Efficient sparse-matrix multi-vector product on GPUs
- Authors
- Hong, C.; Sukumaran-Rajam, A.; Bandyopadhyay, B.; Kim, J.; Kurt, S.E.; Nisa, I.; Sabhlok, S.; Çatalyürek, Ü.V.; Parthasarathy, S.; Sadayappan, P.
- Issue Date
- Jun-2018
- Publisher
- Association for Computing Machinery, Inc
- Keywords
- GPU; Sparse Matrix Multi-Vector Multiplication; Sparse Matrix-Matrix Multiplication; Sparse Matrix-Vector Multiplication
- Citation
- HPDC 2018 - Proceedings of the 2018 International Symposium on High-Performance Parallel and Distributed Computing, pp 66 - 79
- Pages
- 14
- Journal Title
- HPDC 2018 - Proceedings of the 2018 International Symposium on High-Performance Parallel and Distributed Computing
- Start Page
- 66
- End Page
- 79
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/63872
- DOI
- 10.1145/3208040.3208062
- Abstract
- Sparse Matrix-Vector (SpMV) and Sparse Matrix-Multivector (SpMM) products are key kernels for computational science and data science. While GPUs offer significantly higher peak performance and memory bandwidth than multicore CPUs, achieving high performance on sparse computations on GPUs is very challenging. A tremendous amount of recent research has focused on various GPU implementations of the SpMV kernel. But the multi-vector SpMM kernel has received much less attention. In this paper, we present an in-depth analysis to contrast SpMV and SpMM, and develop a new sparse-matrix representation and computation approach suited to achieving high data-movement efficiency and effective GPU parallelization of SpMM. Experimental evaluation using the entire SuiteSparse matrix suite demonstrates significant performance improvement over existing SpMM implementations from vendor libraries. © 2018 Association for Computing Machinery.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/63872)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.