for massively parallel optimization
Dixon, Laurence C. W.; Mills, David
1992-07-01
To apply massively parallel processing systems to the solution of large scale optimization problems it is desirable to be able to evaluate any function f(z), z (epsilon) Rn in a parallel manner. The theorem of Cybenko, Hecht Nielsen, Hornik, Stinchcombe and White, and Funahasi shows that this can be achieved by a neural network with one hidden layer. In this paper we address the problem of the number of nodes required in the layer to achieve a given accuracy in the function and gradient values at all points within a given n dimensional interval. The type of activation function needed to obtain nonsingular Hessian matrices is described and a strategy for obtaining accurate minimal networks presented.
International Nuclear Information System (INIS)
McGhee, J.M.; Roberts, R.M.; Morel, J.E.
1997-01-01
A spherical harmonics research code (DANTE) has been developed which is compatible with parallel computer architectures. DANTE provides 3-D, multi-material, deterministic, transport capabilities using an arbitrary finite element mesh. The linearized Boltzmann transport equation is solved in a second order self-adjoint form utilizing a Galerkin finite element spatial differencing scheme. The core solver utilizes a preconditioned conjugate gradient algorithm. Other distinguishing features of the code include options for discrete-ordinates and simplified spherical harmonics angular differencing, an exact Marshak boundary treatment for arbitrarily oriented boundary faces, in-line matrix construction techniques to minimize memory consumption, and an effective diffusion based preconditioner for scattering dominated problems. Algorithm efficiency is demonstrated for a massively parallel SIMD architecture (CM-5), and compatibility with MPP multiprocessor platforms or workstation clusters is anticipated
Phase space simulation of collisionless stellar systems on the massively parallel processor
International Nuclear Information System (INIS)
White, R.L.
1987-01-01
A numerical technique for solving the collisionless Boltzmann equation describing the time evolution of a self gravitating fluid in phase space was implemented on the Massively Parallel Processor (MPP). The code performs calculations for a two dimensional phase space grid (with one space and one velocity dimension). Some results from calculations are presented. The execution speed of the code is comparable to the speed of a single processor of a Cray-XMP. Advantages and disadvantages of the MPP architecture for this type of problem are discussed. The nearest neighbor connectivity of the MPP array does not pose a significant obstacle. Future MPP-like machines should have much more local memory and easier access to staging memory and disks in order to be effective for this type of problem
Implementation of an Agent-Based Parallel Tissue Modelling Framework for the Intel MIC Architecture
Directory of Open Access Journals (Sweden)
Maciej Cytowski
2017-01-01
Full Text Available Timothy is a novel large scale modelling framework that allows simulating of biological processes involving different cellular colonies growing and interacting with variable environment. Timothy was designed for execution on massively parallel High Performance Computing (HPC systems. The high parallel scalability of the implementation allows for simulations of up to 109 individual cells (i.e., simulations at tissue spatial scales of up to 1 cm3 in size. With the recent advancements of the Timothy model, it has become critical to ensure appropriate performance level on emerging HPC architectures. For instance, the introduction of blood vessels supplying nutrients to the tissue is a very important step towards realistic simulations of complex biological processes, but it greatly increased the computational complexity of the model. In this paper, we describe the process of modernization of the application in order to achieve high computational performance on HPC hybrid systems based on modern Intel® MIC architecture. Experimental results on the Intel Xeon Phi™ coprocessor x100 and the Intel Xeon Phi processor x200 are presented.
PARALLEL SPATIOTEMPORAL SPECTRAL CLUSTERING WITH MASSIVE TRAJECTORY DATA
Directory of Open Access Journals (Sweden)
Y. Z. Gu
2017-09-01
Full Text Available Massive trajectory data contains wealth useful information and knowledge. Spectral clustering, which has been shown to be effective in finding clusters, becomes an important clustering approaches in the trajectory data mining. However, the traditional spectral clustering lacks the temporal expansion on the algorithm and limited in its applicability to large-scale problems due to its high computational complexity. This paper presents a parallel spatiotemporal spectral clustering based on multiple acceleration solutions to make the algorithm more effective and efficient, the performance is proved due to the experiment carried out on the massive taxi trajectory dataset in Wuhan city, China.
Development of massively parallel quantum chemistry program SMASH
International Nuclear Information System (INIS)
Ishimura, Kazuya
2015-01-01
A massively parallel program for quantum chemistry calculations SMASH was released under the Apache License 2.0 in September 2014. The SMASH program is written in the Fortran90/95 language with MPI and OpenMP standards for parallelization. Frequently used routines, such as one- and two-electron integral calculations, are modularized to make program developments simple. The speed-up of the B3LYP energy calculation for (C 150 H 30 ) 2 with the cc-pVDZ basis set (4500 basis functions) was 50,499 on 98,304 cores of the K computer
Massively Parallel Sort-Merge Joins in Main Memory Multi-Core Database Systems
Albutiu, Martina-Cezara; Kemper, Alfons; Neumann, Thomas
2012-01-01
Two emerging hardware trends will dominate the database system technology in the near future: increasing main memory capacities of several TB per server and massively parallel multi-core processing. Many algorithmic and control techniques in current database technology were devised for disk-based systems where I/O dominated the performance. In this work we take a new look at the well-known sort-merge join which, so far, has not been in the focus of research in scalable massively parallel mult...
Calafiura, Paolo; The ATLAS collaboration; Seuster, Rolf; Tsulaia, Vakhtang; van Gemmeren, Peter
2015-01-01
AthenaMP is a multi-process version of the ATLAS reconstruction and data analysis framework Athena. By leveraging Linux fork and copy-on-write, it allows the sharing of memory pages between event processors running on the same compute node with little to no change in the application code. Originally targeted to optimize the memory footprint of reconstruction jobs, AthenaMP has demonstrated that it can reduce the memory usage of certain confugurations of ATLAS production jobs by a factor of 2. AthenaMP has also evolved to become the parallel event-processing core of the recently developed ATLAS infrastructure for fine-grained event processing (Event Service) which allows to run AthenaMP inside massively parallel distributed applications on hundreds of compute nodes simultaneously. We present the architecture of AthenaMP, various strategies implemented by AthenaMP for scheduling workload to worker processes (for example: Shared Event Queue and Shared Distributor of Event Tokens) and the usage of AthenaMP in the...
Calafiura, Paolo; Seuster, Rolf; Tsulaia, Vakhtang; van Gemmeren, Peter
2015-01-01
AthenaMP is a multi-process version of the ATLAS reconstruction, simulation and data analysis framework Athena. By leveraging Linux fork and copy-on-write, it allows for sharing of memory pages between event processors running on the same compute node with little to no change in the application code. Originally targeted to optimize the memory footprint of reconstruction jobs, AthenaMP has demonstrated that it can reduce the memory usage of certain configurations of ATLAS production jobs by a factor of 2. AthenaMP has also evolved to become the parallel event-processing core of the recently developed ATLAS infrastructure for fine-grained event processing (Event Service) which allows to run AthenaMP inside massively parallel distributed applications on hundreds of compute nodes simultaneously. We present the architecture of AthenaMP, various strategies implemented by AthenaMP for scheduling workload to worker processes (for example: Shared Event Queue and Shared Distributor of Event Tokens) and the usage of Ath...
Proxy-equation paradigm: A strategy for massively parallel asynchronous computations
Mittal, Ankita; Girimaji, Sharath
2017-09-01
Massively parallel simulations of transport equation systems call for a paradigm change in algorithm development to achieve efficient scalability. Traditional approaches require time synchronization of processing elements (PEs), which severely restricts scalability. Relaxing synchronization requirement introduces error and slows down convergence. In this paper, we propose and develop a novel "proxy equation" concept for a general transport equation that (i) tolerates asynchrony with minimal added error, (ii) preserves convergence order and thus, (iii) expected to scale efficiently on massively parallel machines. The central idea is to modify a priori the transport equation at the PE boundaries to offset asynchrony errors. Proof-of-concept computations are performed using a one-dimensional advection (convection) diffusion equation. The results demonstrate the promise and advantages of the present strategy.
Energy Technology Data Exchange (ETDEWEB)
Madduri, Kamesh; Ediger, David; Jiang, Karl; Bader, David A.; Chavarria-Miranda, Daniel
2009-02-15
We present a new lock-free parallel algorithm for computing betweenness centralityof massive small-world networks. With minor changes to the data structures, ouralgorithm also achieves better spatial cache locality compared to previous approaches. Betweenness centrality is a key algorithm kernel in HPCS SSCA#2, a benchmark extensively used to evaluate the performance of emerging high-performance computing architectures for graph-theoretic computations. We design optimized implementations of betweenness centrality and the SSCA#2 benchmark for two hardware multithreaded systems: a Cray XMT system with the Threadstorm processor, and a single-socket Sun multicore server with the UltraSPARC T2 processor. For a small-world network of 134 million vertices and 1.073 billion edges, the 16-processor XMT system and the 8-core Sun Fire T5120 server achieve TEPS scores (an algorithmic performance count for the SSCA#2 benchmark) of 160 million and 90 million respectively, which corresponds to more than a 2X performance improvement over the previous parallel implementations. To better characterize the performance of these multithreaded systems, we correlate the SSCA#2 performance results with data from the memory-intensive STREAM and RandomAccess benchmarks. Finally, we demonstrate the applicability of our implementation to analyze massive real-world datasets by computing approximate betweenness centrality for a large-scale IMDb movie-actor network.
Development of massively parallel quantum chemistry program SMASH
Energy Technology Data Exchange (ETDEWEB)
Ishimura, Kazuya [Department of Theoretical and Computational Molecular Science, Institute for Molecular Science 38 Nishigo-Naka, Myodaiji, Okazaki, Aichi 444-8585 (Japan)
2015-12-31
A massively parallel program for quantum chemistry calculations SMASH was released under the Apache License 2.0 in September 2014. The SMASH program is written in the Fortran90/95 language with MPI and OpenMP standards for parallelization. Frequently used routines, such as one- and two-electron integral calculations, are modularized to make program developments simple. The speed-up of the B3LYP energy calculation for (C{sub 150}H{sub 30}){sub 2} with the cc-pVDZ basis set (4500 basis functions) was 50,499 on 98,304 cores of the K computer.
Massively parallel sparse matrix function calculations with NTPoly
Dawson, William; Nakajima, Takahito
2018-04-01
We present NTPoly, a massively parallel library for computing the functions of sparse, symmetric matrices. The theory of matrix functions is a well developed framework with a wide range of applications including differential equations, graph theory, and electronic structure calculations. One particularly important application area is diagonalization free methods in quantum chemistry. When the input and output of the matrix function are sparse, methods based on polynomial expansions can be used to compute matrix functions in linear time. We present a library based on these methods that can compute a variety of matrix functions. Distributed memory parallelization is based on a communication avoiding sparse matrix multiplication algorithm. OpenMP task parallellization is utilized to implement hybrid parallelization. We describe NTPoly's interface and show how it can be integrated with programs written in many different programming languages. We demonstrate the merits of NTPoly by performing large scale calculations on the K computer.
Performance of Air Pollution Models on Massively Parallel Computers
DEFF Research Database (Denmark)
Brown, John; Hansen, Per Christian; Wasniewski, Jerzy
1996-01-01
To compare the performance and use of three massively parallel SIMD computers, we implemented a large air pollution model on the computers. Using a realistic large-scale model, we gain detailed insight about the performance of the three computers when used to solve large-scale scientific problems...
Massively parallel computation of conservation laws
Energy Technology Data Exchange (ETDEWEB)
Garbey, M [Univ. Claude Bernard, Villeurbanne (France); Levine, D [Argonne National Lab., IL (United States)
1990-01-01
The authors present a new method for computing solutions of conservation laws based on the use of cellular automata with the method of characteristics. The method exploits the high degree of parallelism available with cellular automata and retains important features of the method of characteristics. It yields high numerical accuracy and extends naturally to adaptive meshes and domain decomposition methods for perturbed conservation laws. They describe the method and its implementation for a Dirichlet problem with a single conservation law for the one-dimensional case. Numerical results for the one-dimensional law with the classical Burgers nonlinearity or the Buckley-Leverett equation show good numerical accuracy outside the neighborhood of the shocks. The error in the area of the shocks is of the order of the mesh size. The algorithm is well suited for execution on both massively parallel computers and vector machines. They present timing results for an Alliant FX/8, Connection Machine Model 2, and CRAY X-MP.
International Nuclear Information System (INIS)
Rosa, Massimiliano; Warsa, James S.; Perks, Michael
2011-01-01
We have implemented a cell-wise, block-Gauss-Seidel (bGS) iterative algorithm, for the solution of the S_n transport equations on the Roadrunner hybrid, parallel computer architecture. A compute node of this massively parallel machine comprises AMD Opteron cores that are linked to a Cell Broadband Engine™ (Cell/B.E.)"1. LAPACK routines have been ported to the Cell/B.E. in order to make use of its parallel Synergistic Processing Elements (SPEs). The bGS algorithm is based on the LU factorization and solution of a linear system that couples the fluxes for all S_n angles and energy groups on a mesh cell. For every cell of a mesh that has been parallel decomposed on the higher-level Opteron processors, a linear system is transferred to the Cell/B.E. and the parallel LAPACK routines are used to compute a solution, which is then transferred back to the Opteron, where the rest of the computations for the S_n transport problem take place. Compared to standard parallel machines, a hundred-fold speedup of the bGS was observed on the hybrid Roadrunner architecture. Numerical experiments with strong and weak parallel scaling demonstrate the bGS method is viable and compares favorably to full parallel sweeps (FPS) on two-dimensional, unstructured meshes when it is applied to optically thick, multi-material problems. As expected, however, it is not as efficient as FPS in optically thin problems. (author)
Massively Parallel Computing at Sandia and Its Application to National Defense
National Research Council Canada - National Science Library
Dosanjh, Sudip
1991-01-01
Two years ago, researchers at Sandia National Laboratories showed that a massively parallel computer with 1024 processors could solve scientific problems more than 1000 times faster than a single processor...
Massively-parallel best subset selection for ordinary least-squares regression
DEFF Research Database (Denmark)
Gieseke, Fabian; Polsterer, Kai Lars; Mahabal, Ashish
2017-01-01
Selecting an optimal subset of k out of d features for linear regression models given n training instances is often considered intractable for feature spaces with hundreds or thousands of dimensions. We propose an efficient massively-parallel implementation for selecting such optimal feature...
Massive Asynchronous Parallelization of Sparse Matrix Factorizations
Energy Technology Data Exchange (ETDEWEB)
Chow, Edmond [Georgia Inst. of Technology, Atlanta, GA (United States)
2018-01-08
Solving sparse problems is at the core of many DOE computational science applications. We focus on the challenge of developing sparse algorithms that can fully exploit the parallelism in extreme-scale computing systems, in particular systems with massive numbers of cores per node. Our approach is to express a sparse matrix factorization as a large number of bilinear constraint equations, and then solving these equations via an asynchronous iterative method. The unknowns in these equations are the matrix entries of the factorization that is desired.
Computational fluid dynamics on a massively parallel computer
Jespersen, Dennis C.; Levit, Creon
1989-01-01
A finite difference code was implemented for the compressible Navier-Stokes equations on the Connection Machine, a massively parallel computer. The code is based on the ARC2D/ARC3D program and uses the implicit factored algorithm of Beam and Warming. The codes uses odd-even elimination to solve linear systems. Timings and computation rates are given for the code, and a comparison is made with a Cray XMP.
Implementation of PHENIX trigger algorithms on massively parallel computers
International Nuclear Information System (INIS)
Petridis, A.N.; Wohn, F.K.
1995-01-01
The event selection requirements of contemporary high energy and nuclear physics experiments are met by the introduction of on-line trigger algorithms which identify potentially interesting events and reduce the data acquisition rate to levels that are manageable by the electronics. Such algorithms being parallel in nature can be simulated off-line using massively parallel computers. The PHENIX experiment intends to investigate the possible existence of a new phase of matter called the quark gluon plasma which has been theorized to have existed in very early stages of the evolution of the universe by studying collisions of heavy nuclei at ultra-relativistic energies. Such interactions can also reveal important information regarding the structure of the nucleus and mandate a thorough investigation of the simpler proton-nucleus collisions at the same energies. The complexity of PHENIX events and the need to analyze and also simulate them at rates similar to the data collection ones imposes enormous computation demands. This work is a first effort to implement PHENIX trigger algorithms on parallel computers and to study the feasibility of using such machines to run the complex programs necessary for the simulation of the PHENIX detector response. Fine and coarse grain approaches have been studied and evaluated. Depending on the application the performance of a massively parallel computer can be much better or much worse than that of a serial workstation. A comparison between single instruction and multiple instruction computers is also made and possible applications of the single instruction machines to high energy and nuclear physics experiments are outlined. copyright 1995 American Institute of Physics
Capital Architecture: Situating symbolism parallel to architectural methods and technology
Daoud, Bassam
Capital Architecture is a symbol of a nation's global presence and the cultural and social focal point of its inhabitants. Since the advent of High-Modernism in Western cities, and subsequently decolonised capitals, civic architecture no longer seems to be strictly grounded in the philosophy that national buildings shape the legacy of government and the way a nation is regarded through its built environment. Amidst an exceedingly globalized architectural practice and with the growing concern of key heritage foundations over the shortcomings of international modernism in representing its immediate socio-cultural context, the contextualization of public architecture within its sociological, cultural and economic framework in capital cities became the key denominator of this thesis. Civic architecture in capital cities is essential to confront the challenges of symbolizing a nation and demonstrating the legitimacy of the government'. In today's dominantly secular Western societies, governmental architecture, especially where the seat of political power lies, is the ultimate form of architectural expression in conveying a sense of identity and underlining a nation's status. Departing with these convictions, this thesis investigates the embodied symbolic power, the representative capacity, and the inherent permanence in contemporary architecture, and in its modes of production. Through a vast study on Modern architectural ideals and heritage -- in parallel to methodologies -- the thesis stimulates the future of large scale governmental building practices and aims to identify and index the key constituents that may respond to the lack representation in civic architecture in capital cities.
Massively parallel simulator of optical coherence tomography of inhomogeneous turbid media.
Malektaji, Siavash; Lima, Ivan T; Escobar I, Mauricio R; Sherif, Sherif S
2017-10-01
An accurate and practical simulator for Optical Coherence Tomography (OCT) could be an important tool to study the underlying physical phenomena in OCT such as multiple light scattering. Recently, many researchers have investigated simulation of OCT of turbid media, e.g., tissue, using Monte Carlo methods. The main drawback of these earlier simulators is the long computational time required to produce accurate results. We developed a massively parallel simulator of OCT of inhomogeneous turbid media that obtains both Class I diffusive reflectivity, due to ballistic and quasi-ballistic scattered photons, and Class II diffusive reflectivity due to multiply scattered photons. This Monte Carlo-based simulator is implemented on graphic processing units (GPUs), using the Compute Unified Device Architecture (CUDA) platform and programming model, to exploit the parallel nature of propagation of photons in tissue. It models an arbitrary shaped sample medium as a tetrahedron-based mesh and uses an advanced importance sampling scheme. This new simulator speeds up simulations of OCT of inhomogeneous turbid media by about two orders of magnitude. To demonstrate this result, we have compared the computation times of our new parallel simulator and its serial counterpart using two samples of inhomogeneous turbid media. We have shown that our parallel implementation reduced simulation time of OCT of the first sample medium from 407 min to 92 min by using a single GPU card, to 12 min by using 8 GPU cards and to 7 min by using 16 GPU cards. For the second sample medium, the OCT simulation time was reduced from 209 h to 35.6 h by using a single GPU card, and to 4.65 h by using 8 GPU cards, and to only 2 h by using 16 GPU cards. Therefore our new parallel simulator is considerably more practical to use than its central processing unit (CPU)-based counterpart. Our new parallel OCT simulator could be a practical tool to study the different physical phenomena underlying OCT
A Massively Parallel Code for Polarization Calculations
Akiyama, Shizuka; Höflich, Peter
2001-03-01
We present an implementation of our Monte-Carlo radiation transport method for rapidly expanding, NLTE atmospheres for massively parallel computers which utilizes both the distributed and shared memory models. This allows us to take full advantage of the fast communication and low latency inherent to nodes with multiple CPUs, and to stretch the limits of scalability with the number of nodes compared to a version which is based on the shared memory model. Test calculations on a local 20-node Beowulf cluster with dual CPUs showed an improved scalability by about 40%.
A Disciplined Architectural Approach to Scaling Data Analysis for Massive, Scientific Data
Crichton, D. J.; Braverman, A. J.; Cinquini, L.; Turmon, M.; Lee, H.; Law, E.
2014-12-01
Data collections across remote sensing and ground-based instruments in astronomy, Earth science, and planetary science are outpacing scientists' ability to analyze them. Furthermore, the distribution, structure, and heterogeneity of the measurements themselves pose challenges that limit the scalability of data analysis using traditional approaches. Methods for developing science data processing pipelines, distribution of scientific datasets, and performing analysis will require innovative approaches that integrate cyber-infrastructure, algorithms, and data into more systematic approaches that can more efficiently compute and reduce data, particularly distributed data. This requires the integration of computer science, machine learning, statistics and domain expertise to identify scalable architectures for data analysis. The size of data returned from Earth Science observing satellites and the magnitude of data from climate model output, is predicted to grow into the tens of petabytes challenging current data analysis paradigms. This same kind of growth is present in astronomy and planetary science data. One of the major challenges in data science and related disciplines defining new approaches to scaling systems and analysis in order to increase scientific productivity and yield. Specific needs include: 1) identification of optimized system architectures for analyzing massive, distributed data sets; 2) algorithms for systematic analysis of massive data sets in distributed environments; and 3) the development of software infrastructures that are capable of performing massive, distributed data analysis across a comprehensive data science framework. NASA/JPL has begun an initiative in data science to address these challenges. Our goal is to evaluate how scientific productivity can be improved through optimized architectural topologies that identify how to deploy and manage the access, distribution, computation, and reduction of massive, distributed data, while
A massively-parallel electronic-structure calculations based on real-space density functional theory
International Nuclear Information System (INIS)
Iwata, Jun-Ichi; Takahashi, Daisuke; Oshiyama, Atsushi; Boku, Taisuke; Shiraishi, Kenji; Okada, Susumu; Yabana, Kazuhiro
2010-01-01
Based on the real-space finite-difference method, we have developed a first-principles density functional program that efficiently performs large-scale calculations on massively-parallel computers. In addition to efficient parallel implementation, we also implemented several computational improvements, substantially reducing the computational costs of O(N 3 ) operations such as the Gram-Schmidt procedure and subspace diagonalization. Using the program on a massively-parallel computer cluster with a theoretical peak performance of several TFLOPS, we perform electronic-structure calculations for a system consisting of over 10,000 Si atoms, and obtain a self-consistent electronic-structure in a few hundred hours. We analyze in detail the costs of the program in terms of computation and of inter-node communications to clarify the efficiency, the applicability, and the possibility for further improvements.
Lemon : An MPI parallel I/O library for data encapsulation using LIME
Deuzeman, Albert; Reker, Siebren; Urbach, Carsten
We introduce Lemon, an MPI parallel I/O library that provides efficient parallel I/O of both binary and metadata on massively parallel architectures. Motivated by the demands of the lattice Quantum Chromodynamics community, the data is stored in the SciDAC Lattice QCD Interchange Message
The new landscape of parallel computer architecture
International Nuclear Information System (INIS)
Shalf, John
2007-01-01
The past few years has seen a sea change in computer architecture that will impact every facet of our society as every electronic device from cell phone to supercomputer will need to confront parallelism of unprecedented scale. Whereas the conventional multicore approach (2, 4, and even 8 cores) adopted by the computing industry will eventually hit a performance plateau, the highest performance per watt and per chip area is achieved using manycore technology (hundreds or even thousands of cores). However, fully unleashing the potential of the manycore approach to ensure future advances in sustained computational performance will require fundamental advances in computer architecture and programming models that are nothing short of reinventing computing. In this paper we examine the reasons behind the movement to exponentially increasing parallelism, and its ramifications for system design, applications and programming models
The new landscape of parallel computer architecture
Energy Technology Data Exchange (ETDEWEB)
Shalf, John [NERSC Division, Lawrence Berkeley National Laboratory 1 Cyclotron Road, Berkeley California, 94720 (United States)
2007-07-15
The past few years has seen a sea change in computer architecture that will impact every facet of our society as every electronic device from cell phone to supercomputer will need to confront parallelism of unprecedented scale. Whereas the conventional multicore approach (2, 4, and even 8 cores) adopted by the computing industry will eventually hit a performance plateau, the highest performance per watt and per chip area is achieved using manycore technology (hundreds or even thousands of cores). However, fully unleashing the potential of the manycore approach to ensure future advances in sustained computational performance will require fundamental advances in computer architecture and programming models that are nothing short of reinventing computing. In this paper we examine the reasons behind the movement to exponentially increasing parallelism, and its ramifications for system design, applications and programming models.
Massively parallel Monte Carlo for many-particle simulations on GPUs
Energy Technology Data Exchange (ETDEWEB)
Anderson, Joshua A.; Jankowski, Eric [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Grubb, Thomas L. [Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Engel, Michael [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Glotzer, Sharon C., E-mail: sglotzer@umich.edu [Department of Chemical Engineering, University of Michigan, Ann Arbor, MI 48109 (United States); Department of Materials Science and Engineering, University of Michigan, Ann Arbor, MI 48109 (United States)
2013-12-01
Current trends in parallel processors call for the design of efficient massively parallel algorithms for scientific computing. Parallel algorithms for Monte Carlo simulations of thermodynamic ensembles of particles have received little attention because of the inherent serial nature of the statistical sampling. In this paper, we present a massively parallel method that obeys detailed balance and implement it for a system of hard disks on the GPU. We reproduce results of serial high-precision Monte Carlo runs to verify the method. This is a good test case because the hard disk equation of state over the range where the liquid transforms into the solid is particularly sensitive to small deviations away from the balance conditions. On a Tesla K20, our GPU implementation executes over one billion trial moves per second, which is 148 times faster than on a single Intel Xeon E5540 CPU core, enables 27 times better performance per dollar, and cuts energy usage by a factor of 13. With this improved performance we are able to calculate the equation of state for systems of up to one million hard disks. These large system sizes are required in order to probe the nature of the melting transition, which has been debated for the last forty years. In this paper we present the details of our computational method, and discuss the thermodynamics of hard disks separately in a companion paper.
A massively parallel corpus: the Bible in 100 languages.
Christodouloupoulos, Christos; Steedman, Mark
We describe the creation of a massively parallel corpus based on 100 translations of the Bible. We discuss some of the difficulties in acquiring and processing the raw material as well as the potential of the Bible as a corpus for natural language processing. Finally we present a statistical analysis of the corpora collected and a detailed comparison between the English translation and other English corpora.
A parallel architecture for digital filtering using Fermat number transforms
Truong, T. K.; Reed, I. S.; Yeh, C.-S.; Shao, H. M.
1983-01-01
In this correspondence, a parallel architecture is developed to compute the linear convolution of two sequences of arbitrary lengths using the Fermat number transform (FNT). In particular, a pipeline structure is designed to compute a 128-point FNT. In this FNT, only additions and bit rotations are required. The overlap-save method is generalized for the FNT to realize a digital filter of arbitrary length. The generalized overlap-save method alleviates the usual dynamic range limitation of FNT's of long transform lengths. A parallel architecture is developed to realize this type of overlap-save method using one FNT and several inverse FNT's of 128 points. Its architecture is regular, simple, and flexible, and therefore naturally suitable for VLSI implementation.
Smith, Garrett; Phillips, Alan
2002-01-01
There are currently three dominant TSTO class architectures. These are Series Burn (SB), Parallel Burn with crossfeed (PBw/cf), and Parallel Burn without crossfeed (PBncf). The goal of this study was to determine what factors uniquely affect PBncf architectures, how each of these factors interact, and to determine from a performance perspective whether a PBncf vehicle could be competitive with a PBw/cf or SB vehicle using equivalent technology and assumptions. In all cases, performance was evaluated on a relative basis for a fixed payload and mission by comparing gross and dry vehicle masses of a closed vehicle. Propellant combinations studied were LOX: LH2 propelled orbiter and booster (HH) and LOX: Kerosene booster with LOX: LH2 orbiter (KH). The study conclusions were: 1) a PBncf orbiter should be throttled as deeply as possible after launch until the staging point. 2) a detailed structural model is essential to accurate architecture analysis and evaluation. 3) a PBncf TSTO architecture is feasible for systems that stage at mach 7. 3a) HH architectures can achieve a mass growth relative to PBw/cf of ratio and to the position of the orbiter required to align the nozzle heights at liftoff. 5 ) thrust to weight ratios of 1.3 at liftoff and between 1.0 and 0.9 when staging at mach 7 appear to be close to ideal for PBncf vehicles. 6) performance for all vehicles studied is better when staged at mach 7 instead of mach 5. The study showed that a Series Burn architecture has the lowest gross mass for HH cases, and has the lowest dry mass for KH cases. The potential disadvantages of SB are the required use of an air-start for the orbiter engines and potential CG control issues. A Parallel Burn with crossfeed architecture solves both these problems, but the mechanics of a large bipropellant crossfeed system pose significant technical difficulties. Parallel Burn without crossfeed vehicles start both booster and orbiter engines on the ground and thus avoid both the risk of
PEM-PCA: A Parallel Expectation-Maximization PCA Face Recognition Architecture
Directory of Open Access Journals (Sweden)
Kanokmon Rujirakul
2014-01-01
Full Text Available Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages’ complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.
PEM-PCA: a parallel expectation-maximization PCA face recognition architecture.
Rujirakul, Kanokmon; So-In, Chakchai; Arnonkijpanich, Banchar
2014-01-01
Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages' complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.
A learnable parallel processing architecture towards unity of memory and computing.
Li, H; Gao, B; Chen, Z; Zhao, Y; Huang, P; Ye, H; Liu, L; Liu, X; Kang, J
2015-08-14
Developing energy-efficient parallel information processing systems beyond von Neumann architecture is a long-standing goal of modern information technologies. The widely used von Neumann computer architecture separates memory and computing units, which leads to energy-hungry data movement when computers work. In order to meet the need of efficient information processing for the data-driven applications such as big data and Internet of Things, an energy-efficient processing architecture beyond von Neumann is critical for the information society. Here we show a non-von Neumann architecture built of resistive switching (RS) devices named "iMemComp", where memory and logic are unified with single-type devices. Leveraging nonvolatile nature and structural parallelism of crossbar RS arrays, we have equipped "iMemComp" with capabilities of computing in parallel and learning user-defined logic functions for large-scale information processing tasks. Such architecture eliminates the energy-hungry data movement in von Neumann computers. Compared with contemporary silicon technology, adder circuits based on "iMemComp" can improve the speed by 76.8% and the power dissipation by 60.3%, together with a 700 times aggressive reduction in the circuit area.
A learnable parallel processing architecture towards unity of memory and computing
Li, H.; Gao, B.; Chen, Z.; Zhao, Y.; Huang, P.; Ye, H.; Liu, L.; Liu, X.; Kang, J.
2015-08-01
Developing energy-efficient parallel information processing systems beyond von Neumann architecture is a long-standing goal of modern information technologies. The widely used von Neumann computer architecture separates memory and computing units, which leads to energy-hungry data movement when computers work. In order to meet the need of efficient information processing for the data-driven applications such as big data and Internet of Things, an energy-efficient processing architecture beyond von Neumann is critical for the information society. Here we show a non-von Neumann architecture built of resistive switching (RS) devices named “iMemComp”, where memory and logic are unified with single-type devices. Leveraging nonvolatile nature and structural parallelism of crossbar RS arrays, we have equipped “iMemComp” with capabilities of computing in parallel and learning user-defined logic functions for large-scale information processing tasks. Such architecture eliminates the energy-hungry data movement in von Neumann computers. Compared with contemporary silicon technology, adder circuits based on “iMemComp” can improve the speed by 76.8% and the power dissipation by 60.3%, together with a 700 times aggressive reduction in the circuit area.
Engineering-Based Thermal CFD Simulations on Massive Parallel Systems
Frisch, Jérôme
2015-05-22
The development of parallel Computational Fluid Dynamics (CFD) codes is a challenging task that entails efficient parallelization concepts and strategies in order to achieve good scalability values when running those codes on modern supercomputers with several thousands to millions of cores. In this paper, we present a hierarchical data structure for massive parallel computations that supports the coupling of a Navier–Stokes-based fluid flow code with the Boussinesq approximation in order to address complex thermal scenarios for energy-related assessments. The newly designed data structure is specifically designed with the idea of interactive data exploration and visualization during runtime of the simulation code; a major shortcoming of traditional high-performance computing (HPC) simulation codes. We further show and discuss speed-up values obtained on one of Germany’s top-ranked supercomputers with up to 140,000 processes and present simulation results for different engineering-based thermal problems.
Massively parallel computing and the search for jets and black holes at the LHC
Energy Technology Data Exchange (ETDEWEB)
Halyo, V., E-mail: vhalyo@gmail.com; LeGresley, P.; Lujan, P.
2014-04-21
Massively parallel computing at the LHC could be the next leap necessary to reach an era of new discoveries at the LHC after the Higgs discovery. Scientific computing is a critical component of the LHC experiment, including operation, trigger, LHC computing GRID, simulation, and analysis. One way to improve the physics reach of the LHC is to take advantage of the flexibility of the trigger system by integrating coprocessors based on Graphics Processing Units (GPUs) or the Many Integrated Core (MIC) architecture into its server farm. This cutting edge technology provides not only the means to accelerate existing algorithms, but also the opportunity to develop new algorithms that select events in the trigger that previously would have evaded detection. In this paper we describe new algorithms that would allow us to select in the trigger new topological signatures that include non-prompt jet and black hole-like objects in the silicon tracker.
International Nuclear Information System (INIS)
Stankovski, Z.
1995-01-01
The collision probability method in neutron transport, as applied to 2D geometries, consume a great amount of computer time, for a typical 2D assembly calculation evaluations. Consequently RZ or 3D calculations became prohibitive. In this paper we present a simple but efficient parallel algorithm based on the message passing host/node programing model. Parallelization was applied to the energy group treatment. Such approach permits parallelization of the existing code, requiring only limited modifications. Sequential/parallel computer portability is preserved, witch is a necessary condition for a industrial code. Sequential performances are also preserved. The algorithm is implemented on a CRAY 90 coupled to a 128 processor T3D computer, a 16 processor IBM SP1 and a network of workstations, using the Public Domain PVM library. The tests were executed for a 2D geometry with the standard 99-group library. All results were very satisfactory, the best ones with IBM SP1. Because of heterogeneity of the workstation network, we did ask high performances for this architecture. The same source code was used for all computers. A more impressive advantage of this algorithm will appear in the calculations of the SAPHYR project (with the future fine multigroup library of about 8000 groups) with a massively parallel computer, using several hundreds of processors. (author). 5 refs., 6 figs., 2 tabs
International Nuclear Information System (INIS)
Stankovski, Z.
1995-01-01
The collision probability method in neutron transport, as applied to 2D geometries, consume a great amount of computer time, for a typical 2D assembly calculation about 90% of the computing time is consumed in the collision probability evaluations. Consequently RZ or 3D calculations became prohibitive. In this paper the author presents a simple but efficient parallel algorithm based on the message passing host/node programmation model. Parallelization was applied to the energy group treatment. Such approach permits parallelization of the existing code, requiring only limited modifications. Sequential/parallel computer portability is preserved, which is a necessary condition for a industrial code. Sequential performances are also preserved. The algorithm is implemented on a CRAY 90 coupled to a 128 processor T3D computer, a 16 processor IBM SPI and a network of workstations, using the Public Domain PVM library. The tests were executed for a 2D geometry with the standard 99-group library. All results were very satisfactory, the best ones with IBM SPI. Because of heterogeneity of the workstation network, the author did not ask high performances for this architecture. The same source code was used for all computers. A more impressive advantage of this algorithm will appear in the calculations of the SAPHYR project (with the future fine multigroup library of about 8000 groups) with a massively parallel computer, using several hundreds of processors
Three-Dimensional Nanobiocomputing Architectures With Neuronal Hypercells
2007-06-01
Neumann architectures, and CMOS fabrication. Novel solutions of massive parallel distributed computing and processing (pipelined due to systolic... and processing platforms utilizing molecular hardware within an enabling organization and architecture. The design technology is based on utilizing a...Microsystems and Nanotechnologies investigated a novel 3D3 (Hardware Software Nanotechnology) technology to design super-high performance computing
R-GPU : A reconfigurable GPU architecture
van den Braak, G.J.; Corporaal, H.
2016-01-01
Over the last decade, Graphics Processing Unit (GPU) architectures have evolved from a fixed-function graphics pipeline to a programmable, energy-efficient compute accelerator for massively parallel applications. The compute power arises from the GPU's Single Instruction/Multiple Threads
Energy Technology Data Exchange (ETDEWEB)
Lichtner, Peter C. [OFM Research, Redmond, WA (United States); Hammond, Glenn E. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Lu, Chuan [Idaho National Lab. (INL), Idaho Falls, ID (United States); Karra, Satish [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Bisht, Gautam [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Andre, Benjamin [National Center for Atmospheric Research, Boulder, CO (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Mills, Richard [Intel Corporation, Portland, OR (United States); Univ. of Tennessee, Knoxville, TN (United States); Kumar, Jitendra [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
2015-01-20
PFLOTRAN solves a system of generally nonlinear partial differential equations describing multi-phase, multicomponent and multiscale reactive flow and transport in porous materials. The code is designed to run on massively parallel computing architectures as well as workstations and laptops (e.g. Hammond et al., 2011). Parallelization is achieved through domain decomposition using the PETSc (Portable Extensible Toolkit for Scientific Computation) libraries for the parallelization framework (Balay et al., 1997). PFLOTRAN has been developed from the ground up for parallel scalability and has been run on up to 218 processor cores with problem sizes up to 2 billion degrees of freedom. Written in object oriented Fortran 90, the code requires the latest compilers compatible with Fortran 2003. At the time of this writing this requires gcc 4.7.x, Intel 12.1.x and PGC compilers. As a requirement of running problems with a large number of degrees of freedom, PFLOTRAN allows reading input data that is too large to fit into memory allotted to a single processor core. The current limitation to the problem size PFLOTRAN can handle is the limitation of the HDF5 file format used for parallel IO to 32 bit integers. Noting that 2^{32} = 4; 294; 967; 296, this gives an estimate of the maximum problem size that can be currently run with PFLOTRAN. Hopefully this limitation will be remedied in the near future.
Hybrid parallel computing architecture for multiview phase shifting
Zhong, Kai; Li, Zhongwei; Zhou, Xiaohui; Shi, Yusheng; Wang, Congjun
2014-11-01
The multiview phase-shifting method shows its powerful capability in achieving high resolution three-dimensional (3-D) shape measurement. Unfortunately, this ability results in very high computation costs and 3-D computations have to be processed offline. To realize real-time 3-D shape measurement, a hybrid parallel computing architecture is proposed for multiview phase shifting. In this architecture, the central processing unit can co-operate with the graphic processing unit (GPU) to achieve hybrid parallel computing. The high computation cost procedures, including lens distortion rectification, phase computation, correspondence, and 3-D reconstruction, are implemented in GPU, and a three-layer kernel function model is designed to simultaneously realize coarse-grained and fine-grained paralleling computing. Experimental results verify that the developed system can perform 50 fps (frame per second) real-time 3-D measurement with 260 K 3-D points per frame. A speedup of up to 180 times is obtained for the performance of the proposed technique using a NVIDIA GT560Ti graphics card rather than a sequential C in a 3.4 GHZ Inter Core i7 3770.
Energy Technology Data Exchange (ETDEWEB)
Gentzsch, W.; Ferstl, F.; Paap, H.G.; Riedel, E.
1998-03-20
In the ARTS project, system software has been developed to support smog and fluid dynamic applications on massively parallel systems. The aim is to implement and test specific software structures within an adaptive run-time system to separate the parallel core algorithms of the applications from the platform independent runtime aspects. Only slight modifications is existing Fortran and C code are necessary to integrate the application code into the new object oriented parallel integrated ARTS framework. The OO-design offers easy control, re-use and adaptation of the system services, resulting in a dramatic decrease in development time of the application and in ease of maintainability of the application software in the future. (orig.) [Deutsch] Im Projekt ARTS wird Basissoftware zur Unterstuetzung von Anwendungen aus den Bereichen Smoganalyse und Stroemungsmechanik auf massiv parallelen Systemen entwickelt und optimiert. Im Vordergrund steht die Erprobung geeigneter Strukturen, um systemnahe Funktionalitaeten in einer Laufzeitumgebung anzusiedeln und dadurch die parallelen Kernalgorithmen der Anwendungsprogramme von den plattformunabhaengigen Laufzeitaspekten zu trennen. Es handelt sich dabei um herkoemmlich strukturierten Fortran-Code, der unter minimalen Aenderungen auch weiterhin nutzbar sein muss, sowie um objektbasiert entworfenen C-Code, der die volle Funktionalitaet der ARTS-Plattform ausnutzen kann. Ein objektorientiertes Design erlaubt eine einfache Kontrolle, Wiederverwendung und Adaption der vom System vorgegebenen Basisdienste. Daraus resultiert ein deutlich reduzierter Entwicklungs- und Laufzeitaufwand fuer die Anwendung. ARTS schafft eine integrierende Plattform, die moderne Technologien aus dem Bereich objektorientierter Laufzeitsysteme mit praxisrelevanten Anforderungen aus dem Bereich des wissenschaftlichen Hoechstleistungsrechnens kombiniert. (orig.)
Climate models on massively parallel computers
International Nuclear Information System (INIS)
Vitart, F.; Rouvillois, P.
1993-01-01
First results got on massively parallel computers (Multiple Instruction Multiple Data and Simple Instruction Multiple Data) allow to consider building of coupled models with high resolutions. This would make possible simulation of thermoaline circulation and other interaction phenomena between atmosphere and ocean. The increasing of computers powers, and then the improvement of resolution will go us to revise our approximations. Then hydrostatic approximation (in ocean circulation) will not be valid when the grid mesh will be of a dimension lower than a few kilometers: We shall have to find other models. The expert appraisement got in numerical analysis at the Center of Limeil-Valenton (CEL-V) will be used again to imagine global models taking in account atmosphere, ocean, ice floe and biosphere, allowing climate simulation until a regional scale
From parallel to distributed computing for reactive scattering calculations
International Nuclear Information System (INIS)
Lagana, A.; Gervasi, O.; Baraglia, R.
1994-01-01
Some reactive scattering codes have been ported on different innovative computer architectures ranging from massively parallel machines to clustered workstations. The porting has required a drastic restructuring of the codes to single out computationally decoupled cpu intensive subsections. The suitability of different theoretical approaches for parallel and distributed computing restructuring is discussed and the efficiency of related algorithms evaluated
Directory of Open Access Journals (Sweden)
Cronn Richard
2009-12-01
Full Text Available Abstract Background Molecular evolutionary studies share the common goal of elucidating historical relationships, and the common challenge of adequately sampling taxa and characters. Particularly at low taxonomic levels, recent divergence, rapid radiations, and conservative genome evolution yield limited sequence variation, and dense taxon sampling is often desirable. Recent advances in massively parallel sequencing make it possible to rapidly obtain large amounts of sequence data, and multiplexing makes extensive sampling of megabase sequences feasible. Is it possible to efficiently apply massively parallel sequencing to increase phylogenetic resolution at low taxonomic levels? Results We reconstruct the infrageneric phylogeny of Pinus from 37 nearly-complete chloroplast genomes (average 109 kilobases each of an approximately 120 kilobase genome generated using multiplexed massively parallel sequencing. 30/33 ingroup nodes resolved with ≥ 95% bootstrap support; this is a substantial improvement relative to prior studies, and shows massively parallel sequencing-based strategies can produce sufficient high quality sequence to reach support levels originally proposed for the phylogenetic bootstrap. Resampling simulations show that at least the entire plastome is necessary to fully resolve Pinus, particularly in rapidly radiating clades. Meta-analysis of 99 published infrageneric phylogenies shows that whole plastome analysis should provide similar gains across a range of plant genera. A disproportionate amount of phylogenetic information resides in two loci (ycf1, ycf2, highlighting their unusual evolutionary properties. Conclusion Plastome sequencing is now an efficient option for increasing phylogenetic resolution at lower taxonomic levels in plant phylogenetic and population genetic analyses. With continuing improvements in sequencing capacity, the strategies herein should revolutionize efforts requiring dense taxon and character sampling
Visualizing Network Traffic to Understand the Performance of Massively Parallel Simulations
Landge, A. G.
2012-12-01
The performance of massively parallel applications is often heavily impacted by the cost of communication among compute nodes. However, determining how to best use the network is a formidable task, made challenging by the ever increasing size and complexity of modern supercomputers. This paper applies visualization techniques to aid parallel application developers in understanding the network activity by enabling a detailed exploration of the flow of packets through the hardware interconnect. In order to visualize this large and complex data, we employ two linked views of the hardware network. The first is a 2D view, that represents the network structure as one of several simplified planar projections. This view is designed to allow a user to easily identify trends and patterns in the network traffic. The second is a 3D view that augments the 2D view by preserving the physical network topology and providing a context that is familiar to the application developers. Using the massively parallel multi-physics code pF3D as a case study, we demonstrate that our tool provides valuable insight that we use to explain and optimize pF3D-s performance on an IBM Blue Gene/P system. © 1995-2012 IEEE.
Parallel computing of physical maps--a comparative study in SIMD and MIMD parallelism.
Bhandarkar, S M; Chirravuri, S; Arnold, J
1996-01-01
Ordering clones from a genomic library into physical maps of whole chromosomes presents a central computational problem in genetics. Chromosome reconstruction via clone ordering is usually isomorphic to the NP-complete Optimal Linear Arrangement problem. Parallel SIMD and MIMD algorithms for simulated annealing based on Markov chain distribution are proposed and applied to the problem of chromosome reconstruction via clone ordering. Perturbation methods and problem-specific annealing heuristics are proposed and described. The SIMD algorithms are implemented on a 2048 processor MasPar MP-2 system which is an SIMD 2-D toroidal mesh architecture whereas the MIMD algorithms are implemented on an 8 processor Intel iPSC/860 which is an MIMD hypercube architecture. A comparative analysis of the various SIMD and MIMD algorithms is presented in which the convergence, speedup, and scalability characteristics of the various algorithms are analyzed and discussed. On a fine-grained, massively parallel SIMD architecture with a low synchronization overhead such as the MasPar MP-2, a parallel simulated annealing algorithm based on multiple periodically interacting searches performs the best. For a coarse-grained MIMD architecture with high synchronization overhead such as the Intel iPSC/860, a parallel simulated annealing algorithm based on multiple independent searches yields the best results. In either case, distribution of clonal data across multiple processors is shown to exacerbate the tendency of the parallel simulated annealing algorithm to get trapped in a local optimum.
Reduced complexity and latency for a massive MIMO system using a parallel detection algorithm
Directory of Open Access Journals (Sweden)
Shoichi Higuchi
2017-09-01
Full Text Available In recent years, massive MIMO systems have been widely researched to realize high-speed data transmission. Since massive MIMO systems use a large number of antennas, these systems require huge complexity to detect the signal. In this paper, we propose a novel detection method for massive MIMO using parallel detection with maximum likelihood detection with QR decomposition and M-algorithm (QRM-MLD to reduce the complexity and latency. The proposed scheme obtains an R matrix after permutation of an H matrix and QR decomposition. The R matrix is also eliminated using a Gauss–Jordan elimination method. By using a modified R matrix, the proposed method can detect the transmitted signal using parallel detection. From the simulation results, the proposed scheme can achieve a reduced complexity and latency with a little degradation of the bit error rate (BER performance compared with the conventional method.
Parallel PDE-Based Simulations Using the Common Component Architecture
International Nuclear Information System (INIS)
McInnes, Lois C.; Allan, Benjamin A.; Armstrong, Robert; Benson, Steven J.; Bernholdt, David E.; Dahlgren, Tamara L.; Diachin, Lori; Krishnan, Manoj Kumar; Kohl, James A.; Larson, J. Walter; Lefantzi, Sophia; Nieplocha, Jarek; Norris, Boyana; Parker, Steven G.; Ray, Jaideep; Zhou, Shujia
2006-01-01
The complexity of parallel PDE-based simulations continues to increase as multimodel, multiphysics, and multi-institutional projects become widespread. A goal of component based software engineering in such large-scale simulations is to help manage this complexity by enabling better interoperability among various codes that have been independently developed by different groups. The Common Component Architecture (CCA) Forum is defining a component architecture specification to address the challenges of high-performance scientific computing. In addition, several execution frameworks, supporting infrastructure, and general purpose components are being developed. Furthermore, this group is collaborating with others in the high-performance computing community to design suites of domain-specific component interface specifications and underlying implementations. This chapter discusses recent work on leveraging these CCA efforts in parallel PDE-based simulations involving accelerator design, climate modeling, combustion, and accidental fires and explosions. We explain how component technology helps to address the different challenges posed by each of these applications, and we highlight how component interfaces built on existing parallel toolkits facilitate the reuse of software for parallel mesh manipulation, discretization, linear algebra, integration, optimization, and parallel data redistribution. We also present performance data to demonstrate the suitability of this approach, and we discuss strategies for applying component technologies to both new and existing applications
Parallel algorithms and architecture for computation of manipulator forward dynamics
Fijany, Amir; Bejczy, Antal K.
1989-01-01
Parallel computation of manipulator forward dynamics is investigated. Considering three classes of algorithms for the solution of the problem, that is, the O(n), the O(n exp 2), and the O(n exp 3) algorithms, parallelism in the problem is analyzed. It is shown that the problem belongs to the class of NC and that the time and processors bounds are of O(log2/2n) and O(n exp 4), respectively. However, the fastest stable parallel algorithms achieve the computation time of O(n) and can be derived by parallelization of the O(n exp 3) serial algorithms. Parallel computation of the O(n exp 3) algorithms requires the development of parallel algorithms for a set of fundamentally different problems, that is, the Newton-Euler formulation, the computation of the inertia matrix, decomposition of the symmetric, positive definite matrix, and the solution of triangular systems. Parallel algorithms for this set of problems are developed which can be efficiently implemented on a unique architecture, a triangular array of n(n+2)/2 processors with a simple nearest-neighbor interconnection. This architecture is particularly suitable for VLSI and WSI implementations. The developed parallel algorithm, compared to the best serial O(n) algorithm, achieves an asymptotic speedup of more than two orders-of-magnitude in the computation the forward dynamics.
DEFF Research Database (Denmark)
Romero, N. A.; Glinsvad, Christian; Larsen, Ask Hjorth
2013-01-01
Density function theory (DFT) is the most widely employed electronic structure method because of its favorable scaling with system size and accuracy for a broad range of molecular and condensed-phase systems. The advent of massively parallel supercomputers has enhanced the scientific community...
Image processing with massively parallel computer Quadrics Q1
International Nuclear Information System (INIS)
Della Rocca, A.B.; La Porta, L.; Ferriani, S.
