IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs

doi:10.1109/TPDS.2024.3432579

	IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs
	Wei, Cunyang 1,2; Jia, Haipeng 3; Zhang, Yunquan 1,2; Yao, Jianyu 1,2; Li, Chendi 1,2; Cao, Wenxuan 1,2
	2024-09-01
发表期刊	IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
ISSN	1045-9219
卷号	35 期号:9 页码:1672-1689
摘要	The matrix multiplication algorithm is a fundamental numerical technique in linear algebra and plays a crucial role in many scientific computing applications. Despite the high performance of mainstream basic linear algebra libraries for large-scale dense matrix multiplications, they exhibit poor performance when applied to matrix multiplication with irregular input. This paper proposes an input-aware tuning framework that accounts for application scenarios and computer architectures to provide high-performance irregular matrix multiplication on ARMv8 and X86 CPUs. The framework comprises two stages: the install-time stage and the run-time stage. The install-time stage utilizes our proposed computational template to generate high-performance kernels for general data layout and SIMD-friendly data layout. The run-time stage utilizes a tiling algorithm suitable for irregular GEMM to select the optimal kernel and link as an execution plan. Additionally, load-balanced multi-threaded optimization algorithms are defined to exploit the multi-threading capability of modern processors. Experiments demonstrate that the proposed IrGEMM framework can achieve significant performance improvements for irregular GEMM on both ARMv8 and X86 CPUs compared to other mainstream BLAS libraries.
关键词	Kernel Libraries Computer architecture Tuning Layout Optimization Codes Batch GEMM code generation compact GEMM dynamic programming TSMM
DOI	10.1109/TPDS.2024.3432579
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2023YFB3001701] ; National Natural Science Foundation of China[62372432]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001284974600001
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39664
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Jia, Haipeng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100864, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100864, Peoples R China
推荐引用方式 GB/T 7714	Wei, Cunyang,Jia, Haipeng,Zhang, Yunquan,et al. IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs[J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,2024,35(9):1672-1689.
APA	Wei, Cunyang,Jia, Haipeng,Zhang, Yunquan,Yao, Jianyu,Li, Chendi,&Cao, Wenxuan.(2024).IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs.IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS,35(9),1672-1689.
MLA	Wei, Cunyang,et al."IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs".IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 35.9(2024):1672-1689.