检索结果-内蒙古大学图书馆

OpenMP: shared-memory parallelism from the ashes

COMPUTER 1999年第5期32卷 108-109页

作者： Throop, J Kuck & Associates Inc. USA

The paper discusses OpenMP, an emerging standard for shared-memory parallelism that has considerable industry support. Large corporations such as IBM, Intel, and Silicon Graphics are building products to support the s... 详细信息

关键词： IBM Intel OpenMP Silicon Graphics large corporations parallel machines parallel programming parallel programming shared memory systems shared-memory parallelism software standards standard

来源：评论

学校读者我要写书评

暂无评论

High-Level Strategies for Parallel shared-memory Sparse Matrix-Vector Multiplication

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2014年第1期25卷 116-125页

作者： Yzelman, Albert-Jan Nicholas Roose, Dirk Intel Labs Europe Flanders ExaSci Lab B-3001 Louvain Belgium Katholieke Univ Leuven Dept Comp Sci B-3001 Heverlee Belgium

The sparse matrix-vector multiplication is an important computational kernel, but is hard to efficiently execute even in the sequential case. The problems-namely low arithmetic intensity, inefficient cache use, and limited memory bandwidth-are magnified as the core count on shared-memory parallel architectures increases. Existing techniques are discussed in detail, and categorized chiefly based on their distribution types. Based on this, new parallelization techniques are proposed. The theoretical scalability and memory usage of the various strategies are analyzed, and experiments on multiple NUMA architectures confirm the validity of the results. One of the newly proposed methods attains the best average result in experiments on a large set of matrices. In one of the experiments it obtains a parallel efficiency of 90 percent, while on average it performs close to 60 percent.

关键词： Sparse matrix-vector multiplication shared-memory parallelism cache-oblivious sparse matrix partitioning matrix reordering Hilbert space-filling curve high-performance computing NUMA architectures

来源：评论

学校读者我要写书评

暂无评论

High-Quality shared-memory Graph Partitioning

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2020年第11期31卷 2710-2722页

作者： Akhremtsev, Yaroslav Sanders, Peter Schulz, Christian Google Zurich Switzerland Karlsruhe Inst Technol KIT D-76131 Karlsruhe Germany Univ Vienna Fac Comp Sci A-1010 Vienna Austria

Partitioning graphs into blocks of roughly equal size such that few edges run between blocks is a frequently needed operation in processing graphs. Recently, size, variety, and structural complexity of these networks has grown dramatically. Unfortunately, previous approaches to parallel graph partitioning have problems in this context since they often show a negative trade-off between speed and quality. We present an approach to multi-level shared-memory parallel graph partitioning that produces balanced solutions, shows high speedups for a variety of large graphs and yields very good quality independently of the number of cores used. For example, in an extensive experimental study, at 79 cores, one of our closest competitors is faster but fails to meet the balance criterion in the majority of cases and another is mostly slower and incurs about 13 percent larger cut size. Important ingredients include parallel label propagation for both coarsening and refinement, parallel initial partitioning, a simple yet effective approach to parallel localized local search, and fast locality preserving hash tables.

关键词： Partitioning algorithms Clustering algorithms Program processors Complex networks Contracts Parallel algorithms Parallel graph partitioning shared-memory parallelism local search label propagation

来源：评论

学校读者我要写书评

暂无评论

Pairwise Verlet Lists: Combining Cell Lists and Verlet Lists to Improve memory Locality and parallelism

引用

JOURNAL OF COMPUTATIONAL CHEMISTRY 2012年第1期33卷 76-81页

作者： Gonnet, Pedro Univ Oxford Inst Math Oxford OX1 3LB England

Verlet lists, which are commonly used in many particle-based simulations, are not suited for modern, shared-memory parallel multicore architectures. In this article, we introduce pairwise Verlet lists: local Verlet lists containing only interacting particle pairs between a pair of neighboring computational cells. We show that these pairwise Verlet lists are more efficient and scale much better than the traditional global Verlet list, both on a single processor as well as on multiple shared-memory cores. The improved performance on a single core makes them an interesting option for distributed-memory simulations as well. (C) 2011 Wiley Periodicals, Inc. J Comput Chem 33: 76-81, 2012