1995-05-01
Aimed to evaluate the image processing capabilities of the massively parallel computer Quadrics Q1, a convolution algorithm that has been implemented is described in this report. At first the discrete convolution mathematical definition is recalled together with the main Q1 h/w and s/w features. Then the different codification forms of the algorythm are described and the Q1 performances are compared with those obtained by different computers. Finally, the conclusions report on main results and suggestions
Directory of Open Access Journals (Sweden)
Reeba Korah
2008-01-01
Full Text Available This paper presents a low power and high speed architecture for motion estimation with Candidate Block and Pixel Subsampling (CBPS Algorithm. Coarse-to-fine search approach is employed to find the motion vector so that the local minima problem is totally eliminated. Pixel subsampling is performed in the selected candidate blocks which significantly reduces computational cost with low quality degradation. The architecture developed is a fully pipelined parallel design with 9 processing elements. Two different methods are deployed to reduce the power consumption, parallel and pipelined implementation and parallel accessing to memory. For processing 30 CIF frames per second our architecture requires a clock frequency of 4.5 MHz.
Hybrid massively parallel fast sweeping method for static Hamilton–Jacobi equations
Energy Technology Data Exchange (ETDEWEB)
Detrixhe, Miles, E-mail: mdetrixhe@engineering.ucsb.edu [Department of Mechanical Engineering (United States); University of California Santa Barbara, Santa Barbara, CA, 93106 (United States); Gibou, Frédéric, E-mail: fgibou@engineering.ucsb.edu [Department of Mechanical Engineering (United States); University of California Santa Barbara, Santa Barbara, CA, 93106 (United States); Department of Computer Science (United States); Department of Mathematics (United States)
2016-10-01
The fast sweeping method is a popular algorithm for solving a variety of static Hamilton–Jacobi equations. Fast sweeping algorithms for parallel computing have been developed, but are severely limited. In this work, we present a multilevel, hybrid parallel algorithm that combines the desirable traits of two distinct parallel methods. The fine and coarse grained components of the algorithm take advantage of heterogeneous computer architecture common in high performance computing facilities. We present the algorithm and demonstrate its effectiveness on a set of example problems including optimal control, dynamic games, and seismic wave propagation. We give results for convergence, parallel scaling, and show state-of-the-art speedup values for the fast sweeping method.
Hybrid massively parallel fast sweeping method for static Hamilton–Jacobi equations
International Nuclear Information System (INIS)
Detrixhe, Miles; Gibou, Frédéric
2016-01-01
The fast sweeping method is a popular algorithm for solving a variety of static Hamilton–Jacobi equations. Fast sweeping algorithms for parallel computing have been developed, but are severely limited. In this work, we present a multilevel, hybrid parallel algorithm that combines the desirable traits of two distinct parallel methods. The fine and coarse grained components of the algorithm take advantage of heterogeneous computer architecture common in high performance computing facilities. We present the algorithm and demonstrate its effectiveness on a set of example problems including optimal control, dynamic games, and seismic wave propagation. We give results for convergence, parallel scaling, and show state-of-the-art speedup values for the fast sweeping method.
Directions in parallel processor architecture, and GPUs too
CERN. Geneva
2014-01-01
Modern computing is power-limited in every domain of computing. Performance increments extracted from instruction-level parallelism (ILP) are no longer power-efficient; they haven't been for some time. Thread-level parallelism (TLP) is a more easily exploited form of parallelism, at the expense of programmer effort to expose it in the program. In this talk, I will introduce you to disparate topics in parallel processor architecture that will impact programming models (and you) in both the near and far future. About the speaker Olivier is a senior GPU (SM) architect at NVIDIA and an active participant in the concurrency working group of the ISO C++ committee. He has also worked on very large diesel engines as a mechanical engineer, and taught at McGill University (Canada) as a faculty instructor.
A Parallel Saturation Algorithm on Shared Memory Architectures
Ezekiel, Jonathan; Siminiceanu
2007-01-01
Symbolic state-space generators are notoriously hard to parallelize. However, the Saturation algorithm implemented in the SMART verification tool differs from other sequential symbolic state-space generators in that it exploits the locality of ring events in asynchronous system models. This paper explores whether event locality can be utilized to efficiently parallelize Saturation on shared-memory architectures. Conceptually, we propose to parallelize the ring of events within a decision diagram node, which is technically realized via a thread pool. We discuss the challenges involved in our parallel design and conduct experimental studies on its prototypical implementation. On a dual-processor dual core PC, our studies show speed-ups for several example models, e.g., of up to 50% for a Kanban model, when compared to running our algorithm only on a single core.
Time analysis of interconnection network implemented on the honeycomb architecture
Energy Technology Data Exchange (ETDEWEB)
Milutinovic, D [Inst. Michael Pupin, Belgrade (Yugoslavia)
1996-12-31
Problems of time domains analysis of the mapping of interconnection networks for parallel processing on one form of uniform massively parallel architecture of the cellular type are considered. The results of time analysis are discussed. It is found that changing the technology results in changing the mapping rules. 17 refs.
Monte Carlo simulations on SIMD computer architectures
International Nuclear Information System (INIS)
Burmester, C.P.; Gronsky, R.; Wille, L.T.
1992-01-01
In this paper algorithmic considerations regarding the implementation of various materials science applications of the Monte Carlo technique to single instruction multiple data (SIMD) computer architectures are presented. In particular, implementation of the Ising model with nearest, next nearest, and long range screened Coulomb interactions on the SIMD architecture MasPar MP-1 (DEC mpp-12000) series of massively parallel computers is demonstrated. Methods of code development which optimize processor array use and minimize inter-processor communication are presented including lattice partitioning and the use of processor array spanning tree structures for data reduction. Both geometric and algorithmic parallel approaches are utilized. Benchmarks in terms of Monte Carl updates per second for the MasPar architecture are presented and compared to values reported in the literature from comparable studies on other architectures
Teddy, Livian; Hardiman, Gagoek; Nuroji; Tudjono, Sri
2017-12-01
Indonesia is an area prone to earthquake that may cause casualties and damage to buildings. The fatalities or the injured are not largely caused by the earthquake, but by building collapse. The collapse of the building is resulted from the building behaviour against the earthquake, and it depends on many factors, such as architectural design, geometry configuration of structural elements in horizontal and vertical plans, earthquake zone, geographical location (distance to earthquake center), soil type, material quality, and construction quality. One of the geometry configurations that may lead to the collapse of the building is irregular configuration of non-parallel system. In accordance with FEMA-451B, irregular configuration in non-parallel system is defined to have existed if the vertical lateral force-retaining elements are neither parallel nor symmetric with main orthogonal axes of the earthquake-retaining axis system. Such configuration may lead to torque, diagonal translation and local damage to buildings. It does not mean that non-parallel irregular configuration should not be formed on architectural design; however the designer must know the consequence of earthquake behaviour against buildings with irregular configuration of non-parallel system. The present research has the objective to identify earthquake behaviour in architectural geometry with irregular configuration of non-parallel system. The present research was quantitative with simulation experimental method. It consisted of 5 models, where architectural data and model structure data were inputted and analyzed using the software SAP2000 in order to find out its performance, and ETAB2015 to determine the eccentricity occurred. The output of the software analysis was tabulated, graphed, compared and analyzed with relevant theories. For areas of strong earthquake zones, avoid designing buildings which wholly form irregular configuration of non-parallel system. If it is inevitable to design a
Parallel implementation of DNA sequences matching algorithms using PWM on GPU architecture.
Sharma, Rahul; Gupta, Nitin; Narang, Vipin; Mittal, Ankush
2011-01-01
Positional Weight Matrices (PWMs) are widely used in representation and detection of Transcription Factor Of Binding Sites (TFBSs) on DNA. We implement online PWM search algorithm over parallel architecture. A large PWM data can be processed on Graphic Processing Unit (GPU) systems in parallel which can help in matching sequences at a faster rate. Our method employs extensive usage of highly multithreaded architecture and shared memory of multi-cored GPU. An efficient use of shared memory is required to optimise parallel reduction in CUDA. Our optimised method has a speedup of 230-280x over linear implementation on GPU named GeForce GTX 280.
Implementation of QR up- and downdating on a massively parallel |computer
DEFF Research Database (Denmark)
Bendtsen, Claus; Hansen, Per Christian; Madsen, Kaj
1995-01-01
We describe an implementation of QR up- and downdating on a massively parallel computer (the Connection Machine CM-200) and show that the algorithm maps well onto the computer. In particular, we show how the use of corrected semi-normal equations for downdating can be efficiently implemented. We...... also illustrate the use of our algorithms in a new LP algorithm....
A parallel solution for high resolution histological image analysis.
Bueno, G; González, R; Déniz, O; García-Rojo, M; González-García, J; Fernández-Carrobles, M M; Vállez, N; Salido, J
2012-10-01
This paper describes a general methodology for developing parallel image processing algorithms based on message passing for high resolution images (on the order of several Gigabytes). These algorithms have been applied to histological images and must be executed on massively parallel processing architectures. Advances in new technologies for complete slide digitalization in pathology have been combined with developments in biomedical informatics. However, the efficient use of these digital slide systems is still a challenge. The image processing that these slides are subject to is still limited both in terms of data processed and processing methods. The work presented here focuses on the need to design and develop parallel image processing tools capable of obtaining and analyzing the entire gamut of information included in digital slides. Tools have been developed to assist pathologists in image analysis and diagnosis, and they cover low and high-level image processing methods applied to histological images. Code portability, reusability and scalability have been tested by using the following parallel computing architectures: distributed memory with massive parallel processors and two networks, INFINIBAND and Myrinet, composed of 17 and 1024 nodes respectively. The parallel framework proposed is flexible, high performance solution and it shows that the efficient processing of digital microscopic images is possible and may offer important benefits to pathology laboratories. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.
Using Runtime Systems Tools to Implement Efficient Preconditioners for Heterogeneous Architectures
Directory of Open Access Journals (Sweden)
Roussel Adrien
2016-11-01
Full Text Available Solving large sparse linear systems is a time-consuming step in basin modeling or reservoir simulation. The choice of a robust preconditioner strongly impact the performance of the overall simulation. Heterogeneous architectures based on General Purpose computing on Graphic Processing Units (GPGPU or many-core architectures introduce programming challenges which can be managed in a transparent way for developer with the use of runtime systems. Nevertheless, algorithms need to be well suited for these massively parallel architectures. In this paper, we present preconditioning techniques which enable to take advantage of emerging architectures. We also present our task-based implementations through the use of the HARTS (Heterogeneous Abstract RunTime System runtime system, which aims to manage the recent architectures. We focus on two preconditoners. The first is ILU(0 preconditioner implemented on distributing memory systems. The second one is a multi-level domain decomposition method implemented on a shared-memory system. Obtained results are then presented on corresponding architectures, which open the way to discuss on the scalability of such methods according to numerical performances while keeping in mind that the next step is to propose a massively parallel implementations of these techniques.
Application of parallelized software architecture to an autonomous ground vehicle
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.
An efficient implementation of parallel molecular dynamics method on SMP cluster architecture
International Nuclear Information System (INIS)
Suzuki, Masaaki; Okuda, Hiroshi; Yagawa, Genki
2003-01-01
The authors have applied MPI/OpenMP hybrid parallel programming model to parallelize a molecular dynamics (MD) method on a symmetric multiprocessor (SMP) cluster architecture. In that architecture, it can be expected that the hybrid parallel programming model, which uses the message passing library such as MPI for inter-SMP node communication and the loop directive such as OpenMP for intra-SNP node parallelization, is the most effective one. In this study, the parallel performance of the hybrid style has been compared with that of conventional flat parallel programming style, which uses only MPI, both in cases the fast multipole method (FMM) is employed for computing long-distance interactions and that is not employed. The computer environments used here are Hitachi SR8000/MPP placed at the University of Tokyo. The results of calculation are as follows. Without FMM, the parallel efficiency using 16 SMP nodes (128 PEs) is: 90% with the hybrid style, 75% with the flat-MPI style for MD simulation with 33,402 atoms. With FMM, the parallel efficiency using 16 SMP nodes (128 PEs) is: 60% with the hybrid style, 48% with the flat-MPI style for MD simulation with 117,649 atoms. (author)
Massively Parallel Single-Molecule Manipulation Using Centrifugal Force
Wong, Wesley; Halvorsen, Ken
2011-03-01
Precise manipulation of single molecules has led to remarkable insights in physics, chemistry, biology, and medicine. However, two issues that have impeded the widespread adoption of these techniques are equipment cost and the laborious nature of making measurements one molecule at a time. To meet these challenges, we have developed an approach that enables massively parallel single- molecule force measurements using centrifugal force. This approach is realized in the centrifuge force microscope, an instrument in which objects in an orbiting sample are subjected to a calibration-free, macroscopically uniform force- field while their micro-to-nanoscopic motions are observed. We demonstrate high- throughput single-molecule force spectroscopy with this technique by performing thousands of rupture experiments in parallel, characterizing force-dependent unbinding kinetics of an antibody-antigen pair in minutes rather than days. Currently, we are taking steps to integrate high-resolution detection, fluorescence, temperature control and a greater dynamic range in force. With significant benefits in efficiency, cost, simplicity, and versatility, single-molecule centrifugation has the potential to expand single-molecule experimentation to a wider range of researchers and experimental systems.
MADmap: A Massively Parallel Maximum-Likelihood Cosmic Microwave Background Map-Maker
Energy Technology Data Exchange (ETDEWEB)
Cantalupo, Christopher; Borrill, Julian; Jaffe, Andrew; Kisner, Theodore; Stompor, Radoslaw
2009-06-09
MADmap is a software application used to produce maximum-likelihood images of the sky from time-ordered data which include correlated noise, such as those gathered by Cosmic Microwave Background (CMB) experiments. It works efficiently on platforms ranging from small workstations to the most massively parallel supercomputers. Map-making is a critical step in the analysis of all CMB data sets, and the maximum-likelihood approach is the most accurate and widely applicable algorithm; however, it is a computationally challenging task. This challenge will only increase with the next generation of ground-based, balloon-borne and satellite CMB polarization experiments. The faintness of the B-mode signal that these experiments seek to measure requires them to gather enormous data sets. MADmap is already being run on up to O(1011) time samples, O(108) pixels and O(104) cores, with ongoing work to scale to the next generation of data sets and supercomputers. We describe MADmap's algorithm based around a preconditioned conjugate gradient solver, fast Fourier transforms and sparse matrix operations. We highlight MADmap's ability to address problems typically encountered in the analysis of realistic CMB data sets and describe its application to simulations of the Planck and EBEX experiments. The massively parallel and distributed implementation is detailed and scaling complexities are given for the resources required. MADmap is capable of analysing the largest data sets now being collected on computing resources currently available, and we argue that, given Moore's Law, MADmap will be capable of reducing the most massive projected data sets.
Heydt, Carina; Fassunke, Jana; Künstlinger, Helen; Ihle, Michaela Angelika; König, Katharina; Heukamp, Lukas Carl; Schildhaus, Hans-Ulrich; Odenthal, Margarete; Büttner, Reinhard; Merkelbach-Bruse, Sabine
2014-01-01
Over the last years, massively parallel sequencing has rapidly evolved and has now transitioned into molecular pathology routine laboratories. It is an attractive platform for analysing multiple genes at the same time with very little input material. Therefore, the need for high quality DNA obtained from automated DNA extraction systems has increased, especially to those laboratories which are dealing with formalin-fixed paraffin-embedded (FFPE) material and high sample throughput. This study evaluated five automated FFPE DNA extraction systems as well as five DNA quantification systems using the three most common techniques, UV spectrophotometry, fluorescent dye-based quantification and quantitative PCR, on 26 FFPE tissue samples. Additionally, the effects on downstream applications were analysed to find the most suitable pre-analytical methods for massively parallel sequencing in routine diagnostics. The results revealed that the Maxwell 16 from Promega (Mannheim, Germany) seems to be the superior system for DNA extraction from FFPE material. The extracts had a 1.3–24.6-fold higher DNA concentration in comparison to the other extraction systems, a higher quality and were most suitable for downstream applications. The comparison of the five quantification methods showed intermethod variations but all methods could be used to estimate the right amount for PCR amplification and for massively parallel sequencing. Interestingly, the best results in massively parallel sequencing were obtained with a DNA input of 15 ng determined by the NanoDrop 2000c spectrophotometer (Thermo Fisher Scientific, Waltham, MA, USA). No difference could be detected in mutation analysis based on the results of the quantification methods. These findings emphasise, that it is particularly important to choose the most reliable and constant DNA extraction system, especially when using small biopsies and low elution volumes, and that all common DNA quantification techniques can be used for
Directory of Open Access Journals (Sweden)
Carina Heydt
Full Text Available Over the last years, massively parallel sequencing has rapidly evolved and has now transitioned into molecular pathology routine laboratories. It is an attractive platform for analysing multiple genes at the same time with very little input material. Therefore, the need for high quality DNA obtained from automated DNA extraction systems has increased, especially to those laboratories which are dealing with formalin-fixed paraffin-embedded (FFPE material and high sample throughput. This study evaluated five automated FFPE DNA extraction systems as well as five DNA quantification systems using the three most common techniques, UV spectrophotometry, fluorescent dye-based quantification and quantitative PCR, on 26 FFPE tissue samples. Additionally, the effects on downstream applications were analysed to find the most suitable pre-analytical methods for massively parallel sequencing in routine diagnostics. The results revealed that the Maxwell 16 from Promega (Mannheim, Germany seems to be the superior system for DNA extraction from FFPE material. The extracts had a 1.3-24.6-fold higher DNA concentration in comparison to the other extraction systems, a higher quality and were most suitable for downstream applications. The comparison of the five quantification methods showed intermethod variations but all methods could be used to estimate the right amount for PCR amplification and for massively parallel sequencing. Interestingly, the best results in massively parallel sequencing were obtained with a DNA input of 15 ng determined by the NanoDrop 2000c spectrophotometer (Thermo Fisher Scientific, Waltham, MA, USA. No difference could be detected in mutation analysis based on the results of the quantification methods. These findings emphasise, that it is particularly important to choose the most reliable and constant DNA extraction system, especially when using small biopsies and low elution volumes, and that all common DNA quantification techniques can
Kalman Filter Tracking on Parallel Architectures
International Nuclear Information System (INIS)
Cerati, Giuseppe; Elmer, Peter; Krutelyov, Slava; Lantz, Steven; Lefebvre, Matthieu; McDermott, Kevin; Riley, Daniel; Tadel, Matevž; Wittich, Peter; Würthwein, Frank; Yagil, Avi
2016-01-01
Power density constraints are limiting the performance improvements of modern CPUs. To address this we have seen the introduction of lower-power, multi-core processors such as GPGPU, ARM and Intel MIC. In order to achieve the theoretical performance gains of these processors, it will be necessary to parallelize algorithms to exploit larger numbers of lightweight cores and specialized functions like large vector units. Track finding and fitting is one of the most computationally challenging problems for event reconstruction in particle physics. At the High-Luminosity Large Hadron Collider (HL-LHC), for example, this will be by far the dominant problem. The need for greater parallelism has driven investigations of very different track finding techniques such as Cellular Automata or Hough Transforms. The most common track finding techniques in use today, however, are those based on a Kalman filter approach. Significant experience has been accumulated with these techniques on real tracking detector systems, both in the trigger and offline. They are known to provide high physics performance, are robust, and are in use today at the LHC. Given the utility of the Kalman filter in track finding, we have begun to port these algorithms to parallel architectures, namely Intel Xeon and Xeon Phi. We report here on our progress towards an end-to-end track reconstruction algorithm fully exploiting vectorization and parallelization techniques in a simplified experimental environment
Computational chaos in massively parallel neural networks
Barhen, Jacob; Gulati, Sandeep
1989-01-01
A fundamental issue which directly impacts the scalability of current theoretical neural network models to massively parallel embodiments, in both software as well as hardware, is the inherent and unavoidable concurrent asynchronicity of emerging fine-grained computational ensembles and the possible emergence of chaotic manifestations. Previous analyses attributed dynamical instability to the topology of the interconnection matrix, to parasitic components or to propagation delays. However, researchers have observed the existence of emergent computational chaos in a concurrently asynchronous framework, independent of the network topology. Researcher present a methodology enabling the effective asynchronous operation of large-scale neural networks. Necessary and sufficient conditions guaranteeing concurrent asynchronous convergence are established in terms of contracting operators. Lyapunov exponents are computed formally to characterize the underlying nonlinear dynamics. Simulation results are presented to illustrate network convergence to the correct results, even in the presence of large delays.
Massively Parallel and Scalable Implicit Time Integration Algorithms for Structural Dynamics
Farhat, Charbel
1997-01-01
Explicit codes are often used to simulate the nonlinear dynamics of large-scale structural systems, even for low frequency response, because the storage and CPU requirements entailed by the repeated factorizations traditionally found in implicit codes rapidly overwhelm the available computing resources. With the advent of parallel processing, this trend is accelerating because of the following additional facts: (a) explicit schemes are easier to parallelize than implicit ones, and (b) explicit schemes induce short range interprocessor communications that are relatively inexpensive, while the factorization methods used in most implicit schemes induce long range interprocessor communications that often ruin the sought-after speed-up. However, the time step restriction imposed by the Courant stability condition on all explicit schemes cannot yet be offset by the speed of the currently available parallel hardware. Therefore, it is essential to develop efficient alternatives to direct methods that are also amenable to massively parallel processing because implicit codes using unconditionally stable time-integration algorithms are computationally more efficient when simulating the low-frequency dynamics of aerospace structures.
Research in Parallel Algorithms and Software for Computational Aerosciences
Domel, Neal D.
1996-01-01
Phase 1 is complete for the development of a computational fluid dynamics CFD) parallel code with automatic grid generation and adaptation for the Euler analysis of flow over complex geometries. SPLITFLOW, an unstructured Cartesian grid code developed at Lockheed Martin Tactical Aircraft Systems, has been modified for a distributed memory/massively parallel computing environment. The parallel code is operational on an SGI network, Cray J90 and C90 vector machines, SGI Power Challenge, and Cray T3D and IBM SP2 massively parallel machines. Parallel Virtual Machine (PVM) is the message passing protocol for portability to various architectures. A domain decomposition technique was developed which enforces dynamic load balancing to improve solution speed and memory requirements. A host/node algorithm distributes the tasks. The solver parallelizes very well, and scales with the number of processors. Partially parallelized and non-parallelized tasks consume most of the wall clock time in a very fine grain environment. Timing comparisons on a Cray C90 demonstrate that Parallel SPLITFLOW runs 2.4 times faster on 8 processors than its non-parallel counterpart autotasked over 8 processors.
Communication and Memory Architecture Design of Application-Specific High-End Multiprocessors
Directory of Open Access Journals (Sweden)
Yahya Jan
2012-01-01
Full Text Available This paper is devoted to the design of communication and memory architectures of massively parallel hardware multiprocessors necessary for the implementation of highly demanding applications. We demonstrated that for the massively parallel hardware multiprocessors the traditionally used flat communication architectures and multi-port memories do not scale well, and the memory and communication network influence on both the throughput and circuit area dominates the processors influence. To resolve the problems and ensure scalability, we proposed to design highly optimized application-specific hierarchical and/or partitioned communication and memory architectures through exploring and exploiting the regularity and hierarchy of the actual data flows of a given application. Furthermore, we proposed some data distribution and related data mapping schemes in the shared (global partitioned memories with the aim to eliminate the memory access conflicts, as well as, to ensure that our communication design strategies will be applicable. We incorporated these architecture synthesis strategies into our quality-driven model-based multi-processor design method and related automated architecture exploration framework. Using this framework, we performed a large series of experiments that demonstrate many various important features of the synthesized memory and communication architectures. They also demonstrate that our method and related framework are able to efficiently synthesize well scalable memory and communication architectures even for the high-end multiprocessors. The gains as high as 12-times in performance and 25-times in area can be obtained when using the hierarchical communication networks instead of the flat networks. However, for the high parallelism levels only the partitioned approach ensures the scalability in performance.
Routing performance analysis and optimization within a massively parallel computer
Archer, Charles Jens; Peters, Amanda; Pinnow, Kurt Walter; Swartz, Brent Allen
2013-04-16
An apparatus, program product and method optimize the operation of a massively parallel computer system by, in part, receiving actual performance data concerning an application executed by the plurality of interconnected nodes, and analyzing the actual performance data to identify an actual performance pattern. A desired performance pattern may be determined for the application, and an algorithm may be selected from among a plurality of algorithms stored within a memory, the algorithm being configured to achieve the desired performance pattern based on the actual performance data.
Representing and computing regular languages on massively parallel networks
Energy Technology Data Exchange (ETDEWEB)
Miller, M.I.; O' Sullivan, J.A. (Electronic Systems and Research Lab., of Electrical Engineering, Washington Univ., St. Louis, MO (US)); Boysam, B. (Dept. of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Inst., Troy, NY (US)); Smith, K.R. (Dept. of Electrical Engineering, Southern Illinois Univ., Edwardsville, IL (US))
1991-01-01
This paper proposes a general method for incorporating rule-based constraints corresponding to regular languages into stochastic inference problems, thereby allowing for a unified representation of stochastic and syntactic pattern constraints. The authors' approach first established the formal connection of rules to Chomsky grammars, and generalizes the original work of Shannon on the encoding of rule-based channel sequences to Markov chains of maximum entropy. This maximum entropy probabilistic view leads to Gibb's representations with potentials which have their number of minima growing at precisely the exponential rate that the language of deterministically constrained sequences grow. These representations are coupled to stochastic diffusion algorithms, which sample the language-constrained sequences by visiting the energy minima according to the underlying Gibbs' probability law. The coupling to stochastic search methods yields the all-important practical result that fully parallel stochastic cellular automata may be derived to generate samples from the rule-based constraint sets. The production rules and neighborhood state structure of the language of sequences directly determines the necessary connection structures of the required parallel computing surface. Representations of this type have been mapped to the DAP-510 massively-parallel processor consisting of 1024 mesh-connected bit-serial processing elements for performing automated segmentation of electron-micrograph images.
Energy Technology Data Exchange (ETDEWEB)
Bauerle, Matthew [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
2014-08-01
This project utilizes Graphics Processing Units (GPUs) to compute radiograph simulations for arbitrary objects. The generation of radiographs, also known as the forward projection imaging model, is computationally intensive and not widely utilized. The goal of this research is to develop a massively parallel algorithm that can compute forward projections for objects with a trillion voxels (3D pixels). To achieve this end, the data are divided into blocks that can each t into GPU memory. The forward projected image is also divided into segments to allow for future parallelization and to avoid needless computations.
Iterative Multiuser Equalization for Subconnected Hybrid mmWave Massive MIMO Architecture
Directory of Open Access Journals (Sweden)
R. Magueta
2017-01-01
Full Text Available Millimeter waves and massive MIMO are a promising combination to achieve the multi-Gb/s required by future 5G wireless systems. However, fully digital architectures are not feasible due to hardware limitations, which means that there is a need to design signal processing techniques for hybrid analog-digital architectures. In this manuscript, we propose a hybrid iterative block multiuser equalizer for subconnected millimeter wave massive MIMO systems. The low complexity user-terminals employ pure-analog random precoders, each with a single RF chain. For the base station, a subconnected hybrid analog-digital equalizer is designed to remove multiuser interference. The hybrid equalizer is optimized using the average bit-error-rate as a metric. Due to the coupling between the RF chains in the optimization problem, the computation of the optimal solutions is too complex. To address this problem, we compute the analog part of the equalizer sequentially over the RF chains using a dictionary built from the array response vectors. The proposed subconnected hybrid iterative multiuser equalizer is compared with a recently proposed fully connected approach. The results show that the performance of the proposed scheme is close to the fully connected hybrid approach counterpart after just a few iterations.
DIMACS Workshop on Interconnection Networks and Mapping, and Scheduling Parallel Computations
Rosenberg, Arnold L; Sotteau, Dominique; NSF Science and Technology Center in Discrete Mathematics and Theoretical Computer Science; Interconnection networks and mapping and scheduling parallel computations
1995-01-01
The interconnection network is one of the most basic components of a massively parallel computer system. Such systems consist of hundreds or thousands of processors interconnected to work cooperatively on computations. One of the central problems in parallel computing is the task of mapping a collection of processes onto the processors and routing network of a parallel machine. Once this mapping is done, it is critical to schedule computations within and communication among processor from universities and laboratories, as well as practitioners involved in the design, implementation, and application of massively parallel systems. Focusing on interconnection networks of parallel architectures of today and of the near future , the book includes topics such as network topologies,network properties, message routing, network embeddings, network emulation, mappings, and efficient scheduling. inputs for a process are available where and when the process is scheduled to be computed. This book contains the refereed pro...
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
Massively parallel DNA sequencing facilitates diagnosis of patients with Usher syndrome type 1.
Directory of Open Access Journals (Sweden)
Hidekane Yoshimura
Full Text Available Usher syndrome is an autosomal recessive disorder manifesting hearing loss, retinitis pigmentosa and vestibular dysfunction, and having three clinical subtypes. Usher syndrome type 1 is the most severe subtype due to its profound hearing loss, lack of vestibular responses, and retinitis pigmentosa that appears in prepuberty. Six of the corresponding genes have been identified, making early diagnosis through DNA testing possible, with many immediate and several long-term advantages for patients and their families. However, the conventional genetic techniques, such as direct sequence analysis, are both time-consuming and expensive. Targeted exon sequencing of selected genes using the massively parallel DNA sequencing technology will potentially enable us to systematically tackle previously intractable monogenic disorders and improve molecular diagnosis. Using this technique combined with direct sequence analysis, we screened 17 unrelated Usher syndrome type 1 patients and detected probable pathogenic variants in the 16 of them (94.1% who carried at least one mutation. Seven patients had the MYO7A mutation (41.2%, which is the most common type in Japanese. Most of the mutations were detected by only the massively parallel DNA sequencing. We report here four patients, who had probable pathogenic mutations in two different Usher syndrome type 1 genes, and one case of MYO7A/PCDH15 digenic inheritance. This is the first report of Usher syndrome mutation analysis using massively parallel DNA sequencing and the frequency of Usher syndrome type 1 genes in Japanese. Mutation screening using this technique has the power to quickly identify mutations of many causative genes while maintaining cost-benefit performance. In addition, the simultaneous mutation analysis of large numbers of genes is useful for detecting mutations in different genes that are possibly disease modifiers or of digenic inheritance.
Massively parallel DNA sequencing facilitates diagnosis of patients with Usher syndrome type 1.
Yoshimura, Hidekane; Iwasaki, Satoshi; Nishio, Shin-Ya; Kumakawa, Kozo; Tono, Tetsuya; Kobayashi, Yumiko; Sato, Hiroaki; Nagai, Kyoko; Ishikawa, Kotaro; Ikezono, Tetsuo; Naito, Yasushi; Fukushima, Kunihiro; Oshikawa, Chie; Kimitsuki, Takashi; Nakanishi, Hiroshi; Usami, Shin-Ichi
2014-01-01
Usher syndrome is an autosomal recessive disorder manifesting hearing loss, retinitis pigmentosa and vestibular dysfunction, and having three clinical subtypes. Usher syndrome type 1 is the most severe subtype due to its profound hearing loss, lack of vestibular responses, and retinitis pigmentosa that appears in prepuberty. Six of the corresponding genes have been identified, making early diagnosis through DNA testing possible, with many immediate and several long-term advantages for patients and their families. However, the conventional genetic techniques, such as direct sequence analysis, are both time-consuming and expensive. Targeted exon sequencing of selected genes using the massively parallel DNA sequencing technology will potentially enable us to systematically tackle previously intractable monogenic disorders and improve molecular diagnosis. Using this technique combined with direct sequence analysis, we screened 17 unrelated Usher syndrome type 1 patients and detected probable pathogenic variants in the 16 of them (94.1%) who carried at least one mutation. Seven patients had the MYO7A mutation (41.2%), which is the most common type in Japanese. Most of the mutations were detected by only the massively parallel DNA sequencing. We report here four patients, who had probable pathogenic mutations in two different Usher syndrome type 1 genes, and one case of MYO7A/PCDH15 digenic inheritance. This is the first report of Usher syndrome mutation analysis using massively parallel DNA sequencing and the frequency of Usher syndrome type 1 genes in Japanese. Mutation screening using this technique has the power to quickly identify mutations of many causative genes while maintaining cost-benefit performance. In addition, the simultaneous mutation analysis of large numbers of genes is useful for detecting mutations in different genes that are possibly disease modifiers or of digenic inheritance.
Siretskiy, Alexey; Sundqvist, Tore; Voznesenskiy, Mikhail; Spjuth, Ola
2015-01-01
New high-throughput technologies, such as massively parallel sequencing, have transformed the life sciences into a data-intensive field. The most common e-infrastructure for analyzing this data consists of batch systems that are based on high-performance computing resources; however, the bioinformatics software that is built on this platform does not scale well in the general case. Recently, the Hadoop platform has emerged as an interesting option to address the challenges of increasingly large datasets with distributed storage, distributed processing, built-in data locality, fault tolerance, and an appealing programming methodology. In this work we introduce metrics and report on a quantitative comparison between Hadoop and a single node of conventional high-performance computing resources for the tasks of short read mapping and variant calling. We calculate efficiency as a function of data size and observe that the Hadoop platform is more efficient for biologically relevant data sizes in terms of computing hours for both split and un-split data files. We also quantify the advantages of the data locality provided by Hadoop for NGS problems, and show that a classical architecture with network-attached storage will not scale when computing resources increase in numbers. Measurements were performed using ten datasets of different sizes, up to 100 gigabases, using the pipeline implemented in Crossbow. To make a fair comparison, we implemented an improved preprocessor for Hadoop with better performance for splittable data files. For improved usability, we implemented a graphical user interface for Crossbow in a private cloud environment using the CloudGene platform. All of the code and data in this study are freely available as open source in public repositories. From our experiments we can conclude that the improved Hadoop pipeline scales better than the same pipeline on high-performance computing resources, we also conclude that Hadoop is an economically viable
Construction Morphology and the Parallel Architecture of Grammar
Booij, Geert; Audring, Jenny
2017-01-01
This article presents a systematic exposition of how the basic ideas of Construction Grammar (CxG) (Goldberg, 2006) and the Parallel Architecture (PA) of grammar (Jackendoff, 2002]) provide the framework for a proper account of morphological phenomena, in particular word formation. This framework is referred to as Construction Morphology (CxM). As…
Biferale, L.; Mantovani, F.; Pivanti, M.; Pozzati, F.; Sbragaglia, M.; Schifano, S.F.; Toschi, F.; Tripiccione, R.
2011-01-01
We develop a Lattice Boltzmann code for computational fluid-dynamics and optimize it for massively parallel systems based on multi-core processors. Our code describes 2D multi-phase compressible flows. We analyze the performance bottlenecks that we find as we gradually expose a larger fraction of
Applications of parallel computer architectures to the real-time simulation of nuclear power systems
International Nuclear Information System (INIS)
Doster, J.M.; Sills, E.D.
1988-01-01
In this paper the authors report on efforts to utilize parallel computer architectures for the thermal-hydraulic simulation of nuclear power systems and current research efforts toward the development of advanced reactor operator aids and control systems based on this new technology. Many aspects of reactor thermal-hydraulic calculations are inherently parallel, and the computationally intensive portions of these calculations can be effectively implemented on modern computers. Timing studies indicate faster-than-real-time, high-fidelity physics models can be developed when the computational algorithms are designed to take advantage of the computer's architecture. These capabilities allow for the development of novel control systems and advanced reactor operator aids. Coupled with an integral real-time data acquisition system, evolving parallel computer architectures can provide operators and control room designers improved control and protection capabilities. Current research efforts are currently under way in this area
Muscle architectural changes after massive human rotator cuff tear.
Gibbons, Michael C; Sato, Eugene J; Bachasson, Damien; Cheng, Timothy; Azimi, Hassan; Schenk, Simon; Engler, Adam J; Singh, Anshuman; Ward, Samuel R
2016-12-01
Rotator cuff (RC) tendon tears lead to negative structural and functional changes in the associated musculature. The structural features of muscle that predict function are termed "muscle architecture." Although the architectural features of "normal" rotator cuff muscles are known, they are poorly understood in the context of cuff pathology. The purpose of this study was to investigate the effects of tear and repair on RC muscle architecture. To this end thirty cadaveric shoulders were grouped into one of four categories based on tear magnitude: Intact, Full-thickness tear (FTT), Massive tear (MT), or Intervention if sutures or hardware were present, and key parameters of muscle architecture were measured. We found that muscle mass and fiber length decreased proportionally with tear size, with significant differences between all groups. Conversely, sarcomere number was reduced in both FTT and MT with no significant difference between these two groups, in large part because sarcomere length was significantly reduced in MT but not FTT. The loss of muscle mass in FTT is due, in part, to subtraction of serial sarcomeres, which may help preserve sarcomere length. This indicates that function in FTT may be impaired, but there is some remaining mechanical loading to maintain "normal" sarcomere length-tension relationships. However, the changes resulting from MT suggest more severe limitations in force-generating capacity because sarcomere length-tension relationships are no longer normal. The architectural deficits observed in MT muscles may indicate deeper deficiencies in muscle adaptability to length change, which could negatively impact RC function despite successful anatomical repair. © 2016 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 34:2089-2095, 2016. © 2016 Orthopaedic Research Society. Published by Wiley Periodicals, Inc.
Matthew Parks; Richard Cronn; Aaron Liston
2009-01-01
We reconstruct the infrageneric phylogeny of Pinus from 37 nearly-complete chloroplast genomes (average 109 kilobases each of an approximately 120 kilobase genome) generated using multiplexed massively parallel sequencing. We found that 30/33 ingroup nodes resolved wlth > 95-percent bootstrap support; this is a substantial improvement relative...
Energy Technology Data Exchange (ETDEWEB)
Azmy, Yousry
2014-06-10
We employ the Integral Transport Matrix Method (ITMM) 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' fluxes and between the cells' and boundary surfaces' fluxes. The main goals of this work are 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 parallel performance of the developed methods with increasing number of processes, P. The fastest observed parallel solution method, Parallel Gauss-Seidel (PGS), was used in a weak scaling comparison with the PARTISN transport code, which uses the source iteration (SI) scheme parallelized with the Koch-baker-Alcouffe (KBA) method. Compared to the state-of-the-art SI-KBA with diffusion synthetic acceleration (DSA), this new method- even without acceleration/preconditioning-is completitive for optically thick problems as P is increased to the tens of thousands range. For the most optically thick cells tested, PGS reduced execution time by an approximate factor of three for problems with more than 130 million computational cells on P = 32,768. Moreover, the SI-DSA execution times's trend rises generally more steeply with increasing P than the PGS trend. Furthermore, the PGS method outperforms SI for the periodic heterogeneous layers (PHL) configuration problems. The PGS method outperforms SI and SI-DSA on as few as P = 16 for PHL problems and reduces execution time by a factor of ten or more for all problems considered with more than 2 million computational cells on P = 4.096.
Sylwestrzak, Marcin; Szlag, Daniel; Marchand, Paul J.; Kumar, Ashwin S.; Lasser, Theo
2017-08-01
We present an application of massively parallel processing of quantitative flow measurements data acquired using spectral optical coherence microscopy (SOCM). The need for massive signal processing of these particular datasets has been a major hurdle for many applications based on SOCM. In view of this difficulty, we implemented and adapted quantitative total flow estimation algorithms on graphics processing units (GPU) and achieved a 150 fold reduction in processing time when compared to a former CPU implementation. As SOCM constitutes the microscopy counterpart to spectral optical coherence tomography (SOCT), the developed processing procedure can be applied to both imaging modalities. We present the developed DLL library integrated in MATLAB (with an example) and have included the source code for adaptations and future improvements. Catalogue identifier: AFBT_v1_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AFBT_v1_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: GNU GPLv3 No. of lines in distributed program, including test data, etc.: 913552 No. of bytes in distributed program, including test data, etc.: 270876249 Distribution format: tar.gz Programming language: CUDA/C, MATLAB. Computer: Intel x64 CPU, GPU supporting CUDA technology. Operating system: 64-bit Windows 7 Professional. Has the code been vectorized or parallelized?: Yes, CPU code has been vectorized in MATLAB, CUDA code has been parallelized. RAM: Dependent on users parameters, typically between several gigabytes and several tens of gigabytes Classification: 6.5, 18. Nature of problem: Speed up of data processing in optical coherence microscopy Solution method: Utilization of GPU for massively parallel data processing Additional comments: Compiled DLL library with source code and documentation, example of utilization (MATLAB script with raw data) Running time: 1,8 s for one B-scan (150 × faster in comparison to the CPU
MCBooster: a tool for MC generation for massively parallel platforms
Alves Junior, Antonio Augusto
2016-01-01
MCBooster is a header-only, C++11-compliant library for the generation of large samples of phase-space Monte Carlo events on massively parallel platforms. It was released on GitHub in the spring of 2016. The library core algorithms implement the Raubold-Lynch method; they are able to generate the full kinematics of decays with up to nine particles in the final state. The library supports the generation of sequential decays as well as the parallel evaluation of arbitrary functions over the generated events. The output of MCBooster completely accords with popular and well-tested software packages such as GENBOD (W515 from CERNLIB) and TGenPhaseSpace from the ROOT framework. MCBooster is developed on top of the Thrust library and runs on Linux systems. It deploys transparently on NVidia CUDA-enabled GPUs as well as multicore CPUs. This contribution summarizes the main features of MCBooster. A basic description of the user interface and some examples of applications are provided, along with measurements of perfor...
A highly scalable massively parallel fast marching method for the Eikonal equation
Yang, Jianming; Stern, Frederick
2017-03-01
The fast marching method is a widely used numerical method for solving the Eikonal equation arising from a variety of scientific and engineering fields. It is long deemed inherently sequential and an efficient parallel algorithm applicable to large-scale practical applications is not available in the literature. In this study, we present a highly scalable massively parallel implementation of the fast marching method using a domain decomposition approach. Central to this algorithm is a novel restarted narrow band approach that coordinates the frequency of communications and the amount of computations extra to a sequential run for achieving an unprecedented parallel performance. Within each restart, the narrow band fast marching method is executed; simple synchronous local exchanges and global reductions are adopted for communicating updated data in the overlapping regions between neighboring subdomains and getting the latest front status, respectively. The independence of front characteristics is exploited through special data structures and augmented status tags to extract the masked parallelism within the fast marching method. The efficiency, flexibility, and applicability of the parallel algorithm are demonstrated through several examples. These problems are extensively tested on six grids with up to 1 billion points using different numbers of processes ranging from 1 to 65536. Remarkable parallel speedups are achieved using tens of thousands of processes. Detailed pseudo-codes for both the sequential and parallel algorithms are provided to illustrate the simplicity of the parallel implementation and its similarity to the sequential narrow band fast marching algorithm.
Hosokawa, Masahito; Nishikawa, Yohei; Kogawa, Masato; Takeyama, Haruko
2017-07-12
Massively parallel single-cell genome sequencing is required to further understand genetic diversities in complex biological systems. Whole genome amplification (WGA) is the first step for single-cell sequencing, but its throughput and accuracy are insufficient in conventional reaction platforms. Here, we introduce single droplet multiple displacement amplification (sd-MDA), a method that enables massively parallel amplification of single cell genomes while maintaining sequence accuracy and specificity. Tens of thousands of single cells are compartmentalized in millions of picoliter droplets and then subjected to lysis and WGA by passive droplet fusion in microfluidic channels. Because single cells are isolated in compartments, their genomes are amplified to saturation without contamination. This enables the high-throughput acquisition of contamination-free and cell specific sequence reads from single cells (21,000 single-cells/h), resulting in enhancement of the sequence data quality compared to conventional methods. This method allowed WGA of both single bacterial cells and human cancer cells. The obtained sequencing coverage rivals those of conventional techniques with superior sequence quality. In addition, we also demonstrate de novo assembly of uncultured soil bacteria and obtain draft genomes from single cell sequencing. This sd-MDA is promising for flexible and scalable use in single-cell sequencing.
Block iterative restoration of astronomical images with the massively parallel processor
International Nuclear Information System (INIS)
Heap, S.R.; Lindler, D.J.
1987-01-01
A method is described for algebraic image restoration capable of treating astronomical images. For a typical 500 x 500 image, direct algebraic restoration would require the solution of a 250,000 x 250,000 linear system. The block iterative approach is used to reduce the problem to solving 4900 121 x 121 linear systems. The algorithm was implemented on the Goddard Massively Parallel Processor, which can solve a 121 x 121 system in approximately 0.06 seconds. Examples are shown of the results for various astronomical images
Massive MIMO-OFDM indoor visible light communication system downlink architecture design
Lang, Tian; Li, Zening; Chen, Gang
2014-10-01
Multiple-input multiple-output (MIMO) technique is now used in most new broadband communication system, and orthogonal frequency division multiplexing (OFDM) is also utilized within current 4th generation (4G) of mobile telecommunication technology. With MIMO and OFDM combined, visible light communication (VLC) system's diversity gain is increase, yet system capacity for dispersive channels is also enhanced. Moreover, with the emerging massive MIMO-OFDM VLC system, there are significant advantages than smaller systems' such as channel hardening, further increasing of energy efficiency (EE) and spectral efficiency (SE) based on law of large number. This paper addresses one of the major technological challenges, system architecture design, which was solved by semispherical beehive structure (SBS) receiver and so that diversity gain can be identified and applied in Massive MIMO VLC system. Simulation results shows that the proposed design clearly presents a spatial diversity over conventional VLC systems.
MASSIVELY PARALLEL LATENT SEMANTIC ANALYSES USING A GRAPHICS PROCESSING UNIT
Energy Technology Data Exchange (ETDEWEB)
Cavanagh, J.; Cui, S.
2009-01-01
Latent Semantic Analysis (LSA) aims to reduce the dimensions of large term-document datasets using Singular Value Decomposition. However, with the ever-expanding size of datasets, current implementations are not fast enough to quickly and easily compute the results on a standard PC. A graphics processing unit (GPU) can solve some highly parallel problems much faster than a traditional sequential processor or central processing unit (CPU). Thus, a deployable system using a GPU to speed up large-scale LSA processes would be a much more effective choice (in terms of cost/performance ratio) than using a PC cluster. Due to the GPU’s application-specifi c architecture, harnessing the GPU’s computational prowess for LSA is a great challenge. We presented a parallel LSA implementation on the GPU, using NVIDIA® Compute Unifi ed Device Architecture and Compute Unifi ed Basic Linear Algebra Subprograms software. The performance of this implementation is compared to traditional LSA implementation on a CPU using an optimized Basic Linear Algebra Subprograms library. After implementation, we discovered that the GPU version of the algorithm was twice as fast for large matrices (1 000x1 000 and above) that had dimensions not divisible by 16. For large matrices that did have dimensions divisible by 16, the GPU algorithm ran fi ve to six times faster than the CPU version. The large variation is due to architectural benefi ts of the GPU for matrices divisible by 16. It should be noted that the overall speeds for the CPU version did not vary from relative normal when the matrix dimensions were divisible by 16. Further research is needed in order to produce a fully implementable version of LSA. With that in mind, the research we presented shows that the GPU is a viable option for increasing the speed of LSA, in terms of cost/performance ratio.
Craciun, Stefan; Brockmeier, Austin J; George, Alan D; Lam, Herman; Príncipe, José C
2011-01-01
Methods for decoding movements from neural spike counts using adaptive filters often rely on minimizing the mean-squared error. However, for non-Gaussian distribution of errors, this approach is not optimal for performance. Therefore, rather than using probabilistic modeling, we propose an alternate non-parametric approach. In order to extract more structure from the input signal (neuronal spike counts) we propose using minimum error entropy (MEE), an information-theoretic approach that minimizes the error entropy as part of an iterative cost function. However, the disadvantage of using MEE as the cost function for adaptive filters is the increase in computational complexity. In this paper we present a comparison between the decoding performance of the analytic Wiener filter and a linear filter trained with MEE, which is then mapped to a parallel architecture in reconfigurable hardware tailored to the computational needs of the MEE filter. We observe considerable speedup from the hardware design. The adaptation of filter weights for the multiple-input, multiple-output linear filters, necessary in motor decoding, is a highly parallelizable algorithm. It can be decomposed into many independent computational blocks with a parallel architecture readily mapped to a field-programmable gate array (FPGA) and scales to large numbers of neurons. By pipelining and parallelizing independent computations in the algorithm, the proposed parallel architecture has sublinear increases in execution time with respect to both window size and filter order.
Scalable Parallel Distributed Coprocessor System for Graph Searching Problems with Massive Data
Directory of Open Access Journals (Sweden)
Wanrong Huang
2017-01-01
Full Text Available The Internet applications, such as network searching, electronic commerce, and modern medical applications, produce and process massive data. Considerable data parallelism exists in computation processes of data-intensive applications. A traversal algorithm, breadth-first search (BFS, is fundamental in many graph processing applications and metrics when a graph grows in scale. A variety of scientific programming methods have been proposed for accelerating and parallelizing BFS because of the poor temporal and spatial locality caused by inherent irregular memory access patterns. However, new parallel hardware could provide better improvement for scientific methods. To address small-world graph problems, we propose a scalable and novel field-programmable gate array-based heterogeneous multicore system for scientific programming. The core is multithread for streaming processing. And the communication network InfiniBand is adopted for scalability. We design a binary search algorithm to address mapping to unify all processor addresses. Within the limits permitted by the Graph500 test bench after 1D parallel hybrid BFS algorithm testing, our 8-core and 8-thread-per-core system achieved superior performance and efficiency compared with the prior work under the same degree of parallelism. Our system is efficient not as a special acceleration unit but as a processor platform that deals with graph searching applications.
Roever, Stefan
2012-01-01
A massively parallel, low cost molecular analysis platform will dramatically change the nature of protein, molecular and genomics research, DNA sequencing, and ultimately, molecular diagnostics. An integrated circuit (IC) with 264 sensors was fabricated using standard CMOS semiconductor processing technology. Each of these sensors is individually controlled with precision analog circuitry and is capable of single molecule measurements. Under electronic and software control, the IC was used to demonstrate the feasibility of creating and detecting lipid bilayers and biological nanopores using wild type α-hemolysin. The ability to dynamically create bilayers over each of the sensors will greatly accelerate pore development and pore mutation analysis. In addition, the noise performance of the IC was measured to be 30fA(rms). With this noise performance, single base detection of DNA was demonstrated using α-hemolysin. The data shows that a single molecule, electrical detection platform using biological nanopores can be operationalized and can ultimately scale to millions of sensors. Such a massively parallel platform will revolutionize molecular analysis and will completely change the field of molecular diagnostics in the future.
Massively Parallel Sort-Merge Joins in Main Memory Multi-Core Database Systems
Martina-Cezara Albutiu, Alfons Kemper, Thomas Neumann
2012-01-01
Two emerging hardware trends will dominate the database system technology in the near future: increasing main memory capacities of several TB per server and massively parallel multi-core processing. Many algorithmic and control techniques in current database technology were devised for disk-based systems where I/O dominated the performance. In this work we take a new look at the well-known sort-merge join which, so far, has not been in the focus of research ...
