A Systematic Survey of General Sparse Matrix-matrix Multiplication
A Systematic Survey of General Sparse Matrix-matrix Multiplication
复制标题
DOI：
10.1145/3571157
复制
发表时间：
2020-02
影响因子：
16.6
通讯作者：
Jianhua Gao;Weixing Ji;Zhaonian Tan;Yueyan Zhao
中科院分区：
文献类型：
--
作者：
Jianhua Gao;Weixing Ji;Zhaonian Tan;Yueyan Zhao
广义稀疏矩阵-矩阵乘法（SpGEMM）在图分析、科学计算和深度学习等领域受到广泛关注。在过去几十年中，针对不同的应用程序和计算体系结构开发了许多优化技术。本文的目的是为SpGEMM的研究提供一个结构化和全面的概述。现有的研究已经根据目标架构和设计选择分为不同的类别。涵盖的主题包括典型应用程序、压缩格式、通用公式、关键问题和技术、面向体系结构的优化和编程模型。对不同算法的原理进行了分析和总结。本次调查充分揭示了到2021年SpGEMM研究的最新进展。此外，还对现有实现进行了全面的性能比较。基于我们的发现，我们强调了未来的研究方向，鼓励在以后的研究中更好的设计和实现。
General Sparse Matrix-Matrix Multiplication (SpGEMM) has attracted much attention from researchers in graph analyzing, scientific computing, and deep learning. Many optimization techniques have been developed for different applications and computing architectures over the past decades. The objective of this article is to provide a structured and comprehensive overview of the researches on SpGEMM. Existing researches have been grouped into different categories based on target architectures and design choices. Covered topics include typical applications, compression formats, general formulations, key problems and techniques, architecture-oriented optimizations, and programming models. The rationales of different algorithms are analyzed and summarized. This survey sufficiently reveals the latest progress of SpGEMM research to 2021. Moreover, a thorough performance comparison of existing implementations is presented. Based on our findings, we highlight future research directions, which encourage better design and implementations in later studies.