Heterogeneous Multicore Parallel Programming for Graphics Processing Units-Reference-Cited by-同舟云学术

Heterogeneous Multicore Parallel Programming for Graphics Processing Units

Published:2009 Issue:4 Volume:17 Page:325-336
ISSN:1058-9244
Container-title:Scientific Programming
language:en
Short-container-title:Scientific Programming

Author:

Bodin Francois¹,Bihan Stephane¹

Affiliation:

1. CAPS entreprise, 4 allée Marie Berhaut, 35000 Rennes, France

Abstract

Hybrid parallel multicore architectures based on graphics processing units (GPUs) can provide tremendous computing power. Current NVIDIA and AMD Graphics Product Group hardware display a peak performance of hundreds of gigaflops. However, exploiting GPUs from existing applications is a difficult task that requires non-portable rewriting of the code. In this paper, we present HMPP, a Heterogeneous Multicore Parallel Programming workbench with compilers, developed by CAPS entreprise, that allows the integration of heterogeneous hardware accelerators in a unintrusive manner while preserving the legacy code.

Publisher

Hindawi Limited

Subject

Computer Science Applications,Software

Link

http://downloads.hindawi.com/journals/sp/2009/784893.pdf

Cited by 7 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A parallel hybrid implementation of the 2D acoustic wave equation;International Journal of Nonlinear Sciences and Numerical Simulation;2020-07-25

2. Performance Evaluation of OpenMP and CUDA on Multicore Systems;Algorithms and Architectures for Parallel Processing;2012

3. High-Level Support for Pipeline Parallelism on Many-Core Architectures;Euro-Par 2012 Parallel Processing;2012

4. Hybrid CUDA, OpenMP, and MPI parallel programming on multicore GPU clusters;Computer Physics Communications;2011-01

5. Compiler-directed memory management for heterogeneous MPSoCs;Journal of Systems Architecture;2011-01