A Computational Fluid Dynamics Algorithm on a Massively Parallel Computer
Jespersen, Dennis C.; Levit, Creon
1989-01-01
The discipline of computational fluid dynamics is demanding ever-increasing computational power to deal with complex fluid flow problems. We investigate the performance of a finite-difference computational fluid dynamics algorithm on a massively parallel computer, the Connection Machine. Of special interest is an implicit time-stepping algorithm; to obtain maximum performance from the Connection Machine, it is necessary to use a nonstandard algorithm to solve the linear systems that arise in the implicit algorithm. We find that the Connection Machine ran achieve very high computation rates on both explicit and implicit algorithms. The performance of the Connection Machine puts it in the same class as today's most powerful conventional supercomputers.
Directory of Open Access Journals (Sweden)
Matthew O'keefe
1995-01-01
Full Text Available Massively parallel processors (MPPs hold the promise of extremely high performance that, if realized, could be used to study problems of unprecedented size and complexity. One of the primary stumbling blocks to this promise has been the lack of tools to translate application codes to MPP form. In this article we show how applications codes written in a subset of Fortran 77, called Fortran-P, can be translated to achieve good performance on several massively parallel machines. This subset can express codes that are self-similar, where the algorithm applied to the global data domain is also applied to each subdomain. We have found many codes that match the Fortran-P programming style and have converted them using our tools. We believe a self-similar coding style will accomplish what a vectorizable style has accomplished for vector machines by allowing the construction of robust, user-friendly, automatic translation systems that increase programmer productivity and generate fast, efficient code for MPPs.
Heterogeneous computing architecture for fast detection of SNP-SNP interactions.
Sluga, Davor; Curk, Tomaz; Zupan, Blaz; Lotric, Uros
2014-06-25
The extent of data in a typical genome-wide association study (GWAS) poses considerable computational challenges to software tools for gene-gene interaction discovery. Exhaustive evaluation of all interactions among hundreds of thousands to millions of single nucleotide polymorphisms (SNPs) may require weeks or even months of computation. Massively parallel hardware within a modern Graphic Processing Unit (GPU) and Many Integrated Core (MIC) coprocessors can shorten the run time considerably. While the utility of GPU-based implementations in bioinformatics has been well studied, MIC architecture has been introduced only recently and may provide a number of comparative advantages that have yet to be explored and tested. We have developed a heterogeneous, GPU and Intel MIC-accelerated software module for SNP-SNP interaction discovery to replace the previously single-threaded computational core in the interactive web-based data exploration program SNPsyn. We report on differences between these two modern massively parallel architectures and their software environments. Their utility resulted in an order of magnitude shorter execution times when compared to the single-threaded CPU implementation. GPU implementation on a single Nvidia Tesla K20 runs twice as fast as that for the MIC architecture-based Xeon Phi P5110 coprocessor, but also requires considerably more programming effort. General purpose GPUs are a mature platform with large amounts of computing power capable of tackling inherently parallel problems, but can prove demanding for the programmer. On the other hand the new MIC architecture, albeit lacking in performance reduces the programming effort and makes it up with a more general architecture suitable for a wider range of problems.
Directory of Open Access Journals (Sweden)
Rovini Massimo
2009-01-01
Full Text Available This is a reply to the comments by Gunnam et al. "Comments on 'Techniques and architectures for hazard-free semi-parallel decoding of LDPC codes'", EURASIP Journal on Embedded Systems, vol. 2009, Article ID 704174 on our recent work "Techniques and architectures for hazard-free semi-parallel decoding of LDPC codes", EURASIP Journal on Embedded Systems, vol. 2009, Article ID 723465.
Massive Parallelism of Monte-Carlo Simulation on Low-End Hardware using Graphic Processing Units
International Nuclear Information System (INIS)
Mburu, Joe Mwangi; Hah, Chang Joo Hah
2014-01-01
Within the past decade, research has been done on utilizing GPU massive parallelization in core simulation with impressive results but unfortunately, not much commercial application has been done in the nuclear field especially in reactor core simulation. The purpose of this paper is to give an introductory concept on the topic and illustrate the potential of exploiting the massive parallel nature of GPU computing on a simple monte-carlo simulation with very minimal hardware specifications. To do a comparative analysis, a simple two dimension monte-carlo simulation is implemented for both the CPU and GPU in order to evaluate performance gain based on the computing devices. The heterogeneous platform utilized in this analysis is done on a slow notebook with only 1GHz processor. The end results are quite surprising whereby high speedups obtained are almost a factor of 10. In this work, we have utilized heterogeneous computing in a GPU-based approach in applying potential high arithmetic intensive calculation. By applying a complex monte-carlo simulation on GPU platform, we have speed up the computational process by almost a factor of 10 based on one million neutrons. This shows how easy, cheap and efficient it is in using GPU in accelerating scientific computing and the results should encourage in exploring further this avenue especially in nuclear reactor physics simulation where deterministic and stochastic calculations are quite favourable in parallelization
Massive Parallelism of Monte-Carlo Simulation on Low-End Hardware using Graphic Processing Units
Energy Technology Data Exchange (ETDEWEB)
Mburu, Joe Mwangi; Hah, Chang Joo Hah [KEPCO International Nuclear Graduate School, Ulsan (Korea, Republic of)
2014-05-15
Within the past decade, research has been done on utilizing GPU massive parallelization in core simulation with impressive results but unfortunately, not much commercial application has been done in the nuclear field especially in reactor core simulation. The purpose of this paper is to give an introductory concept on the topic and illustrate the potential of exploiting the massive parallel nature of GPU computing on a simple monte-carlo simulation with very minimal hardware specifications. To do a comparative analysis, a simple two dimension monte-carlo simulation is implemented for both the CPU and GPU in order to evaluate performance gain based on the computing devices. The heterogeneous platform utilized in this analysis is done on a slow notebook with only 1GHz processor. The end results are quite surprising whereby high speedups obtained are almost a factor of 10. In this work, we have utilized heterogeneous computing in a GPU-based approach in applying potential high arithmetic intensive calculation. By applying a complex monte-carlo simulation on GPU platform, we have speed up the computational process by almost a factor of 10 based on one million neutrons. This shows how easy, cheap and efficient it is in using GPU in accelerating scientific computing and the results should encourage in exploring further this avenue especially in nuclear reactor physics simulation where deterministic and stochastic calculations are quite favourable in parallelization.
Massively Parallel Dimension Independent Adaptive Metropolis
Chen, Yuxin
2015-05-14
This work considers black-box Bayesian inference over high-dimensional parameter spaces. The well-known and widely respected adaptive Metropolis (AM) algorithm is extended herein to asymptotically scale uniformly with respect to the underlying parameter dimension, by respecting the variance, for Gaussian targets. The result- ing algorithm, referred to as the dimension-independent adaptive Metropolis (DIAM) algorithm, also shows improved performance with respect to adaptive Metropolis on non-Gaussian targets. This algorithm is further improved, and the possibility of probing high-dimensional targets is enabled, via GPU-accelerated numerical libraries and periodically synchronized concurrent chains (justified a posteriori). Asymptoti- cally in dimension, this massively parallel dimension-independent adaptive Metropolis (MPDIAM) GPU implementation exhibits a factor of four improvement versus the CPU-based Intel MKL version alone, which is itself already a factor of three improve- ment versus the serial version. The scaling to multiple CPUs and GPUs exhibits a form of strong scaling in terms of the time necessary to reach a certain convergence criterion, through a combination of longer time per sample batch (weak scaling) and yet fewer necessary samples to convergence. This is illustrated by e ciently sampling from several Gaussian and non-Gaussian targets for dimension d 1000.
Yu, Leiming; Nina-Paravecino, Fanny; Kaeli, David; Fang, Qianqian
2018-01-01
We present a highly scalable Monte Carlo (MC) three-dimensional photon transport simulation platform designed for heterogeneous computing systems. Through the development of a massively parallel MC algorithm using the Open Computing Language framework, this research extends our existing graphics processing unit (GPU)-accelerated MC technique to a highly scalable vendor-independent heterogeneous computing environment, achieving significantly improved performance and software portability. A number of parallel computing techniques are investigated to achieve portable performance over a wide range of computing hardware. Furthermore, multiple thread-level and device-level load-balancing strategies are developed to obtain efficient simulations using multiple central processing units and GPUs. (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).
Park, Seong-Wook; Park, Junyoung; Bong, Kyeongryeol; Shin, Dongjoo; Lee, Jinmook; Choi, Sungpill; Yoo, Hoi-Jun
2015-12-01
Deep Learning algorithm is widely used for various pattern recognition applications such as text recognition, object recognition and action recognition because of its best-in-class recognition accuracy compared to hand-crafted algorithm and shallow learning based algorithms. Long learning time caused by its complex structure, however, limits its usage only in high-cost servers or many-core GPU platforms so far. On the other hand, the demand on customized pattern recognition within personal devices will grow gradually as more deep learning applications will be developed. This paper presents a SoC implementation to enable deep learning applications to run with low cost platforms such as mobile or portable devices. Different from conventional works which have adopted massively-parallel architecture, this work adopts task-flexible architecture and exploits multiple parallelism to cover complex functions of convolutional deep belief network which is one of popular deep learning/inference algorithms. In this paper, we implement the most energy-efficient deep learning and inference processor for wearable system. The implemented 2.5 mm × 4.0 mm deep learning/inference processor is fabricated using 65 nm 8-metal CMOS technology for a battery-powered platform with real-time deep inference and deep learning operation. It consumes 185 mW average power, and 213.1 mW peak power at 200 MHz operating frequency and 1.2 V supply voltage. It achieves 411.3 GOPS peak performance and 1.93 TOPS/W energy efficiency, which is 2.07× higher than the state-of-the-art.
A novel parallel architecture for local histogram equalization
Ohannessian, Mesrob I.; Choueiter, Ghinwa F.; Diab, Hassan
2005-07-01
Local histogram equalization is an image enhancement algorithm that has found wide application in the pre-processing stage of areas such as computer vision, pattern recognition and medical imaging. The computationally intensive nature of the procedure, however, is a main limitation when real time interactive applications are in question. This work explores the possibility of performing parallel local histogram equalization, using an array of special purpose elementary processors, through an HDL implementation that targets FPGA or ASIC platforms. A novel parallelization scheme is presented and the corresponding architecture is derived. The algorithm is reduced to pixel-level operations. Processing elements are assigned image blocks, to maintain a reasonable performance-cost ratio. To further simplify both processor and memory organizations, a bit-serial access scheme is used. A brief performance assessment is provided to illustrate and quantify the merit of the approach.
Analysis of clinical complication data for radiation hepatitis using a parallel architecture model
International Nuclear Information System (INIS)
Jackson, A.; Haken, R.K. ten; Robertson, J.M.; Kessler, M.L.; Kutcher, G.J.; Lawrence, T.S.
1995-01-01
Purpose: The detailed knowledge of dose volume distributions available from the three-dimensional (3D) conformal radiation treatment of tumors in the liver (reported elsewhere) offers new opportunities to quantify the effect of volume on the probability of producing radiation hepatitis. We aim to test a new parallel architecture model of normal tissue complication probability (NTCP) with these data. Methods and Materials: Complication data and dose volume histograms from a total of 93 patients with normal liver function, treated on a prospective protocol with 3D conformal radiation therapy and intraarterial hepatic fluorodeoxyuridine, were analyzed with a new parallel architecture model. Patient treatment fell into six categories differing in doses delivered and volumes irradiated. By modeling the radiosensitivity of liver subunits, we are able to use dose volume histograms to calculate the fraction of the liver damaged in each patient. A complication results if this fraction exceeds the patient's functional reserve. To determine the patient distribution of functional reserves and the subunit radiosensitivity, the maximum likelihood method was used to fit the observed complication data. Results: The parallel model fit the complication data well, although uncertainties on the functional reserve distribution and subunit radiosensitivy are highly correlated. Conclusion: The observed radiation hepatitis complications show a threshold effect that can be described well with a parallel architecture model. However, additional independent studies are required to better determine the parameters defining the functional reserve distribution and subunit radiosensitivity
Tolerating correlated failures in Massively Parallel Stream Processing Engines
DEFF Research Database (Denmark)
Su, L.; Zhou, Y.
2016-01-01
Fault-tolerance techniques for stream processing engines can be categorized into passive and active approaches. A typical passive approach periodically checkpoints a processing task's runtime states and can recover a failed task by restoring its runtime state using its latest checkpoint. On the o......Fault-tolerance techniques for stream processing engines can be categorized into passive and active approaches. A typical passive approach periodically checkpoints a processing task's runtime states and can recover a failed task by restoring its runtime state using its latest checkpoint....... On the other hand, an active approach usually employs backup nodes to run replicated tasks. Upon failure, the active replica can take over the processing of the failed task with minimal latency. However, both approaches have their own inadequacies in Massively Parallel Stream Processing Engines (MPSPE...
An FPGA-Based Quantum Computing Emulation Framework Based on Serial-Parallel Architecture
Directory of Open Access Journals (Sweden)
Y. H. Lee
2016-01-01
Full Text Available Hardware emulation of quantum systems can mimic more efficiently the parallel behaviour of quantum computations, thus allowing higher processing speed-up than software simulations. In this paper, an efficient hardware emulation method that employs a serial-parallel hardware architecture targeted for field programmable gate array (FPGA is proposed. Quantum Fourier transform and Grover’s search are chosen as case studies in this work since they are the core of many useful quantum algorithms. Experimental work shows that, with the proposed emulation architecture, a linear reduction in resource utilization is attained against the pipeline implementations proposed in prior works. The proposed work contributes to the formulation of a proof-of-concept baseline FPGA emulation framework with optimization on datapath designs that can be extended to emulate practical large-scale quantum circuits.
cellGPU: Massively parallel simulations of dynamic vertex models
Sussman, Daniel M.
2017-10-01
Vertex models represent confluent tissue by polygonal or polyhedral tilings of space, with the individual cells interacting via force laws that depend on both the geometry of the cells and the topology of the tessellation. This dependence on the connectivity of the cellular network introduces several complications to performing molecular-dynamics-like simulations of vertex models, and in particular makes parallelizing the simulations difficult. cellGPU addresses this difficulty and lays the foundation for massively parallelized, GPU-based simulations of these models. This article discusses its implementation for a pair of two-dimensional models, and compares the typical performance that can be expected between running cellGPU entirely on the CPU versus its performance when running on a range of commercial and server-grade graphics cards. By implementing the calculation of topological changes and forces on cells in a highly parallelizable fashion, cellGPU enables researchers to simulate time- and length-scales previously inaccessible via existing single-threaded CPU implementations. Program Files doi:http://dx.doi.org/10.17632/6j2cj29t3r.1 Licensing provisions: MIT Programming language: CUDA/C++ Nature of problem: Simulations of off-lattice "vertex models" of cells, in which the interaction forces depend on both the geometry and the topology of the cellular aggregate. Solution method: Highly parallelized GPU-accelerated dynamical simulations in which the force calculations and the topological features can be handled on either the CPU or GPU. Additional comments: The code is hosted at https://gitlab.com/dmsussman/cellGPU, with documentation additionally maintained at http://dmsussman.gitlab.io/cellGPUdocumentation
Real-time objects development: Study and proposal for a parallel scheduling architecture
International Nuclear Information System (INIS)
Rioux, Laurent
1997-01-01
This thesis contributes to the programming and the execution control of real-time object oriented applications. Using real-time objects is very interesting for programming real- time applications, because this model can introduce the concurrence with the encapsulation properties, with modularity and reusability by taking into account the real-time constraints of the application. One essential quality of this approach is that it can directly specify the parallelism and the real-time constraints at the model level of the application. An annotation system of C++ has been defined to describe the real-time specifications in the model (or in the source code) of the application. It will supply to the execution support the different information it needs for the control. In this approach of multitasking, the control is distributed and encapsulated inside each real time object. Three complementary levels of control have been defined: the state level (defining the capability of an object to treat an operation), the concurrence level (assuring the coherence between the object attributes) and a scheduling control (allocating the processors resources to the object by taking real-time constraints into account). The proposed control architecture, named OROS, manages the attribute access of each object in an individual way, then it can parallel treatments which do not access at the same data. This architecture makes a dynamic control of an application that can take benefit from the parallelism of the new machines both for the execution parallelism and the control itself. This architecture uses only the simplest primitives of the industrial real-time operating systems which ensures its feasibility and portability. (author) [fr
An ODMG-compatible testbed architecture for scalable management and analysis of physics data
International Nuclear Information System (INIS)
Malon, D.M.; May, E.N.
1997-01-01
This paper describes a testbed architecture for the investigation and development of scalable approaches to the management and analysis of massive amounts of high energy physics data. The architecture has two components: an interface layer that is compliant with a substantial subset of the ODMG-93 Version 1.2 specification, and a lightweight object persistence manager that provides flexible storage and retrieval services on a variety of single- and multi-level storage architectures, and on a range of parallel and distributed computing platforms
ASSET: Analysis of Sequences of Synchronous Events in Massively Parallel Spike Trains
Canova, Carlos; Denker, Michael; Gerstein, George; Helias, Moritz
2016-01-01
With the ability to observe the activity from large numbers of neurons simultaneously using modern recording technologies, the chance to identify sub-networks involved in coordinated processing increases. Sequences of synchronous spike events (SSEs) constitute one type of such coordinated spiking that propagates activity in a temporally precise manner. The synfire chain was proposed as one potential model for such network processing. Previous work introduced a method for visualization of SSEs in massively parallel spike trains, based on an intersection matrix that contains in each entry the degree of overlap of active neurons in two corresponding time bins. Repeated SSEs are reflected in the matrix as diagonal structures of high overlap values. The method as such, however, leaves the task of identifying these diagonal structures to visual inspection rather than to a quantitative analysis. Here we present ASSET (Analysis of Sequences of Synchronous EvenTs), an improved, fully automated method which determines diagonal structures in the intersection matrix by a robust mathematical procedure. The method consists of a sequence of steps that i) assess which entries in the matrix potentially belong to a diagonal structure, ii) cluster these entries into individual diagonal structures and iii) determine the neurons composing the associated SSEs. We employ parallel point processes generated by stochastic simulations as test data to demonstrate the performance of the method under a wide range of realistic scenarios, including different types of non-stationarity of the spiking activity and different correlation structures. Finally, the ability of the method to discover SSEs is demonstrated on complex data from large network simulations with embedded synfire chains. Thus, ASSET represents an effective and efficient tool to analyze massively parallel spike data for temporal sequences of synchronous activity. PMID:27420734
Parallel processing algorithms for hydrocodes on a computer with MIMD architecture (DENELCOR's HEP)
International Nuclear Information System (INIS)
Hicks, D.L.
1983-11-01
In real time simulation/prediction of complex systems such as water-cooled nuclear reactors, if reactor operators had fast simulator/predictors to check the consequences of their operations before implementing them, events such as the incident at Three Mile Island might be avoided. However, existing simulator/predictors such as RELAP run slower than real time on serial computers. It appears that the only way to overcome the barrier to higher computing rates is to use computers with architectures that allow concurrent computations or parallel processing. The computer architecture with the greatest degree of parallelism is labeled Multiple Instruction Stream, Multiple Data Stream (MIMD). An example of a machine of this type is the HEP computer by DENELCOR. It appears that hydrocodes are very well suited for parallelization on the HEP. It is a straightforward exercise to parallelize explicit, one-dimensional Lagrangean hydrocodes in a zone-by-zone parallelization. Similarly, implicit schemes can be parallelized in a zone-by-zone fashion via an a priori, symbolic inversion of the tridiagonal matrix that arises in an implicit scheme. These techniques are extended to Eulerian hydrocodes by using Harlow's rezone technique. The extension from single-phase Eulerian to two-phase Eulerian is straightforward. This step-by-step extension leads to hydrocodes with zone-by-zone parallelization that are capable of two-phase flow simulation. Extensions to two and three spatial dimensions can be achieved by operator splitting. It appears that a zone-by-zone parallelization is the best way to utilize the capabilities of an MIMD machine. 40 references
Ltaief, Hatem; Luszczek, Piotr R.; Dongarra, Jack
2012-01-01
The objective of this paper is to enhance the parallelism of the tile bidiagonal transformation using tree reduction on multicore architectures. First introduced by Ltaief et. al [LAPACK Working Note #247, 2011], the bidiagonal transformation using
A Massively Parallel Solver for the Mechanical Harmonic Analysis of Accelerator Cavities
International Nuclear Information System (INIS)
2015-01-01
ACE3P is a 3D massively parallel simulation suite that developed at SLAC National Accelerator Laboratory that can perform coupled electromagnetic, thermal and mechanical study. Effectively utilizing supercomputer resources, ACE3P has become a key simulation tool for particle accelerator R and D. A new frequency domain solver to perform mechanical harmonic response analysis of accelerator components is developed within the existing parallel framework. This solver is designed to determine the frequency response of the mechanical system to external harmonic excitations for time-efficient accurate analysis of the large-scale problems. Coupled with the ACE3P electromagnetic modules, this capability complements a set of multi-physics tools for a comprehensive study of microphonics in superconducting accelerating cavities in order to understand the RF response and feedback requirements for the operational reliability of a particle accelerator. (auth)
Directory of Open Access Journals (Sweden)
Ivone U. S. Leong
2014-06-01
Full Text Available Sudden cardiac death in people between the ages of 1–40 years is a devastating event and is frequently caused by several heritable cardiac disorders. These disorders include cardiac ion channelopathies, such as long QT syndrome, catecholaminergic polymorphic ventricular tachycardia and Brugada syndrome and cardiomyopathies, such as hypertrophic cardiomyopathy and arrhythmogenic right ventricular cardiomyopathy. Through careful molecular genetic evaluation of DNA from sudden death victims, the causative gene mutation can be uncovered, and the rest of the family can be screened and preventative measures implemented in at-risk individuals. The current screening approach in most diagnostic laboratories uses Sanger-based sequencing; however, this method is time consuming and labour intensive. The development of massively parallel sequencing has made it possible to produce millions of sequence reads simultaneously and is potentially an ideal approach to screen for mutations in genes that are associated with sudden cardiac death. This approach offers mutation screening at reduced cost and turnaround time. Here, we will review the current commercially available enrichment kits, massively parallel sequencing (MPS platforms, downstream data analysis and its application to sudden cardiac death in a diagnostic environment.
From Massively Parallel Algorithms and Fluctuating Time Horizons to Nonequilibrium Surface Growth
International Nuclear Information System (INIS)
Korniss, G.; Toroczkai, Z.; Novotny, M. A.; Rikvold, P. A.
2000-01-01
We study the asymptotic scaling properties of a massively parallel algorithm for discrete-event simulations where the discrete events are Poisson arrivals. The evolution of the simulated time horizon is analogous to a nonequilibrium surface. Monte Carlo simulations and a coarse-grained approximation indicate that the macroscopic landscape in the steady state is governed by the Edwards-Wilkinson Hamiltonian. Since the efficiency of the algorithm corresponds to the density of local minima in the associated surface, our results imply that the algorithm is asymptotically scalable. (c) 2000 The American Physical Society
Passive and partially active fault tolerance for massively parallel stream processing engines
DEFF Research Database (Denmark)
Su, Li; Zhou, Yongluan
2018-01-01
. On the other hand, an active approach usually employs backup nodes to run replicated tasks. Upon failure, the active replica can take over the processing of the failed task with minimal latency. However, both approaches have their own inadequacies in Massively Parallel Stream Processing Engines (MPSPE...... also propose effective and efficient algorithms to optimize a partially active replication plan to maximize the quality of tentative outputs. We implemented PPA on top of Storm, an open-source MPSPE and conducted extensive experiments using both real and synthetic datasets to verify the effectiveness...
International Nuclear Information System (INIS)
Kimura, Toshiya.
1997-03-01
A two-dimensional explicit Euler solver has been implemented for five MIMD parallel computers of different machine architectures in Center for Promotion of Computational Science and Engineering of Japan Atomic Energy Research Institute. These parallel computers are Fujitsu VPP300, NEC SX-4, CRAY T94, IBM SP2, and Hitachi SR2201. The code was parallelized by several parallelization methods, and a typical compressible flow problem has been calculated for different grid sizes changing the number of processors. Their effective performances for parallel calculations, such as calculation speed, speed-up ratio and parallel efficiency, have been investigated and evaluated. The communication time among processors has been also measured and evaluated. As a result, the differences on the performance and the characteristics between vector-parallel and scalar-parallel computers can be pointed, and it will present the basic data for efficient use of parallel computers and for large scale CFD simulations on parallel computers. (author)
Massively Parallel Interrogation of Aptamer Sequence, Structure and Function
Energy Technology Data Exchange (ETDEWEB)
Fischer, N O; Tok, J B; Tarasow, T M
2008-02-08
Optimization of high affinity reagents is a significant bottleneck in medicine and the life sciences. The ability to synthetically create thousands of permutations of a lead high-affinity reagent and survey the properties of individual permutations in parallel could potentially relieve this bottleneck. Aptamers are single stranded oligonucleotides affinity reagents isolated by in vitro selection processes and as a class have been shown to bind a wide variety of target molecules. Methodology/Principal Findings. High density DNA microarray technology was used to synthesize, in situ, arrays of approximately 3,900 aptamer sequence permutations in triplicate. These sequences were interrogated on-chip for their ability to bind the fluorescently-labeled cognate target, immunoglobulin E, resulting in the parallel execution of thousands of experiments. Fluorescence intensity at each array feature was well resolved and shown to be a function of the sequence present. The data demonstrated high intra- and interchip correlation between the same features as well as among the sequence triplicates within a single array. Consistent with aptamer mediated IgE binding, fluorescence intensity correlated strongly with specific aptamer sequences and the concentration of IgE applied to the array. The massively parallel sequence-function analyses provided by this approach confirmed the importance of a consensus sequence found in all 21 of the original IgE aptamer sequences and support a common stem:loop structure as being the secondary structure underlying IgE binding. The microarray application, data and results presented illustrate an efficient, high information content approach to optimizing aptamer function. It also provides a foundation from which to better understand and manipulate this important class of high affinity biomolecules.
Massively parallel interrogation of aptamer sequence, structure and function.
Directory of Open Access Journals (Sweden)
Nicholas O Fischer
Full Text Available BACKGROUND: Optimization of high affinity reagents is a significant bottleneck in medicine and the life sciences. The ability to synthetically create thousands of permutations of a lead high-affinity reagent and survey the properties of individual permutations in parallel could potentially relieve this bottleneck. Aptamers are single stranded oligonucleotides affinity reagents isolated by in vitro selection processes and as a class have been shown to bind a wide variety of target molecules. METHODOLOGY/PRINCIPAL FINDINGS: High density DNA microarray technology was used to synthesize, in situ, arrays of approximately 3,900 aptamer sequence permutations in triplicate. These sequences were interrogated on-chip for their ability to bind the fluorescently-labeled cognate target, immunoglobulin E, resulting in the parallel execution of thousands of experiments. Fluorescence intensity at each array feature was well resolved and shown to be a function of the sequence present. The data demonstrated high intra- and inter-chip correlation between the same features as well as among the sequence triplicates within a single array. Consistent with aptamer mediated IgE binding, fluorescence intensity correlated strongly with specific aptamer sequences and the concentration of IgE applied to the array. CONCLUSION AND SIGNIFICANCE: The massively parallel sequence-function analyses provided by this approach confirmed the importance of a consensus sequence found in all 21 of the original IgE aptamer sequences and support a common stem:loop structure as being the secondary structure underlying IgE binding. The microarray application, data and results presented illustrate an efficient, high information content approach to optimizing aptamer function. It also provides a foundation from which to better understand and manipulate this important class of high affinity biomolecules.
OKeefe, Matthew (Editor); Kerr, Christopher L. (Editor)
1998-01-01
This report contains the abstracts and technical papers from the Second International Workshop on Software Engineering and Code Design in Parallel Meteorological and Oceanographic Applications, held June 15-18, 1998, in Scottsdale, Arizona. The purpose of the workshop is to bring together software developers in meteorology and oceanography to discuss software engineering and code design issues for parallel architectures, including Massively Parallel Processors (MPP's), Parallel Vector Processors (PVP's), Symmetric Multi-Processors (SMP's), Distributed Shared Memory (DSM) multi-processors, and clusters. Issues to be discussed include: (1) code architectures for current parallel models, including basic data structures, storage allocation, variable naming conventions, coding rules and styles, i/o and pre/post-processing of data; (2) designing modular code; (3) load balancing and domain decomposition; (4) techniques that exploit parallelism efficiently yet hide the machine-related details from the programmer; (5) tools for making the programmer more productive; and (6) the proliferation of programming models (F--, OpenMP, MPI, and HPF).
Parallel Evolutionary Optimization for Neuromorphic Network Training
Energy Technology Data Exchange (ETDEWEB)
Schuman, Catherine D [ORNL; Disney, Adam [University of Tennessee (UT); Singh, Susheela [North Carolina State University (NCSU), Raleigh; Bruer, Grant [University of Tennessee (UT); Mitchell, John Parker [University of Tennessee (UT); Klibisz, Aleksander [University of Tennessee (UT); Plank, James [University of Tennessee (UT)
2016-01-01
One of the key impediments to the success of current neuromorphic computing architectures is the issue of how best to program them. Evolutionary optimization (EO) is one promising programming technique; in particular, its wide applicability makes it especially attractive for neuromorphic architectures, which can have many different characteristics. In this paper, we explore different facets of EO on a spiking neuromorphic computing model called DANNA. We focus on the performance of EO in the design of our DANNA simulator, and on how to structure EO on both multicore and massively parallel computing systems. We evaluate how our parallel methods impact the performance of EO on Titan, the U.S.'s largest open science supercomputer, and BOB, a Beowulf-style cluster of Raspberry Pi's. We also focus on how to improve the EO by evaluating commonality in higher performing neural networks, and present the result of a study that evaluates the EO performed by Titan.
An S_{N} Algorithm for Modern Architectures
Energy Technology Data Exchange (ETDEWEB)
Baker, Randal Scott [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2016-08-29
LANL discrete ordinates transport packages are required to perform large, computationally intensive time-dependent calculations on massively parallel architectures, where even a single such calculation may need many months to complete. While KBA methods scale out well to very large numbers of compute nodes, we are limited by practical constraints on the number of such nodes we can actually apply to any given calculation. Instead, we describe a modified KBA algorithm that allows realization of the reductions in solution time offered by both the current, and future, architectural changes within a compute node.
Multiscale Architectures and Parallel Algorithms for Video Object Tracking
2011-10-01
larger number of cores using the IBM QS22 Blade for handling higher video processing workloads (but at higher cost per core), low power consumption and...Cell/B.E. Blade processors which have a lot more main memory but also higher power consumption . More detailed performance figures for HD and SD video...Parallelism in Algorithms and Architectures, pages 289–298, 2007. [3] S. Ali and M. Shah. COCOA - Tracking in aerial imagery. In Daniel J. Henry
A parallel VLSI architecture for a digital filter of arbitrary length using Fermat number transforms
Truong, T. K.; Reed, I. S.; Yeh, C. S.; Shao, H. M.
1982-01-01
A parallel architecture for computation of the linear convolution of two sequences of arbitrary lengths using the Fermat number transform (FNT) is described. In particular a pipeline structure is designed to compute a 128-point FNT. In this FNT, only additions and bit rotations are required. A standard barrel shifter circuit is modified so that it performs the required bit rotation operation. The overlap-save method is generalized for the FNT to compute a linear convolution of arbitrary length. A parallel architecture is developed to realize this type of overlap-save method using one FNT and several inverse FNTs of 128 points. The generalized overlap save method alleviates the usual dynamic range limitation in FNTs of long transform lengths. Its architecture is regular, simple, and expandable, and therefore naturally suitable for VLSI implementation.
Parallel algorithms for interactive manipulation of digital terrain models
Davis, E. W.; Mcallister, D. F.; Nagaraj, V.
1988-01-01
Interactive three-dimensional graphics applications, such as terrain data representation and manipulation, require extensive arithmetic processing. Massively parallel machines are attractive for this application since they offer high computational rates, and grid connected architectures provide a natural mapping for grid based terrain models. Presented here are algorithms for data movement on the massive parallel processor (MPP) in support of pan and zoom functions over large data grids. It is an extension of earlier work that demonstrated real-time performance of graphics functions on grids that were equal in size to the physical dimensions of the MPP. When the dimensions of a data grid exceed the processing array size, data is packed in the array memory. Windows of the total data grid are interactively selected for processing. Movement of packed data is needed to distribute items across the array for efficient parallel processing. Execution time for data movement was found to exceed that for arithmetic aspects of graphics functions. Performance figures are given for routines written in MPP Pascal.
'Iconic' tracking algorithms for high energy physics using the TRAX-I massively parallel processor
International Nuclear Information System (INIS)
Vesztergombi, G.
1989-01-01
TRAX-I, a cost-effective parallel microcomputer, applying associative string processor (ASP) architecture with 16 K parallel processing elements, is being built by Aspex Microsystems Ltd. (UK). When applied to the tracking problem of very complex events with several hundred tracks, the large number of processors allows one to dedicate one or more processors to each wire (in MWPC), each pixel (in digitized images from streamer chambers or other visual detectors), or each pad (in TPC) to perform very efficient pattern recognition. Some linear tracking algorithms based on this ''ionic'' representation are presented. (orig.)
'Iconic' tracking algorithms for high energy physics using the TRAX-I massively parallel processor
International Nuclear Information System (INIS)
Vestergombi, G.
1989-11-01
TRAX-I, a cost-effective parallel microcomputer, applying Associative String Processor (ASP) architecture with 16 K parallel processing elements, is being built by Aspex Microsystems Ltd. (UK). When applied to the tracking problem of very complex events with several hundred tracks, the large number of processors allows one to dedicate one or more processors to each wire (in MWPC), each pixel (in digitized images from streamer chambers or other visual detectors), or each pad (in TPC) to perform very efficient pattern recognition. Some linear tracking algorithms based on this 'iconic' representation are presented. (orig.)
Ultrascalable petaflop parallel supercomputer
Blumrich, Matthias A [Ridgefield, CT; Chen, Dong [Croton On Hudson, NY; Chiu, George [Cross River, NY; Cipolla, Thomas M [Katonah, NY; Coteus, Paul W [Yorktown Heights, NY; Gara, Alan G [Mount Kisco, NY; Giampapa, Mark E [Irvington, NY; Hall, Shawn [Pleasantville, NY; Haring, Rudolf A [Cortlandt Manor, NY; Heidelberger, Philip [Cortlandt Manor, NY; Kopcsay, Gerard V [Yorktown Heights, NY; Ohmacht, Martin [Yorktown Heights, NY; Salapura, Valentina [Chappaqua, NY; Sugavanam, Krishnan [Mahopac, NY; Takken, Todd [Brewster, NY
2010-07-20
A massively parallel supercomputer of petaOPS-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC) having up to four processing elements. The ASIC nodes are interconnected by multiple independent networks that optimally maximize the throughput of packet communications between nodes with minimal latency. The multiple networks may include three high-speed networks for parallel algorithm message passing including a Torus, collective network, and a Global Asynchronous network that provides global barrier and notification functions. These multiple independent networks may be collaboratively or independently utilized according to the needs or phases of an algorithm for optimizing algorithm processing performance. The use of a DMA engine is provided to facilitate message passing among the nodes without the expenditure of processing resources at the node.
Memristor-based nanoelectronic computing circuits and architectures
Vourkas, Ioannis
2016-01-01
This book considers the design and development of nanoelectronic computing circuits, systems and architectures focusing particularly on memristors, which represent one of today’s latest technology breakthroughs in nanoelectronics. The book studies, explores, and addresses the related challenges and proposes solutions for the smooth transition from conventional circuit technologies to emerging computing memristive nanotechnologies. Its content spans from fundamental device modeling to emerging storage system architectures and novel circuit design methodologies, targeting advanced non-conventional analog/digital massively parallel computational structures. Several new results on memristor modeling, memristive interconnections, logic circuit design, memory circuit architectures, computer arithmetic systems, simulation software tools, and applications of memristors in computing are presented. High-density memristive data storage combined with memristive circuit-design paradigms and computational tools applied t...
DGDFT: A massively parallel method for large scale density functional theory calculations.
Hu, Wei; Lin, Lin; Yang, Chao
2015-09-28
We describe a massively parallel implementation of the recently developed discontinuous Galerkin density functional theory (DGDFT) method, for efficient large-scale Kohn-Sham DFT based electronic structure calculations. The DGDFT method uses adaptive local basis (ALB) functions generated on-the-fly during the self-consistent field iteration to represent the solution to the Kohn-Sham equations. The use of the ALB set provides a systematic way to improve the accuracy of the approximation. By using the pole expansion and selected inversion technique to compute electron density, energy, and atomic forces, we can make the computational complexity of DGDFT scale at most quadratically with respect to the number of electrons for both insulating and metallic systems. We show that for the two-dimensional (2D) phosphorene systems studied here, using 37 basis functions per atom allows us to reach an accuracy level of 1.3 × 10(-4) Hartree/atom in terms of the error of energy and 6.2 × 10(-4) Hartree/bohr in terms of the error of atomic force, respectively. DGDFT can achieve 80% parallel efficiency on 128,000 high performance computing cores when it is used to study the electronic structure of 2D phosphorene systems with 3500-14 000 atoms. This high parallel efficiency results from a two-level parallelization scheme that we will describe in detail.
DGDFT: A massively parallel method for large scale density functional theory calculations
International Nuclear Information System (INIS)
Hu, Wei; Yang, Chao; Lin, Lin
2015-01-01
We describe a massively parallel implementation of the recently developed discontinuous Galerkin density functional theory (DGDFT) method, for efficient large-scale Kohn-Sham DFT based electronic structure calculations. The DGDFT method uses adaptive local basis (ALB) functions generated on-the-fly during the self-consistent field iteration to represent the solution to the Kohn-Sham equations. The use of the ALB set provides a systematic way to improve the accuracy of the approximation. By using the pole expansion and selected inversion technique to compute electron density, energy, and atomic forces, we can make the computational complexity of DGDFT scale at most quadratically with respect to the number of electrons for both insulating and metallic systems. We show that for the two-dimensional (2D) phosphorene systems studied here, using 37 basis functions per atom allows us to reach an accuracy level of 1.3 × 10 −4 Hartree/atom in terms of the error of energy and 6.2 × 10 −4 Hartree/bohr in terms of the error of atomic force, respectively. DGDFT can achieve 80% parallel efficiency on 128,000 high performance computing cores when it is used to study the electronic structure of 2D phosphorene systems with 3500-14 000 atoms. This high parallel efficiency results from a two-level parallelization scheme that we will describe in detail
DGDFT: A massively parallel method for large scale density functional theory calculations
Energy Technology Data Exchange (ETDEWEB)
Hu, Wei, E-mail: whu@lbl.gov; Yang, Chao, E-mail: cyang@lbl.gov [Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720 (United States); Lin, Lin, E-mail: linlin@math.berkeley.edu [Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720 (United States); Department of Mathematics, University of California, Berkeley, California 94720 (United States)
2015-09-28
We describe a massively parallel implementation of the recently developed discontinuous Galerkin density functional theory (DGDFT) method, for efficient large-scale Kohn-Sham DFT based electronic structure calculations. The DGDFT method uses adaptive local basis (ALB) functions generated on-the-fly during the self-consistent field iteration to represent the solution to the Kohn-Sham equations. The use of the ALB set provides a systematic way to improve the accuracy of the approximation. By using the pole expansion and selected inversion technique to compute electron density, energy, and atomic forces, we can make the computational complexity of DGDFT scale at most quadratically with respect to the number of electrons for both insulating and metallic systems. We show that for the two-dimensional (2D) phosphorene systems studied here, using 37 basis functions per atom allows us to reach an accuracy level of 1.3 × 10{sup −4} Hartree/atom in terms of the error of energy and 6.2 × 10{sup −4} Hartree/bohr in terms of the error of atomic force, respectively. DGDFT can achieve 80% parallel efficiency on 128,000 high performance computing cores when it is used to study the electronic structure of 2D phosphorene systems with 3500-14 000 atoms. This high parallel efficiency results from a two-level parallelization scheme that we will describe in detail.
QR-decomposition based SENSE reconstruction using parallel architecture.
Ullah, Irfan; Nisar, Habab; Raza, Haseeb; Qasim, Malik; Inam, Omair; Omer, Hammad
2018-04-01
Magnetic Resonance Imaging (MRI) is a powerful medical imaging technique that provides essential clinical information about the human body. One major limitation of MRI is its long scan time. Implementation of advance MRI algorithms on a parallel architecture (to exploit inherent parallelism) has a great potential to reduce the scan time. Sensitivity Encoding (SENSE) is a Parallel Magnetic Resonance Imaging (pMRI) algorithm that utilizes receiver coil sensitivities to reconstruct MR images from the acquired under-sampled k-space data. At the heart of SENSE lies inversion of a rectangular encoding matrix. This work presents a novel implementation of GPU based SENSE algorithm, which employs QR decomposition for the inversion of the rectangular encoding matrix. For a fair comparison, the performance of the proposed GPU based SENSE reconstruction is evaluated against single and multicore CPU using openMP. Several experiments against various acceleration factors (AFs) are performed using multichannel (8, 12 and 30) phantom and in-vivo human head and cardiac datasets. Experimental results show that GPU significantly reduces the computation time of SENSE reconstruction as compared to multi-core CPU (approximately 12x speedup) and single-core CPU (approximately 53x speedup) without any degradation in the quality of the reconstructed images. Copyright © 2018 Elsevier Ltd. All rights reserved.
International Nuclear Information System (INIS)
Wang Shi; Kang Kejun; Wang Jingjin
1995-01-01
Computerized Tomography (CT) is expected to become an inevitable diagnostic technique in the future. However, the long time required to reconstruct an image has been one of the major drawbacks associated with this technique. Parallel process is one of the best way to solve this problem. This paper gives the architecture and hardware design of PIRS-4 (4-processor Parallel Image Reconstruction System) which is a parallel processing system for fast 3D-CT image reconstruction by circular shifting float memory architecture. It includes structure and component of the system, the design of cross bar switch and details of control model. The test results are described
Multiplexed microsatellite recovery using massively parallel sequencing
Jennings, T.N.; Knaus, B.J.; Mullins, T.D.; Haig, S.M.; Cronn, R.C.
2011-01-01
Conservation and management of natural populations requires accurate and inexpensive genotyping methods. Traditional microsatellite, or simple sequence repeat (SSR), marker analysis remains a popular genotyping method because of the comparatively low cost of marker development, ease of analysis and high power of genotype discrimination. With the availability of massively parallel sequencing (MPS), it is now possible to sequence microsatellite-enriched genomic libraries in multiplex pools. To test this approach, we prepared seven microsatellite-enriched, barcoded genomic libraries from diverse taxa (two conifer trees, five birds) and sequenced these on one lane of the Illumina Genome Analyzer using paired-end 80-bp reads. In this experiment, we screened 6.1 million sequences and identified 356958 unique microreads that contained di- or trinucleotide microsatellites. Examination of four species shows that our conversion rate from raw sequences to polymorphic markers compares favourably to Sanger- and 454-based methods. The advantage of multiplexed MPS is that the staggering capacity of modern microread sequencing is spread across many libraries; this reduces sample preparation and sequencing costs to less than $400 (USD) per species. This price is sufficiently low that microsatellite libraries could be prepared and sequenced for all 1373 organisms listed as 'threatened' and 'endangered' in the United States for under $0.5M (USD).
GPAW - massively parallel electronic structure calculations with Python-based software
DEFF Research Database (Denmark)
Enkovaara, Jussi; Romero, Nichols A.; Shende, Sameer
2011-01-01
of the productivity enhancing features together with a good numerical performance. We have used this approach in implementing an electronic structure simulation software GPAW using the combination of Python and C programming languages. While the chosen approach works well in standard workstations and Unix...... popular choice. While dynamic, interpreted languages, such as Python, can increase the effciency of programmer, they cannot compete directly with the raw performance of compiled languages. However, by using an interpreted language together with a compiled language, it is possible to have most...... environments, massively parallel supercomputing systems can present some challenges in porting, debugging and profiling the software. In this paper we describe some details of the implementation and discuss the advantages and challenges of the combined Python/C approach. We show that despite the challenges...
A System Architecture for Efficient Transmission of Massive DNA Sequencing Data.
Sağiroğlu, Mahmut Şamİl; Külekcİ, M Oğuzhan
2017-11-01
The DNA sequencing data analysis pipelines require significant computational resources. In that sense, cloud computing infrastructures appear as a natural choice for this processing. However, the first practical difficulty in reaching the cloud computing services is the transmission of the massive DNA sequencing data from where they are produced to where they will be processed. The daily practice here begins with compressing the data in FASTQ file format, and then sending these data via fast data transmission protocols. In this study, we address the weaknesses in that daily practice and present a new system architecture that incorporates the computational resources available on the client side while dynamically adapting itself to the available bandwidth. Our proposal considers the real-life scenarios, where the bandwidth of the connection between the parties may fluctuate, and also the computing power on the client side may be of any size ranging from moderate personal computers to powerful workstations. The proposed architecture aims at utilizing both the communication bandwidth and the computing resources for satisfying the ultimate goal of reaching the results as early as possible. We present a prototype implementation of the proposed architecture, and analyze several real-life cases, which provide useful insights for the sequencing centers, especially on deciding when to use a cloud service and in what conditions.
Tyagi, Neelam; Bose, Abhijit; Chetty, Indrin J
2004-09-01
We have parallelized the Dose Planning Method (DPM), a Monte Carlo code optimized for radiotherapy class problems, on distributed-memory processor architectures using the Message Passing Interface (MPI). Parallelization has been investigated on a variety of parallel computing architectures at the University of Michigan-Center for Advanced Computing, with respect to efficiency and speedup as a function of the number of processors. We have integrated the parallel pseudo random number generator from the Scalable Parallel Pseudo-Random Number Generator (SPRNG) library to run with the parallel DPM. The Intel cluster consisting of 800 MHz Intel Pentium III processor shows an almost linear speedup up to 32 processors for simulating 1 x 10(8) or more particles. The speedup results are nearly linear on an Athlon cluster (up to 24 processors based on availability) which consists of 1.8 GHz+ Advanced Micro Devices (AMD) Athlon processors on increasing the problem size up to 8 x 10(8) histories. For a smaller number of histories (1 x 10(8)) the reduction of efficiency with the Athlon cluster (down to 83.9% with 24 processors) occurs because the processing time required to simulate 1 x 10(8) histories is less than the time associated with interprocessor communication. A similar trend was seen with the Opteron Cluster (consisting of 1400 MHz, 64-bit AMD Opteron processors) on increasing the problem size. Because of the 64-bit architecture Opteron processors are capable of storing and processing instructions at a faster rate and hence are faster as compared to the 32-bit Athlon processors. We have validated our implementation with an in-phantom dose calculation study using a parallel pencil monoenergetic electron beam of 20 MeV energy. The phantom consists of layers of water, lung, bone, aluminum, and titanium. The agreement in the central axis depth dose curves and profiles at different depths shows that the serial and parallel codes are equivalent in accuracy.
International Nuclear Information System (INIS)
Tyagi, Neelam; Bose, Abhijit; Chetty, Indrin J.
2004-01-01
We have parallelized the Dose Planning Method (DPM), a Monte Carlo code optimized for radiotherapy class problems, on distributed-memory processor architectures using the Message Passing Interface (MPI). Parallelization has been investigated on a variety of parallel computing architectures at the University of Michigan-Center for Advanced Computing, with respect to efficiency and speedup as a function of the number of processors. We have integrated the parallel pseudo random number generator from the Scalable Parallel Pseudo-Random Number Generator (SPRNG) library to run with the parallel DPM. The Intel cluster consisting of 800 MHz Intel Pentium III processor shows an almost linear speedup up to 32 processors for simulating 1x10 8 or more particles. The speedup results are nearly linear on an Athlon cluster (up to 24 processors based on availability) which consists of 1.8 GHz+ Advanced Micro Devices (AMD) Athlon processors on increasing the problem size up to 8x10 8 histories. For a smaller number of histories (1x10 8 ) the reduction of efficiency with the Athlon cluster (down to 83.9% with 24 processors) occurs because the processing time required to simulate 1x10 8 histories is less than the time associated with interprocessor communication. A similar trend was seen with the Opteron Cluster (consisting of 1400 MHz, 64-bit AMD Opteron processors) on increasing the problem size. Because of the 64-bit architecture Opteron processors are capable of storing and processing instructions at a faster rate and hence are faster as compared to the 32-bit Athlon processors. We have validated our implementation with an in-phantom dose calculation study using a parallel pencil monoenergetic electron beam of 20 MeV energy. The phantom consists of layers of water, lung, bone, aluminum, and titanium. The agreement in the central axis depth dose curves and profiles at different depths shows that the serial and parallel codes are equivalent in accuracy
A Pipelined and Parallel Architecture for Quantum Monte Carlo Simulations on FPGAs
Directory of Open Access Journals (Sweden)
Akila Gothandaraman
2010-01-01
Full Text Available Recent advances in Field-Programmable Gate Array (FPGA technology make reconfigurable computing using FPGAs an attractive platform for accelerating scientific applications. We develop a deeply pipelined and parallel architecture for Quantum Monte Carlo simulations using FPGAs. Quantum Monte Carlo simulations enable us to obtain the structural and energetic properties of atomic clusters. We experiment with different pipeline structures for each component of the design and develop a deeply pipelined architecture that provides the best performance in terms of achievable clock rate, while at the same time has a modest use of the FPGA resources. We discuss the details of the pipelined and generic architecture that is used to obtain the potential energy and wave function of a cluster of atoms.
Massively Parallel Finite Element Programming
Heister, Timo; Kronbichler, Martin; Bangerth, Wolfgang
2010-01-01
Today's large finite element simulations require parallel algorithms to scale on clusters with thousands or tens of thousands of processor cores. We present data structures and algorithms to take advantage of the power of high performance computers in generic finite element codes. Existing generic finite element libraries often restrict the parallelization to parallel linear algebra routines. This is a limiting factor when solving on more than a few hundreds of cores. We describe routines for distributed storage of all major components coupled with efficient, scalable algorithms. We give an overview of our effort to enable the modern and generic finite element library deal.II to take advantage of the power of large clusters. In particular, we describe the construction of a distributed mesh and develop algorithms to fully parallelize the finite element calculation. Numerical results demonstrate good scalability. © 2010 Springer-Verlag.
Massively Parallel Finite Element Programming
Heister, Timo
2010-01-01
Today\\'s large finite element simulations require parallel algorithms to scale on clusters with thousands or tens of thousands of processor cores. We present data structures and algorithms to take advantage of the power of high performance computers in generic finite element codes. Existing generic finite element libraries often restrict the parallelization to parallel linear algebra routines. This is a limiting factor when solving on more than a few hundreds of cores. We describe routines for distributed storage of all major components coupled with efficient, scalable algorithms. We give an overview of our effort to enable the modern and generic finite element library deal.II to take advantage of the power of large clusters. In particular, we describe the construction of a distributed mesh and develop algorithms to fully parallelize the finite element calculation. Numerical results demonstrate good scalability. © 2010 Springer-Verlag.
