Accelerating sparse matrix–matrix multiplication with GPU Tensor Cores. (December 2020)

• Record Type: Journal Article
• Authors: Zachariadis, Orestis; Satpute, Nitin; Gómez-Luna, Juan; Olivares, Joaquín
• Is Part Of: Computers & electrical engineering. Volume 88(2020)
• Publication Date: 2020-12
• Subjects: Sparse matrix multiplication -- GPU -- Tensor Cores -- Parallel computing -- SpGEMM; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106848
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Sparse general matrix–matrix multiplication (spGEMM) is an essential component in many scientific and data analytics applications. However, the sparsity pattern of the input matrices and the interaction of their patterns make spGEMM challenging. Modern GPUs include Tensor Core Units (TCUs), which specialize in dense matrix multiplication. Our aim is to re-purpose TCUs for sparse matrices. The key idea of our spGEMM algorithm, tSparse, is to multiply sparse rectangular blocks using the mixed precision mode of TCUs. tSparse partitions the input matrices into tiles and operates only on tiles which contain one or more elements. It creates a task list of the tiles, and performs matrix multiplication of these tiles using TCUs. To the best of our knowledge, this is the first time that TCUs are used in the context of spGEMM. We show that spGEMM, with our tiling approach, benefits from TCUs. Our approach significantly improves the performance of spGEMM in comparison to cuSPARSE, CUSP, RMerge2, Nsparse, AC-SpGEMM and spECK. Graphical abstract: Highlights: GPU acceleration of sparse matrix–matrix multiplication (spGEMM). Tensor Core units multiply tiles from task lists. Using Tensor Core units with sparse matrices.