Abstract
In the ongoing efforts targeting the vectorization of linear algebra primitives, sparse matrix-matrix multiplication (SpGEMM) has received considerably less attention than sparse Matrix-Vector multiplication (SpMV). While both are equally important, this disparity can be attributed mainly to the additional formidable challenges raised by SpGEMM.
In this paper, we present a dynamic approach for addressing SpGEMM on the GPU. Our approach works directly on the standard compressed sparse rows (CSR) data format. In comparison to previous SpGEMM implementations, our approach guarantees a homogeneous, load-balanced access pattern to the first input matrix and improves memory access to the second input matrix. It adaptively re-purposes GPU threads during execution and maximizes the time efficient on-chip scratchpad memory can be used. Adhering to a completely deterministic scheduling pattern …
In this paper, we present a dynamic approach for addressing SpGEMM on the GPU. Our approach works directly on the standard compressed sparse rows (CSR) data format. In comparison to previous SpGEMM implementations, our approach guarantees a homogeneous, load-balanced access pattern to the first input matrix and improves memory access to the second input matrix. It adaptively re-purposes GPU threads during execution and maximizes the time efficient on-chip scratchpad memory can be used. Adhering to a completely deterministic scheduling pattern …
Originalsprache | englisch |
---|---|
Titel | PPoPP '19, Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming |
Erscheinungsort | New York, NY |
Herausgeber (Verlag) | Association of Computing Machinery |
Seiten | 68-81 |
Seitenumfang | 14 |
ISBN (Print) | 978-1-4503-6225-2 |
DOIs | |
Publikationsstatus | Veröffentlicht - 2019 |
Veranstaltung | 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - Washington, DC, USA / Vereinigte Staaten Dauer: 16 Feb. 2019 → 20 Feb. 2019 |
Konferenz
Konferenz | 24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming |
---|---|
Kurztitel | PPoPP '19 |
Land/Gebiet | USA / Vereinigte Staaten |
Ort | Washington, DC |
Zeitraum | 16/02/19 → 20/02/19 |