Parallel processing of matrix multiplication in a CPU and GPU heterogeneous environment

Authors:
Satoshi Ohshima;Kenji Kise;Takahiro Katagiri;Toshitsugu Yuba
Affiliations:
Graduate School of Information Systems, The University of Electro-Communications, Chofu-shi, Tokyo, Japan;Graduate School of Information Systems, The University of Electro-Communications, Chofu-shi, Tokyo, Japan;Graduate School of Information Systems, The University of Electro-Communications, Chofu-shi, Tokyo, Japan;Graduate School of Information Systems, The University of Electro-Communications, Chofu-shi, Tokyo, Japan
Venue:
VECPAR'06 Proceedings of the 7th international conference on High performance computing for computational science
Year:
2006

Citing 10
Cited 3

Exploiting fast matrix multiplication within the level 3 BLAS

ACM Transactions on Mathematical Software (TOMS)
Practical experience in the numerical dangers of heterogeneous computing

ACM Transactions on Mathematical Software (TOMS)
Fast matrix multiplies using graphics hardware

Proceedings of the 2001 ACM/IEEE conference on Supercomputing
Using modern graphics architectures for general-purpose computing: a framework and analysis

Proceedings of the 35th annual ACM/IEEE international symposium on Microarchitecture
The FFT on a GPU

Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
Linear algebra operators for GPU implementation of numerical algorithms

ACM SIGGRAPH 2003 Papers
GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics

GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics
Understanding the efficiency of GPU algorithms for matrix-matrix multiplication

Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
The GeForce 6800

IEEE Micro
Automatic Tuning Matrix Multiplication Performance on Graphics Hardware

Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques

The Rise of the Commodity Vectors

High Performance Computing for Computational Science - VECPAR 2008
Processing data streams with hard real-time constraints on heterogeneous systems

Proceedings of the international conference on Supercomputing
A Novel CPU-GPU Cooperative Implementation of A Parallel Two-List Algorithm for the Subset-Sum Problem

Proceedings of Programming Models and Applications on Multicores and Manycores

Quantified Score

Hi-index	0.00

Visualization

Abstract

GPUs for numerical computations are becoming an attractive alternative in research. In this paper, we propose a new parallel processing environment for matrix multiplications by using both CPUs and GPUs. The execution time of matrix multiplications can be decreased to 40.1% by our method, compared with using the fastest of either CPU only case or GPU only case. Our method performs well when matrix sizes are large.