Massive parallel 3D PIC simulation of negative ion extraction
Revel, Adrien; Mochalskyy, Serhiy; Montellano, Ivar Mauricio; Wünderlich, Dirk; Fantz, Ursel; Minea, Tiberiu
2017-09-01
The 3D PIC-MCC code ONIX is dedicated to modeling Negative hydrogen/deuterium Ion (NI) extraction and co-extraction of electrons from radio-frequency driven, low pressure plasma sources. It provides valuable insight on the complex phenomena involved in the extraction process. In previous calculations, a mesh size larger than the Debye length was used, implying numerical electron heating. Important steps have been achieved in terms of computation performance and parallelization efficiency allowing successful massive parallel calculations (4096 cores), imperative to resolve the Debye length. In addition, the numerical algorithms have been improved in terms of grid treatment, i.e., the electric field near the complex geometry boundaries (plasma grid) is calculated more accurately. The revised model preserves the full 3D treatment, but can take advantage of a highly refined mesh. ONIX was used to investigate the role of the mesh size, the re-injection scheme for lost particles (extracted or wall absorbed), and the electron thermalization process on the calculated extracted current and plasma characteristics. It is demonstrated that all numerical schemes give the same NI current distribution for extracted ions. Concerning the electrons, the pair-injection technique is found well-adapted to simulate the sheath in front of the plasma grid.
Massively parallel de novo protein design for targeted therapeutics
Chevalier, Aaron
2017-09-26
De novo protein design holds promise for creating small stable proteins with shapes customized to bind therapeutic targets. We describe a massively parallel approach for designing, manufacturing and screening mini-protein binders, integrating large-scale computational design, oligonucleotide synthesis, yeast display screening and next-generation sequencing. We designed and tested 22,660 mini-proteins of 37-43 residues that target influenza haemagglutinin and botulinum neurotoxin B, along with 6,286 control sequences to probe contributions to folding and binding, and identified 2,618 high-affinity binders. Comparison of the binding and non-binding design sets, which are two orders of magnitude larger than any previously investigated, enabled the evaluation and improvement of the computational model. Biophysical characterization of a subset of the binder designs showed that they are extremely stable and, unlike antibodies, do not lose activity after exposure to high temperatures. The designs elicit little or no immune response and provide potent prophylactic and therapeutic protection against influenza, even after extensive repeated dosing.
Massively parallel de novo protein design for targeted therapeutics
Chevalier, Aaron; Silva, Daniel-Adriano; Rocklin, Gabriel J.; Hicks, Derrick R.; Vergara, Renan; Murapa, Patience; Bernard, Steffen M.; Zhang, Lu; Lam, Kwok-Ho; Yao, Guorui; Bahl, Christopher D.; Miyashita, Shin-Ichiro; Goreshnik, Inna; Fuller, James T.; Koday, Merika T.; Jenkins, Cody M.; Colvin, Tom; Carter, Lauren; Bohn, Alan; Bryan, Cassie M.; Ferná ndez-Velasco, D. Alejandro; Stewart, Lance; Dong, Min; Huang, Xuhui; Jin, Rongsheng; Wilson, Ian A.; Fuller, Deborah H.; Baker, David
2017-01-01
De novo protein design holds promise for creating small stable proteins with shapes customized to bind therapeutic targets. We describe a massively parallel approach for designing, manufacturing and screening mini-protein binders, integrating large-scale computational design, oligonucleotide synthesis, yeast display screening and next-generation sequencing. We designed and tested 22,660 mini-proteins of 37-43 residues that target influenza haemagglutinin and botulinum neurotoxin B, along with 6,286 control sequences to probe contributions to folding and binding, and identified 2,618 high-affinity binders. Comparison of the binding and non-binding design sets, which are two orders of magnitude larger than any previously investigated, enabled the evaluation and improvement of the computational model. Biophysical characterization of a subset of the binder designs showed that they are extremely stable and, unlike antibodies, do not lose activity after exposure to high temperatures. The designs elicit little or no immune response and provide potent prophylactic and therapeutic protection against influenza, even after extensive repeated dosing.
Massively parallel performance of neutron transport response matrix algorithms
International Nuclear Information System (INIS)
Hanebutte, U.R.; Lewis, E.E.
1993-01-01
Massively parallel red/black response matrix algorithms for the solution of within-group neutron transport problems are implemented on the Connection Machines-2, 200 and 5. The response matrices are dericed from the diamond-differences and linear-linear nodal discrete ordinate and variational nodal P 3 approximations. The unaccelerated performance of the iterative procedure is examined relative to the maximum rated performances of the machines. The effects of processor partitions size, of virtual processor ratio and of problems size are examined in detail. For the red/black algorithm, the ratio of inter-node communication to computing times is found to be quite small, normally of the order of ten percent or less. Performance increases with problems size and with virtual processor ratio, within the memeory per physical processor limitation. Algorithm adaptation to courser grain machines is straight-forward, with total computing time being virtually inversely proportional to the number of physical processors. (orig.)
Massively parallel de novo protein design for targeted therapeutics
Chevalier, Aaron; Silva, Daniel-Adriano; Rocklin, Gabriel J.; Hicks, Derrick R.; Vergara, Renan; Murapa, Patience; Bernard, Steffen M.; Zhang, Lu; Lam, Kwok-Ho; Yao, Guorui; Bahl, Christopher D.; Miyashita, Shin-Ichiro; Goreshnik, Inna; Fuller, James T.; Koday, Merika T.; Jenkins, Cody M.; Colvin, Tom; Carter, Lauren; Bohn, Alan; Bryan, Cassie M.; Fernández-Velasco, D. Alejandro; Stewart, Lance; Dong, Min; Huang, Xuhui; Jin, Rongsheng; Wilson, Ian A.; Fuller, Deborah H.; Baker, David
2018-01-01
De novo protein design holds promise for creating small stable proteins with shapes customized to bind therapeutic targets. We describe a massively parallel approach for designing, manufacturing and screening mini-protein binders, integrating large-scale computational design, oligonucleotide synthesis, yeast display screening and next-generation sequencing. We designed and tested 22,660 mini-proteins of 37–43 residues that target influenza haemagglutinin and botulinum neurotoxin B, along with 6,286 control sequences to probe contributions to folding and binding, and identified 2,618 high-affinity binders. Comparison of the binding and non-binding design sets, which are two orders of magnitude larger than any previously investigated, enabled the evaluation and improvement of the computational model. Biophysical characterization of a subset of the binder designs showed that they are extremely stable and, unlike antibodies, do not lose activity after exposure to high temperatures. The designs elicit little or no immune response and provide potent prophylactic and therapeutic protection against influenza, even after extensive repeated dosing. PMID:28953867
Design of a real-time wind turbine simulator using a custom parallel architecture
Hoffman, John A.; Gluck, R.; Sridhar, S.
1995-01-01
The design of a new parallel-processing digital simulator is described. The new simulator has been developed specifically for analysis of wind energy systems in real time. The new processor has been named: the Wind Energy System Time-domain simulator, version 3 (WEST-3). Like previous WEST versions, WEST-3 performs many computations in parallel. The modules in WEST-3 are pure digital processors, however. These digital processors can be programmed individually and operated in concert to achieve real-time simulation of wind turbine systems. Because of this programmability, WEST-3 is very much more flexible and general than its two predecessors. The design features of WEST-3 are described to show how the system produces high-speed solutions of nonlinear time-domain equations. WEST-3 has two very fast Computational Units (CU's) that use minicomputer technology plus special architectural features that make them many times faster than a microcomputer. These CU's are needed to perform the complex computations associated with the wind turbine rotor system in real time. The parallel architecture of the CU causes several tasks to be done in each cycle, including an IO operation and the combination of a multiply, add, and store. The WEST-3 simulator can be expanded at any time for additional computational power. This is possible because the CU's interfaced to each other and to other portions of the simulation using special serial buses. These buses can be 'patched' together in essentially any configuration (in a manner very similar to the programming methods used in analog computation) to balance the input/ output requirements. CU's can be added in any number to share a given computational load. This flexible bus feature is very different from many other parallel processors which usually have a throughput limit because of rigid bus architecture.
Performance modeling of parallel algorithms for solving neutron diffusion problems
International Nuclear Information System (INIS)
Azmy, Y.Y.; Kirk, B.L.
1995-01-01
Neutron diffusion calculations are the most common computational methods used in the design, analysis, and operation of nuclear reactors and related activities. Here, mathematical performance models are developed for the parallel algorithm used to solve the neutron diffusion equation on message passing and shared memory multiprocessors represented by the Intel iPSC/860 and the Sequent Balance 8000, respectively. The performance models are validated through several test problems, and these models are used to estimate the performance of each of the two considered architectures in situations typical of practical applications, such as fine meshes and a large number of participating processors. While message passing computers are capable of producing speedup, the parallel efficiency deteriorates rapidly as the number of processors increases. Furthermore, the speedup fails to improve appreciably for massively parallel computers so that only small- to medium-sized message passing multiprocessors offer a reasonable platform for this algorithm. In contrast, the performance model for the shared memory architecture predicts very high efficiency over a wide range of number of processors reasonable for this architecture. Furthermore, the model efficiency of the Sequent remains superior to that of the hypercube if its model parameters are adjusted to make its processors as fast as those of the iPSC/860. It is concluded that shared memory computers are better suited for this parallel algorithm than message passing computers
Quantification of massively parallel sequencing libraries - a comparative study of eight methods
DEFF Research Database (Denmark)
Hussing, Christian; Kampmann, Marie-Louise; Mogensen, Helle Smidt
2018-01-01
Quantification of massively parallel sequencing libraries is important for acquisition of monoclonal beads or clusters prior to clonal amplification and to avoid large variations in library coverage when multiple samples are included in one sequencing analysis. No gold standard for quantification...... estimates followed by Qubit and electrophoresis-based instruments (Bioanalyzer, TapeStation, GX Touch, and Fragment Analyzer), while SYBR Green and TaqMan based qPCR assays gave the lowest estimates. qPCR gave more accurate predictions of sequencing coverage than Qubit and TapeStation did. Costs, time......-consumption, workflow simplicity, and ability to quantify multiple samples are discussed. Technical specifications, advantages, and disadvantages of the various methods are pointed out....
Massive parallel sequencing in sarcoma pathobiology: state of the art and perspectives.
Brenca, Monica; Maestro, Roberta
2015-01-01
Sarcomas are an aggressive and highly heterogeneous group of mesenchymal malignancies with different morphologies and clinical behavior. Current therapeutic strategies remain unsatisfactory. Cytogenetic and molecular characterization of these tumors is resulting in the breakdown of the classical histopathological categories into molecular subgroups that better define sarcoma pathobiology and pave the way to more precise diagnostic criteria and novel therapeutic opportunities. The purpose of this short review is to summarize the state-of-the-art on the exploitation of massive parallel sequencing technologies, also known as next generation sequencing, in the elucidation of sarcoma pathobiology and to discuss how these applications may impact on diagnosis, prognosis and therapy of these tumors.
Centaure: an heterogeneous parallel architecture for computer vision
International Nuclear Information System (INIS)
Peythieux, Marc
1997-01-01
This dissertation deals with the architecture of parallel computers dedicated to computer vision. In the first chapter, the problem to be solved is presented, as well as the architecture of the Sympati and Symphonie computers, on which this work is based. The second chapter is about the state of the art of computers and integrated processors that can execute computer vision and image processing codes. The third chapter contains a description of the architecture of Centaure. It has an heterogeneous structure: it is composed of a multiprocessor system based on Analog Devices ADSP21060 Sharc digital signal processor, and of a set of Symphonie computers working in a multi-SIMD fashion. Centaure also has a modular structure. Its basic node is composed of one Symphonie computer, tightly coupled to a Sharc thanks to a dual ported memory. The nodes of Centaure are linked together by the Sharc communication links. The last chapter deals with a performance validation of Centaure. The execution times on Symphonie and on Centaure of a benchmark which is typical of industrial vision, are presented and compared. In the first place, these results show that the basic node of Centaure allows a faster execution than Symphonie, and that increasing the size of the tested computer leads to a better speed-up with Centaure than with Symphonie. In the second place, these results validate the choice of running the low level structure of Centaure in a multi- SIMD fashion. (author) [fr
Sandalski, Stou
Smooth particle hydrodynamics is an efficient method for modeling the dynamics of fluids. It is commonly used to simulate astrophysical processes such as binary mergers. We present a newly developed GPU accelerated smooth particle hydrodynamics code for astrophysical simulations. The code is named neptune after the Roman god of water. It is written in OpenMP parallelized C++ and OpenCL and includes octree based hydrodynamic and gravitational acceleration. The design relies on object-oriented methodologies in order to provide a flexible and modular framework that can be easily extended and modified by the user. Several pre-built scenarios for simulating collisions of polytropes and black-hole accretion are provided. The code is released under the MIT Open Source license and publicly available at http://code.google.com/p/neptune-sph/.
A Hybrid FPGA/Coarse Parallel Processing Architecture for Multi-modal Visual Feature Descriptors
DEFF Research Database (Denmark)
Jensen, Lars Baunegaard With; Kjær-Nielsen, Anders; Alonso, Javier Díaz
2008-01-01
This paper describes the hybrid architecture developed for speeding up the processing of so-called multi-modal visual primitives which are sparse image descriptors extracted along contours. In the system, the first stages of visual processing are implemented on FPGAs due to their highly parallel...
Design and simulation of parallel and distributed architectures for images processing
International Nuclear Information System (INIS)
Pirson, Alain
1990-01-01
The exploitation of visual information requires special computers. The diversity of operations and the Computing power involved bring about structures founded on the concepts of concurrency and distributed processing. This work identifies a vision computer with an association of dedicated intelligent entities, exchanging messages according to the model of parallelism introduced by the language Occam. It puts forward an architecture of the 'enriched processor network' type. It consists of a classical multiprocessor structure where each node is provided with specific devices. These devices perform processing tasks as well as inter-nodes dialogues. Such an architecture benefits from the homogeneity of multiprocessor networks and the power of dedicated resources. Its implementation corresponds to that of a distributed structure, tasks being allocated to each Computing element. This approach culminates in an original architecture called ATILA. This modular structure is based on a transputer network supplied with vision dedicated co-processors and powerful communication devices. (author) [fr
Techniques and Architectures for Hazard-Free Semi-Parallel Decoding of LDPC Codes
Directory of Open Access Journals (Sweden)
Rovini Massimo
2009-01-01
Full Text Available The layered decoding algorithm has recently been proposed as an efficient means for the decoding of low-density parity-check (LDPC codes, thanks to the remarkable improvement in the convergence speed (2x of the decoding process. However, pipelined semi-parallel decoders suffer from violations or "hazards" between consecutive updates, which not only violate the layered principle but also enforce the loops in the code, thus spoiling the error correction performance. This paper describes three different techniques to properly reschedule the decoding updates, based on the careful insertion of "idle" cycles, to prevent the hazards of the pipeline mechanism. Also, different semi-parallel architectures of a layered LDPC decoder suitable for use with such techniques are analyzed. Then, taking the LDPC codes for the wireless local area network (IEEE 802.11n as a case study, a detailed analysis of the performance attained with the proposed techniques and architectures is reported, and results of the logic synthesis on a 65 nm low-power CMOS technology are shown.
Newman, Gregory A.; Commer, Michael
2009-07-01
Three-dimensional (3D) geophysical imaging is now receiving considerable attention for electrical conductivity mapping of potential offshore oil and gas reservoirs. The imaging technology employs controlled source electromagnetic (CSEM) and magnetotelluric (MT) fields and treats geological media exhibiting transverse anisotropy. Moreover when combined with established seismic methods, direct imaging of reservoir fluids is possible. Because of the size of the 3D conductivity imaging problem, strategies are required exploiting computational parallelism and optimal meshing. The algorithm thus developed has been shown to scale to tens of thousands of processors. In one imaging experiment, 32,768 tasks/processors on the IBM Watson Research Blue Gene/L supercomputer were successfully utilized. Over a 24 hour period we were able to image a large scale field data set that previously required over four months of processing time on distributed clusters based on Intel or AMD processors utilizing 1024 tasks on an InfiniBand fabric. Electrical conductivity imaging using massively parallel computational resources produces results that cannot be obtained otherwise and are consistent with timeframes required for practical exploration problems.
International Nuclear Information System (INIS)
Newman, Gregory A; Commer, Michael
2009-01-01
Three-dimensional (3D) geophysical imaging is now receiving considerable attention for electrical conductivity mapping of potential offshore oil and gas reservoirs. The imaging technology employs controlled source electromagnetic (CSEM) and magnetotelluric (MT) fields and treats geological media exhibiting transverse anisotropy. Moreover when combined with established seismic methods, direct imaging of reservoir fluids is possible. Because of the size of the 3D conductivity imaging problem, strategies are required exploiting computational parallelism and optimal meshing. The algorithm thus developed has been shown to scale to tens of thousands of processors. In one imaging experiment, 32,768 tasks/processors on the IBM Watson Research Blue Gene/L supercomputer were successfully utilized. Over a 24 hour period we were able to image a large scale field data set that previously required over four months of processing time on distributed clusters based on Intel or AMD processors utilizing 1024 tasks on an InfiniBand fabric. Electrical conductivity imaging using massively parallel computational resources produces results that cannot be obtained otherwise and are consistent with timeframes required for practical exploration problems.
International Nuclear Information System (INIS)
Guirande, Ph.; Aleonard, M-M.; Dien, Q-T.; Pedroza, J-L.
1997-01-01
The efficiency increasing in four π (EUROGAM, EUROBALL, DIAMANT) is achieved by an increase in the granularity, hence in the event counting rate in the acquisition system. Consequently, an evolution of the architecture of readout systems, coding and software is necessary. To achieve the required evaluation we have implemented a parallel architecture to check the quality of the events. The first application of this architecture was to make available an improved data acquisition system for the DIAMANT multidetector. The data acquisition system of DIAMANT is based on an ensemble of VME cards which must manage: the event readout, their salvation on magnetic support and histogram construction. The ensemble consists of processors distributed in a net, a workstation to control the experiment and a display system for spectra and arrays. In such architecture the task of VME bus becomes quickly a limitation for performances not only for the data transfer but also for coordination of different processors. The parallel architecture used makes the VME bus operation easy. It is based on three DSP C40 (Digital Signal Processor) implanted in a commercial (LSI) VME. It is provided with an external bus used to read the raw data from an interface card (ROCVI) between the 32 bit ECL bus reading the real time VME-based encoders. The performed tests have evidenced jamming after data exchanges between the processors using two communication lines. The analysis of this problem has indicated the necessity of dynamical changes of tasks to avoid this blocking. Intrinsic evaluation (i.e. without transfer on the VME bus) has been carried out for two parallel topologies (processor farm and tree). The simulation software permitted the generation of event packets. The obtained rates are sensibly equivalent (6 Mo/s) independent of topology. The farm topology has been chosen because it is simple to implant. The charge evaluation has reduced the rate in 'simplex' communication mode to 5.3 Mo/s and
Directory of Open Access Journals (Sweden)
Paolo Cazzaniga
2014-01-01
high-performance computing solutions is motivated by the need of performing large numbers of in silico analysis to study the behavior of biological systems in different conditions, which necessitate a computing power that usually overtakes the capability of standard desktop computers. In this work we present coagSODA, a CUDA-powered computational tool that was purposely developed for the analysis of a large mechanistic model of the blood coagulation cascade (BCC, defined according to both mass-action kinetics and Hill functions. coagSODA allows the execution of parallel simulations of the dynamics of the BCC by automatically deriving the system of ordinary differential equations and then exploiting the numerical integration algorithm LSODA. We present the biological results achieved with a massive exploration of perturbed conditions of the BCC, carried out with one-dimensional and bi-dimensional parameter sweep analysis, and show that GPU-accelerated parallel simulations of this model can increase the computational performances up to a 181× speedup compared to the corresponding sequential simulations.
Beam dynamics calculations and particle tracking using massively parallel processors
International Nuclear Information System (INIS)
Ryne, R.D.; Habib, S.
1995-01-01
During the past decade massively parallel processors (MPPs) have slowly gained acceptance within the scientific community. At present these machines typically contain a few hundred to one thousand off-the-shelf microprocessors and a total memory of up to 32 GBytes. The potential performance of these machines is illustrated by the fact that a month long job on a high end workstation might require only a few hours on an MPP. The acceptance of MPPs has been slow for a variety of reasons. For example, some algorithms are not easily parallelizable. Also, in the past these machines were difficult to program. But in recent years the development of Fortran-like languages such as CM Fortran and High Performance Fortran have made MPPs much easier to use. In the following we will describe how MPPs can be used for beam dynamics calculations and long term particle tracking
Guermond, Jean-Luc; Minev, Peter D.; Salgado, Abner J.
2012-01-01
We provide a convergence analysis for a new fractional timestepping technique for the incompressible Navier-Stokes equations based on direction splitting. This new technique is of linear complexity, unconditionally stable and convergent, and suitable for massive parallelization. © 2012 American Mathematical Society.
GPU: the biggest key processor for AI and parallel processing
Baji, Toru
2017-07-01
Two types of processors exist in the market. One is the conventional CPU and the other is Graphic Processor Unit (GPU). Typical CPU is composed of 1 to 8 cores while GPU has thousands of cores. CPU is good for sequential processing, while GPU is good to accelerate software with heavy parallel executions. GPU was initially dedicated for 3D graphics. However from 2006, when GPU started to apply general-purpose cores, it was noticed that this architecture can be used as a general purpose massive-parallel processor. NVIDIA developed a software framework Compute Unified Device Architecture (CUDA) that make it possible to easily program the GPU for these application. With CUDA, GPU started to be used in workstations and supercomputers widely. Recently two key technologies are highlighted in the industry. The Artificial Intelligence (AI) and Autonomous Driving Cars. AI requires a massive parallel operation to train many-layers of neural networks. With CPU alone, it was impossible to finish the training in a practical time. The latest multi-GPU system with P100 makes it possible to finish the training in a few hours. For the autonomous driving cars, TOPS class of performance is required to implement perception, localization, path planning processing and again SoC with integrated GPU will play a key role there. In this paper, the evolution of the GPU which is one of the biggest commercial devices requiring state-of-the-art fabrication technology will be introduced. Also overview of the GPU demanding key application like the ones described above will be introduced.
A scalable approach to modeling groundwater flow on massively parallel computers
International Nuclear Information System (INIS)
Ashby, S.F.; Falgout, R.D.; Tompson, A.F.B.
1995-12-01
We describe a fully scalable approach to the simulation of groundwater flow on a hierarchy of computing platforms, ranging from workstations to massively parallel computers. Specifically, we advocate the use of scalable conceptual models in which the subsurface model is defined independently of the computational grid on which the simulation takes place. We also describe a scalable multigrid algorithm for computing the groundwater flow velocities. We axe thus able to leverage both the engineer's time spent developing the conceptual model and the computing resources used in the numerical simulation. We have successfully employed this approach at the LLNL site, where we have run simulations ranging in size from just a few thousand spatial zones (on workstations) to more than eight million spatial zones (on the CRAY T3D)-all using the same conceptual model
International Nuclear Information System (INIS)
Aparicio, G.; Blanquer, I.; Hernandez, V.; Segrelles, D.
2007-01-01
The integration of High-performance computing tools is a key issue in biomedical research. Many computer-based applications have been migrated to High-Performance computers to deal with their computing and storage needs such as BLAST. However, the use of clusters and computing farm presents problems in scalability. The use of a higher layer of parallelism that splits the task into highly independent long jobs that can be executed in parallel can improve the performance maintaining the efficiency. Grid technologies combined with parallel computing resources are an important enabling technology. This work presents a software architecture for executing BLAST in a International Grid Infrastructure that guarantees security, scalability and fault tolerance. The software architecture is modular an adaptable to many other high-throughput applications, both inside the field of bio computing and outside. (Author)
DEFF Research Database (Denmark)
Eduardoff, M; Gross, T E; Santos, C
2016-01-01
Seq™ PCR primers was designed for the Global AIM-SNPs to perform massively parallel sequencing using the Ion PGM™ system. This study assessed individual SNP genotyping precision using the Ion PGM™, the forensic sensitivity of the multiplex using dilution series, degraded DNA plus simple mixtures...
DEFF Research Database (Denmark)
Kielpinski, Lukasz J; Boyd, Mette; Sandelin, Albin
2013-01-01
Detection of reverse transcriptase termination sites is important in many different applications, such as structural probing of RNAs, rapid amplification of cDNA 5' ends (5' RACE), cap analysis of gene expression, and detection of RNA modifications and protein-RNA cross-links. The throughput...... of these methods can be increased by applying massive parallel sequencing technologies.Here, we describe a versatile method for detection of reverse transcriptase termination sites based on ligation of an adapter to the 3' end of cDNA with bacteriophage TS2126 RNA ligase (CircLigase™). In the following PCR...
Kim, M.-H.; Cho, J. H.; Park, S.-J.; Eden, J. G.
2017-08-01
Plasmachemical systems based on the production of a specific molecule (O3) in literally thousands of microchannel plasmas simultaneously have been demonstrated, developed and engineered over the past seven years, and commercialized. At the heart of this new plasma technology is the plasma chip, a flat aluminum strip fabricated by photolithographic and wet chemical processes and comprising 24-48 channels, micromachined into nanoporous aluminum oxide, with embedded electrodes. By integrating 4-6 chips into a module, the mass output of an ozone microplasma system is scaled linearly with the number of modules operating in parallel. A 115 g/hr (2.7 kg/day) ozone system, for example, is realized by the combined output of 18 modules comprising 72 chips and 1,800 microchannels. The implications of this plasma processing architecture for scaling ozone production capability, and reducing capital and service costs when introducing redundancy into the system, are profound. In contrast to conventional ozone generator technology, microplasma systems operate reliably (albeit with reduced output) in ambient air and humidity levels up to 90%, a characteristic attributable to the water adsorption/desorption properties and electrical breakdown strength of nanoporous alumina. Extensive testing has documented chip and system lifetimes (MTBF) beyond 5,000 hours, and efficiencies >130 g/kWh when oxygen is the feedstock gas. Furthermore, the weight and volume of microplasma systems are a factor of 3-10 lower than those for conventional ozone systems of comparable output. Massively-parallel plasmachemical processing offers functionality, performance, and commercial value beyond that afforded by conventional technology, and is currently in operation in more than 30 countries worldwide.
International Nuclear Information System (INIS)
Wang Shi; Kang Kejun; Wang Jingjin
1996-01-01
Computerized Tomography (CT) is expected to become an inevitable diagnostic technique in the future. However, the long time required to reconstruct an image has been one of the major drawbacks associated with this technique. Parallel process is one of the best way to solve this problem. This paper gives the architecture, hardware and software design of PIRS-4 (4-processor Parallel Image Reconstruction System), which is a parallel processing system for fast 3D-CT image reconstruction by circular shifting float memory architecture. It includes the structure and components of the system, the design of crossbar switch and details of control model, the description of RPBP image reconstruction, the choice of OS (Operate System) and language, the principle of imitating EMS, direct memory R/W of float and programming in the protect model. Finally, the test results are given
Baumgärtel, M.; Ghanem, K.; Kiani, A.; Koch, E.; Pavarini, E.; Sims, H.; Zhang, G.
2017-07-01
We discuss the efficient implementation of general impurity solvers for dynamical mean-field theory. We show that both Lanczos and quantum Monte Carlo in different flavors (Hirsch-Fye, continuous-time hybridization- and interaction-expansion) exhibit excellent scaling on massively parallel supercomputers. We apply these algorithms to simulate realistic model Hamiltonians including the full Coulomb vertex, crystal-field splitting, and spin-orbit interaction. We discuss how to remove the sign problem in the presence of non-diagonal crystal-field and hybridization matrices. We show how to extract the physically observable quantities from imaginary time data, in particular correlation functions and susceptibilities. Finally, we present benchmarks and applications for representative correlated systems.
Parallel eigenanalysis of finite element models in a completely connected architecture
Akl, F. A.; Morel, M. R.
1989-01-01
A parallel algorithm is presented for the solution of the generalized eigenproblem in linear elastic finite element analysis, (K)(phi) = (M)(phi)(omega), where (K) and (M) are of order N, and (omega) is order of q. The concurrent solution of the eigenproblem is based on the multifrontal/modified subspace method and is achieved in a completely connected parallel architecture in which each processor is allowed to communicate with all other processors. The algorithm was successfully implemented on a tightly coupled multiple-instruction multiple-data parallel processing machine, Cray X-MP. A finite element model is divided into m domains each of which is assumed to process n elements. Each domain is then assigned to a processor or to a logical processor (task) if the number of domains exceeds the number of physical processors. The macrotasking library routines are used in mapping each domain to a user task. Computational speed-up and efficiency are used to determine the effectiveness of the algorithm. The effect of the number of domains, the number of degrees-of-freedom located along the global fronts and the dimension of the subspace on the performance of the algorithm are investigated. A parallel finite element dynamic analysis program, p-feda, is documented and the performance of its subroutines in parallel environment is analyzed.
Algorithm comparison and benchmarking using a parallel spectra transform shallow water model
Energy Technology Data Exchange (ETDEWEB)
Worley, P.H. [Oak Ridge National Lab., TN (United States); Foster, I.T.; Toonen, B. [Argonne National Lab., IL (United States)
1995-04-01
In recent years, a number of computer vendors have produced supercomputers based on a massively parallel processing (MPP) architecture. These computers have been shown to be competitive in performance with conventional vector supercomputers for some applications. As spectral weather and climate models are heavy users of vector supercomputers, it is interesting to determine how these models perform on MPPS, and which MPPs are best suited to the execution of spectral models. The benchmarking of MPPs is complicated by the fact that different algorithms may be more efficient on different architectures. Hence, a comprehensive benchmarking effort must answer two related questions: which algorithm is most efficient on each computer and how do the most efficient algorithms compare on different computers. In general, these are difficult questions to answer because of the high cost associated with implementing and evaluating a range of different parallel algorithms on each MPP platform.
Parallelized Seeded Region Growing Using CUDA
Directory of Open Access Journals (Sweden)
Seongjin Park
2014-01-01
Full Text Available This paper presents a novel method for parallelizing the seeded region growing (SRG algorithm using Compute Unified Device Architecture (CUDA technology, with intention to overcome the theoretical weakness of SRG algorithm of its computation time being directly proportional to the size of a segmented region. The segmentation performance of the proposed CUDA-based SRG is compared with SRG implementations on single-core CPUs, quad-core CPUs, and shader language programming, using synthetic datasets and 20 body CT scans. Based on the experimental results, the CUDA-based SRG outperforms the other three implementations, advocating that it can substantially assist the segmentation during massive CT screening tests.
International Nuclear Information System (INIS)
Idomura, Yasuhiro; Jolliet, Sebastien
2010-01-01
A gyrokinetic toroidal five dimensional Eulerian code GT5D is ported on six advanced massively parallel platforms and comprehensive benchmark tests are performed. A parallelisation technique based on physical properties of the gyrokinetic equation is presented. By extending the parallelisation technique with a hybrid parallel model, the scalability of the code is improved on platforms with multi-core processors. In the benchmark tests, a good salability is confirmed up to several thousands cores on every platforms, and the maximum sustained performance of ∼18.6 Tflops is achieved using 16384 cores of BX900. (author)
Fully parallel write/read in resistive synaptic array for accelerating on-chip learning
Gao, Ligang; Wang, I.-Ting; Chen, Pai-Yu; Vrudhula, Sarma; Seo, Jae-sun; Cao, Yu; Hou, Tuo-Hung; Yu, Shimeng
2015-11-01
A neuro-inspired computing paradigm beyond the von Neumann architecture is emerging and it generally takes advantage of massive parallelism and is aimed at complex tasks that involve intelligence and learning. The cross-point array architecture with synaptic devices has been proposed for on-chip implementation of the weighted sum and weight update in the learning algorithms. In this work, forming-free, silicon-process-compatible Ta/TaO x /TiO2/Ti synaptic devices are fabricated, in which >200 levels of conductance states could be continuously tuned by identical programming pulses. In order to demonstrate the advantages of parallelism of the cross-point array architecture, a novel fully parallel write scheme is designed and experimentally demonstrated in a small-scale crossbar array to accelerate the weight update in the training process, at a speed that is independent of the array size. Compared to the conventional row-by-row write scheme, it achieves >30× speed-up and >30× improvement in energy efficiency as projected in a large-scale array. If realistic synaptic device characteristics such as device variations are taken into an array-level simulation, the proposed array architecture is able to achieve ∼95% recognition accuracy of MNIST handwritten digits, which is close to the accuracy achieved by software using the ideal sparse coding algorithm.
Fully parallel write/read in resistive synaptic array for accelerating on-chip learning
International Nuclear Information System (INIS)
Gao, Ligang; Chen, Pai-Yu; Seo, Jae-sun; Cao, Yu; Yu, Shimeng; Wang, I-Ting; Hou, Tuo-Hung; Vrudhula, Sarma
2015-01-01
A neuro-inspired computing paradigm beyond the von Neumann architecture is emerging and it generally takes advantage of massive parallelism and is aimed at complex tasks that involve intelligence and learning. The cross-point array architecture with synaptic devices has been proposed for on-chip implementation of the weighted sum and weight update in the learning algorithms. In this work, forming-free, silicon-process-compatible Ta/TaO_x/TiO_2/Ti synaptic devices are fabricated, in which >200 levels of conductance states could be continuously tuned by identical programming pulses. In order to demonstrate the advantages of parallelism of the cross-point array architecture, a novel fully parallel write scheme is designed and experimentally demonstrated in a small-scale crossbar array to accelerate the weight update in the training process, at a speed that is independent of the array size. Compared to the conventional row-by-row write scheme, it achieves >30× speed-up and >30× improvement in energy efficiency as projected in a large-scale array. If realistic synaptic device characteristics such as device variations are taken into an array-level simulation, the proposed array architecture is able to achieve ∼95% recognition accuracy of MNIST handwritten digits, which is close to the accuracy achieved by software using the ideal sparse coding algorithm. (paper)
International Nuclear Information System (INIS)
Pedron, Antoine
2013-01-01
This thesis work is placed between the scientific domain of ultrasound non-destructive testing and algorithm-architecture adequation. Ultrasound non-destructive testing includes a group of analysis techniques used in science and industry to evaluate the properties of a material, component, or system without causing damage. In order to characterise possible defects, determining their position, size and shape, imaging and reconstruction tools have been developed at CEA-LIST, within the CIVA software platform. Evolution of acquisition sensors implies a continuous growth of datasets and consequently more and more computing power is needed to maintain interactive reconstructions. General purpose processors (GPP) evolving towards parallelism and emerging architectures such as GPU allow large acceleration possibilities than can be applied to these algorithms. The main goal of the thesis is to evaluate the acceleration than can be obtained for two reconstruction algorithms on these architectures. These two algorithms differ in their parallelization scheme. The first one can be properly parallelized on GPP whereas on GPU, an intensive use of atomic instructions is required. Within the second algorithm, parallelism is easier to express, but loop ordering on GPP, as well as thread scheduling and a good use of shared memory on GPU are necessary in order to obtain efficient results. Different API or libraries, such as OpenMP, CUDA and OpenCL are evaluated through chosen benchmarks. An integration of both algorithms in the CIVA software platform is proposed and different issues related to code maintenance and durability are discussed. (author) [fr
GRAPES: a software for parallel searching on biological graphs targeting multi-core architectures.
Directory of Open Access Journals (Sweden)
Rosalba Giugno
Full Text Available Biological applications, from genomics to ecology, deal with graphs that represents the structure of interactions. Analyzing such data requires searching for subgraphs in collections of graphs. This task is computationally expensive. Even though multicore architectures, from commodity computers to more advanced symmetric multiprocessing (SMP, offer scalable computing power, currently published software implementations for indexing and graph matching are fundamentally sequential. As a consequence, such software implementations (i do not fully exploit available parallel computing power and (ii they do not scale with respect to the size of graphs in the database. We present GRAPES, software for parallel searching on databases of large biological graphs. GRAPES implements a parallel version of well-established graph searching algorithms, and introduces new strategies which naturally lead to a faster parallel searching system especially for large graphs. GRAPES decomposes graphs into subcomponents that can be efficiently searched in parallel. We show the performance of GRAPES on representative biological datasets containing antiviral chemical compounds, DNA, RNA, proteins, protein contact maps and protein interactions networks.
Eigensolution of finite element problems in a completely connected parallel architecture
Akl, Fred A.; Morel, Michael R.
1989-01-01
A parallel algorithm for the solution of the generalized eigenproblem in linear elastic finite element analysis, (K)(phi)=(M)(phi)(omega), where (K) and (M) are of order N, and (omega) is of order q is presented. The parallel algorithm is based on a completely connected parallel architecture in which each processor is allowed to communicate with all other processors. The algorithm has been successfully implemented on a tightly coupled multiple-instruction-multiple-data (MIMD) parallel processing computer, Cray X-MP. A finite element model is divided into m domains each of which is assumed to process n elements. Each domain is then assigned to a processor, or to a logical processor (task) if the number of domains exceeds the number of physical processors. The macro-tasking library routines are used in mapping each domain to a user task. Computational speed-up and efficiency are used to determine the effectiveness of the algorithm. The effect of the number of domains, the number of degrees-of-freedom located along the global fronts and the dimension of the subspace on the performance of the algorithm are investigated. For a 64-element rectangular plate, speed-ups of 1.86, 3.13, 3.18 and 3.61 are achieved on two, four, six and eight processors, respectively.
HTMT-class Latency Tolerant Parallel Architecture for Petaflops Scale Computation
Sterling, Thomas; Bergman, Larry
2000-01-01
Computational Aero Sciences and other numeric intensive computation disciplines demand computing throughputs substantially greater than the Teraflops scale systems only now becoming available. The related fields of fluids, structures, thermal, combustion, and dynamic controls are among the interdisciplinary areas that in combination with sufficient resolution and advanced adaptive techniques may force performance requirements towards Petaflops. This will be especially true for compute intensive models such as Navier-Stokes are or when such system models are only part of a larger design optimization computation involving many design points. Yet recent experience with conventional MPP configurations comprising commodity processing and memory components has shown that larger scale frequently results in higher programming difficulty and lower system efficiency. While important advances in system software and algorithms techniques have had some impact on efficiency and programmability for certain classes of problems, in general it is unlikely that software alone will resolve the challenges to higher scalability. As in the past, future generations of high-end computers may require a combination of hardware architecture and system software advances to enable efficient operation at a Petaflops level. The NASA led HTMT project has engaged the talents of a broad interdisciplinary team to develop a new strategy in high-end system architecture to deliver petaflops scale computing in the 2004/5 timeframe. The Hybrid-Technology, MultiThreaded parallel computer architecture incorporates several advanced technologies in combination with an innovative dynamic adaptive scheduling mechanism to provide unprecedented performance and efficiency within practical constraints of cost, complexity, and power consumption. The emerging superconductor Rapid Single Flux Quantum electronics can operate at 100 GHz (the record is 770 GHz) and one percent of the power required by convention
A massively parallel strategy for STR marker development, capture, and genotyping.
Kistler, Logan; Johnson, Stephen M; Irwin, Mitchell T; Louis, Edward E; Ratan, Aakrosh; Perry, George H
2017-09-06
Short tandem repeat (STR) variants are highly polymorphic markers that facilitate powerful population genetic analyses. STRs are especially valuable in conservation and ecological genetic research, yielding detailed information on population structure and short-term demographic fluctuations. Massively parallel sequencing has not previously been leveraged for scalable, efficient STR recovery. Here, we present a pipeline for developing STR markers directly from high-throughput shotgun sequencing data without a reference genome, and an approach for highly parallel target STR recovery. We employed our approach to capture a panel of 5000 STRs from a test group of diademed sifakas (Propithecus diadema, n = 3), endangered Malagasy rainforest lemurs, and we report extremely efficient recovery of targeted loci-97.3-99.6% of STRs characterized with ≥10x non-redundant sequence coverage. We then tested our STR capture strategy on P. diadema fecal DNA, and report robust initial results and suggestions for future implementations. In addition to STR targets, this approach also generates large, genome-wide single nucleotide polymorphism (SNP) panels from flanking regions. Our method provides a cost-effective and scalable solution for rapid recovery of large STR and SNP datasets in any species without needing a reference genome, and can be used even with suboptimal DNA more easily acquired in conservation and ecological studies. Published by Oxford University Press on behalf of Nucleic Acids Research 2017.
Malloy, Matt; Thiel, Brad; Bunday, Benjamin D.; Wurm, Stefan; Jindal, Vibhu; Mukhtar, Maseeh; Quoi, Kathy; Kemen, Thomas; Zeidler, Dirk; Eberle, Anna Lena; Garbowski, Tomasz; Dellemann, Gregor; Peters, Jan Hendrik
2015-09-01
The new device architectures and materials being introduced for sub-10nm manufacturing, combined with the complexity of multiple patterning and the need for improved hotspot detection strategies, have pushed current wafer inspection technologies to their limits. In parallel, gaps in mask inspection capability are growing as new generations of mask technologies are developed to support these sub-10nm wafer manufacturing requirements. In particular, the challenges associated with nanoimprint and extreme ultraviolet (EUV) mask inspection require new strategies that enable fast inspection at high sensitivity. The tradeoffs between sensitivity and throughput for optical and e-beam inspection are well understood. Optical inspection offers the highest throughput and is the current workhorse of the industry for both wafer and mask inspection. E-beam inspection offers the highest sensitivity but has historically lacked the throughput required for widespread adoption in the manufacturing environment. It is unlikely that continued incremental improvements to either technology will meet tomorrow's requirements, and therefore a new inspection technology approach is required; one that combines the high-throughput performance of optical with the high-sensitivity capabilities of e-beam inspection. To support the industry in meeting these challenges SUNY Poly SEMATECH has evaluated disruptive technologies that can meet the requirements for high volume manufacturing (HVM), for both the wafer fab [1] and the mask shop. Highspeed massively parallel e-beam defect inspection has been identified as the leading candidate for addressing the key gaps limiting today's patterned defect inspection techniques. As of late 2014 SUNY Poly SEMATECH completed a review, system analysis, and proof of concept evaluation of multiple e-beam technologies for defect inspection. A champion approach has been identified based on a multibeam technology from Carl Zeiss. This paper includes a discussion on the
Differences Between Distributed and Parallel Systems
Energy Technology Data Exchange (ETDEWEB)
Brightwell, R.; Maccabe, A.B.; Rissen, R.
1998-10-01
Distributed systems have been studied for twenty years and are now coming into wider use as fast networks and powerful workstations become more readily available. In many respects a massively parallel computer resembles a network of workstations and it is tempting to port a distributed operating system to such a machine. However, there are significant differences between these two environments and a parallel operating system is needed to get the best performance out of a massively parallel system. This report characterizes the differences between distributed systems, networks of workstations, and massively parallel systems and analyzes the impact of these differences on operating system design. In the second part of the report, we introduce Puma, an operating system specifically developed for massively parallel systems. We describe Puma portals, the basic building blocks for message passing paradigms implemented on top of Puma, and show how the differences observed in the first part of the report have influenced the design and implementation of Puma.
International Nuclear Information System (INIS)
Samatova, Nagiza F; Branstetter, Marcia; Ganguly, Auroop R; Hettich, Robert; Khan, Shiraj; Kora, Guruprasad; Li, Jiangtian; Ma, Xiaosong; Pan, Chongle; Shoshani, Arie; Yoginath, Srikanth
2006-01-01
Ultrascale computing and high-throughput experimental technologies have enabled the production of scientific data about complex natural phenomena. With this opportunity, comes a new problem - the massive quantities of data so produced. Answers to fundamental questions about the nature of those phenomena remain largely hidden in the produced data. The goal of this work is to provide a scalable high performance statistical data analysis framework to help scientists perform interactive analyses of these raw data to extract knowledge. Towards this goal we have been developing an open source parallel statistical analysis package, called Parallel R, that lets scientists employ a wide range of statistical analysis routines on high performance shared and distributed memory architectures without having to deal with the intricacies of parallelizing these routines
A massively parallel method of characteristic neutral particle transport code for GPUs
International Nuclear Information System (INIS)
Boyd, W. R.; Smith, K.; Forget, B.
2013-01-01
Over the past 20 years, parallel computing has enabled computers to grow ever larger and more powerful while scientific applications have advanced in sophistication and resolution. This trend is being challenged, however, as the power consumption for conventional parallel computing architectures has risen to unsustainable levels and memory limitations have come to dominate compute performance. Heterogeneous computing platforms, such as Graphics Processing Units (GPUs), are an increasingly popular paradigm for solving these issues. This paper explores the applicability of GPUs for deterministic neutron transport. A 2D method of characteristics (MOC) code - OpenMOC - has been developed with solvers for both shared memory multi-core platforms as well as GPUs. The multi-threading and memory locality methodologies for the GPU solver are presented. Performance results for the 2D C5G7 benchmark demonstrate 25-35 x speedup for MOC on the GPU. The lessons learned from this case study will provide the basis for further exploration of MOC on GPUs as well as design decisions for hardware vendors exploring technologies for the next generation of machines for scientific computing. (authors)
Treinish, Lloyd A.; Gough, Michael L.; Wildenhain, W. David
1987-01-01
The capability was developed of rapidly producing visual representations of large, complex, multi-dimensional space and earth sciences data sets via the implementation of computer graphics modeling techniques on the Massively Parallel Processor (MPP) by employing techniques recently developed for typically non-scientific applications. Such capabilities can provide a new and valuable tool for the understanding of complex scientific data, and a new application of parallel computing via the MPP. A prototype system with such capabilities was developed and integrated into the National Space Science Data Center's (NSSDC) Pilot Climate Data System (PCDS) data-independent environment for computer graphics data display to provide easy access to users. While developing these capabilities, several problems had to be solved independently of the actual use of the MPP, all of which are outlined.
Hegde, Ganapathi; Vaya, Pukhraj
2013-10-01
This article presents a parallel architecture for 3-D discrete wavelet transform (3-DDWT). The proposed design is based on the 1-D pipelined lifting scheme. The architecture is fully scalable beyond the present coherent Daubechies filter bank (9, 7). This 3-DDWT architecture has advantages such as no group of pictures restriction and reduced memory referencing. It offers low power consumption, low latency and high throughput. The computing technique is based on the concept that lifting scheme minimises the storage requirement. The application specific integrated circuit implementation of the proposed architecture is done by synthesising it using 65 nm Taiwan Semiconductor Manufacturing Company standard cell library. It offers a speed of 486 MHz with a power consumption of 2.56 mW. This architecture is suitable for real-time video compression even with large frame dimensions.
Keppenne, Christian L.; Rienecker, Michele; Borovikov, Anna Y.; Suarez, Max
1999-01-01
A massively parallel ensemble Kalman filter (EnKF)is used to assimilate temperature data from the TOGA/TAO array and altimetry from TOPEX/POSEIDON into a Pacific basin version of the NASA Seasonal to Interannual Prediction Project (NSIPP)ls quasi-isopycnal ocean general circulation model. The EnKF is an approximate Kalman filter in which the error-covariance propagation step is modeled by the integration of multiple instances of a numerical model. An estimate of the true error covariances is then inferred from the distribution of the ensemble of model state vectors. This inplementation of the filter takes advantage of the inherent parallelism in the EnKF algorithm by running all the model instances concurrently. The Kalman filter update step also occurs in parallel by having each processor process the observations that occur in the region of physical space for which it is responsible. The massively parallel data assimilation system is validated by withholding some of the data and then quantifying the extent to which the withheld information can be inferred from the assimilation of the remaining data. The distributions of the forecast and analysis error covariances predicted by the ENKF are also examined.
Sun, Degui; Wang, Na-Xin; He, Li-Ming; Weng, Zhao-Heng; Wang, Daheng; Chen, Ray T.
1996-06-01
A space-position-logic-encoding scheme is proposed and demonstrated. This encoding scheme not only makes the best use of the convenience of binary logic operation, but is also suitable for the trinary property of modified signed- digit (MSD) numbers. Based on the space-position-logic-encoding scheme, a fully parallel modified signed-digit adder and subtractor is built using optoelectronic switch technologies in conjunction with fiber-multistage 3D optoelectronic interconnects. Thus an effective combination of a parallel algorithm and a parallel architecture is implemented. In addition, the performance of the optoelectronic switches used in this system is experimentally studied and verified. Both the 3-bit experimental model and the experimental results of a parallel addition and a parallel subtraction are provided and discussed. Finally, the speed ratio between the MSD adder and binary adders is discussed and the advantage of the MSD in operating speed is demonstrated.
A 0.13-µm implementation of 5 Gb/s and 3-mW folded parallel architecture for AES algorithm
Rahimunnisa, K.; Karthigaikumar, P.; Kirubavathy, J.; Jayakumar, J.; Kumar, S. Suresh
2014-02-01
A new architecture for encrypting and decrypting the confidential data using Advanced Encryption Standard algorithm is presented in this article. This structure combines the folded structure with parallel architecture to increase the throughput. The whole architecture achieved high throughput with less power. The proposed architecture is implemented in 0.13-µm Complementary metal-oxide-semiconductor (CMOS) technology. The proposed structure is compared with different existing structures, and from the result it is proved that the proposed structure gives higher throughput and less power compared to existing works.
Lee, J.; Kim, K.
1991-01-01
A Very Large Scale Integration (VLSI) architecture for robot direct kinematic computation suitable for industrial robot manipulators was investigated. The Denavit-Hartenberg transformations are reviewed to exploit a proper processing element, namely an augmented CORDIC. Specifically, two distinct implementations are elaborated on, such as the bit-serial and parallel. Performance of each scheme is analyzed with respect to the time to compute one location of the end-effector of a 6-links manipulator, and the number of transistors required.
Lee, J.; Kim, K.
A Very Large Scale Integration (VLSI) architecture for robot direct kinematic computation suitable for industrial robot manipulators was investigated. The Denavit-Hartenberg transformations are reviewed to exploit a proper processing element, namely an augmented CORDIC. Specifically, two distinct implementations are elaborated on, such as the bit-serial and parallel. Performance of each scheme is analyzed with respect to the time to compute one location of the end-effector of a 6-links manipulator, and the number of transistors required.
International Nuclear Information System (INIS)
Paćko, P; Bielak, T; Staszewski, W J; Uhl, T; Spencer, A B; Worden, K
2012-01-01
This paper demonstrates new parallel computation technology and an implementation for Lamb wave propagation modelling in complex structures. A graphical processing unit (GPU) and computer unified device architecture (CUDA), available in low-cost graphical cards in standard PCs, are used for Lamb wave propagation numerical simulations. The local interaction simulation approach (LISA) wave propagation algorithm has been implemented as an example. Other algorithms suitable for parallel discretization can also be used in practice. The method is illustrated using examples related to damage detection. The results demonstrate good accuracy and effective computational performance of very large models. The wave propagation modelling presented in the paper can be used in many practical applications of science and engineering. (paper)
International Nuclear Information System (INIS)
Barsotti, E.; Booth, A.; Bowden, M.; Swoboda, C.; Lockyer, N.; Vanberg, R.
