openblas: a high performance blas library on loongson 3a cpu

ISCAS OpenIR

	openblas: a high performance blas library on loongson 3a cpu
	Zhang Xian-Yi; Wang Qian; Zhang Yun-Quan
	2011
发表期刊	Ruan Jian Xue Bao/Journal of Software
ISSN	1000-9825
卷号	22 期号:UPPL. 2 页码:208-216
摘要	BLAS is a fundamental math library in scientific computing. Thus, each CPU vendor releases optimized BLAS library for its own CPU. Loongson CPU series are developed by the Institute of Computing Technology, Chinese Academy of Sciences. In 2010, it released Loongson 3 CPU series. This paper introduces the open source BLAS library OpenBLAS, which is forked on GotoBLAS 2-1.13 BSD version. BLAS Level 3 functions of OpenBLAS is optimized on Loongson 3A quad cores CPU. In sequential optimizations, blocking, hand coding assembly kernel, Loongson 3A special instructions and reordering instructions are utilized. The performance of BLAS Level 3 subroutines exceeded GotoBLAS and ATLAS by about 75% and 17%. Meanwhile, it exceeded GotoBLAS and ATLAS by about 103% and 36% in double precision functions. In parallel multi-threads optimization, this study used interleaved data buffer layout to avoid shared L2 Cache conflictions among multi-threads. OpenBLAS achieved 3.47 speedups on quad cores. In 4 threads, the performance of OpenBLAS BLAS Level3 functions exceeded GotoBLAS and ATLAS by about 69% and 34%, 89% and 55% in double precision functions. ©2011 Journal of Software.; BLAS is a fundamental math library in scientific computing. Thus, each CPU vendor releases optimized BLAS library for its own CPU. Loongson CPU series are developed by the Institute of Computing Technology, Chinese Academy of Sciences. In 2010, it released Loongson 3 CPU series. This paper introduces the open source BLAS library OpenBLAS, which is forked on GotoBLAS 2-1.13 BSD version. BLAS Level 3 functions of OpenBLAS is optimized on Loongson 3A quad cores CPU. In sequential optimizations, blocking, hand coding assembly kernel, Loongson 3A special instructions and reordering instructions are utilized. The performance of BLAS Level 3 subroutines exceeded GotoBLAS and ATLAS by about 75% and 17%. Meanwhile, it exceeded GotoBLAS and ATLAS by about 103% and 36% in double precision functions. In parallel multi-threads optimization, this study used interleaved data buffer layout to avoid shared L2 Cache conflictions among multi-threads. OpenBLAS achieved 3.47 speedups on quad cores. In 4 threads, the performance of OpenBLAS BLAS Level3 functions exceeded GotoBLAS and ATLAS by about 69% and 34%, 89% and 55% in double precision functions. ©2011 Journal of Software.
收录类别	EI
关键词	Computer Software Software Engineering
部门归属	(1) Laboratory of Parallel Software and Computational Science Institute of Software Chinese Academy of Sciences Beijing 100190 China; (2) State Key Laboratory of Computing Science Chinese Academy of Sciences Beijing 100190 China; (3) Graduate University Chinese Academy of Sciences Beijing 100190 China
语种	中文
内容类型	期刊论文
URI标识	http://ir.iscas.ac.cn/handle/311060/16164
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Zhang Xian-Yi,Wang Qian,Zhang Yun-Quan. openblas: a high performance blas library on loongson 3a cpu[J]. Ruan Jian Xue Bao/Journal of Software,2011,22(UPPL. 2):208-216.
APA	Zhang Xian-Yi,Wang Qian,&Zhang Yun-Quan.(2011).openblas: a high performance blas library on loongson 3a cpu.Ruan Jian Xue Bao/Journal of Software,22(UPPL. 2),208-216.
MLA	Zhang Xian-Yi,et al."openblas: a high performance blas library on loongson 3a cpu".Ruan Jian Xue Bao/Journal of Software 22.UPPL. 2(2011):208-216.