检索结果-内蒙古大学图书馆

distributed-memory systems FOR SIMULATING ARTIFICIAL NEURAL NETWORKS

COMPUTERS & ELECTRICAL ENGINEERING 1993年第6期19卷 431-443页

作者： PATNAIK, LM KUMAR, JM INDIAN INST SCI MICROPROCESSOR APPLICAT LABBANGALORE 560012KARNATAKAINDIA

In executing tasks involving intelligent information processing, the human brain performs better than the digital computer. The human brain derives its power from a large number [O(10(11))] of neurons which are interconnected by a dense interconnection network [O(10(5)) connections per neuron]. Artificial neural network (ANN) paradigms adopt the structure of the brain to try to emulate the intelligent information processing methods of the brain. ANN techniques are being employed to solve problems in areas such as pattern recognition, and robotic processing. Simulation of ANNs involves implementation of large number of neurons and a massive interconnection network. In this paper, we discuss various simulation models of ANNs and their implementation on distributed memory systems. Our investigations reveal that communication-efficient networks of distributed memory systems perform better than other topologies in implementing ANNs.

关键词： ARTIFICIAL NEURAL NETWORKS distributed memory systems TOTAL EXCHANGE MULTINODE BROADCASE HIERARCHICAL NETWORK OF HYPERCUBES

来源：评论

学校读者我要写书评

暂无评论

A domain decomposition technique for spline image restoration on distributed memory systems

引用

PARALLEL COMPUTING 1996年第1期22卷 101-110页

作者： Baronio, A Zama, F UNIV BOLOGNA DEPT MATHI-40127 BOLOGNAITALY

The problem of image restoration is considered when the point spread function is Space Variant Non Separable. The algorithm determines a continuous approximation of the original object, following the continuous object-discrete image approach. The image spatial domain is decomposed into subdomains and the local approximants are computed on a distributed memory environment. The continuity of the solution across the image subdomains is obtained by adding a suitable overlapping area to the sides of the subdomains. Numerical experiments have been carried out on a Hypercube Intel iPSC/860 and the most interesting results are reported.

关键词： domain decomposition image restoration regularization basis spline function distributed memory systems

来源：评论

学校读者我要写书评

暂无评论

A SCALABLE IMPLEMENTATION OF THE NAS PARALLEL BENCHMARK BT ON distributed-memory systems

引用

IBM systems JOURNAL 1995年第2期34卷 273-291页

作者： NAIK, VK IBM Research Division

In this paper, we describe an efficient and scalable implementation of the NAS Parallel Benchmark BT suitable for distributed memory systems such as the IBM Scalable POWERparallei systems(R). After describing the parallelization and data partitioning methods used, we outline some of the optimization steps used to realize good performance on individual processors and to reduce the communication overheads on the IBM SP1(TM) and SP2(TM) systems. We present performance results on up to 128 nodes of the SP1, and on the SP2 with wide nodes. We describe the performance on the standard Class A and Class B problem sets. To show the scalability of our parallelization methods, we present the performance of two additional data sets.

关键词： .Performance Results Benchmark Data Sets nodes processor partitioning computations good performance kernels NAS Parallel distributed memory systems IBM Scalable SP systems Class problem

来源：评论

学校读者我要写书评

暂无评论

A task duplication based scalable scheduling algorithm for distributed memory systems

引用

JOURNAL OF PARALLEL AND distributed COMPUTING 1997年第1期46卷 15-27页

作者： Darbha, S Agrawal, DP Rutgers State Univ Dept Elect & Comp Engn Piscataway NJ 08855 USA N Carolina State Univ Dept Elect & Comp Engn Raleigh NC 27695 USA

One of the major limitations of distributed memory systems (DMSs) is the high cost for interprocessor communication, which can be minimized by having an efficient task partitioning and scheduling algorithm. It is well known that scheduling the tasks of a directed acyclic graph (DAG) to obtain an optimal solution is a strong NP-hard problem, This paper presents a scalable task duplication based scheduling (STDS) algorithm which can schedule the tasks of a DAG onto the processors of a DMS with a worst case complexity of O(\V\(2)), where \V\ is the number of nodes of the DAG, This algorithm generates an optimal schedule for DAGs provided a cost relationship is satisfied and if the required number of processors are available, The STDS algorithm generates a schedule for the number of processors available in the system, The performance of the STDS algorithm has been observed by comparing the parallel execution times for practical DAGs with the theoretical lowerbound. (C) 1997 Academic Press.