1990-01-01
A new era of high-energy physics research is beginning requiring accelerators with much higher luminosities and interaction rates in order to discover new elementary particles. As a consequence, both orders of magnitude higher data rates from the detector and online processing power, well beyond the capabilities of current high energy physics data acquisition systems, are required. This paper describes a proposed new data acquisition system architecture which draws heavily from the communications industry, is totally parallel (i.e., without any bottlenecks), is capable of data rates of hundreds of Gigabytes per second from the detector and into an array of online processors (i.e., processor farm), and uses an open systems architecture to guarantee compatibility with future commercially available online processor farms. The main features of the proposed Scalable Parallel Open Architecture data acquisition system are standard interface ICs to detector subsystems wherever possible, fiber optic digital data transmission from the near-detector electronics, a self-routing parallel event builder, and the use of industry-supported and high-level language programmable processors in the proposed BCD system for both triggers and online filters. A brief status report of an ongoing project at Fermilab to build a prototype of the proposed data acquisition system architecture is given in the paper. The major component of the system, a self-routing parallel event builder, is described in detail
Directory of Open Access Journals (Sweden)
Sonja Hall-Mendelin
Full Text Available Human disease incidence attributed to arbovirus infection is increasing throughout the world, with effective control interventions limited by issues of sustainability, insecticide resistance and the lack of effective vaccines. Several promising control strategies are currently under development, such as the release of mosquitoes trans-infected with virus-blocking Wolbachia bacteria. Implementation of any control program is dependent on effective virus surveillance and a thorough understanding of virus-vector interactions. Massively parallel sequencing has enormous potential for providing comprehensive genomic information that can be used to assess many aspects of arbovirus ecology, as well as to evaluate novel control strategies. To demonstrate proof-of-principle, we analyzed Aedes aegypti or Aedes albopictus experimentally infected with dengue, yellow fever or chikungunya viruses. Random amplification was used to prepare sufficient template for sequencing on the Personal Genome Machine. Viral sequences were present in all infected mosquitoes. In addition, in most cases, we were also able to identify the mosquito species and mosquito micro-organisms, including the bacterial endosymbiont Wolbachia. Importantly, naturally occurring Wolbachia strains could be differentiated from strains that had been trans-infected into the mosquito. The method allowed us to assemble near full-length viral genomes and detect other micro-organisms without prior sequence knowledge, in a single reaction. This is a step toward the application of massively parallel sequencing as an arbovirus surveillance tool. It has the potential to provide insight into virus transmission dynamics, and has applicability to the post-release monitoring of Wolbachia in mosquito populations.
Computations on the massively parallel processor at the Goddard Space Flight Center
Strong, James P.
1991-01-01
Described are four significant algorithms implemented on the massively parallel processor (MPP) at the Goddard Space Flight Center. Two are in the area of image analysis. Of the other two, one is a mathematical simulation experiment and the other deals with the efficient transfer of data between distantly separated processors in the MPP array. The first algorithm presented is the automatic determination of elevations from stereo pairs. The second algorithm solves mathematical logistic equations capable of producing both ordered and chaotic (or random) solutions. This work can potentially lead to the simulation of artificial life processes. The third algorithm is the automatic segmentation of images into reasonable regions based on some similarity criterion, while the fourth is an implementation of a bitonic sort of data which significantly overcomes the nearest neighbor interconnection constraints on the MPP for transferring data between distant processors.
Between history, criticism, and wit: texts and images of English modern architecture (1933-36
Directory of Open Access Journals (Sweden)
Michela Rosso
2016-06-01
Full Text Available It has often been remarked that modern architecture in Britain began late and that its emergence largely depended on the contribution of a massive influx of European exiles seeking refuge from the political and racial persecution of totalitarian regimes. In the attempt to discard the tired narrative of Britain’s insular modernism as a mere echo of continental European achievements, an alternative historiography has recently directed attention to Britain’s own distinctive and original version of modern architecture in the 1930s. Through the examination of a small group of articles, books and pamphlets on English modern architecture written by English authors and published in the mid-1930s, this paper argues that the emergence of a distinctive version of architectural modernism in Britain was paralleled by the development of an equally original brand of architectural criticism and historiography.
Operational Numerical Weather Prediction systems based on Linux cluster architectures
International Nuclear Information System (INIS)
Pasqui, M.; Baldi, M.; Gozzini, B.; Maracchi, G.; Giuliani, G.; Montagnani, S.
2005-01-01
The progress in weather forecast and atmospheric science has been always closely linked to the improvement of computing technology. In order to have more accurate weather forecasts and climate predictions, more powerful computing resources are needed, in addition to more complex and better-performing numerical models. To overcome such a large computing request, powerful workstations or massive parallel systems have been used. In the last few years, parallel architectures, based on the Linux operating system, have been introduced and became popular, representing real high performance-low cost systems. In this work the Linux cluster experience achieved at the Laboratory far Meteorology and Environmental Analysis (LaMMA-CNR-IBIMET) is described and tips and performances analysed
Energy Technology Data Exchange (ETDEWEB)
Verma, Prakash; Morales, Jorge A., E-mail: jorge.morales@ttu.edu [Department of Chemistry and Biochemistry, Texas Tech University, P.O. Box 41061, Lubbock, Texas 79409-1061 (United States); Perera, Ajith [Department of Chemistry and Biochemistry, Texas Tech University, P.O. Box 41061, Lubbock, Texas 79409-1061 (United States); Department of Chemistry, Quantum Theory Project, University of Florida, Gainesville, Florida 32611 (United States)
2013-11-07
Coupled cluster (CC) methods provide highly accurate predictions of molecular properties, but their high computational cost has precluded their routine application to large systems. Fortunately, recent computational developments in the ACES III program by the Bartlett group [the OED/ERD atomic integral package, the super instruction processor, and the super instruction architecture language] permit overcoming that limitation by providing a framework for massively parallel CC implementations. In that scheme, we are further extending those parallel CC efforts to systematically predict the three main electron spin resonance (ESR) tensors (A-, g-, and D-tensors) to be reported in a series of papers. In this paper inaugurating that series, we report our new ACES III parallel capabilities that calculate isotropic hyperfine coupling constants in 38 neutral, cationic, and anionic radicals that include the {sup 11}B, {sup 17}O, {sup 9}Be, {sup 19}F, {sup 1}H, {sup 13}C, {sup 35}Cl, {sup 33}S,{sup 14}N, {sup 31}P, and {sup 67}Zn nuclei. Present parallel calculations are conducted at the Hartree-Fock (HF), second-order many-body perturbation theory [MBPT(2)], CC singles and doubles (CCSD), and CCSD with perturbative triples [CCSD(T)] levels using Roos augmented double- and triple-zeta atomic natural orbitals basis sets. HF results consistently overestimate isotropic hyperfine coupling constants. However, inclusion of electron correlation effects in the simplest way via MBPT(2) provides significant improvements in the predictions, but not without occasional failures. In contrast, CCSD results are consistently in very good agreement with experimental results. Inclusion of perturbative triples to CCSD via CCSD(T) leads to small improvements in the predictions, which might not compensate for the extra computational effort at a non-iterative N{sup 7}-scaling in CCSD(T). The importance of these accurate computations of isotropic hyperfine coupling constants to elucidate
Corvino, R.; Diken, E.; Gamatié, A.; Jozwiak, L.
2012-01-01
In this paper, we present a method for the design of MPSoCs for complex data-intensive applications. This method aims at a blend exploration of the communication, the memory system architecture and the computation resource parallelism. The proposed method is exemplified on a JPEG Encoder case study
User's Guide for TOUGH2-MP - A Massively Parallel Version of the TOUGH2 Code
International Nuclear Information System (INIS)
Earth Sciences Division; Zhang, Keni; Zhang, Keni; Wu, Yu-Shu; Pruess, Karsten
2008-01-01
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 is 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
Cloud identification using genetic algorithms and massively parallel computation
Buckles, Bill P.; Petry, Frederick E.
1996-01-01
As a Guest Computational Investigator under the NASA administered component of the High Performance Computing and Communication Program, we implemented a massively parallel genetic algorithm on the MasPar SIMD computer. Experiments were conducted using Earth Science data in the domains of meteorology and oceanography. Results obtained in these domains are competitive with, and in most cases better than, similar problems solved using other methods. In the meteorological domain, we chose to identify clouds using AVHRR spectral data. Four cloud speciations were used although most researchers settle for three. Results were remarkedly consistent across all tests (91% accuracy). Refinements of this method may lead to more timely and complete information for Global Circulation Models (GCMS) that are prevalent in weather forecasting and global environment studies. In the oceanographic domain, we chose to identify ocean currents from a spectrometer having similar characteristics to AVHRR. Here the results were mixed (60% to 80% accuracy). Given that one is willing to run the experiment several times (say 10), then it is acceptable to claim the higher accuracy rating. This problem has never been successfully automated. Therefore, these results are encouraging even though less impressive than the cloud experiment. Successful conclusion of an automated ocean current detection system would impact coastal fishing, naval tactics, and the study of micro-climates. Finally we contributed to the basic knowledge of GA (genetic algorithm) behavior in parallel environments. We developed better knowledge of the use of subpopulations in the context of shared breeding pools and the migration of individuals. Rigorous experiments were conducted based on quantifiable performance criteria. While much of the work confirmed current wisdom, for the first time we were able to submit conclusive evidence. The software developed under this grant was placed in the public domain. An extensive user
Méthodes numériques pour les plasmas sur architectures multicoeurs
Massaro , Michel
2016-01-01
This thesis deals with the resolution of the Magneto-Hydro-Dynamic (MHD) system on massively parallel architectures. This problem is an hyperbolic system of conservation laws. For cost reasons in terms of time and space, we use the finite volume method. These criteria are particularly important in the case of MHD because the solutions obtained may have many shock waves and be very turbulent. The approach of a physical phenomenon requires working on a fine mesh which involves a large quantity ...
Exploiting Symmetry on Parallel Architectures.
Stiller, Lewis Benjamin
1995-01-01
This thesis describes techniques for the design of parallel programs that solve well-structured problems with inherent symmetry. Part I demonstrates the reduction of such problems to generalized matrix multiplication by a group-equivariant matrix. Fast techniques for this multiplication are described, including factorization, orbit decomposition, and Fourier transforms over finite groups. Our algorithms entail interaction between two symmetry groups: one arising at the software level from the problem's symmetry and the other arising at the hardware level from the processors' communication network. Part II illustrates the applicability of our symmetry -exploitation techniques by presenting a series of case studies of the design and implementation of parallel programs. First, a parallel program that solves chess endgames by factorization of an associated dihedral group-equivariant matrix is described. This code runs faster than previous serial programs, and discovered it a number of results. Second, parallel algorithms for Fourier transforms for finite groups are developed, and preliminary parallel implementations for group transforms of dihedral and of symmetric groups are described. Applications in learning, vision, pattern recognition, and statistics are proposed. Third, parallel implementations solving several computational science problems are described, including the direct n-body problem, convolutions arising from molecular biology, and some communication primitives such as broadcast and reduce. Some of our implementations ran orders of magnitude faster than previous techniques, and were used in the investigation of various physical phenomena.
Parallel integer sorting with medium and fine-scale parallelism
Dagum, Leonardo
1993-01-01
Two new parallel integer sorting algorithms, queue-sort and barrel-sort, are presented and analyzed in detail. These algorithms do not have optimal parallel complexity, yet they show very good performance in practice. Queue-sort designed for fine-scale parallel architectures which allow the queueing of multiple messages to the same destination. Barrel-sort is designed for medium-scale parallel architectures with a high message passing overhead. The performance results from the implementation of queue-sort on a Connection Machine CM-2 and barrel-sort on a 128 processor iPSC/860 are given. The two implementations are found to be comparable in performance but not as good as a fully vectorized bucket sort on the Cray YMP.
International Nuclear Information System (INIS)
Liu, H.
1996-01-01
Computer simulations using the multi-particle code PARMELA with a three-dimensional point-by-point space charge algorithm have turned out to be very helpful in supporting injector commissioning and operations at Thomas Jefferson National Accelerator Facility (Jefferson Lab, formerly called CEBAF). However, this algorithm, which defines a typical N 2 problem in CPU time scaling, is very time-consuming when N, the number of macro-particles, is large. Therefore, it is attractive to use massively parallel processors (MPPs) to speed up the simulations. Motivated by this, the authors modified the space charge subroutine for using the MPPs of the Cray T3D. The techniques used to parallelize and optimize the code on the T3D are discussed in this paper. The performance of the code on the T3D is examined in comparison with a Parallel Vector Processing supercomputer of the Cray C90 and an HP 735/15 high-end workstation
Directory of Open Access Journals (Sweden)
Fang Huang
2016-06-01
Full Text Available In some digital Earth engineering applications, spatial interpolation algorithms are required to process and analyze large amounts of data. Due to its powerful computing capacity, heterogeneous computing has been used in many applications for data processing in various fields. In this study, we explore the design and implementation of a parallel universal kriging spatial interpolation algorithm using the OpenCL programming model on heterogeneous computing platforms for massive Geo-spatial data processing. This study focuses primarily on transforming the hotspots in serial algorithms, i.e., the universal kriging interpolation function, into the corresponding kernel function in OpenCL. We also employ parallelization and optimization techniques in our implementation to improve the code performance. Finally, based on the results of experiments performed on two different high performance heterogeneous platforms, i.e., an NVIDIA graphics processing unit system and an Intel Xeon Phi system (MIC, we show that the parallel universal kriging algorithm can achieve the highest speedup of up to 40× with a single computing device and the highest speedup of up to 80× with multiple devices.
Scalable parallel prefix solvers for discrete ordinates transport
International Nuclear Information System (INIS)
Pautz, S.; Pandya, T.; Adams, M.
2009-01-01
The well-known 'sweep' algorithm for inverting the streaming-plus-collision term in first-order deterministic radiation transport calculations has some desirable numerical properties. However, it suffers from parallel scaling issues caused by a lack of concurrency. The maximum degree of concurrency, and thus the maximum parallelism, grows more slowly than the problem size for sweeps-based solvers. We investigate a new class of parallel algorithms that involves recasting the streaming-plus-collision problem in prefix form and solving via cyclic reduction. This method, although computationally more expensive at low levels of parallelism than the sweep algorithm, offers better theoretical scalability properties. Previous work has demonstrated this approach for one-dimensional calculations; we show how to extend it to multidimensional calculations. Notably, for multiple dimensions it appears that this approach is limited to long-characteristics discretizations; other discretizations cannot be cast in prefix form. We implement two variants of the algorithm within the radlib/SCEPTRE transport code library at Sandia National Laboratories and show results on two different massively parallel systems. Both the 'forward' and 'symmetric' solvers behave similarly, scaling well to larger degrees of parallelism then sweeps-based solvers. We do observe some issues at the highest levels of parallelism (relative to the system size) and discuss possible causes. We conclude that this approach shows good potential for future parallel systems, but the parallel scalability will depend heavily on the architecture of the communication networks of these systems. (authors)
A parallel-pipelined architecture for a multi carrier demodulator
Kwatra, S. C.; Jamali, M. M.; Eugene, Linus P.
1991-03-01
Analog devices have been used for processing the information on board the satellites. Presently, digital devices are being used because they are economical and flexible as compared to their analog counterparts. Several schemes of digital transmission can be used depending on the data rate requirement of the user. An economical scheme of transmission for small earth stations uses single channel per carrier/frequency division multiple access (SCPC/FDMA) on the uplink and time division multiplexing (TDM) on the downlink. This is a typical communication service offered to low data rate users in commercial mass market. These channels usually pertain to either voice or data transmission. An efficient digital demodulator architecture is provided for a large number of law data rate users. A demodulator primarily consists of carrier, clock, and data recovery modules. This design uses principles of parallel processing, pipelining, and time sharing schemes to process large numbers of voice or data channels. It maintains the optimum throughput which is derived from the designed architecture and from the use of high speed components. The design is optimized for reduced power and area requirements. This is essential for satellite applications. The design is also flexible in processing a group of a varying number of channels. The algorithms that are used are verified by the use of a computer aided software engineering (CASE) tool called the Block Oriented System Simulator. The data flow, control circuitry, and interface of the hardware design is simulated in C language. Also, a multiprocessor approach is provided to map, model, and simulate the demodulation algorithms mainly from a speed view point. A hypercude based architecture implementation is provided for such a scheme of operation. The hypercube structure and the demodulation models on hypercubes are simulated in Ada.
Energy Technology Data Exchange (ETDEWEB)
Amadio, G.; et al.
2017-11-22
An intensive R&D and programming effort is required to accomplish new challenges posed by future experimental high-energy particle physics (HEP) programs. The GeantV project aims to narrow the gap between the performance of the existing HEP detector simulation software and the ideal performance achievable, exploiting latest advances in computing technology. The project has developed a particle detector simulation prototype capable of transporting in parallel particles in complex geometries exploiting instruction level microparallelism (SIMD and SIMT), task-level parallelism (multithreading) and high-level parallelism (MPI), leveraging both the multi-core and the many-core opportunities. We present preliminary verification results concerning the electromagnetic (EM) physics models developed for parallel computing architectures within the GeantV project. In order to exploit the potential of vectorization and accelerators and to make the physics model effectively parallelizable, advanced sampling techniques have been implemented and tested. In this paper we introduce a set of automated statistical tests in order to verify the vectorized models by checking their consistency with the corresponding Geant4 models and to validate them against experimental data.
A study of objective functions for organs with parallel and serial architecture
International Nuclear Information System (INIS)
Stavrev, P.V.; Stavreva, N.A.; Round, W.H.
1997-01-01
An objective function analysis when target volumes are deliberately enlarged to account for tumour mobility and consecutive uncertainty in the tumour position in external beam radiotherapy has been carried out. The dose distribution inside the tumour is assumed to have logarithmic dependence on the tumour cell density which assures an iso-local tumour control probability. The normal tissue immediately surrounding the tumour is irradiated homogeneously at a dose level equal to the dose D(R)) delivered at the edge of the tumour The normal tissue in the high dose field is modelled as being organized in identical functional subunits (FSUs) composed of a relatively large number of cells. Two types of organs - having serial and parallel architecture are considered. Implicit averaging over intrapatient normal tissue radiosensitivity variations is done. A function describing the normal tissue survival probability S 0 is constructed. The objective function is given as a product of the total tumour control probability (TCP) and the normal tissue survival probability S 0 . The values of the dose D(R)) which result in a maximum of the objective function are obtained for different combinations of tumour and normal tissue parameters, such as tumour and normal tissue radiosensitivities, number of cells constituting a normal tissue functional unit, total number of normal cells under high dose (D(R)) exposure and functional reserve for organs having parallel architecture. The corresponding TCP and S 0 values are computed and discussed. (authors)
A Massively Scalable Architecture for Instant Messaging & Presence
Schippers, Jorrit; Remke, Anne Katharina Ingrid; Punt, Henk; Wegdam, M.; Haverkort, Boudewijn R.H.M.; Thomas, N.; Bradley, J.; Knottenbelt, W.; Dingle, N.; Harder, U.
2010-01-01
This paper analyzes the scalability of Instant Messaging & Presence (IM&P) architectures. We take a queueing-based modelling and analysis approach to ��?nd the bottlenecks of the current IM&P architecture at the Dutch social network Hyves, as well as of alternative architectures. We use the
Revealing the Physics of Galactic Winds Through Massively-Parallel Hydrodynamics Simulations
Schneider, Evan Elizabeth
This thesis documents the hydrodynamics code Cholla and a numerical study of multiphase galactic winds. Cholla is a massively-parallel, GPU-based code designed for astrophysical simulations that is freely available to the astrophysics community. A static-mesh Eulerian code, Cholla is ideally suited to carrying out massive simulations (> 20483 cells) that require very high resolution. The code incorporates state-of-the-art hydrodynamics algorithms including third-order spatial reconstruction, exact and linearized Riemann solvers, and unsplit integration algorithms that account for transverse fluxes on multidimensional grids. Operator-split radiative cooling and a dual-energy formalism for high mach number flows are also included. An extensive test suite demonstrates Cholla's superior ability to model shocks and discontinuities, while the GPU-native design makes the code extremely computationally efficient - speeds of 5-10 million cell updates per GPU-second are typical on current hardware for 3D simulations with all of the aforementioned physics. The latter half of this work comprises a comprehensive study of the mixing between a hot, supernova-driven wind and cooler clouds representative of those observed in multiphase galactic winds. Both adiabatic and radiatively-cooling clouds are investigated. The analytic theory of cloud-crushing is applied to the problem, and adiabatic turbulent clouds are found to be mixed with the hot wind on similar timescales as the classic spherical case (4-5 t cc) with an appropriate rescaling of the cloud-crushing time. Radiatively cooling clouds survive considerably longer, and the differences in evolution between turbulent and spherical clouds cannot be reconciled with a simple rescaling. The rapid incorporation of low-density material into the hot wind implies efficient mass-loading of hot phases of galactic winds. At the same time, the extreme compression of high-density cloud material leads to long-lived but slow-moving clumps
International Nuclear Information System (INIS)
Matsunoshita, Jun-ichi; Akamatsu, Shigeo; Yamamoto, Shinji.
1993-01-01
This paper describes about the system architecture of a new image recognition system TOPS (top-down parallel pattern recognition system), and its application to the automatic extraction of brain organs (cerebrum, cerebellum, brain stem) from 3D-MRI images. Main concepts of TOPS are as follows: (1) TOPS is the top-down type recognition system, which allows parallel models in each level of hierarchy structure. (2) TOPS allows parallel image processing algorithms for one purpose (for example, for extraction of one special organ). This results in multiple candidates for one purpose, and judgment to get unique solution for it will be made at upper level of hierarchy structure. (author)
SWAMP+: multiple subsequence alignment using associative massive parallelism
Energy Technology Data Exchange (ETDEWEB)
Steinfadt, Shannon Irene [Los Alamos National Laboratory; Baker, Johnnie W [KENT STATE UNIV.
2010-10-18
A new parallel algorithm SWAMP+ incorporates the Smith-Waterman sequence alignment on an associative parallel model known as ASC. It is a highly sensitive parallel approach that expands traditional pairwise sequence alignment. This is the first parallel algorithm to provide multiple non-overlapping, non-intersecting subsequence alignments with the accuracy of Smith-Waterman. The efficient algorithm provides multiple alignments similar to BLAST while creating a better workflow for the end users. The parallel portions of the code run in O(m+n) time using m processors. When m = n, the algorithmic analysis becomes O(n) with a coefficient of two, yielding a linear speedup. Implementation of the algorithm on the SIMD ClearSpeed CSX620 confirms this theoretical linear speedup with real timings.
Parallel algorithms for mapping pipelined and parallel computations
Nicol, David M.
1988-01-01
Many computational problems in image processing, signal processing, and scientific computing are naturally structured for either pipelined or parallel computation. When mapping such problems onto a parallel architecture it is often necessary to aggregate an obvious problem decomposition. Even in this context the general mapping problem is known to be computationally intractable, but recent advances have been made in identifying classes of problems and architectures for which optimal solutions can be found in polynomial time. Among these, the mapping of pipelined or parallel computations onto linear array, shared memory, and host-satellite systems figures prominently. This paper extends that work first by showing how to improve existing serial mapping algorithms. These improvements have significantly lower time and space complexities: in one case a published O(nm sup 3) time algorithm for mapping m modules onto n processors is reduced to an O(nm log m) time complexity, and its space requirements reduced from O(nm sup 2) to O(m). Run time complexity is further reduced with parallel mapping algorithms based on these improvements, which run on the architecture for which they create the mappings.
Laurie, Matthew T; Bertout, Jessica A; Taylor, Sean D; Burton, Joshua N; Shendure, Jay A; Bielas, Jason H
2013-08-01
Due to the high cost of failed runs and suboptimal data yields, quantification and determination of fragment size range are crucial steps in the library preparation process for massively parallel sequencing (or next-generation sequencing). Current library quality control methods commonly involve quantification using real-time quantitative PCR and size determination using gel or capillary electrophoresis. These methods are laborious and subject to a number of significant limitations that can make library calibration unreliable. Herein, we propose and test an alternative method for quality control of sequencing libraries using droplet digital PCR (ddPCR). By exploiting a correlation we have discovered between droplet fluorescence and amplicon size, we achieve the joint quantification and size determination of target DNA with a single ddPCR assay. We demonstrate the accuracy and precision of applying this method to the preparation of sequencing libraries.
Architecture and VHDL behavioural validation of a parallel processor dedicated to computer vision
International Nuclear Information System (INIS)
Collette, Thierry
1992-01-01
Speeding up image processing is mainly obtained using parallel computers; SIMD processors (single instruction stream, multiple data stream) have been developed, and have proven highly efficient regarding low-level image processing operations. Nevertheless, their performances drop for most intermediate of high level operations, mainly when random data reorganisations in processor memories are involved. The aim of this thesis was to extend the SIMD computer capabilities to allow it to perform more efficiently at the image processing intermediate level. The study of some representative algorithms of this class, points out the limits of this computer. Nevertheless, these limits can be erased by architectural modifications. This leads us to propose SYMPATIX, a new SIMD parallel computer. To valid its new concept, a behavioural model written in VHDL - Hardware Description Language - has been elaborated. With this model, the new computer performances have been estimated running image processing algorithm simulations. VHDL modeling approach allows to perform the system top down electronic design giving an easy coupling between system architectural modifications and their electronic cost. The obtained results show SYMPATIX to be an efficient computer for low and intermediate level image processing. It can be connected to a high level computer, opening up the development of new computer vision applications. This thesis also presents, a top down design method, based on the VHDL, intended for electronic system architects. (author) [fr
Energy Technology Data Exchange (ETDEWEB)
2017-04-04
A parallelization of the k-means++ seed selection algorithm on three distinct hardware platforms: GPU, multicore CPU, and multithreaded architecture. K-means++ was developed by David Arthur and Sergei Vassilvitskii in 2007 as an extension of the k-means data clustering technique. These algorithms allow people to cluster multidimensional data, by attempting to minimize the mean distance of data points within a cluster. K-means++ improved upon traditional k-means by using a more intelligent approach to selecting the initial seeds for the clustering process. While k-means++ has become a popular alternative to traditional k-means clustering, little work has been done to parallelize this technique. We have developed original C++ code for parallelizing the algorithm on three unique hardware architectures: GPU using NVidia's CUDA/Thrust framework, multicore CPU using OpenMP, and the Cray XMT multithreaded architecture. By parallelizing the process for these platforms, we are able to perform k-means++ clustering much more quickly than it could be done before.
Parallel processing for fluid dynamics applications
International Nuclear Information System (INIS)
Johnson, G.M.
1989-01-01
The impact of parallel processing on computational science and, in particular, on computational fluid dynamics is growing rapidly. In this paper, particular emphasis is given to developments which have occurred within the past two years. Parallel processing is defined and the reasons for its importance in high-performance computing are reviewed. Parallel computer architectures are classified according to the number and power of their processing units, their memory, and the nature of their connection scheme. Architectures which show promise for fluid dynamics applications are emphasized. Fluid dynamics problems are examined for parallelism inherent at the physical level. CFD algorithms and their mappings onto parallel architectures are discussed. Several example are presented to document the performance of fluid dynamics applications on present-generation parallel processing devices
Statistical method to compare massive parallel sequencing pipelines.
Elsensohn, M H; Leblay, N; Dimassi, S; Campan-Fournier, A; Labalme, A; Roucher-Boulez, F; Sanlaville, D; Lesca, G; Bardel, C; Roy, P
2017-03-01
Today, sequencing is frequently carried out by Massive Parallel Sequencing (MPS) that cuts drastically sequencing time and expenses. Nevertheless, Sanger sequencing remains the main validation method to confirm the presence of variants. The analysis of MPS data involves the development of several bioinformatic tools, academic or commercial. We present here a statistical method to compare MPS pipelines and test it in a comparison between an academic (BWA-GATK) and a commercial pipeline (TMAP-NextGENe®), with and without reference to a gold standard (here, Sanger sequencing), on a panel of 41 genes in 43 epileptic patients. This method used the number of variants to fit log-linear models for pairwise agreements between pipelines. To assess the heterogeneity of the margins and the odds ratios of agreement, four log-linear models were used: a full model, a homogeneous-margin model, a model with single odds ratio for all patients, and a model with single intercept. Then a log-linear mixed model was fitted considering the biological variability as a random effect. Among the 390,339 base-pairs sequenced, TMAP-NextGENe® and BWA-GATK found, on average, 2253.49 and 1857.14 variants (single nucleotide variants and indels), respectively. Against the gold standard, the pipelines had similar sensitivities (63.47% vs. 63.42%) and close but significantly different specificities (99.57% vs. 99.65%; p < 0.001). Same-trend results were obtained when only single nucleotide variants were considered (99.98% specificity and 76.81% sensitivity for both pipelines). The method allows thus pipeline comparison and selection. It is generalizable to all types of MPS data and all pipelines.
Wideband aperture array using RF channelizers and massively parallel digital 2D IIR filterbank
Sengupta, Arindam; Madanayake, Arjuna; Gómez-García, Roberto; Engeberg, Erik D.
2014-05-01
Wideband receive-mode beamforming applications in wireless location, electronically-scanned antennas for radar, RF sensing, microwave imaging and wireless communications require digital aperture arrays that offer a relatively constant far-field beam over several octaves of bandwidth. Several beamforming schemes including the well-known true time-delay and the phased array beamformers have been realized using either finite impulse response (FIR) or fast Fourier transform (FFT) digital filter-sum based techniques. These beamforming algorithms offer the desired selectivity at the cost of a high computational complexity and frequency-dependant far-field array patterns. A novel approach to receiver beamforming is the use of massively parallel 2-D infinite impulse response (IIR) fan filterbanks for the synthesis of relatively frequency independent RF beams at an order of magnitude lower multiplier complexity compared to FFT or FIR filter based conventional algorithms. The 2-D IIR filterbanks demand fast digital processing that can support several octaves of RF bandwidth, fast analog-to-digital converters (ADCs) for RF-to-bits type direct conversion of wideband antenna element signals. Fast digital implementation platforms that can realize high-precision recursive filter structures necessary for real-time beamforming, at RF radio bandwidths, are also desired. We propose a novel technique that combines a passive RF channelizer, multichannel ADC technology, and single-phase massively parallel 2-D IIR digital fan filterbanks, realized at low complexity using FPGA and/or ASIC technology. There exists native support for a larger bandwidth than the maximum clock frequency of the digital implementation technology. We also strive to achieve More-than-Moore throughput by processing a wideband RF signal having content with N-fold (B = N Fclk/2) bandwidth compared to the maximum clock frequency Fclk Hz of the digital VLSI platform under consideration. Such increase in bandwidth is
Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures
Energy Technology Data Exchange (ETDEWEB)
Cerati, Giuseppe [Fermilab; Elmer, Peter [Princeton U.; Krutelyov, Slava [UC, San Diego; Lantz, Steven [Cornell U., Phys. Dept.; Lefebvre, Matthieu [Princeton U.; Masciovecchio, Mario [UC, San Diego; McDermott, Kevin [Cornell U., Phys. Dept.; Riley, Daniel [Cornell U., Phys. Dept.; Tadel, Matevž [UC, San Diego; Wittich, Peter [Cornell U., Phys. Dept.; Würthwein, Frank [UC, San Diego; Yagil, Avi [UC, San Diego
2017-11-16
Faced with physical and energy density limitations on clock speed, contemporary microprocessor designers have increasingly turned to on-chip parallelism for performance gains. Examples include the Intel Xeon Phi, GPGPUs, and similar technologies. Algorithms should accordingly be designed with ample amounts of fine-grained parallelism if they are to realize the full performance of the hardware. This requirement can be challenging for algorithms that are naturally expressed as a sequence of small-matrix operations, such as the Kalman filter methods widely in use in high-energy physics experiments. In the High-Luminosity Large Hadron Collider (HL-LHC), for example, one of the dominant computational problems is expected to be finding and fitting charged-particle tracks during event reconstruction; today, the most common track-finding methods are those based on the Kalman filter. Experience at the LHC, both in the trigger and offline, has shown that these methods are robust and provide high physics performance. Previously we reported the significant parallel speedups that resulted from our efforts to adapt Kalman-filter-based tracking to many-core architectures such as Intel Xeon Phi. Here we report on how effectively those techniques can be applied to more realistic detector configurations and event complexity.
Comments on “Techniques and Architectures for Hazard-Free Semi-Parallel Decoding of LDPC Codes”
Directory of Open Access Journals (Sweden)
Mark B. Yeary
2009-01-01
Full Text Available This is a comment article on the publication “Techniques and Architectures for Hazard-Free Semi-Parallel Decoding of LDPC Codes” Rovini et al. (2009. We mention that there has been similar work reported in the literature before, and the previous work has not been cited correctly, for example Gunnam et al. (2006, 2007. This brief note serves to clarify these issues.
High performance 3D neutron transport on peta scale and hybrid architectures within APOLLO3 code
International Nuclear Information System (INIS)
Jamelot, E.; Dubois, J.; Lautard, J-J.; Calvin, C.; Baudron, A-M.
2011-01-01
APOLLO3 code is a common project of CEA, AREVA and EDF for the development of a new generation system for core physics analysis. We present here the parallelization of two deterministic transport solvers of APOLLO3: MINOS, a simplified 3D transport solver on structured Cartesian and hexagonal grids, and MINARET, a transport solver based on triangular meshes on 2D and prismatic ones in 3D. We used two different techniques to accelerate MINOS: a domain decomposition method, combined with an accelerated algorithm using GPU. The domain decomposition is based on the Schwarz iterative algorithm, with Robin boundary conditions to exchange information. The Robin parameters influence the convergence and we detail how we optimized the choice of these parameters. MINARET parallelization is based on angular directions calculation using explicit message passing. Fine grain parallelization is also available for each angular direction using shared memory multithreaded acceleration. Many performance results are presented on massively parallel architectures using more than 103 cores and on hybrid architectures using some tens of GPUs. This work contributes to the HPC development in reactor physics at the CEA Nuclear Energy Division. (author)
Directory of Open Access Journals (Sweden)
Asker Noomi
2009-07-01
Full Text Available Abstract Background The teleost Zoarces viviparus (eelpout lives along the coasts of Northern Europe and has long been an established model organism for marine ecology and environmental monitoring. The scarce information about this species genome has however restrained the use of efficient molecular-level assays, such as gene expression microarrays. Results In the present study we present the first comprehensive characterization of the Zoarces viviparus liver transcriptome. From 400,000 reads generated by massively parallel pyrosequencing, more than 50,000 pieces of putative transcripts were assembled, annotated and functionally classified. The data was estimated to cover roughly 40% of the total transcriptome and homologues for about half of the genes of Gasterosteus aculeatus (stickleback were identified. The sequence data was consequently used to design an oligonucleotide microarray for large-scale gene expression analysis. Conclusion Our results show that one run using a Genome Sequencer FLX from 454 Life Science/Roche generates enough genomic information for adequate de novo assembly of a large number of genes in a higher vertebrate. The generated sequence data, including the validated microarray probes, are publicly available to promote genome-wide research in Zoarces viviparus.
High performance parallel computing of flows in complex geometries: I. Methods
International Nuclear Information System (INIS)
Gourdain, N; Gicquel, L; Montagnac, M; Vermorel, O; Staffelbach, G; Garcia, M; Boussuge, J-F; Gazaix, M; Poinsot, T
2009-01-01
Efficient numerical tools coupled with high-performance computers, have become a key element of the design process in the fields of energy supply and transportation. However flow phenomena that occur in complex systems such as gas turbines and aircrafts are still not understood mainly because of the models that are needed. In fact, most computational fluid dynamics (CFD) predictions as found today in industry focus on a reduced or simplified version of the real system (such as a periodic sector) and are usually solved with a steady-state assumption. This paper shows how to overcome such barriers and how such a new challenge can be addressed by developing flow solvers running on high-end computing platforms, using thousands of computing cores. Parallel strategies used by modern flow solvers are discussed with particular emphases on mesh-partitioning, load balancing and communication. Two examples are used to illustrate these concepts: a multi-block structured code and an unstructured code. Parallel computing strategies used with both flow solvers are detailed and compared. This comparison indicates that mesh-partitioning and load balancing are more straightforward with unstructured grids than with multi-block structured meshes. However, the mesh-partitioning stage can be challenging for unstructured grids, mainly due to memory limitations of the newly developed massively parallel architectures. Finally, detailed investigations show that the impact of mesh-partitioning on the numerical CFD solutions, due to rounding errors and block splitting, may be of importance and should be accurately addressed before qualifying massively parallel CFD tools for a routine industrial use.
International Nuclear Information System (INIS)
Woodruff, S.B.
1992-01-01
The Transient Reactor Analysis Code (TRAC), which features a two- fluid treatment of thermal-hydraulics, is designed to model transients in water reactors and related facilities. One of the major computational costs associated with TRAC and similar codes is calculating constitutive coefficients. Although the formulations for these coefficients are local the costs are flow-regime- or data-dependent; i.e., the computations needed for a given spatial node often vary widely as a function of time. Consequently, poor load balancing will degrade efficiency on either vector or data parallel architectures when the data are organized according to spatial location. Unfortunately, a general automatic solution to the load-balancing problem associated with data-dependent computations is not yet available for massively parallel architectures. This document discusses why developers algorithms, such as a neural net representation, that do not exhibit algorithms, such as a neural net representation, that do not exhibit load-balancing problems
A Case Study of a Hybrid Parallel 3D Surface Rendering Graphics Architecture
DEFF Research Database (Denmark)
Holten-Lund, Hans Erik; Madsen, Jan; Pedersen, Steen
1997-01-01
This paper presents a case study in the design strategy used inbuilding a graphics computer, for drawing very complex 3Dgeometric surfaces. The goal is to build a PC based computer systemcapable of handling surfaces built from about 2 million triangles, andto be able to render a perspective view...... of these on a computer displayat interactive frame rates, i.e. processing around 50 milliontriangles per second. The paper presents a hardware/softwarearchitecture called HPGA (Hybrid Parallel Graphics Architecture) whichis likely to be able to carry out this task. The case study focuses ontechniques to increase...
Eduardoff, M; Gross, T E; Santos, C; de la Puente, M; Ballard, D; Strobl, C; Børsting, C; Morling, N; Fusco, L; Hussing, C; Egyed, B; Souto, L; Uacyisrael, J; Syndercombe Court, D; Carracedo, Á; Lareu, M V; Schneider, P M; Parson, W; Phillips, C; Parson, W; Phillips, C
2016-07-01
The EUROFORGEN Global ancestry-informative SNP (AIM-SNPs) panel is a forensic multiplex of 128 markers designed to differentiate an individual's ancestry from amongst the five continental population groups of Africa, Europe, East Asia, Native America, and Oceania. A custom multiplex of AmpliSeq™ PCR primers was designed for the Global AIM-SNPs to perform massively parallel sequencing using the Ion PGM™ system. This study assessed individual SNP genotyping precision using the Ion PGM™, the forensic sensitivity of the multiplex using dilution series, degraded DNA plus simple mixtures, and the ancestry differentiation power of the final panel design, which required substitution of three original ancestry-informative SNPs with alternatives. Fourteen populations that had not been previously analyzed were genotyped using the custom multiplex and these studies allowed assessment of genotyping performance by comparison of data across five laboratories. Results indicate a low level of genotyping error can still occur from sequence misalignment caused by homopolymeric tracts close to the target SNP, despite careful scrutiny of candidate SNPs at the design stage. Such sequence misalignment required the exclusion of component SNP rs2080161 from the Global AIM-SNPs panel. However, the overall genotyping precision and sensitivity of this custom multiplex indicates the Ion PGM™ assay for the Global AIM-SNPs is highly suitable for forensic ancestry analysis with massively parallel sequencing. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.
Arkin, Ethem; Tekinerdogan, Bedir; Imre, Kayhan M.
2017-01-01
The need for high-performance computing together with the increasing trend from single processor to parallel computer architectures has leveraged the adoption of parallel computing. To benefit from parallel computing power, usually parallel algorithms are defined that can be mapped and executed
DEFF Research Database (Denmark)
Jensen, Lars Baunegaard With
. The current top model GPUs from NVIDIA possess up to 240 homogeneous cores. In the past, GPUs have beenhard to program, forcing the programmer to map the algorithm to the graphics processing pipeline and think in terms of vertex and fragment shaders, imposing a limiting factor in the implementation of non......-graphics applications. This, however, has changed with the introduction of the Compute Unified Device Architecture (CUDA) framework from NVIDIA. The EV and ECV stages have different parallel properties. The regular, pixel-based processing of EV fit the GPU architecture very well, and parts of ECV, on the other hand...
Parallel Monte Carlo reactor neutronics
International Nuclear Information System (INIS)
Blomquist, R.N.; Brown, F.B.
1994-01-01
The issues affecting implementation of parallel algorithms for large-scale engineering Monte Carlo neutron transport simulations are discussed. For nuclear reactor calculations, these include load balancing, recoding effort, reproducibility, domain decomposition techniques, I/O minimization, and strategies for different parallel architectures. Two codes were parallelized and tested for performance. The architectures employed include SIMD, MIMD-distributed memory, and workstation network with uneven interactive load. Speedups linear with the number of nodes were achieved
Ltaief, Hatem
2012-01-01
The objective of this paper is to enhance the parallelism of the tile bidiagonal transformation using tree reduction on multicore architectures. First introduced by Ltaief et. al [LAPACK Working Note #247, 2011], the bidiagonal transformation using tile algorithms with a two-stage approach has shown very promising results on square matrices. However, for tall and skinny matrices, the inherent problem of processing the panel in a domino-like fashion generates unnecessary sequential tasks. By using tree reduction, the panel is horizontally split, which creates another dimension of parallelism and engenders many concurrent tasks to be dynamically scheduled on the available cores. The results reported in this paper are very encouraging. The new tile bidiagonal transformation, targeting tall and skinny matrices, outperforms the state-of-the-art numerical linear algebra libraries LAPACK V3.2 and Intel MKL ver. 10.3 by up to 29-fold speedup and the standard two-stage PLASMA BRD by up to 20-fold speedup, on an eight socket hexa-core AMD Opteron multicore shared-memory system. © 2012 Springer-Verlag.
Parallel computing techniques for rotorcraft aerodynamics
Ekici, Kivanc
The modification of unsteady three-dimensional Navier-Stokes codes for application on massively parallel and distributed computing environments is investigated. The Euler/Navier-Stokes code TURNS (Transonic Unsteady Rotor Navier-Stokes) was chosen as a test bed because of its wide use by universities and industry. For the efficient implementation of TURNS on parallel computing systems, two algorithmic changes are developed. First, main modifications to the implicit operator, Lower-Upper Symmetric Gauss Seidel (LU-SGS) originally used in TURNS, is performed. Second, application of an inexact Newton method, coupled with a Krylov subspace iterative method (Newton-Krylov method) is carried out. Both techniques have been tried previously for the Euler equations mode of the code. In this work, we have extended the methods to the Navier-Stokes mode. Several new implicit operators were tried because of convergence problems of traditional operators with the high cell aspect ratio (CAR) grids needed for viscous calculations on structured grids. Promising results for both Euler and Navier-Stokes cases are presented for these operators. For the efficient implementation of Newton-Krylov methods to the Navier-Stokes mode of TURNS, efficient preconditioners must be used. The parallel implicit operators used in the previous step are employed as preconditioners and the results are compared. The Message Passing Interface (MPI) protocol has been used because of its portability to various parallel architectures. It should be noted that the proposed methodology is general and can be applied to several other CFD codes (e.g. OVERFLOW).
Directory of Open Access Journals (Sweden)
Dwi Purnomo
2015-08-01
Full Text Available Register is one of the computer components that have a key role in computer organisation. Every computer contains millions of registers that are manifested by flip-flop. This research focuses on the investigation of flip-flop performance based on its type (D, T, S-R, and J-K and architecture (structural, behavioural, and hybrid. Each type of flip-flop on each architecture would be tested in different bit of shift register with parallel load applications. The experiment criteria that will be assessed are power consumption, resources required, memory required, latency, and efficiency. Based on the experiment, it could be shown that D flip-flop and hybrid architecture showed the best performance in required memory, latency, power consumption, and efficiency. In addition, the experiment results showed that the greater the register number, the less efficient the system would be.
Evaluating the performance of the particle finite element method in parallel architectures
Gimenez, Juan M.; Nigro, Norberto M.; Idelsohn, Sergio R.
2014-05-01
This paper presents a high performance implementation for the particle-mesh based method called particle finite element method two (PFEM-2). It consists of a material derivative based formulation of the equations with a hybrid spatial discretization which uses an Eulerian mesh and Lagrangian particles. The main aim of PFEM-2 is to solve transport equations as fast as possible keeping some level of accuracy. The method was found to be competitive with classical Eulerian alternatives for these targets, even in their range of optimal application. To evaluate the goodness of the method with large simulations, it is imperative to use of parallel environments. Parallel strategies for Finite Element Method have been widely studied and many libraries can be used to solve Eulerian stages of PFEM-2. However, Lagrangian stages, such as streamline integration, must be developed considering the parallel strategy selected. The main drawback of PFEM-2 is the large amount of memory needed, which limits its application to large problems with only one computer. Therefore, a distributed-memory implementation is urgently needed. Unlike a shared-memory approach, using domain decomposition the memory is automatically isolated, thus avoiding race conditions; however new issues appear due to data distribution over the processes. Thus, a domain decomposition strategy for both particle and mesh is adopted, which minimizes the communication between processes. Finally, performance analysis running over multicore and multinode architectures are presented. The Courant-Friedrichs-Lewy number used influences the efficiency of the parallelization and, in some cases, a weighted partitioning can be used to improve the speed-up. However the total cputime for cases presented is lower than that obtained when using classical Eulerian strategies.
Yarovyi, Andrii A.; Timchenko, Leonid I.; Kozhemiako, Volodymyr P.; Kokriatskaia, Nataliya I.; Hamdi, Rami R.; Savchuk, Tamara O.; Kulyk, Oleksandr O.; Surtel, Wojciech; Amirgaliyev, Yedilkhan; Kashaganova, Gulzhan
2017-08-01
The paper deals with a problem of insufficient productivity of existing computer means for large image processing, which do not meet modern requirements posed by resource-intensive computing tasks of laser beam profiling. The research concentrated on one of the profiling problems, namely, real-time processing of spot images of the laser beam profile. Development of a theory of parallel-hierarchic transformation allowed to produce models for high-performance parallel-hierarchical processes, as well as algorithms and software for their implementation based on the GPU-oriented architecture using GPGPU technologies. The analyzed performance of suggested computerized tools for processing and classification of laser beam profile images allows to perform real-time processing of dynamic images of various sizes.
Parallel peak pruning for scalable SMP contour tree computation
Energy Technology Data Exchange (ETDEWEB)
Carr, Hamish A. [Univ. of Leeds (United Kingdom); Weber, Gunther H. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Davis, CA (United States); Sewell, Christopher M. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Ahrens, James P. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2017-03-09
As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Here in this paper, we report the first shared SMP algorithm for fully parallel contour tree computation, withfor-mal guarantees of O(lgnlgt) parallel steps and O(n lgn) work, and implementations with up to 10x parallel speed up in OpenMP and up to 50x speed up in NVIDIA Thrust.
International Nuclear Information System (INIS)
Dubois, J.
2011-01-01
In science, simulation is a key process for research or validation. Modern computer technology allows faster numerical experiments, which are cheaper than real models. In the field of neutron simulation, the calculation of eigenvalues is one of the key challenges. The complexity of these problems is such that a lot of computing power may be necessary. The work of this thesis is first the evaluation of new computing hardware such as graphics card or massively multi-core chips, and their application to eigenvalue problems for neutron simulation. Then, in order to address the massive parallelism of supercomputers national, we also study the use of asynchronous hybrid methods for solving eigenvalue problems with this very high level of parallelism. Then we experiment the work of this research on several national supercomputers such as the Titane hybrid machine of the Computing Center, Research and Technology (CCRT), the Curie machine of the Very Large Computing Centre (TGCC), currently being installed, and the Hopper machine at the Lawrence Berkeley National Laboratory (LBNL). We also do our experiments on local workstations to illustrate the interest of this research in an everyday use with local computing resources. (author) [fr
High fidelity thermal-hydraulic analysis using CFD and massively parallel computers
International Nuclear Information System (INIS)
Weber, D.P.; Wei, T.Y.C.; Brewster, R.A.; Rock, Daniel T.; Rizwan-uddin
2000-01-01
Thermal-hydraulic analyses play an important role in design and reload analysis of nuclear power plants. These analyses have historically relied on early generation computational fluid dynamics capabilities, originally developed in the 1960s and 1970s. Over the last twenty years, however, dramatic improvements in both computational fluid dynamics codes in the commercial sector and in computing power have taken place. These developments offer the possibility of performing large scale, high fidelity, core thermal hydraulics analysis. Such analyses will allow a determination of the conservatism employed in traditional design approaches and possibly justify the operation of nuclear power systems at higher powers without compromising safety margins. The objective of this work is to demonstrate such a large scale analysis approach using a state of the art CFD code, STAR-CD, and the computing power of massively parallel computers, provided by IBM. A high fidelity representation of a current generation PWR was analyzed with the STAR-CD CFD code and the results were compared to traditional analyses based on the VIPRE code. Current design methodology typically involves a simplified representation of the assemblies, where a single average pin is used in each assembly to determine the hot assembly from a whole core analysis. After determining this assembly, increased refinement is used in the hot assembly, and possibly some of its neighbors, to refine the analysis for purposes of calculating DNBR. This latter calculation is performed with sub-channel codes such as VIPRE. The modeling simplifications that are used involve the approximate treatment of surrounding assemblies and coarse representation of the hot assembly, where the subchannel is the lowest level of discretization. In the high fidelity analysis performed in this study, both restrictions have been removed. Within the hot assembly, several hundred thousand to several million computational zones have been used, to
MT-ADRES: Multithreading on Coarse-Grained Reconfigurable Architecture
DEFF Research Database (Denmark)
Wu, Kehuai; Kanstein, Andreas; Madsen, Jan
2007-01-01
The coarse-grained reconfigurable architecture ADRES (Architecture for Dynamically Reconfigurable Embedded Systems) and its compiler offer high instruction-level parallelism (ILP) to applications by means of a sparsely interconnected array of functional units and register files. As high-ILP archi......The coarse-grained reconfigurable architecture ADRES (Architecture for Dynamically Reconfigurable Embedded Systems) and its compiler offer high instruction-level parallelism (ILP) to applications by means of a sparsely interconnected array of functional units and register files. As high......-ILP architectures achieve only low parallelism when executing partially sequential code segments, which is also known as Amdahl’s law, this paper proposes to extend ADRES to MT-ADRES (Multi-Threaded ADRES) to also exploit thread-level parallelism. On MT-ADRES architectures, the array can be partitioned in multiple...
Evaluation of the Intel iWarp parallel processor for space flight applications
Hine, Butler P., III; Fong, Terrence W.
