Memory bandwidth optimization of SpMV on GPGPUs

It is an important task to improve performance for sparse matrix vector multiplication （SpMV）, and it is a difficult task because of its irregular memory access. Gen- eral purpose GPU （GPGPU） provides high computing abil- ity and substantial bandwidth that cannot be fully exploited by SpMV due to it...

Full description

Saved in:
Bibliographic Details
Published inFrontiers of Computer Science Vol. 9; no. 3; pp. 431 - 441
Main Authors YAN, Chenggang Clarence, YU, Hui, XU, Weizhi, ZHANG, Yingping, CHEN, Bochuan, TIAN, Zhu, WANG, Yuxuan, YIN, Jian
Format Journal Article
LanguageEnglish
Published Beijing Higher Education Press 01.06.2015
Springer Nature B.V
Subjects
Bandwidths
cache blocking
Computer architecture
Computer Science
Format
GeForce
GPGPU
GPU
Graphics processing units
Mathematical analysis
memory bandwidth
Performance enhancement
performance tuning
Research Article
Sparse matrices
Sparsity
SpMV
内存带宽
存储器
存储格式
带宽优化
稀疏矩阵
高速缓存
memory bandwidth
SpMV
cache blocking
performance tuning
GPGPU
Online AccessGet full text

Cover

More Information
Summary:It is an important task to improve performance for sparse matrix vector multiplication （SpMV）, and it is a difficult task because of its irregular memory access. Gen- eral purpose GPU （GPGPU） provides high computing abil- ity and substantial bandwidth that cannot be fully exploited by SpMV due to its irregularity. In this paper, we propose two novel methods to optimize the memory bandwidth for SpMV on GPGPU. First, a new storage format is proposed to exploit memory bandwidth of GPU architecture more effi- ciently. The new storage format can ensure that there are as many non-zeros as possible in the format which is suitable to exploit the memory bandwidth of the GPU. Second, we pro- pose a cache blocking method to improve the performance of SpMV on GPU architecture. The sparse matrix is partitioned into sub-blocks that are stored in CSR format. With the block- ing method, the corresponding part of vector x can be reused in the GPU cache, so the time to access the global memory for vector x is reduced heavily. Experiments are carried out on three GPU platforms, GeForce 9800 GX2, GeForce GTX 480, and Tesla K40. Experimental results show that both new methods can efficiently improve the utilization of GPU mem- ory bandwidth and the performance of the GPU.
Bibliography:11-5731/TP
It is an important task to improve performance for sparse matrix vector multiplication （SpMV）, and it is a difficult task because of its irregular memory access. Gen- eral purpose GPU （GPGPU） provides high computing abil- ity and substantial bandwidth that cannot be fully exploited by SpMV due to its irregularity. In this paper, we propose two novel methods to optimize the memory bandwidth for SpMV on GPGPU. First, a new storage format is proposed to exploit memory bandwidth of GPU architecture more effi- ciently. The new storage format can ensure that there are as many non-zeros as possible in the format which is suitable to exploit the memory bandwidth of the GPU. Second, we pro- pose a cache blocking method to improve the performance of SpMV on GPU architecture. The sparse matrix is partitioned into sub-blocks that are stored in CSR format. With the block- ing method, the corresponding part of vector x can be reused in the GPU cache, so the time to access the global memory for vector x is reduced heavily. Experiments are carried out on three GPU platforms, GeForce 9800 GX2, GeForce GTX 480, and Tesla K40. Experimental results show that both new methods can efficiently improve the utilization of GPU mem- ory bandwidth and the performance of the GPU.
GPGPU, performance tuning, SpMV, cacheblocking, memory bandwidth
memory bandwidth
SpMV
Document received on :2014-05-15
cache blocking
performance tuning
Document accepted on :2014-06-10
GPGPU
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2095-2228
2095-2236
DOI:10.1007/s11704-014-4127-1