版权说明 帮助中心
首页 > 成果 > 详情

A hybrid computing method of SpMV on CPU–GPU heterogeneous computing systems

SCI-EEI
WOS被引频次:8
认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Yang, Wangdong;Li, Kenli*;Li, Keqin
通讯作者:
Li, Kenli
作者机构:
[Li, Keqin; Yang, Wangdong; Li, Kenli] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410008, Hunan, Peoples R China.
[Li, Keqin] SUNY Coll New Paltz, Dept Comp Sci, New Paltz, NY 12561 USA.
[Yang, Wangdong] Hunan City Univ, Coll Informat Sci & Engn, Yiyang 413000, Hunan, Peoples R China.
[Li, Kenli] Hunan Univ, Natl Supercomp Ctr Changsha, Changsha 410008, Hunan, Peoples R China.
通讯机构:
[Li, Kenli] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410008, Hunan, Peoples R China.
语种:
英文
关键词:
Heterogeneous computing;Hybrid storage format;Partition;Sparse matrix-vector multiplication
期刊:
Journal of Parallel and Distributed Computing
ISSN:
0743-7315
年:
2017
卷:
104
页码:
49-60
文献类别:
WOS:Article;EI:Journal article (JA)
所属学科:
ESI学科类别:计算机科学;WOS学科类别:Computer Science, Theory & Methods
入藏号:
WOS:000398763100005;EI:20170403274131
基金类别:
National Natural Science Foundation of China [61572175, 61472124]; Key Program of National Natural Science Foundation of China [61432005]
机构署名:
本校为其他机构
院系归属:
信息与电子工程学院
摘要:
Sparse matrix-vector multiplication (SpMV) is an important issue in scientific computing and engineering applications. The performance of SpMV can be improved using parallel computing. The implementation and optimization of SpMV on GPU are research hotspots. Due to some irregularities of sparse matrices, the use of a single compression format is not satisfactory. The hybrid storage format can expand the range of adaptation of the compression algorithms. However, because of the imbalance of non-zero elements, the parallel computing capability of a GPU cannot be fully utilized. The parallel computing capability of a CPU is also rising due to increased number of cores in CPU. However, when a GPU is computing, the CPU controls the process instead of contributing to the computational work. It leads to under-utilization of the computing power of CPU. Due to the characteristics of the sparse matrices, the data can be split into two parts using the hybrid storage format to be allocated to CPU and GPU for simultaneous computing. In order to take full advantage of computing resources of CPU and GPU, the CPU-GPU heterogeneous computing model is adopted in this paper to improve the performance of SpMV. With analysis of the characteristics of CPU and GPU, an optimization strategy of sparse matrix partitioning using a distribution function is proposed to improve the computing performance of SpMV on the heterogeneous computing platform. The experimental results on two test machines demonstrate noticeable performance improvement. (C) 2017 Elsevier Inc. All rights reserved.
参考文献:
Baskaran M. M., 2008, RC24704 IBM TJ WATS
Belgin M, 2009, ICS'09: PROCEEDINGS OF THE 2009 ACM SIGARCH INTERNATIONAL CONFERENCE ON SUPERCOMPUTING, P100, DOI 10.1145/1542275.1542294
Boyer B., 2010, P 4 INT WORKSH PAR S, P80
Brodtkorb AR, 2013, J PARALLEL DISTR COM, V73, P4, DOI 10.1016/j.jpdc.2012.04.003
Buatois L, 2009, INT J PARALLEL EMERG, V24, P205, DOI 10.1080/17445760802337010

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com