1993-01-01
The potential of a DARPA-sponsored advanced processor, the Intel iWarp, for use in future SSF Data Management Systems (DMS) upgrades is evaluated through integration into the Ames DMS testbed and applications testing. The iWarp is a distributed, parallel computing system well suited for high performance computing applications such as matrix operations and image processing. The system architecture is modular, supports systolic and message-based computation, and is capable of providing massive computational power in a low-cost, low-power package. As a consequence, the iWarp offers significant potential for advanced space-based computing. This research seeks to determine the iWarp's suitability as a processing device for space missions. In particular, the project focuses on evaluating the ease of integrating the iWarp into the SSF DMS baseline architecture and the iWarp's ability to support computationally stressing applications representative of SSF tasks.
Parallel computing by Monte Carlo codes MVP/GMVP
International Nuclear Information System (INIS)
Nagaya, Yasunobu; Nakagawa, Masayuki; Mori, Takamasa
2001-01-01
General-purpose Monte Carlo codes MVP/GMVP are well-vectorized and thus enable us to perform high-speed Monte Carlo calculations. In order to achieve more speedups, we parallelized the codes on the different types of parallel computing platforms or by using a standard parallelization library MPI. The platforms used for benchmark calculations are a distributed-memory vector-parallel computer Fujitsu VPP500, a distributed-memory massively parallel computer Intel paragon and a distributed-memory scalar-parallel computer Hitachi SR2201, IBM SP2. As mentioned generally, linear speedup could be obtained for large-scale problems but parallelization efficiency decreased as the batch size per a processing element(PE) was smaller. It was also found that the statistical uncertainty for assembly powers was less than 0.1% by the PWR full-core calculation with more than 10 million histories and it took about 1.5 hours by massively parallel computing. (author)
Design and Implementation of Papyrus: Parallel Aggregate Persistent Storage
Energy Technology Data Exchange (ETDEWEB)
Kim, Jungwon [ORNL; Sajjapongse, Kittisak [ORNL; Lee, Seyong [ORNL; Vetter, Jeffrey S [ORNL
2017-01-01
A surprising development in recently announced HPC platforms is the addition of, sometimes massive amounts of, persistent (nonvolatile) memory (NVM) in order to increase memory capacity and compensate for plateauing I/O capabilities. However, there are no portable and scalable programming interfaces using aggregate NVM effectively. This paper introduces Papyrus: a new software system built to exploit emerging capability of NVM in HPC architectures. Papyrus (or Parallel Aggregate Persistent -YRU- Storage) is a novel programming system that provides features for scalable, aggregate, persistent memory in an extreme-scale system for typical HPC usage scenarios. Papyrus mainly consists of Papyrus Virtual File System (VFS) and Papyrus Template Container Library (TCL). Papyrus VFS provides a uniform aggregate NVM storage image across diverse NVM architectures. It enables Papyrus TCL to provide a portable and scalable high-level container programming interface whose data elements are distributed across multiple NVM nodes without requiring the user to handle complex communication, synchronization, replication, and consistency model. We evaluate Papyrus on two HPC systems, including UTK Beacon and NERSC Cori, using real NVM storage devices.
A task parallel implementation of fast multipole methods
Taura, Kenjiro; Nakashima, Jun; Yokota, Rio; Maruyama, Naoya
2012-01-01
This paper describes a task parallel implementation of ExaFMM, an open source implementation of fast multipole methods (FMM), using a lightweight task parallel library MassiveThreads. Although there have been many attempts on parallelizing FMM
Implementation of collisions on GPU architecture in the Vorpal code
Leddy, Jarrod; Averkin, Sergey; Cowan, Ben; Sides, Scott; Werner, Greg; Cary, John
2017-10-01
The Vorpal code contains a variety of collision operators allowing for the simulation of plasmas containing multiple charge species interacting with neutrals, background gas, and EM fields. These existing algorithms have been improved and reimplemented to take advantage of the massive parallelization allowed by GPU architecture. The use of GPUs is most effective when algorithms are single-instruction multiple-data, so particle collisions are an ideal candidate for this parallelization technique due to their nature as a series of independent processes with the same underlying operation. This refactoring required data memory reorganization and careful consideration of device/host data allocation to minimize memory access and data communication per operation. Successful implementation has resulted in an order of magnitude increase in simulation speed for a test-case involving multiple binary collisions using the null collision method. Work supported by DARPA under contract W31P4Q-16-C-0009.
Tramm, John R.; Gunow, Geoffrey; He, Tim; Smith, Kord S.; Forget, Benoit; Siegel, Andrew R.
2016-05-01
In this study we present and analyze a formulation of the 3D Method of Characteristics (MOC) technique applied to the simulation of full core nuclear reactors. Key features of the algorithm include a task-based parallelism model that allows independent MOC tracks to be assigned to threads dynamically, ensuring load balancing, and a wide vectorizable inner loop that takes advantage of modern SIMD computer architectures. The algorithm is implemented in a set of highly optimized proxy applications in order to investigate its performance characteristics on CPU, GPU, and Intel Xeon Phi architectures. Speed, power, and hardware cost efficiencies are compared. Additionally, performance bottlenecks are identified for each architecture in order to determine the prospects for continued scalability of the algorithm on next generation HPC architectures.
Engineering-Based Thermal CFD Simulations on Massive Parallel Systems
Frisch, Jé rô me; Mundani, Ralf-Peter; Rank, Ernst; van Treeck, Christoph
2015-01-01
The development of parallel Computational Fluid Dynamics (CFD) codes is a challenging task that entails efficient parallelization concepts and strategies in order to achieve good scalability values when running those codes on modern supercomputers
Algorithmically specialized parallel computers
Snyder, Lawrence; Gannon, Dennis B
1985-01-01
Algorithmically Specialized Parallel Computers focuses on the concept and characteristics of an algorithmically specialized computer.This book discusses the algorithmically specialized computers, algorithmic specialization using VLSI, and innovative architectures. The architectures and algorithms for digital signal, speech, and image processing and specialized architectures for numerical computations are also elaborated. Other topics include the model for analyzing generalized inter-processor, pipelined architecture for search tree maintenance, and specialized computer organization for raster
International Nuclear Information System (INIS)
Barsotti, E.; Booth, A.; Bowden, M.; Swoboda, C.; Lockyer, N.; VanBerg, R.
1989-12-01
A new era of high-energy physics research is beginning requiring accelerators with much higher luminosities and interaction rates in order to discover new elementary particles. As a consequences, both orders of magnitude higher data rates from the detector and online processing power, well beyond the capabilities of current high energy physics data acquisition systems, are required. This paper describes a new data acquisition system architecture which draws heavily from the communications industry, is totally parallel (i.e., without any bottlenecks), is capable of data rates of hundreds of GigaBytes per second from the detector and into an array of online processors (i.e., processor farm), and uses an open systems architecture to guarantee compatibility with future commercially available online processor farms. The main features of the system architecture are standard interface ICs to detector subsystems wherever possible, fiber optic digital data transmission from the near-detector electronics, a self-routing parallel event builder, and the use of industry-supported and high-level language programmable processors in the proposed BCD system for both triggers and online filters. A brief status report of an ongoing project at Fermilab to build the self-routing parallel event builder will also be given in the paper. 3 figs., 1 tab
Kalman filter tracking on parallel architectures
Cerati, G.; Elmer, P.; Krutelyov, S.; Lantz, S.; Lefebvre, M.; McDermott, K.; Riley, D.; Tadel, M.; Wittich, P.; Wurthwein, F.; Yagil, A.
2017-10-01
We report on the progress of our studies towards a Kalman filter track reconstruction algorithm with optimal performance on manycore architectures. The combinatorial structure of these algorithms is not immediately compatible with an efficient SIMD (or SIMT) implementation; the challenge for us is to recast the existing software so it can readily generate hundreds of shared-memory threads that exploit the underlying instruction set of modern processors. We show how the data and associated tasks can be organized in a way that is conducive to both multithreading and vectorization. We demonstrate very good performance on Intel Xeon and Xeon Phi architectures, as well as promising first results on Nvidia GPUs.
MT-ADRES: multi-threading on coarse-grained reconfigurable architecture
DEFF Research Database (Denmark)
Wu, Kehuai; Kanstein, Andreas; Madsen, Jan
2008-01-01
The coarse-grained reconfigurable architecture ADRES (architecture for dynamically reconfigurable embedded systems) and its compiler offer high instruction-level parallelism (ILP) to applications by means of a sparsely interconnected array of functional units and register files. As high-ILP archi......The coarse-grained reconfigurable architecture ADRES (architecture for dynamically reconfigurable embedded systems) and its compiler offer high instruction-level parallelism (ILP) to applications by means of a sparsely interconnected array of functional units and register files. As high......-ILP architectures achieve only low parallelism when executing partially sequential code segments, which is also known as Amdahl's law, this article proposes to extend ADRES to MT-ADRES (multi-threaded ADRES) to also exploit thread-level parallelism. On MT-ADRES architectures, the array can be partitioned...
Ford, Eric B.; Dindar, Saleh; Peters, Jorg
2015-08-01
The realism of astrophysical simulations and statistical analyses of astronomical data are set by the available computational resources. Thus, astronomers and astrophysicists are constantly pushing the limits of computational capabilities. For decades, astronomers benefited from massive improvements in computational power that were driven primarily by increasing clock speeds and required relatively little attention to details of the computational hardware. For nearly a decade, increases in computational capabilities have come primarily from increasing the degree of parallelism, rather than increasing clock speeds. Further increases in computational capabilities will likely be led by many-core architectures such as Graphical Processing Units (GPUs) and Intel Xeon Phi. Successfully harnessing these new architectures, requires significantly more understanding of the hardware architecture, cache hierarchy, compiler capabilities and network network characteristics.I will provide an astronomer's overview of the opportunities and challenges provided by modern many-core architectures and elastic cloud computing. The primary goal is to help an astronomical audience understand what types of problems are likely to yield more than order of magnitude speed-ups and which problems are unlikely to parallelize sufficiently efficiently to be worth the development time and/or costs.I will draw on my experience leading a team in developing the Swarm-NG library for parallel integration of large ensembles of small n-body systems on GPUs, as well as several smaller software projects. I will share lessons learned from collaborating with computer scientists, including both technical and soft skills. Finally, I will discuss the challenges of training the next generation of astronomers to be proficient in this new era of high-performance computing, drawing on experience teaching a graduate class on High-Performance Scientific Computing for Astrophysics and organizing a 2014 advanced summer
Energy Technology Data Exchange (ETDEWEB)
Souris, Kevin, E-mail: kevin.souris@uclouvain.be; Lee, John Aldo [Center for Molecular Imaging and Experimental Radiotherapy, Institut de Recherche Expérimentale et Clinique, Université catholique de Louvain, Avenue Hippocrate 54, 1200 Brussels, Belgium and ICTEAM Institute, Université catholique de Louvain, Louvain-la-Neuve 1348 (Belgium); Sterpin, Edmond [Center for Molecular Imaging and Experimental Radiotherapy, Institut de Recherche Expérimentale et Clinique, Université catholique de Louvain, Avenue Hippocrate 54, 1200 Brussels, Belgium and Department of Oncology, Katholieke Universiteit Leuven, O& N I Herestraat 49, 3000 Leuven (Belgium)
2016-04-15
Purpose: Accuracy in proton therapy treatment planning can be improved using Monte Carlo (MC) simulations. However the long computation time of such methods hinders their use in clinical routine. This work aims to develop a fast multipurpose Monte Carlo simulation tool for proton therapy using massively parallel central processing unit (CPU) architectures. Methods: A new Monte Carlo, called MCsquare (many-core Monte Carlo), has been designed and optimized for the last generation of Intel Xeon processors and Intel Xeon Phi coprocessors. These massively parallel architectures offer the flexibility and the computational power suitable to MC methods. The class-II condensed history algorithm of MCsquare provides a fast and yet accurate method of simulating heavy charged particles such as protons, deuterons, and alphas inside voxelized geometries. Hard ionizations, with energy losses above a user-specified threshold, are simulated individually while soft events are regrouped in a multiple scattering theory. Elastic and inelastic nuclear interactions are sampled from ICRU 63 differential cross sections, thereby allowing for the computation of prompt gamma emission profiles. MCsquare has been benchmarked with the GATE/GEANT4 Monte Carlo application for homogeneous and heterogeneous geometries. Results: Comparisons with GATE/GEANT4 for various geometries show deviations within 2%–1 mm. In spite of the limited memory bandwidth of the coprocessor simulation time is below 25 s for 10{sup 7} primary 200 MeV protons in average soft tissues using all Xeon Phi and CPU resources embedded in a single desktop unit. Conclusions: MCsquare exploits the flexibility of CPU architectures to provide a multipurpose MC simulation tool. Optimized code enables the use of accurate MC calculation within a reasonable computation time, adequate for clinical practice. MCsquare also simulates prompt gamma emission and can thus be used also for in vivo range verification.
International Nuclear Information System (INIS)
Souris, Kevin; Lee, John Aldo; Sterpin, Edmond
2016-01-01
Purpose: Accuracy in proton therapy treatment planning can be improved using Monte Carlo (MC) simulations. However the long computation time of such methods hinders their use in clinical routine. This work aims to develop a fast multipurpose Monte Carlo simulation tool for proton therapy using massively parallel central processing unit (CPU) architectures. Methods: A new Monte Carlo, called MCsquare (many-core Monte Carlo), has been designed and optimized for the last generation of Intel Xeon processors and Intel Xeon Phi coprocessors. These massively parallel architectures offer the flexibility and the computational power suitable to MC methods. The class-II condensed history algorithm of MCsquare provides a fast and yet accurate method of simulating heavy charged particles such as protons, deuterons, and alphas inside voxelized geometries. Hard ionizations, with energy losses above a user-specified threshold, are simulated individually while soft events are regrouped in a multiple scattering theory. Elastic and inelastic nuclear interactions are sampled from ICRU 63 differential cross sections, thereby allowing for the computation of prompt gamma emission profiles. MCsquare has been benchmarked with the GATE/GEANT4 Monte Carlo application for homogeneous and heterogeneous geometries. Results: Comparisons with GATE/GEANT4 for various geometries show deviations within 2%–1 mm. In spite of the limited memory bandwidth of the coprocessor simulation time is below 25 s for 10"7 primary 200 MeV protons in average soft tissues using all Xeon Phi and CPU resources embedded in a single desktop unit. Conclusions: MCsquare exploits the flexibility of CPU architectures to provide a multipurpose MC simulation tool. Optimized code enables the use of accurate MC calculation within a reasonable computation time, adequate for clinical practice. MCsquare also simulates prompt gamma emission and can thus be used also for in vivo range verification.
Souris, Kevin; Lee, John Aldo; Sterpin, Edmond
2016-04-01
Accuracy in proton therapy treatment planning can be improved using Monte Carlo (MC) simulations. However the long computation time of such methods hinders their use in clinical routine. This work aims to develop a fast multipurpose Monte Carlo simulation tool for proton therapy using massively parallel central processing unit (CPU) architectures. A new Monte Carlo, called MCsquare (many-core Monte Carlo), has been designed and optimized for the last generation of Intel Xeon processors and Intel Xeon Phi coprocessors. These massively parallel architectures offer the flexibility and the computational power suitable to MC methods. The class-II condensed history algorithm of MCsquare provides a fast and yet accurate method of simulating heavy charged particles such as protons, deuterons, and alphas inside voxelized geometries. Hard ionizations, with energy losses above a user-specified threshold, are simulated individually while soft events are regrouped in a multiple scattering theory. Elastic and inelastic nuclear interactions are sampled from ICRU 63 differential cross sections, thereby allowing for the computation of prompt gamma emission profiles. MCsquare has been benchmarked with the gate/geant4 Monte Carlo application for homogeneous and heterogeneous geometries. Comparisons with gate/geant4 for various geometries show deviations within 2%-1 mm. In spite of the limited memory bandwidth of the coprocessor simulation time is below 25 s for 10(7) primary 200 MeV protons in average soft tissues using all Xeon Phi and CPU resources embedded in a single desktop unit. MCsquare exploits the flexibility of CPU architectures to provide a multipurpose MC simulation tool. Optimized code enables the use of accurate MC calculation within a reasonable computation time, adequate for clinical practice. MCsquare also simulates prompt gamma emission and can thus be used also for in vivo range verification.
Benefits of a parallel hybrid electric architecture on medium commercial vehicles
Energy Technology Data Exchange (ETDEWEB)
Boot, Marco Aimo; Consano, Ludovico [Iveco S.p.A, Turin (Italy)
2009-07-01
Hybrid electric technology is becoming an increasingly interesting solution for medium and heavy trucks involved in urban and suburban missions. The increasing demand for gas and oil, consequent price rises and environmental concerns are driving a market that is in need of alternative solutions. For these reasons, the growth in the global hybrid market significantly exceeded all the hybrid sales forecasts. The parallel hybrid electric vehicle (PHEV) employs an additional power source (electric motogenerator) in combination with the conventional diesel engine. This architecture exploits the benefits of both power sources in order to reduce the fuel consumption, increase the overall power, and above all, decrease CO2 emissions. Moreover, the emissions reduction target is lead by EU Regulations and local initiatives for traffic limitations, but the real drivers for the growth in the market are demonstrable fuel economy improvements and productivity costs optimization (global efficiency). This paper presents the results achieved by Iveco in the development and testing of parallel hybrid systems applied to medium range commercial vehicles, with the intent to evaluate the functionality, driveability performance and leading the best reduction in terms of fuel consumption and emissions in different real-world missions. The system architecture foresees one electric motor/generator and a single clutch unit. An external electrical power source for the battery recharging it is not necessary. The chosen configuration allows to implement the following functional modes: Stop and Start with Electric Launch, Hybrid Mode, Regenerative Braking Mode, Inertial Start and Creeping Mode. The software contained in the supervisor control unit has been tuned to the customer specific missions, taking in account on road data acquisition in order to demonstrate the reliability, driveability and the overall efficiency of the hybrid system. The field tests carried out in collaboration with
Cardenas, Erick; Wu, Wei-Min; Leigh, Mary Beth; Carley, Jack; Carroll, Sue; Gentry, Terry; Luo, Jian; Watson, David; Gu, Baohua; Ginder-Vogel, Matthew; Kitanidis, Peter K.; Jardine, Philip M.; Zhou, Jizhong; Criddle, Craig S.; Marsh, Terence L.
2010-01-01
Massively parallel sequencing has provided a more affordable and high-throughput method to study microbial communities, although it has mostly been used in an exploratory fashion. We combined pyrosequencing with a strict indicator species statistical analysis to test if bacteria specifically responded to ethanol injection that successfully promoted dissimilatory uranium(VI) reduction in the subsurface of a uranium contamination plume at the Oak Ridge Field Research Center in Tennessee. Remedi...
A memory-array architecture for computer vision
Energy Technology Data Exchange (ETDEWEB)
Balsara, P.T.
1989-01-01
With the fast advances in the area of computer vision and robotics there is a growing need for machines that can understand images at a very high speed. A conventional von Neumann computer is not suited for this purpose because it takes a tremendous amount of time to solve most typical image processing problems. Exploiting the inherent parallelism present in various vision tasks can significantly reduce the processing time. Fortunately, parallelism is increasingly affordable as hardware gets cheaper. Thus it is now imperative to study computer vision in a parallel processing framework. The author should first design a computational structure which is well suited for a wide range of vision tasks and then develop parallel algorithms which can run efficiently on this structure. Recent advances in VLSI technology have led to several proposals for parallel architectures for computer vision. In this thesis he demonstrates that a memory array architecture with efficient local and global communication capabilities can be used for high speed execution of a wide range of computer vision tasks. This architecture, called the Access Constrained Memory Array Architecture (ACMAA), is efficient for VLSI implementation because of its modular structure, simple interconnect and limited global control. Several parallel vision algorithms have been designed for this architecture. The choice of vision problems demonstrates the versatility of ACMAA for a wide range of vision tasks. These algorithms were simulated on a high level ACMAA simulator running on the Intel iPSC/2 hypercube, a parallel architecture. The results of this simulation are compared with those of sequential algorithms running on a single hypercube node. Details of the ACMAA processor architecture are also presented.
Parallel evolutionary computation in bioinformatics applications.
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.
International Nuclear Information System (INIS)
Zee, S.K.
1987-01-01
A numeric algorithm and an associated computer code were developed for the rapid solution of the finite-difference method representation of the few-group neutron-diffusion equations on parallel computers. Applications of the numeric algorithm on both SIMD (vector pipeline) and MIMD/SIMD (multi-CUP/vector pipeline) architectures were explored. The algorithm was successfully implemented in the two-group, 3-D neutron diffusion computer code named DIFPAR3D (DIFfusion PARallel 3-Dimension). Numerical-solution techniques used in the code include the Chebyshev polynomial acceleration technique in conjunction with the power method of outer iteration. For inner iterations, a parallel form of red-black (cyclic) line SOR with automated determination of group dependent relaxation factors and iteration numbers required to achieve specified inner iteration error tolerance is incorporated. The code employs a macroscopic depletion model with trace capability for selected fission products' transients and critical boron. In addition to this, moderator and fuel temperature feedback models are also incorporated into the DIFPAR3D code, for realistic simulation of power reactor cores. The physics models used were proven acceptable in separate benchmarking studies
Massively parallel diffuse optical tomography
Energy Technology Data Exchange (ETDEWEB)
Sandusky, John V.; Pitts, Todd A.
2017-09-05
Diffuse optical tomography systems and methods are described herein. In a general embodiment, the diffuse optical tomography system comprises a plurality of sensor heads, the plurality of sensor heads comprising respective optical emitter systems and respective sensor systems. A sensor head in the plurality of sensors heads is caused to act as an illuminator, such that its optical emitter system transmits a transillumination beam towards a portion of a sample. Other sensor heads in the plurality of sensor heads act as observers, detecting portions of the transillumination beam that radiate from the sample in the fields of view of the respective sensory systems of the other sensor heads. Thus, sensor heads in the plurality of sensors heads generate sensor data in parallel.
Parallel Computing Strategies for Irregular Algorithms
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.
Choudhary, Alok N.; Patel, Janak H.; Ahuja, Narendra
1989-01-01
In part 1 architecture of NETRA is presented. A performance evaluation of NETRA using several common vision algorithms is also presented. Performance of algorithms when they are mapped on one cluster is described. It is shown that SIMD, MIMD, and systolic algorithms can be easily mapped onto processor clusters, and almost linear speedups are possible. For some algorithms, analytical performance results are compared with implementation performance results. It is observed that the analysis is very accurate. Performance analysis of parallel algorithms when mapped across clusters is presented. Mappings across clusters illustrate the importance and use of shared as well as distributed memory in achieving high performance. The parameters for evaluation are derived from the characteristics of the parallel algorithms, and these parameters are used to evaluate the alternative communication strategies in NETRA. Furthermore, the effect of communication interference from other processors in the system on the execution of an algorithm is studied. Using the analysis, performance of many algorithms with different characteristics is presented. It is observed that if communication speeds are matched with the computation speeds, good speedups are possible when algorithms are mapped across clusters.
Image processing methods and architectures in diagnostic pathology.
Directory of Open Access Journals (Sweden)
Oscar DĂŠniz
2010-05-01
Full Text Available Grid technology has enabled the clustering and the efficient and secure access to and interaction among a wide variety of geographically distributed resources such as: supercomputers, storage systems, data sources, instruments and special devices and services. Their main applications include large-scale computational and data intensive problems in science and engineering. General grid structures and methodologies for both software and hardware in image analysis for virtual tissue-based diagnosis has been considered in this paper. This methods are focus on the user level middleware. The article describes the distributed programming system developed by the authors for virtual slide analysis in diagnostic pathology. The system supports different image analysis operations commonly done in anatomical pathology and it takes into account secured aspects and specialized infrastructures with high level services designed to meet application requirements. Grids are likely to have a deep impact on health related applications, and therefore they seem to be suitable for tissue-based diagnosis too. The implemented system is a joint application that mixes both Web and Grid Service Architecture around a distributed architecture for image processing. It has shown to be a successful solution to analyze a big and heterogeneous group of histological images under architecture of massively parallel processors using message passing and non-shared memory.
Customizable Memory Schemes for Data Parallel Architectures
Gou, C.
2011-01-01
Memory system efficiency is crucial for any processor to achieve high performance, especially in the case of data parallel machines. Processing capabilities of parallel lanes will be wasted, when data requests are not accomplished in a sustainable and timely manner. Irregular vector memory accesses
Hierarchical Image Segmentation of Remotely Sensed Data using Massively Parallel GNU-LINUX Software
Tilton, James C.
2003-01-01
A hierarchical set of image segmentations is a set of several image segmentations of the same image at different levels of detail in which the segmentations at coarser levels of detail can be produced from simple merges of regions at finer levels of detail. In [1], Tilton, et a1 describes an approach for producing hierarchical segmentations (called HSEG) and gave a progress report on exploiting these hierarchical segmentations for image information mining. The HSEG algorithm is a hybrid of region growing and constrained spectral clustering that produces a hierarchical set of image segmentations based on detected convergence points. In the main, HSEG employs the hierarchical stepwise optimization (HSWO) approach to region growing, which was described as early as 1989 by Beaulieu and Goldberg. The HSWO approach seeks to produce segmentations that are more optimized than those produced by more classic approaches to region growing (e.g. Horowitz and T. Pavlidis, [3]). In addition, HSEG optionally interjects between HSWO region growing iterations, merges between spatially non-adjacent regions (i.e., spectrally based merging or clustering) constrained by a threshold derived from the previous HSWO region growing iteration. While the addition of constrained spectral clustering improves the utility of the segmentation results, especially for larger images, it also significantly increases HSEG s computational requirements. To counteract this, a computationally efficient recursive, divide-and-conquer, implementation of HSEG (RHSEG) was devised, which includes special code to avoid processing artifacts caused by RHSEG s recursive subdivision of the image data. The recursive nature of RHSEG makes for a straightforward parallel implementation. This paper describes the HSEG algorithm, its recursive formulation (referred to as RHSEG), and the implementation of RHSEG using massively parallel GNU-LINUX software. Results with Landsat TM data are included comparing RHSEG with classic
The BLAZE language - A parallel language for scientific programming
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.
The BLAZE language: A parallel language for scientific programming
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.
International Nuclear Information System (INIS)
Wong Unhong; Wong Honcheng; Tang Zesheng
2010-01-01
The smoothed particle hydrodynamics (SPH), which is a class of meshfree particle methods (MPMs), has a wide range of applications from micro-scale to macro-scale as well as from discrete systems to continuum systems. Graphics hardware, originally designed for computer graphics, now provide unprecedented computational power for scientific computation. Particle system needs a huge amount of computations in physical simulation. In this paper, an efficient parallel implementation of a SPH method on graphics hardware using the Compute Unified Device Architecture is developed for fluid simulation. Comparing to the corresponding CPU implementation, our experimental results show that the new approach allows significant speedups of fluid simulation through handling huge amount of computations in parallel on graphics hardware.
A massively parallel GPU-accelerated model for analysis of fully nonlinear free surface waves
DEFF Research Database (Denmark)
Engsig-Karup, Allan Peter; Madsen, Morten G.; Glimberg, Stefan Lemvig
2011-01-01
-storage flexible-order accurate finite difference method that is known to be efficient and scalable on a CPU core (single thread). To achieve parallel performance of the relatively complex numerical model, we investigate a new trend in high-performance computing where many-core GPUs are utilized as high......-throughput co-processors to the CPU. We describe and demonstrate how this approach makes it possible to do fast desktop computations for large nonlinear wave problems in numerical wave tanks (NWTs) with close to 50/100 million total grid points in double/ single precision with 4 GB global device memory...... available. A new code base has been developed in C++ and compute unified device architecture C and is found to improve the runtime more than an order in magnitude in double precision arithmetic for the same accuracy over an existing CPU (single thread) Fortran 90 code when executed on a single modern GPU...
Parallel Architectures for Planetary Exploration Requirements (PAPER)
Cezzar, Ruknet
1993-01-01
The project's main contributions have been in the area of student support. Throughout the project, at least one, in some cases two, undergraduate students have been supported. By working with the project, these students gained valuable knowledge involving the scientific research project, including the not-so-pleasant reporting requirements to the funding agencies. The other important contribution was towards the establishment of a graduate program in computer science at Hampton University. Primarily, the PAPER project has served as the main research basis in seeking funds from other agencies, such as the National Science Foundation, for establishing a research infrastructure in the department. In technical areas, especially in the first phase, we believe the trip to Jet Propulsion Laboratory, and gathering together all the pertinent information involving experimental computer architectures aimed for planetary explorations was very helpful. Indeed, if this effort is to be revived in the future due to congressional funding for planetary explorations, say an unmanned mission to Mars, our interim report will be an important starting point. In other technical areas, our simulator has pinpointed and highlighted several important performance issues related to the design of operating system kernels for MIMD machines. In particular, the critical issue of how the kernel itself will run in parallel on a multiple-processor system has been addressed through the various ready list organization and access policies. In the area of neural computing, our main contribution was an introductory tutorial package to familiarize the researchers at NASA with this new and promising field zone axes (20). Finally, we have introduced the notion of reversibility in programming systems which may find applications in various areas of space research.
International Nuclear Information System (INIS)
Byers, J.A.; Williams, T.J.; Cohen, B.I.; Dimits, A.M.
1994-01-01
One of the programs of the Magnetic fusion Energy (MFE) Theory and computations Program is studying the anomalous transport of thermal energy across the field lines in the core of a tokamak. We use the method of gyrokinetic particle-in-cell simulation in this study. For this LDRD project we employed massively parallel processing, new algorithms, and new algorithms, and new formal techniques to improve this research. Specifically, we sought to take steps toward: researching experimentally-relevant parameters in our simulations, learning parallel computing to have as a resource for our group, and achieving a 100 x speedup over our starting-point Cray2 simulation code's performance
Oliker, Leonid; Heber, Gerd; Biswas, Rupak
2000-01-01
The Conjugate Gradient (CG) algorithm is perhaps the best-known iterative technique to solve sparse linear systems that are symmetric and positive definite. A sparse matrix-vector multiply (SPMV) usually accounts for most of the floating-point operations within a CG iteration. In this paper, we investigate the effects of various ordering and partitioning strategies on the performance of parallel CG and SPMV using different programming paradigms and architectures. Results show that for this class of applications, ordering significantly improves overall performance, that cache reuse may be more important than reducing communication, and that it is possible to achieve message passing performance using shared memory constructs through careful data ordering and distribution. However, a multi-threaded implementation of CG on the Tera MTA does not require special ordering or partitioning to obtain high efficiency and scalability.
A New Electronic Commerce Architecture in the Cloud
Guigang Zhang; Chao Li; Sixin Xue; Yuenan Liu; Yong Zhang; Chunxiao Xing
2012-01-01
In this paper, the authors propose a new electronic commerce architecture in the cloud that satisfies the requirements of the cloud. This architecture includes five technologies, which are the massive EC data storage technology in the cloud, the massive EC data processing technology in the cloud, the EC security management technology in the cloud, OLAP technology for EC in the cloud, and active EC technology in the cloud. Finally, a detailed discussion of future trends for EC in the cloud env...
Farris, M Heath; Scott, Andrew R; Texter, Pamela A; Bartlett, Marta; Coleman, Patricia; Masters, David
2018-04-11
Single nucleotide polymorphisms (SNPs) located within the human genome have been shown to have utility as markers of identity in the differentiation of DNA from individual contributors. Massively parallel DNA sequencing (MPS) technologies and human genome SNP databases allow for the design of suites of identity-linked target regions, amenable to sequencing in a multiplexed and massively parallel manner. Therefore, tools are needed for leveraging the genotypic information found within SNP databases for the discovery of genomic targets that can be evaluated on MPS platforms. The SNP island target identification algorithm (TIA) was developed as a user-tunable system to leverage SNP information within databases. Using data within the 1000 Genomes Project SNP database, human genome regions were identified that contain globally ubiquitous identity-linked SNPs and that were responsive to targeted resequencing on MPS platforms. Algorithmic filters were used to exclude target regions that did not conform to user-tunable SNP island target characteristics. To validate the accuracy of TIA for discovering these identity-linked SNP islands within the human genome, SNP island target regions were amplified from 70 contributor genomic DNA samples using the polymerase chain reaction. Multiplexed amplicons were sequenced using the Illumina MiSeq platform, and the resulting sequences were analyzed for SNP variations. 166 putative identity-linked SNPs were targeted in the identified genomic regions. Of the 309 SNPs that provided discerning power across individual SNP profiles, 74 previously undefined SNPs were identified during evaluation of targets from individual genomes. Overall, DNA samples of 70 individuals were uniquely identified using a subset of the suite of identity-linked SNP islands. TIA offers a tunable genome search tool for the discovery of targeted genomic regions that are scalable in the population frequency and numbers of SNPs contained within the SNP island regions
Energy Technology Data Exchange (ETDEWEB)
Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)
1992-01-01
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
Parallel plasma fluid turbulence calculations
International Nuclear Information System (INIS)
Leboeuf, J.N.; Carreras, B.A.; Charlton, L.A.; Drake, J.B.; Lynch, V.E.; Newman, D.E.; Sidikman, K.L.; Spong, D.A.
1994-01-01
The study of plasma turbulence and transport is a complex problem of critical importance for fusion-relevant plasmas. To this day, the fluid treatment of plasma dynamics is the best approach to realistic physics at the high resolution required for certain experimentally relevant calculations. Core and edge turbulence in a magnetic fusion device have been modeled using state-of-the-art, nonlinear, three-dimensional, initial-value fluid and gyrofluid codes. Parallel implementation of these models on diverse platforms--vector parallel (National Energy Research Supercomputer Center's CRAY Y-MP C90), massively parallel (Intel Paragon XP/S 35), and serial parallel (clusters of high-performance workstations using the Parallel Virtual Machine protocol)--offers a variety of paths to high resolution and significant improvements in real-time efficiency, each with its own advantages. The largest and most efficient calculations have been performed at the 200 Mword memory limit on the C90 in dedicated mode, where an overlap of 12 to 13 out of a maximum of 16 processors has been achieved with a gyrofluid model of core fluctuations. The richness of the physics captured by these calculations is commensurate with the increased resolution and efficiency and is limited only by the ingenuity brought to the analysis of the massive amounts of data generated
Parallel computation for distributed parameter system-from vector processors to Adena computer
Energy Technology Data Exchange (ETDEWEB)
Nogi, T
1983-04-01
Research on advanced parallel hardware and software architectures for very high-speed computation deserves and needs more support and attention to fulfil its promise. Novel architectures for parallel processing are being made ready. Architectures for parallel processing can be roughly divided into two groups. One is a vector processor in which a single central processing unit involves multiple vector-arithmetic registers. The other is a processor array in which slave processors are connected to a host processor to perform parallel computation. In this review, the concept and data structure of the Adena (alternating-direction edition nexus array) architecture, which is conformable to distributed-parameter simulation algorithms, are described. 5 references.
Big Data GPU-Driven Parallel Processing Spatial and Spatio-Temporal Clustering Algorithms
Konstantaras, Antonios; Skounakis, Emmanouil; Kilty, James-Alexander; Frantzeskakis, Theofanis; Maravelakis, Emmanuel
2016-04-01
Advances in graphics processing units' technology towards encompassing parallel architectures [1], comprised of thousands of cores and multiples of parallel threads, provide the foundation in terms of hardware for the rapid processing of various parallel applications regarding seismic big data analysis. Seismic data are normally stored as collections of vectors in massive matrices, growing rapidly in size as wider areas are covered, denser recording networks are being established and decades of data are being compiled together [2]. Yet, many processes regarding seismic data analysis are performed on each seismic event independently or as distinct tiles [3] of specific grouped seismic events within a much larger data set. Such processes, independent of one another can be performed in parallel narrowing down processing times drastically [1,3]. This research work presents the development and implementation of three parallel processing algorithms using Cuda C [4] for the investigation of potentially distinct seismic regions [5,6] present in the vicinity of the southern Hellenic seismic arc. The algorithms, programmed and executed in parallel comparatively, are the: fuzzy k-means clustering with expert knowledge [7] in assigning overall clusters' number; density-based clustering [8]; and a selves-developed spatio-temporal clustering algorithm encompassing expert [9] and empirical knowledge [10] for the specific area under investigation. Indexing terms: GPU parallel programming, Cuda C, heterogeneous processing, distinct seismic regions, parallel clustering algorithms, spatio-temporal clustering References [1] Kirk, D. and Hwu, W.: 'Programming massively parallel processors - A hands-on approach', 2nd Edition, Morgan Kaufman Publisher, 2013 [2] Konstantaras, A., Valianatos, F., Varley, M.R. and Makris, J.P.: 'Soft-Computing Modelling of Seismicity in the Southern Hellenic Arc', Geoscience and Remote Sensing Letters, vol. 5 (3), pp. 323-327, 2008 [3] Papadakis, S. and
Sakr, Rita A; Schizas, Michail; Carniello, Jose V Scarpa; Ng, Charlotte K Y; Piscuoglio, Salvatore; Giri, Dilip; Andrade, Victor P; De Brot, Marina; Lim, Raymond S; Towers, Russell; Weigelt, Britta; Reis-Filho, Jorge S; King, Tari A
2016-02-01
Lobular carcinoma in situ (LCIS) has been proposed as a non-obligate precursor of invasive lobular carcinoma (ILC). Here we sought to define the repertoire of somatic genetic alterations in pure LCIS and in synchronous LCIS and ILC using targeted massively parallel sequencing. DNA samples extracted from microdissected LCIS, ILC and matched normal breast tissue or peripheral blood from 30 patients were subjected to massively parallel sequencing targeting all exons of 273 genes, including the genes most frequently mutated in breast cancer and DNA repair-related genes. Single nucleotide variants and insertions and deletions were identified using state-of-the-art bioinformatics approaches. The constellation of somatic mutations found in LCIS (n = 34) and ILC (n = 21) were similar, with the most frequently mutated genes being CDH1 (56% and 66%, respectively), PIK3CA (41% and 52%, respectively) and CBFB (12% and 19%, respectively). Among 19 LCIS and ILC synchronous pairs, 14 (74%) had at least one identical mutation in common, including identical PIK3CA and CDH1 mutations. Paired analysis of independent foci of LCIS from 3 breasts revealed at least one common mutation in each of the 3 pairs (CDH1, PIK3CA, CBFB and PKHD1L1). LCIS and ILC have a similar repertoire of somatic mutations, with PIK3CA and CDH1 being the most frequently mutated genes. The presence of identical mutations between LCIS-LCIS and LCIS-ILC pairs demonstrates that LCIS is a clonal neoplastic lesion, and provides additional evidence that at least some LCIS are non-obligate precursors of ILC. Copyright © 2015 Federation of European Biochemical Societies. Published by Elsevier B.V. All rights reserved.
Parallel generation of architecture on the GPU
Steinberger, Markus
2014-05-01
In this paper, we present a novel approach for the parallel evaluation of procedural shape grammars on the graphics processing unit (GPU). Unlike previous approaches that are either limited in the kind of shapes they allow, the amount of parallelism they can take advantage of, or both, our method supports state of the art procedural modeling including stochasticity and context-sensitivity. To increase parallelism, we explicitly express independence in the grammar, reduce inter-rule dependencies required for context-sensitive evaluation, and introduce intra-rule parallelism. Our rule scheduling scheme avoids unnecessary back and forth between CPU and GPU and reduces round trips to slow global memory by dynamically grouping rules in on-chip shared memory. Our GPU shape grammar implementation is multiple orders of magnitude faster than the standard in CPU-based rule evaluation, while offering equal expressive power. In comparison to the state of the art in GPU shape grammar derivation, our approach is nearly 50 times faster, while adding support for geometric context-sensitivity. © 2014 The Author(s) Computer Graphics Forum © 2014 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
Directory of Open Access Journals (Sweden)
Jiayi Wu
Full Text Available Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM. We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.
A massive parallel sequencing workflow for diagnostic genetic testing of mismatch repair genes
Hansen, Maren F; Neckmann, Ulrike; Lavik, Liss A S; Vold, Trine; Gilde, Bodil; Toft, Ragnhild K; Sjursen, Wenche
2014-01-01
The purpose of this study was to develop a massive parallel sequencing (MPS) workflow for diagnostic analysis of mismatch repair (MMR) genes using the GS Junior system (Roche). A pathogenic variant in one of four MMR genes, (MLH1, PMS2, MSH6, and MSH2), is the cause of Lynch Syndrome (LS), which mainly predispose to colorectal cancer. We used an amplicon-based sequencing method allowing specific and preferential amplification of the MMR genes including PMS2, of which several pseudogenes exist. The amplicons were pooled at different ratios to obtain coverage uniformity and maximize the throughput of a single-GS Junior run. In total, 60 previously identified and distinct variants (substitutions and indels), were sequenced by MPS and successfully detected. The heterozygote detection range was from 19% to 63% and dependent on sequence context and coverage. We were able to distinguish between false-positive and true-positive calls in homopolymeric regions by cross-sample comparison and evaluation of flow signal distributions. In addition, we filtered variants according to a predefined status, which facilitated variant annotation. Our study shows that implementation of MPS in routine diagnostics of LS can accelerate sample throughput and reduce costs without compromising sensitivity, compared to Sanger sequencing. PMID:24689082
Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi; Mao, Youdong
2017-01-01
Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.
Directory of Open Access Journals (Sweden)
Varghese Mathew Vaidyan
2015-09-01
Full Text Available Present self-tuning regulator architectures based on recursive least-square estimation are computationally expensive and require large amount of resources and time in generating the first control signal due to computational bottlenecks imposed by the calculations involved in estimation stage, different stages of matrix multiplications and the number of intermediate variables at each iteration and precludes its use in applications that have fast required response times and those which run on embedded computing platforms with low-power or low-cost requirements with constraints on resource usage. A salient feature of this study is that a new modular parallel pipelined stochastic approximation-based self-tuning regulator architecture which reduces the time required to generate the first control signal, reduces resource usage and reduces the number of intermediate variables is proposed. Fast matrix multiplication, pipelining and high-speed arithmetic function implementations were used for improving the performance. Results of implementation demonstrate that the proposed architecture has an improvement in control signal generation time by 38% and reduction in resource usage by 41% in terms of multipliers and 44.4% in terms of adders compared with the best existing related work, opening up new possibilities for the application of online embedded self-tuning regulators.
Schultz, A.
2010-12-01
3D forward solvers lie at the core of inverse formulations used to image the variation of electrical conductivity within the Earth's interior. This property is associated with variations in temperature, composition, phase, presence of volatiles, and in specific settings, the presence of groundwater, geothermal resources, oil/gas or minerals. The high cost of 3D solutions has been a stumbling block to wider adoption of 3D methods. Parallel algorithms for modeling frequency domain 3D EM problems have not achieved wide scale adoption, with emphasis on fairly coarse grained parallelism using MPI and similar approaches. The communications bandwidth as well as the latency required to send and receive network communication packets is a limiting factor in implementing fine grained parallel strategies, inhibiting wide adoption of these algorithms. Leading Graphics Processor Unit (GPU) companies now produce GPUs with hundreds of GPU processor cores per die. The footprint, in silicon, of the GPU's restricted instruction set is much smaller than the general purpose instruction set required of a CPU. Consequently, the density of processor cores on a GPU can be much greater than on a CPU. GPUs also have local memory, registers and high speed communication with host CPUs, usually through PCIe type interconnects. The extremely low cost and high computational power of GPUs provides the EM geophysics community with an opportunity to achieve fine grained (i.e. massive) parallelization of codes on low cost hardware. The current generation of GPUs (e.g. NVidia Fermi) provides 3 billion transistors per chip die, with nearly 500 processor cores and up to 6 GB of fast (DDR5) GPU memory. This latest generation of GPU supports fast hardware double precision (64 bit) floating point operations of the type required for frequency domain EM forward solutions. Each Fermi GPU board can sustain nearly 1 TFLOP in double precision, and multiple boards can be installed in the host computer system. We
Parallel-Architecture Simulator Development Using Hardware Transactional Memory
Armejach Sanosa, Adrià
2009-01-01
To address the need for a simpler parallel programming model, Transactional Memory (TM) has been developed and promises good parallel performance with easy-to-write parallel code. Unlike lock-based approaches, with TM, programmers do not need to explicitly specify and manage the synchronization among threads. However, programmers simply mark code segments as transactions, and the TM system manages the concurrency control for them. TM can be implemented either in software (STM) or hardware (HT...
International Nuclear Information System (INIS)
1994-08-01
This is the first annual report of the MPP pilot project 93MPR05. In this pilot project four research groups with different, complementary backgrounds collaborate with the aim to develop new algorithms and codes to simulate the magnetohydrodynamics of thermonuclear and astrophysical plasmas on massively parallel machines. The expected speed-up is required to simulate the dynamics of the hot plasmas of interest which are characterized by very large magnetic Reynolds numbers and, hence, require high spatial and temporal resolutions (for details see section 1). The four research groups that collaborated to produce the results reported here are: The MHD group of Prof. Dr. J.P. Goedbloed at the FOM-Institute for Plasma Physics 'Rijnhuizen' in Nieuwegein, the group of Prof. Dr. H. van der Vorst at the Mathematics Institute of Utrecht University, the group of Prof. Dr. A.G. Hearn at the Astronomical Institute of Utrecht University, and the group of Dr. Ir. H.J.J. te Riele at the CWI in Amsterdam. The full project team met frequently during this first project year to discuss progress reports, current problems, etc. (see section 2). The main results of the first project year are: - Proof of the scalability of typical linear and nonlinear MHD codes - development and testing of a parallel version of the Arnoldi algorithm - development and testing of alternative methods for solving large non-Hermitian eigenvalue problems - porting of the 3D nonlinear semi-implicit time evolution code HERA to an MPP system. The steps that were scheduled to reach these intended results are given in section 3. (orig./WL)
Energy Technology Data Exchange (ETDEWEB)
NONE
1994-08-01
This is the first annual report of the MPP pilot project 93MPR05. In this pilot project four research groups with different, complementary backgrounds collaborate with the aim to develop new algorithms and codes to simulate the magnetohydrodynamics of thermonuclear and astrophysical plasmas on massively parallel machines. The expected speed-up is required to simulate the dynamics of the hot plasmas of interest which are characterized by very large magnetic Reynolds numbers and, hence, require high spatial and temporal resolutions (for details see section 1). The four research groups that collaborated to produce the results reported here are: The MHD group of Prof. Dr. J.P. Goedbloed at the FOM-Institute for Plasma Physics `Rijnhuizen` in Nieuwegein, the group of Prof. Dr. H. van der Vorst at the Mathematics Institute of Utrecht University, the group of Prof. Dr. A.G. Hearn at the Astronomical Institute of Utrecht University, and the group of Dr. Ir. H.J.J. te Riele at the CWI in Amsterdam. The full project team met frequently during this first project year to discuss progress reports, current problems, etc. (see section 2). The main results of the first project year are: - Proof of the scalability of typical linear and nonlinear MHD codes - development and testing of a parallel version of the Arnoldi algorithm - development and testing of alternative methods for solving large non-Hermitian eigenvalue problems - porting of the 3D nonlinear semi-implicit time evolution code HERA to an MPP system. The steps that were scheduled to reach these intended results are given in section 3. (orig./WL).
Design of a Load-Balancing Architecture For Parallel Firewalls
National Research Council Canada - National Science Library
Joyner, William
1999-01-01
.... This thesis proposes a load-balancing firewall architecture to meet the Navy's needs. It first conducts an architectural analysis of the problem and then presents a high-level system design as a solution...
Compiler Technology for Parallel Scientific Computation
Directory of Open Access Journals (Sweden)
Can Özturan
1994-01-01
Full Text Available There is a need for compiler technology that, given the source program, will generate efficient parallel codes for different architectures with minimal user involvement. Parallel computation is becoming indispensable in solving large-scale problems in science and engineering. Yet, the use of parallel computation is limited by the high costs of developing the needed software. To overcome this difficulty we advocate a comprehensive approach to the development of scalable architecture-independent software for scientific computation based on our experience with equational programming language (EPL. Our approach is based on a program decomposition, parallel code synthesis, and run-time support for parallel scientific computation. The program decomposition is guided by the source program annotations provided by the user. The synthesis of parallel code is based on configurations that describe the overall computation as a set of interacting components. Run-time support is provided by the compiler-generated code that redistributes computation and data during object program execution. The generated parallel code is optimized using techniques of data alignment, operator placement, wavefront determination, and memory optimization. In this article we discuss annotations, configurations, parallel code generation, and run-time support suitable for parallel programs written in the functional parallel programming language EPL and in Fortran.
Optimisation of a parallel ocean general circulation model
M. I. Beare; D. P. Stevens
1997-01-01
International audience; This paper presents the development of a general-purpose parallel ocean circulation model, for use on a wide range of computer platforms, from traditional scalar machines to workstation clusters and massively parallel processors. Parallelism is provided, as a modular option, via high-level message-passing routines, thus hiding the technical intricacies from the user. An initial implementation highlights that the parallel efficiency of the model is adversely affected by...
Parallel hierarchical radiosity rendering
Energy Technology Data Exchange (ETDEWEB)
Carter, Michael [Iowa State Univ., Ames, IA (United States)
1993-07-01
In this dissertation, the step-by-step development of a scalable parallel hierarchical radiosity renderer is documented. First, a new look is taken at the traditional radiosity equation, and a new form is presented in which the matrix of linear system coefficients is transformed into a symmetric matrix, thereby simplifying the problem and enabling a new solution technique to be applied. Next, the state-of-the-art hierarchical radiosity methods are examined for their suitability to parallel implementation, and scalability. Significant enhancements are also discovered which both improve their theoretical foundations and improve the images they generate. The resultant hierarchical radiosity algorithm is then examined for sources of parallelism, and for an architectural mapping. Several architectural mappings are discussed. A few key algorithmic changes are suggested during the process of making the algorithm parallel. Next, the performance, efficiency, and scalability of the algorithm are analyzed. The dissertation closes with a discussion of several ideas which have the potential to further enhance the hierarchical radiosity method, or provide an entirely new forum for the application of hierarchical methods.
Crockett, Thomas W.
1995-01-01
This article provides a broad introduction to the subject of parallel rendering, encompassing both hardware and software systems. The focus is on the underlying concepts and the issues which arise in the design of parallel rendering algorithms and systems. We examine the different types of parallelism and how they can be applied in rendering applications. Concepts from parallel computing, such as data decomposition, task granularity, scalability, and load balancing, are considered in relation to the rendering problem. We also explore concepts from computer graphics, such as coherence and projection, which have a significant impact on the structure of parallel rendering algorithms. Our survey covers a number of practical considerations as well, including the choice of architectural platform, communication and memory requirements, and the problem of image assembly and display. We illustrate the discussion with numerous examples from the parallel rendering literature, representing most of the principal rendering methods currently used in computer graphics.
MulticoreBSP for C : A high-performance library for shared-memory parallel programming
Yzelman, A. N.; Bisseling, R. H.; Roose, D.; Meerbergen, K.
