arrow
Return

Revisiting thread configuration of SpMV kernels on GPU: A machine learning based approach

delete2024-03-01
delete2
PRE
AI
J
Jianhua Gao
W
Weixing Ji *
J
Jie Liu
王一拙 (Yizhuo Wang)
F
Feng Shi
DOI:10.1016/j.jpdc.2023.104799delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Sparse matrix-vector multiplication (SpMV) optimization on GPUs has been challenging due to irregular memory accesses and unbalanced workloads. The majority of existing solutions assign a fixed number of threads to one or more rows of sparse matrices according to empirical formulas. However, this method does not give the optimal thread configuration and results in a significant performance loss. This paper proposes a new machine learning-based thread assignment strategy for SpMV on GPU, predicting the near-optimal thread configuration for matrices. Further, we partition irregular sparse matrices into blocks according to the distribution of non-zero elements and predict the optimal thread configuration for each block. A new SpMV kernel is designed to accelerate the execution of different blocks. Experimental results show that our machine learning-based approach can select the near-optimal thread configuration for most matrices. The efficiency of SpMV for irregular matrices is also improved by matrix partitioning and blockwise prediction. Finally, we dive into the trained model to find out the connection between the features of a sparse matrix and its optimal thread configuration.
Keywords:
SpMV
Machine learning
GPU
Thread configuration

Journal

Journal of Parallel and Distributed Computing cover
Journal of Parallel and Distributed Computing
IF:
4
Papers:
3.8K
Citations:
4.8K

Organization

B
beijing institute of technology
Scholars:
5.4W
Papers: 4.0W
Citations: 63