关键词： molecular dynamics Verlet list cell list neighbor list shared-memory parallelism parallel efficiency

来源：评论

学校读者我要写书评

暂无评论

Parallelizable adjoint stencil computations using transposed forward-mode algorithmic differentiation

引用

OPTIMIZATION METHODS & SOFTWARE 2018年第4-6期33卷 672-693页

作者： Huckelheim, J. C. Hovland, P. D. Strout, M. M. Mueller, J. -D. Imperial Coll London Dept Earth Sci & Engn London England Argonne Natl Lab Lemont IL USA Univ Arizona Dept Comp Sci Tucson AZ 85721 USA Queen Mary Univ London Sch Engn & Mat Sci London England

Algorithmic differentiation (AD) is a tool for generating discrete adjoint solvers, which efficiently compute gradients of functions with many inputs, for example for use in gradient-based optimization. AD is often applied to large computations such as stencil operators, which are an important part of most structured-mesh PDE solvers. Stencil computations are often parallelized, for example by using OpenMP, and optimized by using techniques such as cache-blocking and tiling to fully utilize multicore CPUs and many-core accelerators and GPUs. Differentiating these codes with conventional reverse-mode AD results in adjoint codes that cannot be expressed as stencil operations and may not be easily parallelizable. They thus leave most of the compute power of modern architectures unused. We present a method that combines forward-mode AD and loop transformation to generate adjoint solvers that use the same memory access pattern as the original computation that they are derived from and can benefit from the same optimization techniques. The effectiveness of this method is demonstrated by generating a scalable adjoint CFD solver for multicore CPUs and Xeon Phi accelerators.

关键词： algorithmic differentiation reverse mode discrete adjoints shared-memory parallelism OpenMP

来源：评论

学校读者我要写书评

暂无评论

Speculative Barriers With Transactional memory

引用

IEEE TRANSACTIONS ON COMPUTERS 2022年第1期71卷 197-208页

作者： Pedrero, Manuel Quislant, Ricardo Gutierrez, Eladio Zapata, Emilio L. Plata, Oscar Univ Malaga Dept Comp Architecture Malaga 29071 Spain

Transactional memory (TM) is a synchronization model for parallel programming which provides optimistic concurrency control. Transactions can run in parallel and are only serialized in case of conflict. In this article we use hardware TM (HTM) to implement an optimistic speculative barrier (SB) to replace the lock-based solution. SBs leverage HTM support to elide barriers speculatively. When a thread reaches an SB, a new SB transaction is started, keeping the updates private to the thread, and letting the HTM system detect potential conflicts. Once the last thread reaches the corresponding SB, the speculative threads can commit their changes. The main contributions of this work are: an API for SBs implemented with HTM extensions;a procedure to check the speculation state in between barriers to enable SBs with non-transactional codes;a HTM SB-aware conflict resolution enhancement where SB transactions stall on a conflict with a standard transaction;and a set of SB use guidelines derived from our experience on using SBs in a variety of applications. We evaluated our proposals in two different architectures with a full-system simulator and an IBM Power8 server. Results show an overall performance improvement of SBs over traditional barriers.

关键词： Message systems Instruction sets Standards Hardware Protocols Proposals Computer architecture Speculative barriers hardware transactional memory shared-memory parallelism IBM power8 GEMS

来源：评论

学校读者我要写书评

暂无评论

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2008年第16期20卷 1877-1891页

作者： Noble, Michael S. MIT Kavli Inst Astrophys & Space Res Cambridge MA 02139 USA

We introduce SLIRP, a module generator for the S-Lang numerical scripting language, with a focus on its vectorization capabilities. We demonstrate how both SLIRP and S-Lang were easily adapted to exploit the inherent parallelism of high-level mathematical languages with OpenMP, allowing general users to employ tightly coupled multiprocessors in scriptable research calculations while requiring no special knowledge of parallel programming. Motivated by examples in the ISIS astrophysical modeling and analysis tool, performance figures are presented for several machine and compiler configurations, demonstrating beneficial speedups for real-world operations. Copyright (C) 2008 John Wiley & Sons, Ltd.

