Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing units
View/ Open
Impact
Scholar |
Other documents of the author: Aliaga Estellés, José Ignacio; Anzt, Hartwig; Grützmacher, Thomas; Quintana-Orti, Enrique S.; Tomás Domínguez, Andrés Enrique
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing unitsAuthor (s)
Date
2021Publisher
John Wiley and SonsISSN
1532-0634; 1532-0626Bibliographic citation
Aliaga, JI, Anzt, H, Grützmacher, T, Quintana-Ortí, ES, Tomás, AE. Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing units. Concurrency Computat Pract Exper. 2021;e6515. https://doi.org/10.1002/cpe.6515Type
info:eu-repo/semantics/articlePublisher version
https://onlinelibrary.wiley.com/doi/full/10.1002/cpe.6515Version
info:eu-repo/semantics/acceptedVersionSubject
Abstract
We contribute to the optimization of the sparse matrix-vector product by introducing a variant of the coordinate sparse matrix format that balances the workload distribution and compresses both the indexing arrays and ... [+]
We contribute to the optimization of the sparse matrix-vector product by introducing a variant of the coordinate sparse matrix format that balances the workload distribution and compresses both the indexing arrays and the numerical information. Our approach is multi-platform, in the sense that the realizations for (general-purpose) multicore processors as well as graphics accelerators (GPUs) are built upon common principles, but differ in the implementation details, which are adapted to avoid thread divergence in the GPU case or maximize compression element-wise (i.e., for each matrix entry) for multicore architectures. Our evaluation on the two last generations of NVIDIA GPUs as well as Intel and AMD processors demonstrate the benefits of the new kernels when compared with the optimized implementations of the sparse matrix-vector product in NVIDIA's cuSPARSE and Intel's MKL, respectively. [-]
Is part of
Concurrency and Computation: Practice and Experience, 2021Funder Name
Ministerio de Ciencia, Innovación y Universidades (España) | Helmholtz Association | United States Department of Energy (DOE)
Project code
TIN2017-82972 | VH-NG-1241 | 17-SC-20-SC
Rights
Copyright © John Wiley & Sons, Inc.
http://rightsstatements.org/vocab/CNE/1.0/
info:eu-repo/semantics/openAccess
http://rightsstatements.org/vocab/CNE/1.0/
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- ICC_Articles [423]