2014-01-01
The bulk synchronous parallel (BSP) model, as well as parallel programming interfaces based on BSP, classically target distributed-memory parallel architectures. In earlier work, Yzelman and Bisseling designed a MulticoreBSP for Java library specifically for shared-memory architectures. In the
Genotypic tropism testing by massively parallel sequencing: qualitative and quantitative analysis
Directory of Open Access Journals (Sweden)
Thiele Bernhard
2011-05-01
Full Text Available Abstract Background Inferring viral tropism from genotype is a fast and inexpensive alternative to phenotypic testing. While being highly predictive when performed on clonal samples, sensitivity of predicting CXCR4-using (X4 variants drops substantially in clinical isolates. This is mainly attributed to minor variants not detected by standard bulk-sequencing. Massively parallel sequencing (MPS detects single clones thereby being much more sensitive. Using this technology we wanted to improve genotypic prediction of coreceptor usage. Methods Plasma samples from 55 antiretroviral-treated patients tested for coreceptor usage with the Monogram Trofile Assay were sequenced with standard population-based approaches. Fourteen of these samples were selected for further analysis with MPS. Tropism was predicted from each sequence with geno2pheno[coreceptor]. Results Prediction based on bulk-sequencing yielded 59.1% sensitivity and 90.9% specificity compared to the trofile assay. With MPS, 7600 reads were generated on average per isolate. Minorities of sequences with high confidence in CXCR4-usage were found in all samples, irrespective of phenotype. When using the default false-positive-rate of geno2pheno[coreceptor] (10%, and defining a minority cutoff of 5%, the results were concordant in all but one isolate. Conclusions The combination of MPS and coreceptor usage prediction results in a fast and accurate alternative to phenotypic assays. The detection of X4-viruses in all isolates suggests that coreceptor usage as well as fitness of minorities is important for therapy outcome. The high sensitivity of this technology in combination with a quantitative description of the viral population may allow implementing meaningful cutoffs for predicting response to CCR5-antagonists in the presence of X4-minorities.
Genotypic tropism testing by massively parallel sequencing: qualitative and quantitative analysis.
Däumer, Martin; Kaiser, Rolf; Klein, Rolf; Lengauer, Thomas; Thiele, Bernhard; Thielen, Alexander
2011-05-13
Inferring viral tropism from genotype is a fast and inexpensive alternative to phenotypic testing. While being highly predictive when performed on clonal samples, sensitivity of predicting CXCR4-using (X4) variants drops substantially in clinical isolates. This is mainly attributed to minor variants not detected by standard bulk-sequencing. Massively parallel sequencing (MPS) detects single clones thereby being much more sensitive. Using this technology we wanted to improve genotypic prediction of coreceptor usage. Plasma samples from 55 antiretroviral-treated patients tested for coreceptor usage with the Monogram Trofile Assay were sequenced with standard population-based approaches. Fourteen of these samples were selected for further analysis with MPS. Tropism was predicted from each sequence with geno2pheno[coreceptor]. Prediction based on bulk-sequencing yielded 59.1% sensitivity and 90.9% specificity compared to the trofile assay. With MPS, 7600 reads were generated on average per isolate. Minorities of sequences with high confidence in CXCR4-usage were found in all samples, irrespective of phenotype. When using the default false-positive-rate of geno2pheno[coreceptor] (10%), and defining a minority cutoff of 5%, the results were concordant in all but one isolate. The combination of MPS and coreceptor usage prediction results in a fast and accurate alternative to phenotypic assays. The detection of X4-viruses in all isolates suggests that coreceptor usage as well as fitness of minorities is important for therapy outcome. The high sensitivity of this technology in combination with a quantitative description of the viral population may allow implementing meaningful cutoffs for predicting response to CCR5-antagonists in the presence of X4-minorities.
A high performance parallel approach to medical imaging
International Nuclear Information System (INIS)
Frieder, G.; Frieder, O.; Stytz, M.R.
1988-01-01
Research into medical imaging using general purpose parallel processing architectures is described and a review of the performance of previous medical imaging machines is provided. Results demonstrating that general purpose parallel architectures can achieve performance comparable to other, specialized, medical imaging machine architectures is presented. A new back-to-front hidden-surface removal algorithm is described. Results demonstrating the computational savings obtained by using the modified back-to-front hidden-surface removal algorithm are presented. Performance figures for forming a full-scale medical image on a mesh interconnected multiprocessor are presented
An inherently parallel method for solving discretized diffusion equations
International Nuclear Information System (INIS)
Eccleston, B.R.; Palmer, T.S.
1999-01-01
A Monte Carlo approach to solving linear systems of equations is being investigated in the context of the solution of discretized diffusion equations. While the technique was originally devised decades ago, changes in computer architectures (namely, massively parallel machines) have driven the authors to revisit this technique. There are a number of potential advantages to this approach: (1) Analog Monte Carlo techniques are inherently parallel; this is not necessarily true to today's more advanced linear equation solvers (multigrid, conjugate gradient, etc.); (2) Some forms of this technique are adaptive in that they allow the user to specify locations in the problem where resolution is of particular importance and to concentrate the work at those locations; and (3) These techniques permit the solution of very large systems of equations in that matrix elements need not be stored. The user could trade calculational speed for storage if elements of the matrix are calculated on the fly. The goal of this study is to compare the parallel performance of Monte Carlo linear solvers to that of a more traditional parallelized linear solver. The authors observe the linear speedup that they expect from the Monte Carlo algorithm, given that there is no domain decomposition to cause significant communication overhead. Overall, PETSc outperforms the Monte Carlo solver for the test problem. The PETSc parallel performance improves with larger numbers of unknowns for a given number of processors. Parallel performance of the Monte Carlo technique is independent of the size of the matrix and the number of processes. They are investigating modifications to the scheme to accommodate matrix problems with positive off-diagonal elements. They are also currently coding an on-the-fly version of the algorithm to investigate the solution of very large linear systems
Scalable Distributed Architectures for Information Retrieval
National Research Council Canada - National Science Library
Lu, Zhihong
1999-01-01
.... Our distributed architectures exploit parallelism in information retrieval on a cluster of parallel IR servers using symmetric multiprocessors, and use partial collection replication and selection...
GRay: A MASSIVELY PARALLEL GPU-BASED CODE FOR RAY TRACING IN RELATIVISTIC SPACETIMES
Energy Technology Data Exchange (ETDEWEB)
Chan, Chi-kwan; Psaltis, Dimitrios; Özel, Feryal [Department of Astronomy, University of Arizona, 933 N. Cherry Ave., Tucson, AZ 85721 (United States)
2013-11-01
We introduce GRay, a massively parallel integrator designed to trace the trajectories of billions of photons in a curved spacetime. This graphics-processing-unit (GPU)-based integrator employs the stream processing paradigm, is implemented in CUDA C/C++, and runs on nVidia graphics cards. The peak performance of GRay using single-precision floating-point arithmetic on a single GPU exceeds 300 GFLOP (or 1 ns per photon per time step). For a realistic problem, where the peak performance cannot be reached, GRay is two orders of magnitude faster than existing central-processing-unit-based ray-tracing codes. This performance enhancement allows more effective searches of large parameter spaces when comparing theoretical predictions of images, spectra, and light curves from the vicinities of compact objects to observations. GRay can also perform on-the-fly ray tracing within general relativistic magnetohydrodynamic algorithms that simulate accretion flows around compact objects. Making use of this algorithm, we calculate the properties of the shadows of Kerr black holes and the photon rings that surround them. We also provide accurate fitting formulae of their dependencies on black hole spin and observer inclination, which can be used to interpret upcoming observations of the black holes at the center of the Milky Way, as well as M87, with the Event Horizon Telescope.
Parallel Application Development Using Architecture View Driven Model Transformations
Arkin, E.; Tekinerdogan, B.
2015-01-01
o realize the increased need for computing performance the current trend is towards applying parallel computing in which the tasks are run in parallel on multiple nodes. On its turn we can observe the rapid increase of the scale of parallel computing platforms. This situation has led to a complexity
Parallel computing of a climate model on the dawn 1000 by domain decomposition method
Bi, Xunqiang
1997-12-01
In this paper the parallel computing of a grid-point nine-level atmospheric general circulation model on the Dawn 1000 is introduced. The model was developed by the Institute of Atmospheric Physics (IAP), Chinese Academy of Sciences (CAS). The Dawn 1000 is a MIMD massive parallel computer made by National Research Center for Intelligent Computer (NCIC), CAS. A two-dimensional domain decomposition method is adopted to perform the parallel computing. The potential ways to increase the speed-up ratio and exploit more resources of future massively parallel supercomputation are also discussed.
DEFF Research Database (Denmark)
Zhang, Chi; Guerrero, Josep M.; Vasquez, Juan Carlos
2015-01-01
In this paper, a control strategy for the parallel operation of three-phase inverters forming an online uninterruptible power system (UPS) is presented. The UPS system consists of a cluster of paralleled inverters with LC filters directly connected to an AC critical bus and an AC/DC forming a DC...... bus. The proposed control scheme is performed on two layers: (i) a local layer that contains a “reactive power vs phase” in order to synchronize the phase angle of each inverter and a virtual resistance loop that guarantees equal power sharing among inverters; (ii) a central controller that guarantees...... synchronization with an external real/fictitious utility, and critical bus voltage restoration. Constant transient and steady-state frequency, active, reactive and harmonic power sharing, and global phase-locked loop resynchronization capability are achieved. Detailed system topology and control architecture...
3D streamers simulation in a pin to plane configuration using massively parallel computing
Plewa, J.-M.; Eichwald, O.; Ducasse, O.; Dessante, P.; Jacobs, C.; Renon, N.; Yousfi, M.
2018-03-01
This paper concerns the 3D simulation of corona discharge using high performance computing (HPC) managed with the message passing interface (MPI) library. In the field of finite volume methods applied on non-adaptive mesh grids and in the case of a specific 3D dynamic benchmark test devoted to streamer studies, the great efficiency of the iterative R&B SOR and BiCGSTAB methods versus the direct MUMPS method was clearly demonstrated in solving the Poisson equation using HPC resources. The optimization of the parallelization and the resulting scalability was undertaken as a function of the HPC architecture for a number of mesh cells ranging from 8 to 512 million and a number of cores ranging from 20 to 1600. The R&B SOR method remains at least about four times faster than the BiCGSTAB method and requires significantly less memory for all tested situations. The R&B SOR method was then implemented in a 3D MPI parallelized code that solves the classical first order model of an atmospheric pressure corona discharge in air. The 3D code capabilities were tested by following the development of one, two and four coplanar streamers generated by initial plasma spots for 6 ns. The preliminary results obtained allowed us to follow in detail the formation of the tree structure of a corona discharge and the effects of the mutual interactions between the streamers in terms of streamer velocity, trajectory and diameter. The computing time for 64 million of mesh cells distributed over 1000 cores using the MPI procedures is about 30 min ns-1, regardless of the number of streamers.
Thread-level parallelization and optimization of NWChem for the Intel MIC architecture
Energy Technology Data Exchange (ETDEWEB)
Shan, Hongzhang [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Williams, Samuel [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); de Jong, Wibe [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Oliker, Leonid [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
2015-01-01
In the multicore era it was possible to exploit the increase in on-chip parallelism by simply running multiple MPI processes per chip. Unfortunately, manycore processors' greatly increased thread- and data-level parallelism coupled with a reduced memory capacity demand an altogether different approach. In this paper we explore augmenting two NWChem modules, triples correction of the CCSD(T) and Fock matrix construction, with OpenMP in order that they might run efficiently on future manycore architectures. As the next NERSC machine will be a self-hosted Intel MIC (Xeon Phi) based supercomputer, we leverage an existing MIC testbed at NERSC to evaluate our experiments. In order to proxy the fact that future MIC machines will not have a host processor, we run all of our experiments in native mode. We found that while straightforward application of OpenMP to the deep loop nests associated with the tensor contractions of CCSD(T) was sufficient in attaining high performance, significant e ort was required to safely and efeciently thread the TEXAS integral package when constructing the Fock matrix. Ultimately, our new MPI+OpenMP hybrid implementations attain up to 65× better performance for the triples part of the CCSD(T) due in large part to the fact that the limited on-card memory limits the existing MPI implementation to a single process per card. Additionally, we obtain up to 1.6× better performance on Fock matrix constructions when compared with the best MPI implementations running multiple processes per card.
Thread-Level Parallelization and Optimization of NWChem for the Intel MIC Architecture
Energy Technology Data Exchange (ETDEWEB)
Shan, Hongzhang; Williams, Samuel; Jong, Wibe de; Oliker, Leonid
2014-10-10
In the multicore era it was possible to exploit the increase in on-chip parallelism by simply running multiple MPI processes per chip. Unfortunately, manycore processors' greatly increased thread- and data-level parallelism coupled with a reduced memory capacity demand an altogether different approach. In this paper we explore augmenting two NWChem modules, triples correction of the CCSD(T) and Fock matrix construction, with OpenMP in order that they might run efficiently on future manycore architectures. As the next NERSC machine will be a self-hosted Intel MIC (Xeon Phi) based supercomputer, we leverage an existing MIC testbed at NERSC to evaluate our experiments. In order to proxy the fact that future MIC machines will not have a host processor, we run all of our experiments in tt native mode. We found that while straightforward application of OpenMP to the deep loop nests associated with the tensor contractions of CCSD(T) was sufficient in attaining high performance, significant effort was required to safely and efficiently thread the TEXAS integral package when constructing the Fock matrix. Ultimately, our new MPI OpenMP hybrid implementations attain up to 65x better performance for the triples part of the CCSD(T) due in large part to the fact that the limited on-card memory limits the existing MPI implementation to a single process per card. Additionally, we obtain up to 1.6x better performance on Fock matrix constructions when compared with the best MPI implementations running multiple processes per card.
Nishizawa, Hiroaki; Nishimura, Yoshifumi; Kobayashi, Masato; Irle, Stephan; Nakai, Hiromi
2016-08-05
The linear-scaling divide-and-conquer (DC) quantum chemical methodology is applied to the density-functional tight-binding (DFTB) theory to develop a massively parallel program that achieves on-the-fly molecular reaction dynamics simulations of huge systems from scratch. The functions to perform large scale geometry optimization and molecular dynamics with DC-DFTB potential energy surface are implemented to the program called DC-DFTB-K. A novel interpolation-based algorithm is developed for parallelizing the determination of the Fermi level in the DC method. The performance of the DC-DFTB-K program is assessed using a laboratory computer and the K computer. Numerical tests show the high efficiency of the DC-DFTB-K program, a single-point energy gradient calculation of a one-million-atom system is completed within 60 s using 7290 nodes of the K computer. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.
Roofline model toolkit: A practical tool for architectural and program analysis
Energy Technology Data Exchange (ETDEWEB)
Lo, Yu Jung [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Williams, Samuel [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Van Straalen, Brian [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Ligocki, Terry J. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Cordery, Matthew J. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Wright, Nicholas J. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Hall, Mary W. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Oliker, Leonid [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
2015-04-18
We present preliminary results of the Roofline Toolkit for multicore, many core, and accelerated architectures. This paper focuses on the processor architecture characterization engine, a collection of portable instrumented micro benchmarks implemented with Message Passing Interface (MPI), and OpenMP used to express thread-level parallelism. These benchmarks are specialized to quantify the behavior of different architectural features. Compared to previous work on performance characterization, these microbenchmarks focus on capturing the performance of each level of the memory hierarchy, along with thread-level parallelism, instruction-level parallelism and explicit SIMD parallelism, measured in the context of the compilers and run-time environments. We also measure sustained PCIe throughput with four GPU memory managed mechanisms. By combining results from the architecture characterization with the Roofline model based solely on architectural specifications, this work offers insights for performance prediction of current and future architectures and their software systems. To that end, we instrument three applications and plot their resultant performance on the corresponding Roofline model when run on a Blue Gene/Q architecture.
Frequency of Usher syndrome type 1 in deaf children by massively parallel DNA sequencing.
Yoshimura, Hidekane; Miyagawa, Maiko; Kumakawa, Kozo; Nishio, Shin-Ya; Usami, Shin-Ichi
2016-05-01
Usher syndrome type 1 (USH1) is the most severe of the three USH subtypes due to its profound hearing loss, absent vestibular response and retinitis pigmentosa appearing at a prepubescent age. Six causative genes have been identified for USH1, making early diagnosis and therapy possible through DNA testing. Targeted exon sequencing of selected genes using massively parallel DNA sequencing (MPS) technology enables clinicians to systematically tackle previously intractable monogenic disorders and improve molecular diagnosis. Using MPS along with direct sequence analysis, we screened 227 unrelated non-syndromic deaf children and detected recessive mutations in USH1 causative genes in five patients (2.2%): three patients harbored MYO7A mutations and one each carried CDH23 or PCDH15 mutations. As indicated by an earlier genotype-phenotype correlation study of the CDH23 and PCDH15 genes, we considered the latter two patients to have USH1. Based on clinical findings, it was also highly likely that one patient with MYO7A mutations possessed USH1 due to a late onset age of walking. This first report describing the frequency (1.3-2.2%) of USH1 among non-syndromic deaf children highlights the importance of comprehensive genetic testing for early disease diagnosis.
Parallel Ada benchmarks for the SVMS
Collard, Philippe E.
1990-01-01
The use of parallel processing paradigm to design and develop faster and more reliable computers appear to clearly mark the future of information processing. NASA started the development of such an architecture: the Spaceborne VHSIC Multi-processor System (SVMS). Ada will be one of the languages used to program the SVMS. One of the unique characteristics of Ada is that it supports parallel processing at the language level through the tasking constructs. It is important for the SVMS project team to assess how efficiently the SVMS architecture will be implemented, as well as how efficiently Ada environment will be ported to the SVMS. AUTOCLASS II, a Bayesian classifier written in Common Lisp, was selected as one of the benchmarks for SVMS configurations. The purpose of the R and D effort was to provide the SVMS project team with the version of AUTOCLASS II, written in Ada, that would make use of Ada tasking constructs as much as possible so as to constitute a suitable benchmark. Additionally, a set of programs was developed that would measure Ada tasking efficiency on parallel architectures as well as determine the critical parameters influencing tasking efficiency. All this was designed to provide the SVMS project team with a set of suitable tools in the development of the SVMS architecture.
Optimizing a massive parallel sequencing workflow for quantitative miRNA expression analysis.
Directory of Open Access Journals (Sweden)
Francesca Cordero
Full Text Available BACKGROUND: Massive Parallel Sequencing methods (MPS can extend and improve the knowledge obtained by conventional microarray technology, both for mRNAs and short non-coding RNAs, e.g. miRNAs. The processing methods used to extract and interpret the information are an important aspect of dealing with the vast amounts of data generated from short read sequencing. Although the number of computational tools for MPS data analysis is constantly growing, their strengths and weaknesses as part of a complex analytical pipe-line have not yet been well investigated. PRIMARY FINDINGS: A benchmark MPS miRNA dataset, resembling a situation in which miRNAs are spiked in biological replication experiments was assembled by merging a publicly available MPS spike-in miRNAs data set with MPS data derived from healthy donor peripheral blood mononuclear cells. Using this data set we observed that short reads counts estimation is strongly under estimated in case of duplicates miRNAs, if whole genome is used as reference. Furthermore, the sensitivity of miRNAs detection is strongly dependent by the primary tool used in the analysis. Within the six aligners tested, specifically devoted to miRNA detection, SHRiMP and MicroRazerS show the highest sensitivity. Differential expression estimation is quite efficient. Within the five tools investigated, two of them (DESseq, baySeq show a very good specificity and sensitivity in the detection of differential expression. CONCLUSIONS: The results provided by our analysis allow the definition of a clear and simple analytical optimized workflow for miRNAs digital quantitative analysis.
Optimizing a massive parallel sequencing workflow for quantitative miRNA expression analysis.
Cordero, Francesca; Beccuti, Marco; Arigoni, Maddalena; Donatelli, Susanna; Calogero, Raffaele A
2012-01-01
Massive Parallel Sequencing methods (MPS) can extend and improve the knowledge obtained by conventional microarray technology, both for mRNAs and short non-coding RNAs, e.g. miRNAs. The processing methods used to extract and interpret the information are an important aspect of dealing with the vast amounts of data generated from short read sequencing. Although the number of computational tools for MPS data analysis is constantly growing, their strengths and weaknesses as part of a complex analytical pipe-line have not yet been well investigated. A benchmark MPS miRNA dataset, resembling a situation in which miRNAs are spiked in biological replication experiments was assembled by merging a publicly available MPS spike-in miRNAs data set with MPS data derived from healthy donor peripheral blood mononuclear cells. Using this data set we observed that short reads counts estimation is strongly under estimated in case of duplicates miRNAs, if whole genome is used as reference. Furthermore, the sensitivity of miRNAs detection is strongly dependent by the primary tool used in the analysis. Within the six aligners tested, specifically devoted to miRNA detection, SHRiMP and MicroRazerS show the highest sensitivity. Differential expression estimation is quite efficient. Within the five tools investigated, two of them (DESseq, baySeq) show a very good specificity and sensitivity in the detection of differential expression. The results provided by our analysis allow the definition of a clear and simple analytical optimized workflow for miRNAs digital quantitative analysis.
Parallel thermal radiation transport in two dimensions
International Nuclear Information System (INIS)
Smedley-Stevenson, R.P.; Ball, S.R.
2003-01-01
This paper describes the distributed memory parallel implementation of a deterministic thermal radiation transport algorithm in a 2-dimensional ALE hydrodynamics code. The parallel algorithm consists of a variety of components which are combined in order to produce a state of the art computational capability, capable of solving large thermal radiation transport problems using Blue-Oak, the 3 Tera-Flop MPP (massive parallel processors) computing facility at AWE (United Kingdom). Particular aspects of the parallel algorithm are described together with examples of the performance on some challenging applications. (author)
Parallel thermal radiation transport in two dimensions
Energy Technology Data Exchange (ETDEWEB)
Smedley-Stevenson, R.P.; Ball, S.R. [AWE Aldermaston (United Kingdom)
2003-07-01
This paper describes the distributed memory parallel implementation of a deterministic thermal radiation transport algorithm in a 2-dimensional ALE hydrodynamics code. The parallel algorithm consists of a variety of components which are combined in order to produce a state of the art computational capability, capable of solving large thermal radiation transport problems using Blue-Oak, the 3 Tera-Flop MPP (massive parallel processors) computing facility at AWE (United Kingdom). Particular aspects of the parallel algorithm are described together with examples of the performance on some challenging applications. (author)
Automatic Management of Parallel and Distributed System Resources
Yan, Jerry; Ngai, Tin Fook; Lundstrom, Stephen F.
1990-01-01
Viewgraphs on automatic management of parallel and distributed system resources are presented. Topics covered include: parallel applications; intelligent management of multiprocessing systems; performance evaluation of parallel architecture; dynamic concurrent programs; compiler-directed system approach; lattice gaseous cellular automata; and sparse matrix Cholesky factorization.
Directory of Open Access Journals (Sweden)
Cord Drögemüller
2010-08-01
Full Text Available Arachnomelia is a monogenic recessive defect of skeletal development in cattle. The causative mutation was previously mapped to a ∼7 Mb interval on chromosome 5. Here we show that array-based sequence capture and massively parallel sequencing technology, combined with the typical family structure in livestock populations, facilitates the identification of the causative mutation. We re-sequenced the entire critical interval in a healthy partially inbred cow carrying one copy of the critical chromosome segment in its ancestral state and one copy of the same segment with the arachnomelia mutation, and we detected a single heterozygous position. The genetic makeup of several partially inbred cattle provides extremely strong support for the causality of this mutation. The mutation represents a single base insertion leading to a premature stop codon in the coding sequence of the SUOX gene and is perfectly associated with the arachnomelia phenotype. Our findings suggest an important role for sulfite oxidase in bone development.
Drögemüller, Cord; Tetens, Jens; Sigurdsson, Snaevar; Gentile, Arcangelo; Testoni, Stefania; Lindblad-Toh, Kerstin; Leeb, Tosso
2010-01-01
Arachnomelia is a monogenic recessive defect of skeletal development in cattle. The causative mutation was previously mapped to a ∼7 Mb interval on chromosome 5. Here we show that array-based sequence capture and massively parallel sequencing technology, combined with the typical family structure in livestock populations, facilitates the identification of the causative mutation. We re-sequenced the entire critical interval in a healthy partially inbred cow carrying one copy of the critical chromosome segment in its ancestral state and one copy of the same segment with the arachnomelia mutation, and we detected a single heterozygous position. The genetic makeup of several partially inbred cattle provides extremely strong support for the causality of this mutation. The mutation represents a single base insertion leading to a premature stop codon in the coding sequence of the SUOX gene and is perfectly associated with the arachnomelia phenotype. Our findings suggest an important role for sulfite oxidase in bone development. PMID:20865119
Hu, Peng; Fabyanic, Emily; Kwon, Deborah Y; Tang, Sheng; Zhou, Zhaolan; Wu, Hao
2017-12-07
Massively parallel single-cell RNA sequencing can precisely resolve cellular diversity in a high-throughput manner at low cost, but unbiased isolation of intact single cells from complex tissues such as adult mammalian brains is challenging. Here, we integrate sucrose-gradient-assisted purification of nuclei with droplet microfluidics to develop a highly scalable single-nucleus RNA-seq approach (sNucDrop-seq), which is free of enzymatic dissociation and nucleus sorting. By profiling ∼18,000 nuclei isolated from cortical tissues of adult mice, we demonstrate that sNucDrop-seq not only accurately reveals neuronal and non-neuronal subtype composition with high sensitivity but also enables in-depth analysis of transient transcriptional states driven by neuronal activity, at single-cell resolution, in vivo. Copyright © 2017 Elsevier Inc. All rights reserved.
Design for scalability in 3D computer graphics architectures
DEFF Research Database (Denmark)
Holten-Lund, Hans Erik
2002-01-01
This thesis describes useful methods and techniques for designing scalable hybrid parallel rendering architectures for 3D computer graphics. Various techniques for utilizing parallelism in a pipelines system are analyzed. During the Ph.D study a prototype 3D graphics architecture named Hybris has...
Patterns for Parallel Software Design
Ortega-Arjona, Jorge Luis
2010-01-01
Essential reading to understand patterns for parallel programming Software patterns have revolutionized the way we think about how software is designed, built, and documented, and the design of parallel software requires you to consider other particular design aspects and special skills. From clusters to supercomputers, success heavily depends on the design skills of software developers. Patterns for Parallel Software Design presents a pattern-oriented software architecture approach to parallel software design. This approach is not a design method in the classic sense, but a new way of managin
Massively parallel computation of PARASOL code on the Origin 3800 system
International Nuclear Information System (INIS)
Hosokawa, Masanari; Takizuka, Tomonori
2001-10-01
The divertor particle simulation code named PARASOL simulates open-field plasmas between divertor walls self-consistently by using an electrostatic PIC method and a binary collision Monte Carlo model. The PARASOL parallelized with MPI-1.1 for scalar parallel computer worked on Intel Paragon XP/S system. A system SGI Origin 3800 was newly installed (May, 2001). The parallel programming was improved at this switchover. As a result of the high-performance new hardware and this improvement, the PARASOL is speeded up by about 60 times with the same number of processors. (author)
Parallelization of quantum molecular dynamics simulation code
International Nuclear Information System (INIS)
Kato, Kaori; Kunugi, Tomoaki; Shibahara, Masahiko; Kotake, Susumu
1998-02-01
A quantum molecular dynamics simulation code has been developed for the analysis of the thermalization of photon energies in the molecule or materials in Kansai Research Establishment. The simulation code is parallelized for both Scalar massively parallel computer (Intel Paragon XP/S75) and Vector parallel computer (Fujitsu VPP300/12). Scalable speed-up has been obtained with a distribution to processor units by division of particle group in both parallel computers. As a result of distribution to processor units not only by particle group but also by the particles calculation that is constructed with fine calculations, highly parallelization performance is achieved in Intel Paragon XP/S75. (author)
Parallel Tensor Compression for Large-Scale Scientific Data.
Energy Technology Data Exchange (ETDEWEB)
Kolda, Tamara G. [Sandia National Lab. (SNL-CA), Livermore, CA (United States); Ballard, Grey [Sandia National Lab. (SNL-CA), Livermore, CA (United States); Austin, Woody Nathan [Univ. of Texas, Austin, TX (United States)
2015-10-01
As parallel computing trends towards the exascale, scientific data produced by high-fidelity simulations are growing increasingly massive. For instance, a simulation on a three-dimensional spatial grid with 512 points per dimension that tracks 64 variables per grid point for 128 time steps yields 8 TB of data. By viewing the data as a dense five way tensor, we can compute a Tucker decomposition to find inherent low-dimensional multilinear structure, achieving compression ratios of up to 10000 on real-world data sets with negligible loss in accuracy. So that we can operate on such massive data, we present the first-ever distributed memory parallel implementation for the Tucker decomposition, whose key computations correspond to parallel linear algebra operations, albeit with nonstandard data layouts. Our approach specifies a data distribution for tensors that avoids any tensor data redistribution, either locally or in parallel. We provide accompanying analysis of the computation and communication costs of the algorithms. To demonstrate the compression and accuracy of the method, we apply our approach to real-world data sets from combustion science simulations. We also provide detailed performance results, including parallel performance in both weak and strong scaling experiments.
Design considerations for parallel graphics libraries
Crockett, Thomas W.
1994-01-01
Applications which run on parallel supercomputers are often characterized by massive datasets. Converting these vast collections of numbers to visual form has proven to be a powerful aid to comprehension. For a variety of reasons, it may be desirable to provide this visual feedback at runtime. One way to accomplish this is to exploit the available parallelism to perform graphics operations in place. In order to do this, we need appropriate parallel rendering algorithms and library interfaces. This paper provides a tutorial introduction to some of the issues which arise in designing parallel graphics libraries and their underlying rendering algorithms. The focus is on polygon rendering for distributed memory message-passing systems. We illustrate our discussion with examples from PGL, a parallel graphics library which has been developed on the Intel family of parallel systems.
Yang, Sheng-Chun; Lu, Zhong-Yuan; Qian, Hu-Jun; Wang, Yong-Lei; Han, Jie-Ping
2017-11-01
, 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
A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification
Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun
2016-01-01
Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520
A multimodal parallel architecture: A cognitive framework for multimodal interactions.
Cohn, Neil
2016-01-01
Human communication is naturally multimodal, and substantial focus has examined the semantic correspondences in speech-gesture and text-image relationships. However, visual narratives, like those in comics, provide an interesting challenge to multimodal communication because the words and/or images can guide the overall meaning, and both modalities can appear in complicated "grammatical" sequences: sentences use a syntactic structure and sequential images use a narrative structure. These dual structures create complexity beyond those typically addressed by theories of multimodality where only a single form uses combinatorial structure, and also poses challenges for models of the linguistic system that focus on single modalities. This paper outlines a broad theoretical framework for multimodal interactions by expanding on Jackendoff's (2002) parallel architecture for language. Multimodal interactions are characterized in terms of their component cognitive structures: whether a particular modality (verbal, bodily, visual) is present, whether it uses a grammatical structure (syntax, narrative), and whether it "dominates" the semantics of the overall expression. Altogether, this approach integrates multimodal interactions into an existing framework of language and cognition, and characterizes interactions between varying complexity in the verbal, bodily, and graphic domains. The resulting theoretical model presents an expanded consideration of the boundaries of the "linguistic" system and its involvement in multimodal interactions, with a framework that can benefit research on corpus analyses, experimentation, and the educational benefits of multimodality. Copyright © 2015.
FPGAs and parallel architectures for aerospace applications soft errors and fault-tolerant design
Rech, Paolo
2016-01-01
This book introduces the concepts of soft errors in FPGAs, as well as the motivation for using commercial, off-the-shelf (COTS) FPGAs in mission-critical and remote applications, such as aerospace. The authors describe the effects of radiation in FPGAs, present a large set of soft-error mitigation techniques that can be applied in these circuits, as well as methods for qualifying these circuits under radiation. Coverage includes radiation effects in FPGAs, fault-tolerant techniques for FPGAs, use of COTS FPGAs in aerospace applications, experimental data of FPGAs under radiation, FPGA embedded processors under radiation, and fault injection in FPGAs. Since dedicated parallel processing architectures such as GPUs have become more desirable in aerospace applications due to high computational power, GPU analysis under radiation is also discussed. · Discusses features and drawbacks of reconfigurability methods for FPGAs, focused on aerospace applications; · Explains how radia...
Efficient parallel implementation of active appearance model fitting algorithm on GPU.
Wang, Jinwei; Ma, Xirong; Zhu, Yuanping; Sun, Jizhou
2014-01-01
The active appearance model (AAM) is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs) that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA) on the Nvidia's GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.
Parallel processing from applications to systems
Moldovan, Dan I
1993-01-01
This text provides one of the broadest presentations of parallelprocessing available, including the structure of parallelprocessors and parallel algorithms. The emphasis is on mappingalgorithms to highly parallel computers, with extensive coverage ofarray and multiprocessor architectures. Early chapters provideinsightful coverage on the analysis of parallel algorithms andprogram transformations, effectively integrating a variety ofmaterial previously scattered throughout the literature. Theory andpractice are well balanced across diverse topics in this concisepresentation. For exceptional cla
DEFF Research Database (Denmark)
Ryhl, Camilla
2009-01-01
Accommodating sensory disabilities in architectural design requires specific design considerations. These are different from the ones included by the existing design concept 'accessibility', which primarily accommodates physical disabilites. Hence a new design concept 'sensory accessbility......' is presented as a parallel and complementary concept to the existing one. Sensory accessiblity accommodates sensory disabilities and describes architectural design requirements needed to ensure access to to the sensory experiences and architectural quality of a given space. The article is based on research...
Proposed hardware architectures of particle filter for object tracking
Abd El-Halym, Howida A.; Mahmoud, Imbaby Ismail; Habib, SED
2012-12-01
In this article, efficient hardware architectures for particle filter (PF) are presented. We propose three different architectures for Sequential Importance Resampling Filter (SIRF) implementation. The first architecture is a two-step sequential PF machine, where particle sampling, weight, and output calculations are carried out in parallel during the first step followed by sequential resampling in the second step. For the weight computation step, a piecewise linear function is used instead of the classical exponential function. This decreases the complexity of the architecture without degrading the results. The second architecture speeds up the resampling step via a parallel, rather than a serial, architecture. This second architecture targets a balance between hardware resources and the speed of operation. The third architecture implements the SIRF as a distributed PF composed of several processing elements and central unit. All the proposed architectures are captured using VHDL synthesized using Xilinx environment, and verified using the ModelSim simulator. Synthesis results confirmed the resource reduction and speed up advantages of our architectures.
Directory of Open Access Journals (Sweden)
Md Selim Hossain
Full Text Available In this paper, we propose a novel parallel architecture for fast hardware implementation of elliptic curve point multiplication (ECPM, which is the key operation of an elliptic curve cryptography processor. The point multiplication over binary fields is synthesized on both FPGA and ASIC technology by designing fast elliptic curve group operations in Jacobian projective coordinates. A novel combined point doubling and point addition (PDPA architecture is proposed for group operations to achieve high speed and low hardware requirements for ECPM. It has been implemented over the binary field which is recommended by the National Institute of Standards and Technology (NIST. The proposed ECPM supports two Koblitz and random curves for the key sizes 233 and 163 bits. For group operations, a finite-field arithmetic operation, e.g. multiplication, is designed on a polynomial basis. The delay of a 233-bit point multiplication is only 3.05 and 3.56 μs, in a Xilinx Virtex-7 FPGA, for Koblitz and random curves, respectively, and 0.81 μs in an ASIC 65-nm technology, which are the fastest hardware implementation results reported in the literature to date. In addition, a 163-bit point multiplication is also implemented in FPGA and ASIC for fair comparison which takes around 0.33 and 0.46 μs, respectively. The area-time product of the proposed point multiplication is very low compared to similar designs. The performance ([Formula: see text] and Area × Time × Energy (ATE product of the proposed design are far better than the most significant studies found in the literature.
Machine Learning and Parallelism in the Reconstruction of LHCb and its Upgrade
De Cian, Michel
2016-11-01
The LHCb detector at the LHC is a general purpose detector in the forward region with a focus on reconstructing decays of c- and b-hadrons. For Run II of the LHC, a new trigger strategy with a real-time reconstruction, alignment and calibration was employed. This was made possible by implementing an offline-like track reconstruction in the high level trigger. However, the ever increasing need for a higher throughput and the move to parallelism in the CPU architectures in the last years necessitated the use of vectorization techniques to achieve the desired speed and a more extensive use of machine learning to veto bad events early on. This document discusses selected improvements in computationally expensive parts of the track reconstruction, like the Kalman filter, as well as an improved approach to get rid of fake tracks using fast machine learning techniques. In the last part, a short overview of the track reconstruction challenges for the upgrade of LHCb, is given. Running a fully software-based trigger, a large gain in speed in the reconstruction has to be achieved to cope with the 40 MHz bunch-crossing rate. Two possible approaches for techniques exploiting massive parallelization are discussed.
Machine Learning and Parallelism in the Reconstruction of LHCb and its Upgrade
International Nuclear Information System (INIS)
Cian, Michel De
2016-01-01
The LHCb detector at the LHC is a general purpose detector in the forward region with a focus on reconstructing decays of c- and b-hadrons. For Run II of the LHC, a new trigger strategy with a real-time reconstruction, alignment and calibration was employed. This was made possible by implementing an offline-like track reconstruction in the high level trigger. However, the ever increasing need for a higher throughput and the move to parallelism in the CPU architectures in the last years necessitated the use of vectorization techniques to achieve the desired speed and a more extensive use of machine learning to veto bad events early on. This document discusses selected improvements in computationally expensive parts of the track reconstruction, like the Kalman filter, as well as an improved approach to get rid of fake tracks using fast machine learning techniques. In the last part, a short overview of the track reconstruction challenges for the upgrade of LHCb, is given. Running a fully software-based trigger, a large gain in speed in the reconstruction has to be achieved to cope with the 40 MHz bunch-crossing rate. Two possible approaches for techniques exploiting massive parallelization are discussed
Real-time stereo matching architecture based on 2D MRF model: a memory-efficient systolic array
Directory of Open Access Journals (Sweden)
Park Sungchan
2011-01-01
Full Text Available Abstract There is a growing need in computer vision applications for stereopsis, requiring not only accurate distance but also fast and compact physical implementation. Global energy minimization techniques provide remarkably precise results. But they suffer from huge computational complexity. One of the main challenges is to parallelize the iterative computation, solving the memory access problem between the big external memory and the massive processors. Remarkable memory saving can be obtained with our memory reduction scheme, and our new architecture is a systolic array. If we expand it into N's multiple chips in a cascaded manner, we can cope with various ranges of image resolutions. We have realized it using the FPGA technology. Our architecture records 19 times smaller memory than the global minimization technique, which is a principal step toward real-time chip implementation of the various iterative image processing algorithms with tiny and distributed memory resources like optical flow, image restoration, etc.
cudaBayesreg: Parallel Implementation of a Bayesian Multilevel Model for fMRI Data Analysis
Directory of Open Access Journals (Sweden)
Adelino R. Ferreira da Silva
2011-10-01
Full Text Available Graphic processing units (GPUs are rapidly gaining maturity as powerful general parallel computing devices. A key feature in the development of modern GPUs has been the advancement of the programming model and programming tools. Compute Unified Device Architecture (CUDA is a software platform for massively parallel high-performance computing on Nvidia many-core GPUs. In functional magnetic resonance imaging (fMRI, the volume of the data to be processed, and the type of statistical analysis to perform call for high-performance computing strategies. In this work, we present the main features of the R-CUDA package cudaBayesreg which implements in CUDA the core of a Bayesian multilevel model for the analysis of brain fMRI data. The statistical model implements a Gibbs sampler for multilevel/hierarchical linear models with a normal prior. The main contribution for the increased performance comes from the use of separate threads for fitting the linear regression model at each voxel in parallel. The R-CUDA implementation of the Bayesian model proposed here has been able to reduce significantly the run-time processing of Markov chain Monte Carlo (MCMC simulations used in Bayesian fMRI data analyses. Presently, cudaBayesreg is only configured for Linux systems with Nvidia CUDA support.
Cellular automata a parallel model
Mazoyer, J
1999-01-01
Cellular automata can be viewed both as computational models and modelling systems of real processes. This volume emphasises the first aspect. In articles written by leading researchers, sophisticated massive parallel algorithms (firing squad, life, Fischer's primes recognition) are treated. Their computational power and the specific complexity classes they determine are surveyed, while some recent results in relation to chaos from a new dynamic systems point of view are also presented. Audience: This book will be of interest to specialists of theoretical computer science and the parallelism challenge.
Scudder, Nathan; McNevin, Dennis; Kelty, Sally F; Walsh, Simon J; Robertson, James
2018-03-01
Use of DNA in forensic science will be significantly influenced by new technology in coming years. Massively parallel sequencing and forensic genomics will hasten the broadening of forensic DNA analysis beyond short tandem repeats for identity towards a wider array of genetic markers, in applications as diverse as predictive phenotyping, ancestry assignment, and full mitochondrial genome analysis. With these new applications come a range of legal and policy implications, as forensic science touches on areas as diverse as 'big data', privacy and protected health information. Although these applications have the potential to make a more immediate and decisive forensic intelligence contribution to criminal investigations, they raise policy issues that will require detailed consideration if this potential is to be realised. The purpose of this paper is to identify the scope of the issues that will confront forensic and user communities. Copyright © 2017 The Chartered Society of Forensic Sciences. All rights reserved.
Architectural heritage or theme park
Directory of Open Access Journals (Sweden)
Ignasi Solà-Morales
1998-04-01
Full Text Available The growing parallelism between the perception and the consumer use of theme parks and architectural heritage gives rise to a reflection about the fact that the architectural object has been turned into a museum piece, stripped of its original value and its initial cultural substance to become images exposed to multiple gazes, thus producing what the author calis the "Theme Park effect", with consequences on protected architecture.
Directory of Open Access Journals (Sweden)
Kim De Leeneer
Full Text Available Despite improvements in terms of sequence quality and price per basepair, Sanger sequencing remains restricted to screening of individual disease genes. The development of massively parallel sequencing (MPS technologies heralded an era in which molecular diagnostics for multigenic disorders becomes reality. Here, we outline different PCR amplification based strategies for the screening of a multitude of genes in a patient cohort. We performed a thorough evaluation in terms of set-up, coverage and sequencing variants on the data of 10 GS-FLX experiments (over 200 patients. Crucially, we determined the actual coverage that is required for reliable diagnostic results using MPS, and provide a tool to calculate the number of patients that can be screened in a single run. Finally, we provide an overview of factors contributing to false negative or false positive mutation calls and suggest ways to maximize sensitivity and specificity, both important in a routine setting. By describing practical strategies for screening of multigenic disorders in a multitude of samples and providing answers to questions about minimum required coverage, the number of patients that can be screened in a single run and the factors that may affect sensitivity and specificity we hope to facilitate the implementation of MPS technology in molecular diagnostics.
Enterprise Architecture Integration in E-government
Janssen, M.F.W.H.A.; Cresswell, A.
2005-01-01
Achieving goals of better integrated and responsive government services requires moving away from stand alone applications toward more comprehensive, integrated architectures. As a result there is mounting pressure to move from disparate systems operating in parallel toward a shared architecture
Architectural design and analysis of a programmable image processor
International Nuclear Information System (INIS)
Siyal, M.Y.; Chowdhry, B.S.; Rajput, A.Q.K.
2003-01-01
In this paper we present an architectural design and analysis of a programmable image processor, nicknamed Snake. The processor was designed with a high degree of parallelism to speed up a range of image processing operations. Data parallelism found in array processors has been included into the architecture of the proposed processor. The implementation of commonly used image processing algorithms and their performance evaluation are also discussed. The performance of Snake is also compared with other types of processor architectures. (author)
Parallelization and checkpointing of GPU applications through program transformation
Energy Technology Data Exchange (ETDEWEB)
Solano-Quinde, Lizandro Damian [Iowa State Univ., Ames, IA (United States)
2012-01-01
GPUs have emerged as a powerful tool for accelerating general-purpose applications. The availability of programming languages that makes writing general-purpose applications for running on GPUs tractable have consolidated GPUs as an alternative for accelerating general purpose applications. Among the areas that have benefited from GPU acceleration are: signal and image processing, computational fluid dynamics, quantum chemistry, and, in general, the High Performance Computing (HPC) Industry. In order to continue to exploit higher levels of parallelism with GPUs, multi-GPU systems are gaining popularity. In this context, single-GPU applications are parallelized for running in multi-GPU systems. Furthermore, multi-GPU systems help to solve the GPU memory limitation for applications with large application memory footprint. Parallelizing single-GPU applications has been approached by libraries that distribute the workload at runtime, however, they impose execution overhead and are not portable. On the other hand, on traditional CPU systems, parallelization has been approached through application transformation at pre-compile time, which enhances the application to distribute the workload at application level and does not have the issues of library-based approaches. Hence, a parallelization scheme for GPU systems based on application transformation is needed. Like any computing engine of today, reliability is also a concern in GPUs. GPUs are vulnerable to transient and permanent failures. Current checkpoint/restart techniques are not suitable for systems with GPUs. Checkpointing for GPU systems present new and interesting challenges, primarily due to the natural differences imposed by the hardware design, the memory subsystem architecture, the massive number of threads, and the limited amount of synchronization among threads. Therefore, a checkpoint/restart technique suitable for GPU systems is needed. The goal of this work is to exploit higher levels of parallelism and
Parallel generation of architecture on the GPU
Steinberger, Markus; Kenzel, Michael; Kainz, Bernhard K.; Mü ller, Jö rg; Wonka, Peter; Schmalstieg, Dieter
2014-01-01
they can take advantage of, or both, our method supports state of the art procedural modeling including stochasticity and context-sensitivity. To increase parallelism, we explicitly express independence in the grammar, reduce inter-rule dependencies
Directory of Open Access Journals (Sweden)
Kim Vancampenhout
Full Text Available The advent of massive parallel sequencing (MPS has revolutionized the field of human molecular genetics, including the diagnostic study of mitochondrial (mt DNA dysfunction. The analysis of the complete mitochondrial genome using MPS platforms is now common and will soon outrun conventional sequencing. However, the development of a robust and reliable protocol is rather challenging. A previous pilot study for the re-sequencing of human mtDNA revealed an uneven coverage, affecting predominantly part of the plus strand. In an attempt to address this problem, we undertook a comparative study of standard and modified protocols for the Ion Torrent PGM system. We could not improve strand representation by altering the recommended shearing methodology of the standard workflow or omitting the DNA polymerase amplification step from the library construction process. However, we were able to associate coverage bias of the plus strand with a specific sequence motif. Additionally, we compared coverage and variant calling across technologies. The same samples were also sequenced on a MiSeq device which showed that coverage and heteroplasmic variant calling were much improved.
Fernández-Caballero Rico, Jose Ángel; Chueca Porcuna, Natalia; Álvarez Estévez, Marta; Mosquera Gutiérrez, María Del Mar; Marcos Maeso, María Ángeles; García, Federico
2018-02-01
To show how to generate a consensus sequence from the information of massive parallel sequences data obtained from routine HIV anti-retroviral resistance studies, and that may be suitable for molecular epidemiology studies. Paired Sanger (Trugene-Siemens) and next-generation sequencing (NGS) (454 GSJunior-Roche) HIV RT and protease sequences from 62 patients were studied. NGS consensus sequences were generated using Mesquite, using 10%, 15%, and 20% thresholds. Molecular evolutionary genetics analysis (MEGA) was used for phylogenetic studies. At a 10% threshold, NGS-Sanger sequences from 17/62 patients were phylogenetically related, with a median bootstrap-value of 88% (IQR83.5-95.5). Association increased to 36/62 sequences, median bootstrap 94% (IQR85.5-98)], using a 15% threshold. Maximum association was at the 20% threshold, with 61/62 sequences associated, and a median bootstrap value of 99% (IQR98-100). A safe method is presented to generate consensus sequences from HIV-NGS data at 20% threshold, which will prove useful for molecular epidemiological studies. Copyright © 2016 Elsevier España, S.L.U. and Sociedad Española de Enfermedades Infecciosas y Microbiología Clínica. All rights reserved.
Parallel, Asynchronous Executive (PAX): System concepts, facilities, and architecture
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.
Algorithms for computational fluid dynamics n parallel processors
International Nuclear Information System (INIS)
Van de Velde, E.F.
1986-01-01
A study of parallel algorithms for the numerical solution of partial differential equations arising in computational fluid dynamics is presented. The actual implementation on parallel processors of shared and nonshared memory design is discussed. The performance of these algorithms is analyzed in terms of machine efficiency, communication time, bottlenecks and software development costs. For elliptic equations, a parallel preconditioned conjugate gradient method is described, which has been used to solve pressure equations discretized with high order finite elements on irregular grids. A parallel full multigrid method and a parallel fast Poisson solver are also presented. Hyperbolic conservation laws were discretized with parallel versions of finite difference methods like the Lax-Wendroff scheme and with the Random Choice method. Techniques are developed for comparing the behavior of an algorithm on different architectures as a function of problem size and local computational effort. Effective use of these advanced architecture machines requires the use of machine dependent programming. It is shown that the portability problems can be minimized by introducing high level operations on vectors and matrices structured into program libraries
Parallelism in matrix computations
Gallopoulos, Efstratios; Sameh, Ahmed H
2016-01-01
This book is primarily intended as a research monograph that could also be used in graduate courses for the design of parallel algorithms in matrix computations. It assumes general but not extensive knowledge of numerical linear algebra, parallel architectures, and parallel programming paradigms. The book consists of four parts: (I) Basics; (II) Dense and Special Matrix Computations; (III) Sparse Matrix Computations; and (IV) Matrix functions and characteristics. Part I deals with parallel programming paradigms and fundamental kernels, including reordering schemes for sparse matrices. Part II is devoted to dense matrix computations such as parallel algorithms for solving linear systems, linear least squares, the symmetric algebraic eigenvalue problem, and the singular-value decomposition. It also deals with the development of parallel algorithms for special linear systems such as banded ,Vandermonde ,Toeplitz ,and block Toeplitz systems. Part III addresses sparse matrix computations: (a) the development of pa...
Distributed and parallel approach for handle and perform huge datasets
Konopko, Joanna
2015-12-01
Big Data refers to the dynamic, large and disparate volumes of data comes from many different sources (tools, machines, sensors, mobile devices) uncorrelated with each others. It requires new, innovative and scalable technology to collect, host and analytically process the vast amount of data. Proper architecture of the system that perform huge data sets is needed. In this paper, the comparison of distributed and parallel system architecture is presented on the example of MapReduce (MR) Hadoop platform and parallel database platform (DBMS). This paper also analyzes the problem of performing and handling valuable information from petabytes of data. The both paradigms: MapReduce and parallel DBMS are described and compared. The hybrid architecture approach is also proposed and could be used to solve the analyzed problem of storing and processing Big Data.
Efficient Parallel Implementation of Active Appearance Model Fitting Algorithm on GPU
Directory of Open Access Journals (Sweden)
Jinwei Wang
2014-01-01
Full Text Available The active appearance model (AAM is one of the most powerful model-based object detecting and tracking methods which has been widely used in various situations. However, the high-dimensional texture representation causes very time-consuming computations, which makes the AAM difficult to apply to real-time systems. The emergence of modern graphics processing units (GPUs that feature a many-core, fine-grained parallel architecture provides new and promising solutions to overcome the computational challenge. In this paper, we propose an efficient parallel implementation of the AAM fitting algorithm on GPUs. Our design idea is fine grain parallelism in which we distribute the texture data of the AAM, in pixels, to thousands of parallel GPU threads for processing, which makes the algorithm fit better into the GPU architecture. We implement our algorithm using the compute unified device architecture (CUDA on the Nvidia’s GTX 650 GPU, which has the latest Kepler architecture. To compare the performance of our algorithm with different data sizes, we built sixteen face AAM models of different dimensional textures. The experiment results show that our parallel AAM fitting algorithm can achieve real-time performance for videos even on very high-dimensional textures.