关键词： shared-memory parallelism high-level languages code generation astrophysics

来源：评论

学校读者我要写书评

暂无评论

Parallel algorithms for computing sparse matrix permanents

引用

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES 2019年第6期27卷 4284-4297页

作者： Kaya, Kamer Sabanci Univ Fac Engn & Nat Sci Dept Comp Sci & Engn Istanbul Turkey

The permanent is an important characteristic of a matrix and it has been used in many applications. Unfortunately, it is a hard to compute and hard to approximate the immanant. For dense/full matrices, the fastest exact algorithm, RYSER, has O(2(n-1)n) complexity. In this work, a parallel algorithm, SKIPPER, is proposed to exploit the sparsity within the input matrix as much as possible. SKIPPER restructures the matrix to reduce the overall work, skips the unnecessary steps, and employs a coarse-grain, shared-memory parallelization with dynamic scheduling. The experiments show that SKIPPER increases the performance of exact permanent computation up to 140x compared to the naive version for general matrices. Furthermore, thanks to the coarse-grain parallelization, 14-15x speedup on average is obtained with tau = 16 threads over sequential SKIPPER. Overall, by exploiting the sparsity and parallelism, the speedup is 2000x for some of the matrices used in the experimental setting. The proposed techniques in this paper can be used to significantly improve the performance of exact permanent computation by simply replacing RYSER with SKIPPER, especially when the matrix is highly sparse.

关键词： Sparse matrices permanent Ryser's algorithm multicore CPUs shared-memory parallelism load balancing

来源：评论

学校读者我要写书评

暂无评论

PBBFMM3D: A parallel black-box algorithm for kernel matrix-vector multiplication

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2021年 154卷 64-73页

作者： Wang, Ruoxi Chen, Chao Lee, Jonghyun Darve, Eric Stanford Univ Inst Computat & Math Engn Stanford CA 94305 USA Univ Hawaii Manoa Dept Civil & Environm Engn & Water Resources Res Honolulu HI USA Stanford Univ Dept Mech Engn Stanford CA 94305 USA

Kernel matrix-vector product is ubiquitous in many science and engineering applications. However, a naive method requires O(N-2) operations, which becomes prohibitive for large-scale problems. To reduce the computation cost, we introduce a parallel method that provably requires O(N) operations and delivers an approximate result within a prescribed tolerance. The distinct feature of our method is that it requires only the ability to evaluate the kernel function, offering a black-box interface to users. Our parallel approach targets multi-core shared-memory machines and is implemented using vertical bar OpenMP vertical bar. Numerical results demonstrate up to 19x speedup on 32 cores. We also present a real-world application in geo-statistics, where our parallel method was used to deliver fast principle component analysis of covariance matrices. (C) 2021 Elsevier Inc. All rights reserved.

关键词： Kernel method Matrix-vector multiplication Covariance matrix Fast multipole method shared-memory parallelism

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm for the Sylvester observer equation

引用

SIAM JOURNAL ON SCIENTIFIC COMPUTING 1996年第3期17卷 686-698页

作者： Bischof, CH Datta, BN Purkayastha, A NO ILLINOIS UNIV DEPT MATH SCIDE KALBIL 60115 UNIV PUERTO RICO DEPT MATHMAYAGUEZPR 00681

We present a new algorithm for solving the Sylvester observer equation arising in the context of the Luenberger observer. The algorithm embodies two main computational phases: the solution of several independent equation systems and a series of matrix-matrix multiplications. The algorithm is, thus, well suited for parallel and high-performance computing. By reducing the coefficient matrix A to lower-Hessenberg form, one can implement the algorithm efficiently, with few floating-point operations and little workspace. The algorithm has been successfully implemented on a GRAY C90. A comparison, both theoretical and experimental, has been made with the well-known Hessenberg-Schur algorithm which solves an arbitrary Sylvester equation. Our theoretical analysis and experimental results confirm the superiority of the proposed algorithm, both in efficiency and speed, over the Hessenberg-Schur algorithm.

关键词： Sylvester observer equation parallel algorithm orthogonal factorization shared-memory parallelism Hessenberg-Schur algorithm

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：