关键词： Graphs Machines PROCESSOR interprocessor communication KCNK3 gene Scheduling algorithms algorithms machinery machine distributed memory systems

来源：评论

学校读者我要写书评

暂无评论

A computation plus communication load balanced loop partitioning method for distributed memory systems

引用

JOURNAL OF PARALLEL AND distributed COMPUTING 1999年第3期58卷 515-545页

作者： Pande, S Bali, T Univ Cincinnati Dept ECECS Compiler Res Lab Cincinnati OH 45221 USA

Due to a significant communication overhead of sending and receiving data, the loop partitioning approaches on distributed memory systems must guarantee not just the computation load balance but computation + communication load balance. The previous approaches in loop partitioning have achieved a communication-free. computation load balanced iteration space partitioning solution for a limited subset of DOALL loops. But a large category of DOALL loops inevitably result in communication and the tradeoffs between computation and communication must be carefully analyzed for these loops in order to balance out the combined computation time and communication overheads. In this work, we describe a partitioning approach based on the above motivation for the general cases of DOALL loops. Our goal is to achieve a computation + communication load balanced partitioning through static data and iteration space distribution. Our approach first performs partitioning of iteration and data spaces of a loop nest by analyzing communication and parallelism;it then performs architecture-dependent analysis to adjust the granularity of partitions. load balance each partition with respect to total computation + communication, and then performs mapping of partitions onto the available number of processors. This multiphase partitioning method works as follows. First, the code partitioning phase analyzes the references in the body of the DOALL loop nest and determines a set of directions for reducing a larger degree of communication by trading a lesser degree of parallelism. The partitioning is carried out in the iteration space of the loop by cyclically following a set of direction vectors such that the data references are maximally localized and reused, eliminating a larger communication volume than parallelism. We then perform data space partitioning based on a new larger partition owns rule to minimize the communication overhead for a compute intensive partition by localizing its reference

关键词： parallelizing compilers distributed memory systems data partitioning communication optimizations loop partitioning and scheduling

来源：评论

学校读者我要写书评

暂无评论

Code Generation for Parallel Execution of a Class of Irregular Loops on distributed memory systems

Code Generation for Parallel Execution of a Class of Irregul...

引用

25th ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC)

作者： Ravishankar, Mahesh Eisenlohr, John Pouchet, Louis-Noel Ramanujam, J. Rountev, Atanas Sadayappan, P. Ohio State Univ Columbus OH 43210 USA Louisiana State Univ Louvain Belgium

ISBN: (纸本)9781467308052;9781467308045

Parallelization and locality optimization of affine loop nests has been successfully addressed for shared-memory machines. However, many large-scale simulation applications must be executed in a distributed-memory environment, and use irregular/sparse computations where the control-flow and array-access patterns are data-dependent. In this paper, we propose an approach for effective parallel execution of a class of irregular loop computations in a distributed-memory environment, using a combination of static and runtime analysis. We discuss algorithms that analyze sequential code to generate an inspector and an executor. The inspector captures the data-dependent behavior of the computation in parallel and without requiring complete replication of any of the data structures used in the original computation. The executor performs the computation in parallel. The effectiveness of the framework is demonstrated on several benchmarks and a climate modeling application.

关键词： distributed memory systems optimisation program compilers program diagnostics shared memory systems

来源：评论

学校读者我要写书评

暂无评论

Pipelined Preconditioned Conjugate Gradient Methods for distributed memory systems 27

Pipelined Preconditioned Conjugate Gradient Methods for Dist...

引用

27th IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC)

作者： Tiwari, Manasi Vadhiyar, Sathish Indian Inst Sci Dept Computat & Data Sci Bengaluru India

ISBN: (纸本)9781665422925

Preconditioned Conjugate Gradient (PCG) method has been one of the widely used methods for solving linear systems of equations for sparse problems. Pipelined PCG (PIPECG) attempts to eliminate the dependencies in the computations in the PCG algorithm and overlap non-dependent computations by reorganizing the traditional PCG code and using non-blocking allreduces. We have developed a novel pipelined PCG algorithm called PIPECG-OATI (One Allreduce per Two Iterations) that provides large overlap of global communication and computations at higher number of cores in distributed memory CPU systems. Our method achieves this overlapping by using iteration combination and by introducing new non-recurrence computations. We compare our method with other pipelined CG methods on a variety of problems and demonstrate that our method always gives the least runtimes. Our method gives up to 3x speedup over PCG method and 1.73x speedup over PIPECG method at large number of cores.

