AMF-CSR: Adaptive Multi-Row Folding of CSR for SpMV on GPU

Jianhua Gao, Weixing Ji*, Jie Liu, Senhao Shao, Yizhuo Wang, Feng Shi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

SpMV is a cost-dominant operation used in many iterative methods for solving large-scale sparse linear systems. However, irregular memory access of SpMV to the multiplied vector leads to low data locality and then harms the performance. This paper presents an adaptive multi-row folding of CSR (AMF-CSR) format for SpMV calculation on GPU. This new storage format supports the folding of the variable number of rows in order to achieve better load balancing in computation. AMF-CSR not only increases the density of non-zero elements in a folded row, thereby improving the access locality of the multiplied vector, but also merges an approximately equal number of nonzero elements in a folded row, hence achieving load balancing. The performance evaluation using 28 sparse matrices shows that the proposed SpMV algorithm based on AMF-CSR achieves the highest speedup of 4.11x and 3.62x on GTX 1080 Ti and Tesla V100 respectively against a fixed multi-row folding-based SpMV algorithm. Evaluation results using 450 regular sparse matrices and 450 irregular sparse matrices also show that AMF-CSR is superior to other SpMV implementations.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 27th International Conference on Parallel and Distributed Systems, ICPADS 2021
PublisherIEEE Computer Society
Pages418-425
Number of pages8
ISBN (Electronic)9781665408783
DOIs
Publication statusPublished - 2021
Event27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021 - Beijing, China
Duration: 14 Dec 202116 Dec 2021

Publication series

NameProceedings of the International Conference on Parallel and Distributed Systems - ICPADS
Volume2021-December
ISSN (Print)1521-9097

Conference

Conference27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021
Country/TerritoryChina
CityBeijing
Period14/12/2116/12/21

Keywords

  • GPU
  • SpMV
  • data locality
  • load balancing
  • sparse matrix

Fingerprint

Dive into the research topics of 'AMF-CSR: Adaptive Multi-Row Folding of CSR for SpMV on GPU'. Together they form a unique fingerprint.

Cite this