Parallel phase model : a programming model for high-end parallel machines with manycores.
Energy Technology Data Exchange (ETDEWEB)
Wu, Junfeng (Syracuse University, Syracuse, NY); Wen, Zhaofang; Heroux, Michael Allen; Brightwell, Ronald Brian
2009-04-01
This paper presents a parallel programming model, Parallel Phase Model (PPM), for next-generation high-end parallel machines based on a distributed memory architecture consisting of a networked cluster of nodes with a large number of cores on each node. PPM has a unified high-level programming abstraction that facilitates the design and implementation of parallel algorithms to exploit both the parallelism of the many cores and the parallelism at the cluster level. The programming abstraction will be suitable for expressing both fine-grained and coarse-grained parallelism. It includes a few high-level parallel programming language constructs that can be added as an extension to an existing (sequential or parallel) programming language such as C; and the implementation of PPM also includes a light-weight runtime library that runs on top of an existing network communication software layer (e.g. MPI). Design philosophy of PPM and details of the programming abstraction are also presented. Several unstructured applications that inherently require high-volume random fine-grained data accesses have been implemented in PPM with very promising results.
International Nuclear Information System (INIS)
Li Hanyu; Zhou Haijing; Dong Zhiwei; Liao Cheng; Chang Lei; Cao Xiaolin; Xiao Li
2010-01-01
A large-scale parallel electromagnetic field simulation program JEMS-FDTD(J Electromagnetic Solver-Finite Difference Time Domain) is designed and implemented on JASMIN (J parallel Adaptive Structured Mesh applications INfrastructure). This program can simulate propagation, radiation, couple of electromagnetic field by solving Maxwell equations on structured mesh explicitly with FDTD method. JEMS-FDTD is able to simulate billion-mesh-scale problems on thousands of processors. In this article, the program is verified by simulating the radiation of an electric dipole. A beam waveguide is simulated to demonstrate the capability of large scale parallel computation. A parallel performance test indicates that a high parallel efficiency is obtained. (authors)
Directory of Open Access Journals (Sweden)
Pietro Quaglio
2017-05-01
Full Text Available Repeated, precise sequences of spikes are largely considered a signature of activation of cell assemblies. These repeated sequences are commonly known under the name of spatio-temporal patterns (STPs. STPs are hypothesized to play a role in the communication of information in the computational process operated by the cerebral cortex. A variety of statistical methods for the detection of STPs have been developed and applied to electrophysiological recordings, but such methods scale poorly with the current size of available parallel spike train recordings (more than 100 neurons. In this work, we introduce a novel method capable of overcoming the computational and statistical limits of existing analysis techniques in detecting repeating STPs within massively parallel spike trains (MPST. We employ advanced data mining techniques to efficiently extract repeating sequences of spikes from the data. Then, we introduce and compare two alternative approaches to distinguish statistically significant patterns from chance sequences. The first approach uses a measure known as conceptual stability, of which we investigate a computationally cheap approximation for applications to such large data sets. The second approach is based on the evaluation of pattern statistical significance. In particular, we provide an extension to STPs of a method we recently introduced for the evaluation of statistical significance of synchronous spike patterns. The performance of the two approaches is evaluated in terms of computational load and statistical power on a variety of artificial data sets that replicate specific features of experimental data. Both methods provide an effective and robust procedure for detection of STPs in MPST data. The method based on significance evaluation shows the best overall performance, although at a higher computational cost. We name the novel procedure the spatio-temporal Spike PAttern Detection and Evaluation (SPADE analysis.
Parallelism and Scalability in an Image Processing Application
DEFF Research Database (Denmark)
Rasmussen, Morten Sleth; Stuart, Matthias Bo; Karlsson, Sven
2008-01-01
parallel programs. This paper investigates parallelism and scalability of an embedded image processing application. The major challenges faced when parallelizing the application were to extract enough parallelism from the application and to reduce load imbalance. The application has limited immediately......The recent trends in processor architecture show that parallel processing is moving into new areas of computing in the form of many-core desktop processors and multi-processor system-on-chip. This means that parallel processing is required in application areas that traditionally have not used...
Parallelism and Scalability in an Image Processing Application
DEFF Research Database (Denmark)
Rasmussen, Morten Sleth; Stuart, Matthias Bo; Karlsson, Sven
2009-01-01
parallel programs. This paper investigates parallelism and scalability of an embedded image processing application. The major challenges faced when parallelizing the application were to extract enough parallelism from the application and to reduce load imbalance. The application has limited immediately......The recent trends in processor architecture show that parallel processing is moving into new areas of computing in the form of many-core desktop processors and multi-processor system-on-chips. This means that parallel processing is required in application areas that traditionally have not used...
Massive Sensor Array Fault Tolerance: Tolerance Mechanism and Fault Injection for Validation
Directory of Open Access Journals (Sweden)
Dugan Um
2010-01-01
Full Text Available As today's machines become increasingly complex in order to handle intricate tasks, the number of sensors must increase for intelligent operations. Given the large number of sensors, detecting, isolating, and then tolerating faulty sensors is especially important. In this paper, we propose fault tolerance architecture suitable for a massive sensor array often found in highly advanced systems such as autonomous robots. One example is the sensitive skin, a type of massive sensor array. The objective of the sensitive skin is autonomous guidance of machines in unknown environments, requiring elongated operations in a remote site. The entirety of such a system needs to be able to work remotely without human attendance for an extended period of time. To that end, we propose a fault-tolerant architecture whereby component and analytical redundancies are integrated cohesively for effective failure tolerance of a massive array type sensor or sensor system. In addition, we discuss the evaluation results of the proposed tolerance scheme by means of fault injection and validation analysis as a measure of system reliability and performance.
Liu, Kuojuey Ray
1990-01-01
Least-squares (LS) estimations and spectral decomposition algorithms constitute the heart of modern signal processing and communication problems. Implementations of recursive LS and spectral decomposition algorithms onto parallel processing architectures such as systolic arrays with efficient fault-tolerant schemes are the major concerns of this dissertation. There are four major results in this dissertation. First, we propose the systolic block Householder transformation with application to the recursive least-squares minimization. It is successfully implemented on a systolic array with a two-level pipelined implementation at the vector level as well as at the word level. Second, a real-time algorithm-based concurrent error detection scheme based on the residual method is proposed for the QRD RLS systolic array. The fault diagnosis, order degraded reconfiguration, and performance analysis are also considered. Third, the dynamic range, stability, error detection capability under finite-precision implementation, order degraded performance, and residual estimation under faulty situations for the QRD RLS systolic array are studied in details. Finally, we propose the use of multi-phase systolic algorithms for spectral decomposition based on the QR algorithm. Two systolic architectures, one based on triangular array and another based on rectangular array, are presented for the multiphase operations with fault-tolerant considerations. Eigenvectors and singular vectors can be easily obtained by using the multi-pase operations. Performance issues are also considered.
Scalable Algorithms for Clustering Large Geospatiotemporal Data Sets on Manycore Architectures
Mills, R. T.; Hoffman, F. M.; Kumar, J.; Sreepathi, S.; Sripathi, V.
2016-12-01
The increasing availability of high-resolution geospatiotemporal data sets from sources such as observatory networks, remote sensing platforms, and computational Earth system models has opened new possibilities for knowledge discovery using data sets fused from disparate sources. Traditional algorithms and computing platforms are impractical for the analysis and synthesis of data sets of this size; however, new algorithmic approaches that can effectively utilize the complex memory hierarchies and the extremely high levels of available parallelism in state-of-the-art high-performance computing platforms can enable such analysis. We describe a massively parallel implementation of accelerated k-means clustering and some optimizations to boost computational intensity and utilization of wide SIMD lanes on state-of-the art multi- and manycore processors, including the second-generation Intel Xeon Phi ("Knights Landing") processor based on the Intel Many Integrated Core (MIC) architecture, which includes several new features, including an on-package high-bandwidth memory. We also analyze the code in the context of a few practical applications to the analysis of climatic and remotely-sensed vegetation phenology data sets, and speculate on some of the new applications that such scalable analysis methods may enable.
Implementation of GPU parallel equilibrium reconstruction for plasma control in EAST
Energy Technology Data Exchange (ETDEWEB)
Huang, Yao, E-mail: yaohuang@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); Xiao, B.J. [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); School of Nuclear Science & Technology, University of Science & Technology of China (China); Luo, Z.P.; Yuan, Q.P.; Pei, X.F. [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei (China); Yue, X.N. [School of Nuclear Science & Technology, University of Science & Technology of China (China)
2016-11-15
Highlights: • We described parallel equilibrium reconstruction code P-EFIT running on GPU was integrated with EAST plasma control system. • Compared with RT-EFIT used in EAST, P-EFIT has better spatial resolution and full algorithm of EFIT per iteration. • With the data interface through RFM, 65 × 65 spatial grids P-EFIT can satisfy the accuracy and time feasibility requirements for plasma control. • Successful control using ISOFLUX/P-EFIT was established in the dedicated experiment during the EAST 2014 campaign. • This work is a stepping-stone towards versatile ISOFLUX/P-EFIT control, such as real-time equilibrium reconstruction with more diagnostics. - Abstract: Implementation of P-EFIT code for plasma control in EAST is described. P-EFIT is based on the EFIT framework, but built with the CUDA™ architecture to take advantage of massively parallel Graphical Processing Unit (GPU) cores to significantly accelerate the computation. 65 × 65 grid size P-EFIT can complete one reconstruction iteration in 300 μs, with one iteration strategy, it can satisfy the needs of real-time plasma shape control. Data interface between P-EFIT and PCS is realized and developed by transferring data through RFM. First application of P-EFIT to discharge control in EAST is described.
Construction of a digital elevation model: methods and parallelization
International Nuclear Information System (INIS)
Mazzoni, Christophe
1995-01-01
The aim of this work is to reduce the computation time needed to produce the Digital Elevation Models (DEM) by using a parallel machine. It is made in collaboration between the French 'Institut Geographique National' (IGN) and the Laboratoire d'Electronique de Technologie et d'Instrumentation (LETI) of the French Atomic Energy Commission (CEA). The IGN has developed a system which provides DEM that is used to produce topographic maps. The kernel of this system is the correlator, a software which automatically matches pairs of homologous points of a stereo-pair of photographs. Nevertheless the correlator is expensive In computing time. In order to reduce computation time and to produce the DEM with same accuracy that the actual system, we have parallelized the IGN's correlator on the OPENVISION system. This hardware solution uses a SIMD (Single Instruction Multiple Data) parallel machine SYMPATI-2, developed by the LETI that is involved in parallel architecture and image processing. Our analysis of the implementation has demonstrated the difficulty of efficient coupling between scalar and parallel structure. So we propose solutions to reinforce this coupling. In order to accelerate more the processing we evaluate SYMPHONIE, a SIMD calculator, successor of SYMPATI-2. On an other hand, we developed a multi-agent approach for what a MIMD (Multiple Instruction, Multiple Data) architecture is available. At last, we describe a Multi-SIMD architecture that conciliates our two approaches. This architecture offers a capacity to apprehend efficiently multi-level treatment image. It is flexible by its modularity, and its communication network supplies reliability that interest sensible systems. (author) [fr
PSHED: a simplified approach to developing parallel programs
International Nuclear Information System (INIS)
Mahajan, S.M.; Ramesh, K.; Rajesh, K.; Somani, A.; Goel, M.
1992-01-01
This paper presents a simplified approach in the forms of a tree structured computational model for parallel application programs. An attempt is made to provide a standard user interface to execute programs on BARC Parallel Processing System (BPPS), a scalable distributed memory multiprocessor. The interface package called PSHED provides a basic framework for representing and executing parallel programs on different parallel architectures. The PSHED package incorporates concepts from a broad range of previous research in programming environments and parallel computations. (author). 6 refs
Large-Scale, Parallel, Multi-Sensor Atmospheric Data Fusion Using Cloud Computing
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
PRISMA/DB: A Parallel Main-Memory Relational DBMS
Apers, Peter M.G.; Flokstra, Jan; van den Berg, Carel A.; Grefen, P.W.P.J.; Wilschut, A.N.; Kersten, Martin L.; van den Berg, C.A.
1992-01-01
PRISMA/DB, a full-fledged parallel, main memory relational database management system (DBMS) is described. PRISMA/DB's high performance is obtained by the use of parallelism for query processing and main memory storage of the entire database. A flexible architecture for experimenting with
Performative Architecture and Urban Spaces
DEFF Research Database (Denmark)
Kiib, Hans
2008-01-01
3 Workshops one exibition Three conceptual architectural workshops took take place in parallel from August 16th - 22nd 2008. Each workshop carried a specific methodology and the goal is to come up with conceptual proposals that could be further developed for selected sites in the city of Aalb...... This workshop focus on temporary architecture and urban catalysts. Informal spaces and the interface between the built and the void are foremost in the development of performative urban environments and cultural interaction. ...... 3 Workshops one exibition Three conceptual architectural workshops took take place in parallel from August 16th - 22nd 2008. Each workshop carried a specific methodology and the goal is to come up with conceptual proposals that could be further developed for selected sites in the city...... The workshop model includes an open workshop where a handful of international architects are invited to spend five days with local architects, engineers and scholars contributing to a work of architectural vision and quality. The workshop includes presentations and discussions and development of projects...
Scalable Strategies for Computing with Massive Data
Directory of Open Access Journals (Sweden)
Michael Kane
2013-11-01
Full Text Available This paper presents two complementary statistical computing frameworks that address challenges in parallel processing and the analysis of massive data. First, the foreach package allows users of the R programming environment to define parallel loops that may be run sequentially on a single machine, in parallel on a symmetric multiprocessing (SMP machine, or in cluster environments without platform-specific code. Second, the bigmemory package implements memory- and file-mapped data structures that provide (a access to arbitrarily large data while retaining a look and feel that is familiar to R users and (b data structures that are shared across processor cores in order to support efficient parallel computing techniques. Although these packages may be used independently, this paper shows how they can be used in combination to address challenges that have effectively been beyond the reach of researchers who lack specialized software development skills or expensive hardware.
Load Scheduling in a Cloud Based Massive Video-Storage Environment
DEFF Research Database (Denmark)
Bayyapu, Karunakar Reddy; Fischer, Paul
2015-01-01
We propose an architecture for a storage system of surveillance videos. Such systems have to handle massive amounts of incoming video streams and relatively few requests for replay. In such a system load (i.e., Write requests) scheduling is essential to guarantee performance. Large-scale data-sto...
Computer architecture fundamentals and principles of computer design
Dumas II, Joseph D
2005-01-01
Introduction to Computer ArchitectureWhat is Computer Architecture?Architecture vs. ImplementationBrief History of Computer SystemsThe First GenerationThe Second GenerationThe Third GenerationThe Fourth GenerationModern Computers - The Fifth GenerationTypes of Computer SystemsSingle Processor SystemsParallel Processing SystemsSpecial ArchitecturesQuality of Computer SystemsGenerality and ApplicabilityEase of UseExpandabilityCompatibilityReliabilitySuccess and Failure of Computer Architectures and ImplementationsQuality and the Perception of QualityCost IssuesArchitectural Openness, Market Timi
Exploiting parallel R in the cloud with SPRINT.
Piotrowski, M; McGilvary, G A; Sloan, T M; Mewissen, M; Lloyd, A D; Forster, T; Mitchell, L; Ghazal, P; Hill, J
2013-01-01
Advances in DNA Microarray devices and next-generation massively parallel DNA sequencing platforms have led to an exponential growth in data availability but the arising opportunities require adequate computing resources. High Performance Computing (HPC) in the Cloud offers an affordable way of meeting this need. Bioconductor, a popular tool for high-throughput genomic data analysis, is distributed as add-on modules for the R statistical programming language but R has no native capabilities for exploiting multi-processor architectures. SPRINT is an R package that enables easy access to HPC for genomics researchers. This paper investigates: setting up and running SPRINT-enabled genomic analyses on Amazon's Elastic Compute Cloud (EC2), the advantages of submitting applications to EC2 from different parts of the world and, if resource underutilization can improve application performance. The SPRINT parallel implementations of correlation, permutation testing, partitioning around medoids and the multi-purpose papply have been benchmarked on data sets of various size on Amazon EC2. Jobs have been submitted from both the UK and Thailand to investigate monetary differences. It is possible to obtain good, scalable performance but the level of improvement is dependent upon the nature of the algorithm. Resource underutilization can further improve the time to result. End-user's location impacts on costs due to factors such as local taxation. Although not designed to satisfy HPC requirements, Amazon EC2 and cloud computing in general provides an interesting alternative and provides new possibilities for smaller organisations with limited funds.
Physics Detector Simulation Facility (PDSF) architecture/utilization
International Nuclear Information System (INIS)
Scipioni, B.
1993-05-01
The current systems architecture for the SSCL's Physics Detector Simulation Facility (PDSF) is presented. Systems analysis data is presented and discussed. In particular, these data disclose the effectiveness of utilization of the facility for meeting the needs of physics computing, especially as concerns parallel architecture and processing. Detailed design plans for the highly networked, symmetric, parallel, UNIX workstation-based facility are given and discussed in light of the design philosophy. Included are network, CPU, disk, router, concentrator, tape, user and job capacities and throughput
Geospatial Applications on Different Parallel and Distributed Systems in enviroGRIDS Project
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
Hoekstra, A.G.; Sloot, P.M.A.; Haan, M.J.; Hertzberger, L.O.; van Leeuwen, J.
1991-01-01
New developments in Computer Science, both hardware and software, offer researchers, such as physicists, unprecedented possibilities to solve their computational intensive problems.However, full exploitation of e.g. new massively parallel computers, parallel languages or runtime environments
Optimisation of a parallel ocean general circulation model
Beare, M. I.; Stevens, D. P.
1997-10-01
This paper presents the development of a general-purpose parallel ocean circulation model, for use on a wide range of computer platforms, from traditional scalar machines to workstation clusters and massively parallel processors. Parallelism is provided, as a modular option, via high-level message-passing routines, thus hiding the technical intricacies from the user. An initial implementation highlights that the parallel efficiency of the model is adversely affected by a number of factors, for which optimisations are discussed and implemented. The resulting ocean code is portable and, in particular, allows science to be achieved on local workstations that could otherwise only be undertaken on state-of-the-art supercomputers.
Design strategies for irregularly adapting parallel applications
International Nuclear Information System (INIS)
Oliker, Leonid; Biswas, Rupak; Shan, Hongzhang; Sing, Jaswinder Pal
2000-01-01
Achieving scalable performance for dynamic irregular applications is eminently challenging. Traditional message-passing approaches have been making steady progress towards this goal; however, they suffer from complex implementation requirements. The use of a global address space greatly simplifies the programming task, but can degrade the performance of dynamically adapting computations. In this work, we examine two major classes of adaptive applications, under five competing programming methodologies and four leading parallel architectures. Results indicate that it is possible to achieve message-passing performance using shared-memory programming techniques by carefully following the same high level strategies. Adaptive applications have computational work loads and communication patterns which change unpredictably at runtime, requiring dynamic load balancing to achieve scalable performance on parallel machines. Efficient parallel implementations of such adaptive applications are therefore a challenging task. This work examines the implementation of two typical adaptive applications, Dynamic Remeshing and N-Body, across various programming paradigms and architectural platforms. We compare several critical factors of the parallel code development, including performance, programmability, scalability, algorithmic development, and portability
Recent progress in 3D EM/EM-PIC simulation with ARGUS and parallel ARGUS
International Nuclear Information System (INIS)
Mankofsky, A.; Petillo, J.; Krueger, W.; Mondelli, A.; McNamara, B.; Philp, R.
1994-01-01
ARGUS is an integrated, 3-D, volumetric simulation model for systems involving electric and magnetic fields and charged particles, including materials embedded in the simulation region. The code offers the capability to carry out time domain and frequency domain electromagnetic simulations of complex physical systems. ARGUS offers a boolean solid model structure input capability that can include essentially arbitrary structures on the computational domain, and a modular architecture that allows multiple physics packages to access the same data structure and to share common code utilities. Physics modules are in place to compute electrostatic and electromagnetic fields, the normal modes of RF structures, and self-consistent particle-in-cell (PIC) simulation in either a time dependent mode or a steady state mode. The PIC modules include multiple particle species, the Lorentz equations of motion, and algorithms for the creation of particles by emission from material surfaces, injection onto the grid, and ionization. In this paper, we present an updated overview of ARGUS, with particular emphasis given in recent algorithmic and computational advances. These include a completely rewritten frequency domain solver which efficiently treats lossy materials and periodic structures, a parallel version of ARGUS with support for both shared memory parallel vector (i.e. CRAY) machines and distributed memory massively parallel MIMD systems, and numerous new applications of the code
Murni, Bustamam, A.; Ernastuti, Handhika, T.; Kerami, D.
2017-07-01
Calculation of the matrix-vector multiplication in the real-world problems often involves large matrix with arbitrary size. Therefore, parallelization is needed to speed up the calculation process that usually takes a long time. Graph partitioning techniques that have been discussed in the previous studies cannot be used to complete the parallelized calculation of matrix-vector multiplication with arbitrary size. This is due to the assumption of graph partitioning techniques that can only solve the square and symmetric matrix. Hypergraph partitioning techniques will overcome the shortcomings of the graph partitioning technique. This paper addresses the efficient parallelization of matrix-vector multiplication through hypergraph partitioning techniques using CUDA GPU-based parallel computing. CUDA (compute unified device architecture) is a parallel computing platform and programming model that was created by NVIDIA and implemented by the GPU (graphics processing unit).
Regional-scale calculation of the LS factor using parallel processing
Liu, Kai; Tang, Guoan; Jiang, Ling; Zhu, A.-Xing; Yang, Jianyi; Song, Xiaodong
2015-05-01
With the increase of data resolution and the increasing application of USLE over large areas, the existing serial implementation of algorithms for computing the LS factor is becoming a bottleneck. In this paper, a parallel processing model based on message passing interface (MPI) is presented for the calculation of the LS factor, so that massive datasets at a regional scale can be processed efficiently. The parallel model contains algorithms for calculating flow direction, flow accumulation, drainage network, slope, slope length and the LS factor. According to the existence of data dependence, the algorithms are divided into local algorithms and global algorithms. Parallel strategy are designed according to the algorithm characters including the decomposition method for maintaining the integrity of the results, optimized workflow for reducing the time taken for exporting the unnecessary intermediate data and a buffer-communication-computation strategy for improving the communication efficiency. Experiments on a multi-node system show that the proposed parallel model allows efficient calculation of the LS factor at a regional scale with a massive dataset.
Shared Variable Oriented Parallel Precompiler for SPMD Model
Institute of Scientific and Technical Information of China (English)
无
1995-01-01
For the moment,commercial parallel computer systems with distributed memory architecture are usually provided with parallel FORTRAN or parallel C compliers,which are just traditional sequential FORTRAN or C compilers expanded with communication statements.Programmers suffer from writing parallel programs with communication statements. The Shared Variable Oriented Parallel Precompiler (SVOPP) proposed in this paper can automatically generate appropriate communication statements based on shared variables for SPMD(Single Program Multiple Data) computation model and greatly ease the parallel programming with high communication efficiency.The core function of parallel C precompiler has been successfully verified on a transputer-based parallel computer.Its prominent performance shows that SVOPP is probably a break-through in parallel programming technique.
AMIDST: Analysis of MassIve Data STreams
DEFF Research Database (Denmark)
Masegosa, Andres; Martinez, Ana Maria; Borchani, Hanen
2015-01-01
The Analysis of MassIve Data STreams (AMIDST) Java toolbox provides a collection of scalable and parallel algorithms for inference and learning of hybrid Bayesian networks from data streams. The toolbox, available at http://amidst.github.io/toolbox/ under the Apache Software License version 2.......0, also efficiently leverages existing functionalities and algorithms by interfacing to software tools such as HUGIN and MOA....
Parallel algorithm of real-time infrared image restoration based on total variation theory
Zhu, Ran; Li, Miao; Long, Yunli; Zeng, Yaoyuan; An, Wei
2015-10-01
Image restoration is a necessary preprocessing step for infrared remote sensing applications. Traditional methods allow us to remove the noise but penalize too much the gradients corresponding to edges. Image restoration techniques based on variational approaches can solve this over-smoothing problem for the merits of their well-defined mathematical modeling of the restore procedure. The total variation (TV) of infrared image is introduced as a L1 regularization term added to the objective energy functional. It converts the restoration process to an optimization problem of functional involving a fidelity term to the image data plus a regularization term. Infrared image restoration technology with TV-L1 model exploits the remote sensing data obtained sufficiently and preserves information at edges caused by clouds. Numerical implementation algorithm is presented in detail. Analysis indicates that the structure of this algorithm can be easily implemented in parallelization. Therefore a parallel implementation of the TV-L1 filter based on multicore architecture with shared memory is proposed for infrared real-time remote sensing systems. Massive computation of image data is performed in parallel by cooperating threads running simultaneously on multiple cores. Several groups of synthetic infrared image data are used to validate the feasibility and effectiveness of the proposed parallel algorithm. Quantitative analysis of measuring the restored image quality compared to input image is presented. Experiment results show that the TV-L1 filter can restore the varying background image reasonably, and that its performance can achieve the requirement of real-time image processing.
Lee, Li-Yu; Lin, Gigin; Chen, Shu-Jen; Lu, Yen-Jung; Huang, Huei-Jean; Yen, Chi-Feng; Han, Chien Min; Lee, Yun-Shien; Wang, Tzu-Hao; Chao, Angel
2017-01-01
Benign metastasizing leiomyoma (BML) is a rare disease entity typically presenting as multiple extrauterine leiomyomas associated with a uterine leiomyoma. It has been hypothesized that the extrauterine leiomyomata represent distant metastasis of the uterine leiomyoma. To date, the only molecular evidence supporting this hypothesis was derived from clonality analyses based on X-chromosome inactivation assays. Here, we sought to address this issue by examining paired specimens of synchronous pulmonary and uterine leiomyomata from three patients using targeted massively parallel sequencing and molecular inversion probe array analysis for detecting somatic mutations and copy number aberrations. We detected identical non-hot-spot somatic mutations and similar patterns of copy number aberrations (CNAs) in paired pulmonary and uterine leiomyomata from two patients, indicating the clonal relationship between pulmonary and uterine leiomyomata. In addition to loss of chromosome 22q found in the literature, we identified additional recurrent CNAs including losses of chromosome 3q and 11q. In conclusion, our findings of the clonal relationship between synchronous pulmonary and uterine leiomyomas support the hypothesis that BML represents a condition wherein a uterine leiomyoma disseminates to distant extrauterine locations. PMID:28533481
Wu, Ren-Chin; Chao, An-Shine; Lee, Li-Yu; Lin, Gigin; Chen, Shu-Jen; Lu, Yen-Jung; Huang, Huei-Jean; Yen, Chi-Feng; Han, Chien Min; Lee, Yun-Shien; Wang, Tzu-Hao; Chao, Angel
2017-07-18
Benign metastasizing leiomyoma (BML) is a rare disease entity typically presenting as multiple extrauterine leiomyomas associated with a uterine leiomyoma. It has been hypothesized that the extrauterine leiomyomata represent distant metastasis of the uterine leiomyoma. To date, the only molecular evidence supporting this hypothesis was derived from clonality analyses based on X-chromosome inactivation assays. Here, we sought to address this issue by examining paired specimens of synchronous pulmonary and uterine leiomyomata from three patients using targeted massively parallel sequencing and molecular inversion probe array analysis for detecting somatic mutations and copy number aberrations. We detected identical non-hot-spot somatic mutations and similar patterns of copy number aberrations (CNAs) in paired pulmonary and uterine leiomyomata from two patients, indicating the clonal relationship between pulmonary and uterine leiomyomata. In addition to loss of chromosome 22q found in the literature, we identified additional recurrent CNAs including losses of chromosome 3q and 11q. In conclusion, our findings of the clonal relationship between synchronous pulmonary and uterine leiomyomas support the hypothesis that BML represents a condition wherein a uterine leiomyoma disseminates to distant extrauterine locations.
Truly nested data-parallelism: compiling SaC for the Microgrid architecture
Herhut, S.; Joslin, C.; Scholz, S.-B.; Grelck, C.; Morazan, M.
2009-01-01
Data-parallel programming facilitates elegant specification of concurrency. However, the composability of data-parallel operations so far has been constrained by the requirement to have only at data- parallel operation at runtime. In this paper, we present early results on our work to exploit
Parallel adaptive simulations on unstructured meshes
International Nuclear Information System (INIS)
Shephard, M S; Jansen, K E; Sahni, O; Diachin, L A
2007-01-01
This paper discusses methods being developed by the ITAPS center to support the execution of parallel adaptive simulations on unstructured meshes. The paper first outlines the ITAPS approach to the development of interoperable mesh, geometry and field services to support the needs of SciDAC application in these areas. The paper then demonstrates the ability of unstructured adaptive meshing methods built on such interoperable services to effectively solve important physics problems. Attention is then focused on ITAPs' developing ability to solve adaptive unstructured mesh problems on massively parallel computers
Computer programming and architecture the VAX
Levy, Henry
2014-01-01
Takes a unique systems approach to programming and architecture of the VAXUsing the VAX as a detailed example, the first half of this book offers a complete course in assembly language programming. The second describes higher-level systems issues in computer architecture. Highlights include the VAX assembler and debugger, other modern architectures such as RISCs, multiprocessing and parallel computing, microprogramming, caches and translation buffers, and an appendix on the Berkeley UNIX assembler.
A multitransputer parallel processing system (MTPPS)
International Nuclear Information System (INIS)
Jethra, A.K.; Pande, S.S.; Borkar, S.P.; Khare, A.N.; Ghodgaonkar, M.D.; Bairi, B.R.
1993-01-01
This report describes the design and implementation of a 16 node Multi Transputer Parallel Processing System(MTPPS) which is a platform for parallel program development. It is a MIMD machine based on message passing paradigm. The basic compute engine is an Inmos Transputer Ims T800-20. Transputer with local memory constitutes the processing element (NODE) of this MIMD architecture. Multiple NODES can be connected to each other in an identifiable network topology through the high speed serial links of the transputer. A Network Configuration Unit (NCU) incorporates the necessary hardware to provide software controlled network configuration. System is modularly expandable and more NODES can be added to the system to achieve the required processing power. The system is backend to the IBM-PC which has been integrated into the system to provide user I/O interface. PC resources are available to the programmer. Interface hardware between the PC and the network of transputers is INMOS compatible. Therefore, all the commercially available development software compatible to INMOS products can run on this system. While giving the details of design and implementation, this report briefly summarises MIMD Architectures, Transputer Architecture and Parallel Processing Software Development issues. LINPACK performance evaluation of the system and solutions of neutron physics and plasma physics problem have been discussed along with results. (author). 12 refs., 22 figs., 3 tabs., 3 appendixes
Lagardère, Louis; Jolly, Luc-Henri; Lipparini, Filippo; Aviat, Félix; Stamm, Benjamin; Jing, Zhifeng F; Harger, Matthew; Torabifard, Hedieh; Cisneros, G Andrés; Schnieders, Michael J; Gresh, Nohad; Maday, Yvon; Ren, Pengyu Y; Ponder, Jay W; Piquemal, Jean-Philip
2018-01-28
We present Tinker-HP, a massively MPI parallel package dedicated to classical molecular dynamics (MD) and to multiscale simulations, using advanced polarizable force fields (PFF) encompassing distributed multipoles electrostatics. Tinker-HP is an evolution of the popular Tinker package code that conserves its simplicity of use and its reference double precision implementation for CPUs. Grounded on interdisciplinary efforts with applied mathematics, Tinker-HP allows for long polarizable MD simulations on large systems up to millions of atoms. We detail in the paper the newly developed extension of massively parallel 3D spatial decomposition to point dipole polarizable models as well as their coupling to efficient Krylov iterative and non-iterative polarization solvers. The design of the code allows the use of various computer systems ranging from laboratory workstations to modern petascale supercomputers with thousands of cores. Tinker-HP proposes therefore the first high-performance scalable CPU computing environment for the development of next generation point dipole PFFs and for production simulations. Strategies linking Tinker-HP to Quantum Mechanics (QM) in the framework of multiscale polarizable self-consistent QM/MD simulations are also provided. The possibilities, performances and scalability of the software are demonstrated via benchmarks calculations using the polarizable AMOEBA force field on systems ranging from large water boxes of increasing size and ionic liquids to (very) large biosystems encompassing several proteins as well as the complete satellite tobacco mosaic virus and ribosome structures. For small systems, Tinker-HP appears to be competitive with the Tinker-OpenMM GPU implementation of Tinker. As the system size grows, Tinker-HP remains operational thanks to its access to distributed memory and takes advantage of its new algorithmic enabling for stable long timescale polarizable simulations. Overall, a several thousand-fold acceleration over
Implementation and analysis of a Navier-Stokes algorithm on parallel computers
Fatoohi, Raad A.; Grosch, Chester E.
1988-01-01
The results of the implementation of a Navier-Stokes algorithm on three parallel/vector computers are presented. The object of this research is to determine how well, or poorly, a single numerical algorithm would map onto three different architectures. The algorithm is a compact difference scheme for the solution of the incompressible, two-dimensional, time-dependent Navier-Stokes equations. The computers were chosen so as to encompass a variety of architectures. They are the following: the MPP, an SIMD machine with 16K bit serial processors; Flex/32, an MIMD machine with 20 processors; and Cray/2. The implementation of the algorithm is discussed in relation to these architectures and measures of the performance on each machine are given. The basic comparison is among SIMD instruction parallelism on the MPP, MIMD process parallelism on the Flex/32, and vectorization of a serial code on the Cray/2. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Finally, conclusions are presented.
Experimental high energy physics and modern computer architectures
International Nuclear Information System (INIS)
Hoek, J.
1988-06-01
The paper examines how experimental High Energy Physics can use modern computer architectures efficiently. In this connection parallel and vector architectures are investigated, and the types available at the moment for general use are discussed. A separate section briefly describes some architectures that are either a combination of both, or exemplify other architectures. In an appendix some directions in which computing seems to be developing in the USA are mentioned. (author)
Smoldyn on graphics processing units: massively parallel Brownian dynamics simulations.
Dematté, Lorenzo
2012-01-01
Space is a very important aspect in the simulation of biochemical systems; recently, the need for simulation algorithms able to cope with space is becoming more and more compelling. Complex and detailed models of biochemical systems need to deal with the movement of single molecules and particles, taking into consideration localized fluctuations, transportation phenomena, and diffusion. A common drawback of spatial models lies in their complexity: models can become very large, and their simulation could be time consuming, especially if we want to capture the systems behavior in a reliable way using stochastic methods in conjunction with a high spatial resolution. In order to deliver the promise done by systems biology to be able to understand a system as whole, we need to scale up the size of models we are able to simulate, moving from sequential to parallel simulation algorithms. In this paper, we analyze Smoldyn, a widely diffused algorithm for stochastic simulation of chemical reactions with spatial resolution and single molecule detail, and we propose an alternative, innovative implementation that exploits the parallelism of Graphics Processing Units (GPUs). The implementation executes the most computational demanding steps (computation of diffusion, unimolecular, and bimolecular reaction, as well as the most common cases of molecule-surface interaction) on the GPU, computing them in parallel on each molecule of the system. The implementation offers good speed-ups and real time, high quality graphics output
A Review of Lightweight Thread Approaches for High Performance Computing
Energy Technology Data Exchange (ETDEWEB)
Castello, Adrian; Pena, Antonio J.; Seo, Sangmin; Mayo, Rafael; Balaji, Pavan; Quintana-Orti, Enrique S.
2016-09-12
High-level, directive-based solutions are becoming the programming models (PMs) of the multi/many-core architectures. Several solutions relying on operating system (OS) threads perfectly work with a moderate number of cores. However, exascale systems will spawn hundreds of thousands of threads in order to exploit their massive parallel architectures and thus conventional OS threads are too heavy for that purpose. Several lightweight thread (LWT) libraries have recently appeared offering lighter mechanisms to tackle massive concurrency. In order to examine the suitability of LWTs in high-level runtimes, we develop a set of microbenchmarks consisting of commonlyfound patterns in current parallel codes. Moreover, we study the semantics offered by some LWT libraries in order to expose the similarities between different LWT application programming interfaces. This study reveals that a reduced set of LWT functions can be sufficient to cover the common parallel code patterns and that those LWT libraries perform better than OS threads-based solutions in cases where task and nested parallelism are becoming more popular with new architectures.
Optical Neural Network Classifier Architectures
National Research Council Canada - National Science Library
Getbehead, Mark
1998-01-01
We present an adaptive opto-electronic neural network hardware architecture capable of exploiting parallel optics to realize real-time processing and classification of high-dimensional data for Air...
SiGN-SSM: open source parallel software for estimating gene networks with state space models.
Tamada, Yoshinori; Yamaguchi, Rui; Imoto, Seiya; Hirose, Osamu; Yoshida, Ryo; Nagasaki, Masao; Miyano, Satoru
2011-04-15
SiGN-SSM is an open-source gene network estimation software able to run in parallel on PCs and massively parallel supercomputers. The software estimates a state space model (SSM), that is a statistical dynamic model suitable for analyzing short time and/or replicated time series gene expression profiles. SiGN-SSM implements a novel parameter constraint effective to stabilize the estimated models. Also, by using a supercomputer, it is able to determine the gene network structure by a statistical permutation test in a practical time. SiGN-SSM is applicable not only to analyzing temporal regulatory dependencies between genes, but also to extracting the differentially regulated genes from time series expression profiles. SiGN-SSM is distributed under GNU Affero General Public Licence (GNU AGPL) version 3 and can be downloaded at http://sign.hgc.jp/signssm/. The pre-compiled binaries for some architectures are available in addition to the source code. The pre-installed binaries are also available on the Human Genome Center supercomputer system. The online manual and the supplementary information of SiGN-SSM is available on our web site. tamada@ims.u-tokyo.ac.jp.
Execution Model of Three Parallel Languages: OpenMP, UPC and CAF
Directory of Open Access Journals (Sweden)
Ami Marowka
2005-01-01
Full Text Available The aim of this paper is to present a qualitative evaluation of three state-of-the-art parallel languages: OpenMP, Unified Parallel C (UPC and Co-Array Fortran (CAF. OpenMP and UPC are explicit parallel programming languages based on the ANSI standard. CAF is an implicit programming language. On the one hand, OpenMP designs for shared-memory architectures and extends the base-language by using compiler directives that annotate the original source-code. On the other hand, UPC and CAF designs for distribute-shared memory architectures and extends the base-language by new parallel constructs. We deconstruct each language into its basic components, show examples, make a detailed analysis, compare them, and finally draw some conclusions.
Performance evaluation of canny edge detection on a tiled multicore architecture
Brethorst, Andrew Z.; Desai, Nehal; Enright, Douglas P.; Scrofano, Ronald
2011-01-01
In the last few years, a variety of multicore architectures have been used to parallelize image processing applications. In this paper, we focus on assessing the parallel speed-ups of different Canny edge detection parallelization strategies on the Tile64, a tiled multicore architecture developed by the Tilera Corporation. Included in these strategies are different ways Canny edge detection can be parallelized, as well as differences in data management. The two parallelization strategies examined were loop-level parallelism and domain decomposition. Loop-level parallelism is achieved through the use of OpenMP,1 and it is capable of parallelization across the range of values over which a loop iterates. Domain decomposition is the process of breaking down an image into subimages, where each subimage is processed independently, in parallel. The results of the two strategies show that for the same number of threads, programmer implemented, domain decomposition exhibits higher speed-ups than the compiler managed, loop-level parallelism implemented with OpenMP.
Automated Design of Application-Specific Smart Camera Architectures
Caarls, W.
2008-01-01
Parallel heterogeneous multiprocessor systems are often shunned in embedded system design, not only because of their design complexity but because of the programming burden. Programs for such systems are architecture-dependent: the application developer needs architecture-specific knowledge to
Image Quality Improvement on OpenGL-Based Animations by Using CUDA Architecture
Directory of Open Access Journals (Sweden)
Taner UÇKAN
2016-04-01
Full Text Available 2D or 3D rendering technology is used for graphically modelling many physical phenomena occurring in real life by means of the computers. On the other hand, the ever-increasing intensity of the graphics applications require that the image quality of the so-called modellings is enhanced and they are performed more quickly. In this direction, a new software and hardware-based architecture called CUDA has been introduced by Nvidia at the end of 2006. Thanks to this architecture, larger number of graphics processors has started contributing towards the parallel solutions of the general-purpose problems. In this study, this new parallel computing architecture is taken into consideration and an animation application consisting of humanoid robots with different behavioral characteristics is developed using the OpenGL library in C++. This animation is initially implemented on a single serial CPU and then parallelized using the CUDA architecture. Eventually, the serial and the parallel versions of the same animation are compared against each other on the basis of the number of image frames per second. The results reveal that the parallel application is by far the best yielding high quality images.
Power-efficient computer architectures recent advances
Själander, Magnus; Kaxiras, Stefanos
2014-01-01
As Moore's Law and Dennard scaling trends have slowed, the challenges of building high-performance computer architectures while maintaining acceptable power efficiency levels have heightened. Over the past ten years, architecture techniques for power efficiency have shifted from primarily focusing on module-level efficiencies, toward more holistic design styles based on parallelism and heterogeneity. This work highlights and synthesizes recent techniques and trends in power-efficient computer architecture.Table of Contents: Introduction / Voltage and Frequency Management / Heterogeneity and Sp
Lock-free parallel garbage collection
H. Gao; J.F. Groote (Jan Friso); W.H. Hesselink (Wim)
2005-01-01
htmlabstract This paper presents a lock-free parallel algorithm for mark&sweep garbage collection (GC) in a realistic model using synchronization primitives compare-and-swap (CAS) and load-linked/store-conditional (LL/SC) offered by machine architectures. Mutators and collectors can simultaneously
Optimisation of a parallel ocean general circulation model
Directory of Open Access Journals (Sweden)
M. I. Beare
1997-10-01
Full Text Available This paper presents the development of a general-purpose parallel ocean circulation model, for use on a wide range of computer platforms, from traditional scalar machines to workstation clusters and massively parallel processors. Parallelism is provided, as a modular option, via high-level message-passing routines, thus hiding the technical intricacies from the user. An initial implementation highlights that the parallel efficiency of the model is adversely affected by a number of factors, for which optimisations are discussed and implemented. The resulting ocean code is portable and, in particular, allows science to be achieved on local workstations that could otherwise only be undertaken on state-of-the-art supercomputers.
Optimisation of a parallel ocean general circulation model
Directory of Open Access Journals (Sweden)
M. I. Beare
Full Text Available This paper presents the development of a general-purpose parallel ocean circulation model, for use on a wide range of computer platforms, from traditional scalar machines to workstation clusters and massively parallel processors. Parallelism is provided, as a modular option, via high-level message-passing routines, thus hiding the technical intricacies from the user. An initial implementation highlights that the parallel efficiency of the model is adversely affected by a number of factors, for which optimisations are discussed and implemented. The resulting ocean code is portable and, in particular, allows science to be achieved on local workstations that could otherwise only be undertaken on state-of-the-art supercomputers.
QuASAR-MPRA: accurate allele-specific analysis for massively parallel reporter assays.
Kalita, Cynthia A; Moyerbrailean, Gregory A; Brown, Christopher; Wen, Xiaoquan; Luca, Francesca; Pique-Regi, Roger
2018-03-01
The majority of the human genome is composed of non-coding regions containing regulatory elements such as enhancers, which are crucial for controlling gene expression. Many variants associated with complex traits are in these regions, and may disrupt gene regulatory sequences. Consequently, it is important to not only identify true enhancers but also to test if a variant within an enhancer affects gene regulation. Recently, allele-specific analysis in high-throughput reporter assays, such as massively parallel reporter assays (MPRAs), have been used to functionally validate non-coding variants. However, we are still missing high-quality and robust data analysis tools for these datasets. We have further developed our method for allele-specific analysis QuASAR (quantitative allele-specific analysis of reads) to analyze allele-specific signals in barcoded read counts data from MPRA. Using this approach, we can take into account the uncertainty on the original plasmid proportions, over-dispersion, and sequencing errors. The provided allelic skew estimate and its standard error also simplifies meta-analysis of replicate experiments. Additionally, we show that a beta-binomial distribution better models the variability present in the allelic imbalance of these synthetic reporters and results in a test that is statistically well calibrated under the null. Applying this approach to the MPRA data, we found 602 SNPs with significant (false discovery rate 10%) allele-specific regulatory function in LCLs. We also show that we can combine MPRA with QuASAR estimates to validate existing experimental and computational annotations of regulatory variants. Our study shows that with appropriate data analysis tools, we can improve the power to detect allelic effects in high-throughput reporter assays. http://github.com/piquelab/QuASAR/tree/master/mpra. fluca@wayne.edu or rpique@wayne.edu. Supplementary data are available online at Bioinformatics. © The Author (2017). Published by
Cellular Automata-Based Parallel Random Number Generators Using FPGAs
Directory of Open Access Journals (Sweden)
David H. K. Hoe
2012-01-01
Full Text Available Cellular computing represents a new paradigm for implementing high-speed massively parallel machines. Cellular automata (CA, which consist of an array of locally connected processing elements, are a basic form of a cellular-based architecture. The use of field programmable gate arrays (FPGAs for implementing CA accelerators has shown promising results. This paper investigates the design of CA-based pseudo-random number generators (PRNGs using an FPGA platform. To improve the quality of the random numbers that are generated, the basic CA structure is enhanced in two ways. First, the addition of a superrule to each CA cell is considered. The resulting self-programmable CA (SPCA uses the superrule to determine when to make a dynamic rule change in each CA cell. The superrule takes its inputs from neighboring cells and can be considered itself a second CA working in parallel with the main CA. When implemented on an FPGA, the use of lookup tables in each logic cell removes any restrictions on how the super-rules should be defined. Second, a hybrid configuration is formed by combining a CA with a linear feedback shift register (LFSR. This is advantageous for FPGA designs due to the compactness of the LFSR implementations. A standard software package for statistically evaluating the quality of random number sequences known as Diehard is used to validate the results. Both the SPCA and the hybrid CA/LFSR were found to pass all the Diehard tests.
Parallel Programming using OpenCL on Modern Architectures
DEFF Research Database (Denmark)
Nielsen, Allan Svejstrup; Engsig-Karup, Allan Peter; Dammann, Bernd
as they are at graphics. To conclude the presentation of OpenCL as a language for compute, a matrix-matrix multiplication example is devised and optimized for the VLIW4, Tesla and Fermi architectures. The performance is measured as a function of both matrix and work-group size and results are discussed. Where applicable...
Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects
International Nuclear Information System (INIS)
Agullo, Emmanuel; Demmel, Jim; Dongarra, Jack; Hadri, Bilel; Kurzak, Jakub; Langou, Julien; Ltaief, Hatem; Luszczek, Piotr; Tomov, Stanimire
2009-01-01
The emergence and continuing use of multi-core architectures and graphics processing units require changes in the existing software and sometimes even a redesign of the established algorithms in order to take advantage of now prevailing parallelism. Parallel Linear Algebra for Scalable Multi-core Architectures (PLASMA) and Matrix Algebra on GPU and Multics Architectures (MAGMA) are two projects that aims to achieve high performance and portability across a wide range of multi-core architectures and hybrid systems respectively. We present in this document a comparative study of PLASMA's performance against established linear algebra packages and some preliminary results of MAGMA on hybrid multi-core and GPU systems.
A framework for plasticity implementation on the SpiNNaker neural architecture.
Galluppi, Francesco; Lagorce, Xavier; Stromatias, Evangelos; Pfeiffer, Michael; Plana, Luis A; Furber, Steve B; Benosman, Ryad B
2014-01-01
Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system.
International Nuclear Information System (INIS)
Woodruff, S.B.
1994-01-01
The Transient Reactor Analysis Code (TRAC), which features a two-fluid treatment of thermal-hydraulics, is designed to model transients in water reactors and related facilities. One of the major computational costs associated with TRAC and similar codes is calculating constitutive coefficients. Although the formulations for these coefficients are local, the costs are flow-regime- or data-dependent; i.e., the computations needed for a given spatial node often vary widely as a function of time. Consequently, a fixed, uniform assignment of nodes to prallel processors will result in degraded computational efficiency due to the poor load balancing. A standard method for treating data-dependent models on vector architectures has been to use gather operations (or indirect adressing) to sort the nodes into subsets that (temporarily) share a common computational model. However, this method is not effective on distributed memory data parallel architectures, where indirect adressing involves expensive communication overhead. Another serious problem with this method involves software engineering challenges in the areas of maintainability and extensibility. For example, an implementation that was hand-tuned to achieve good computational efficiency would have to be rewritten whenever the decision tree governing the sorting was modified. Using an example based on the calculation of the wall-to-liquid and wall-to-vapor heat-transfer coefficients for three nonboiling flow regimes, we describe how the use of the Fortran 90 WHERE construct and automatic inlining of functions can be used to ameliorate this problem while improving both efficiency and software engineering. Unfortunately, a general automatic solution to the load-balancing problem associated with data-dependent computations is not yet available for massively parallel architectures. We discuss why developers should either wait for such solutions or consider alternative numerical algorithms, such as a neural network
Fast parallel tandem mass spectral library searching using GPU hardware acceleration.
Baumgardner, Lydia Ashleigh; Shanmugam, Avinash Kumar; Lam, Henry; Eng, Jimmy K; Martin, Daniel B
2011-06-03
Mass spectrometry-based proteomics is a maturing discipline of biologic research that is experiencing substantial growth. Instrumentation has steadily improved over time with the advent of faster and more sensitive instruments collecting ever larger data files. Consequently, the computational process of matching a peptide fragmentation pattern to its sequence, traditionally accomplished by sequence database searching and more recently also by spectral library searching, has become a bottleneck in many mass spectrometry experiments. In both of these methods, the main rate-limiting step is the comparison of an acquired spectrum with all potential matches from a spectral library or sequence database. This is a highly parallelizable process because the core computational element can be represented as a simple but arithmetically intense multiplication of two vectors. In this paper, we present a proof of concept project taking advantage of the massively parallel computing available on graphics processing units (GPUs) to distribute and accelerate the process of spectral assignment using spectral library searching. This program, which we have named FastPaSS (for Fast Parallelized Spectral Searching), is implemented in CUDA (Compute Unified Device Architecture) from NVIDIA, which allows direct access to the processors in an NVIDIA GPU. Our efforts demonstrate the feasibility of GPU computing for spectral assignment, through implementation of the validated spectral searching algorithm SpectraST in the CUDA environment.
Algorithms for parallel flow solvers on message passing architectures
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