关键词： Preconditioned Conjugate Gradient distributed memory systems pipelining overlapping communication and computations

来源：评论

学校读者我要写书评

暂无评论

Global tiling for communication minimal parallelization on distributed memory systems

Global tiling for communication minimal parallelization on d...

引用

14th International Euro-Par Conference on Parallel Computing

作者： Liu, Lei Chen, Li Wu, Cheng Yong Feng, Xiao-bing Chinese Acad Sci Inst Comp Technol Key Lab Comp Architecture Beijing 100080 Peoples R China

ISBN: (纸本)9783540854500

Most previous studies on tiling focus on the division of iteration space. However, on distributed memory parallel systems, the decomposition of computation and the distribution of data must be handled at the same time, in order to attain load balancing and to minimize data migration. In this paper, we formulate a 0-1 integer linear programming for the problem of globally optimal tiling to minimize the total execution time. To simplify the selection of tiling parameters, we restrict the tile shape to semi-oblique shape, and present two effective approaches to decide the tile shape for multi-dimensional semi-oblique shaped tiling. Besides, we present a tile-to-processor mapping scheme based on hyperplanes, which can express diverse parallelism and gain better performance than traditional methods. The experimentations with NPB2.3-serial SP and LU on Qsnet connected cluster achieved the average parallel efficiency of 87% and 73% respectively.

关键词： compiler parallelization tiling distributed memory systems tile-to-processor mapping semi-oblique shaped tile

来源：评论

学校读者我要写书评

暂无评论

Pipelined Preconditioned s-step Conjugate Gradient Methods for distributed memory systems

Pipelined Preconditioned s-step Conjugate Gradient Methods f...

引用

IEEE International Conference on Cluster Computing (Cluster)

作者： Tiwari, Manasi Vadhiyar, Sathish Indian Inst Sci Dept Computat & Data Sci Bengaluru India

ISBN: (纸本)9781728196664

Preconditioned Conjugate Gradient (PCG) method is a widely used iterative method for solving large linear systems of equations. Pipelined variants of PCG present independent computations in the PCG method and overlap these computations with non-blocking allreduces. We have developed a novel pipelined PCG algorithm called PIPE-sCG (Pipelined s-step Conjugate Gradient) that provides a large overlap of global communication and computations at higher number of cores in distributed memory CPU systems. Our method achieves this overlap by introducing new recurrence computations. We have also developed a preconditioned version of PIPE-sCG. The advantages of our methods are that they do not introduce any extra preconditioner or sparse matrix vector product kernels in order to provide the overlap and can work with preconditioned, unpreconditioned and natural norms of the residual, as opposed to the state-of-the-art methods. We compare our method with other pipelined CG methods for Poisson problems and demonstrate that our method gives the least runtimes. Our method gives up to 2.9x speedup over PCG method, 2.15x speedup over PIPECG method and 1.2x speedup over PIPECG-OATI method at large number of cores.

关键词： Preconditioned Conjugate Gradient distributed memory systems Pipelining Overlapping communication and computations s-step Methods

来源：评论

学校读者我要写书评

暂无评论

Communication Overlapping Pipelined Conjugate Gradients for distributed memory systems and Heterogeneous Architectures 27th

Communication Overlapping Pipelined Conjugate Gradients for ...

引用

27th International European Conference on Parallel and distributed Computing (Euro-Par)

作者： Tiwari, Manasi Vadhiyar, Sathish Indian Inst Sci Dept Computat & Data Sci Bangalore Karnataka India

ISBN: (纸本)9783031061561;9783031061554

Preconditioned Conjugate Gradient (PCG) method has been one of the widely used methods for solving linear systems of equations for sparse problems. Pipelined PCG (PIPECG) attempts to eliminate the dependencies in the computations in the PCG algorithm and overlap non-dependent computations by reorganizing the traditional PCG code and using non-blocking allreduces . We have developed a novel pipelined PCG algorithm called PIPECG-OATI (One Allreduce per Two Iterations) which reduces the number of non-blocking allreduces to one per two iterations and provides large overlap of global communication and computations at higher number of cores in distributed memory CPU systems. PIPECG-OATI gives up to 3x speedup over PCG and 1.73x speedup over PIPECG at large number of cores. For GPU accelerated heterogeneous architectures, we have developed three methods for efficient execution of the PIPECG algorithm. These methods achieve task and data parallelism. Our methods give considerable performance improvements over PCG CPU and GPU implementations of Paralution and PETSc libraries.

关键词： Preconditioned Conjugate Gradient Overlapping communication and computations distributed memory systems Heterogeneous architectures

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：