Abstract
We contribute to the optimization of the sparse matrix-vector product on graphics processing units by introducing a variant of the coordinate sparse matrix layout that compresses the integer representation of the matrix indices. In addition, we employ a look-ahead table to avoid the storage of repeated numerical values in the sparse matrix, yielding a more compact data representation that is easier to maintain in the cache. Our evaluation on the two most recent generations of NVIDIA GPUs, the V100 and the A100 architectures, shows considerable performance improvements over the kernels for the sparse matrix-vector product in cuSPARSE (CUDA 11.0.167).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Suitesparse matrix collection (2018). https://sparse.tamu.edu. Accessed Sept 2020
Bell, N., Garland, M.: Efficient sparse matrix-vector multiplication on CUDA. NVIDIA Technical report NVR-2008-004, NVIDIA Corporation, December 2008
Buluç, A., Williams, S., Oliker, L., Demmel, J.: Reduced-bandwidth multithreaded algorithms for sparse matrix-vector multiplication. In: Proceedings of the IEEE International Parallel & Distributed Processing Symposium, pp. 721–733 (2011)
Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. In: Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2010, pp. 115–126 (2010)
Filippone, S., Cardellini, V., Barbieri, D., Fanfarillo, A.: Sparse matrix-vector multiplication on GPGPUs. ACM Trans. Math. Softw. 43(4), 1–49 (2017)
Flegar, G., Anzt, H.: Overcoming load imbalance for irregular sparse matrices. In: Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms, IA3 2017 (2017)
Flegar, G., Quintana-Ortí, E.S.: Balanced CSR sparse matrix-vector product on graphics processors. In: Rivera, F.F., Pena, T.F., Cabaleiro, J.C. (eds.) Euro-Par 2017. LNCS, vol. 10417, pp. 697–709. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-64203-1_50
Grossman, M., Thiele, C., Araya-Polo, M., Frank, F., Alpak, F.O., Sarkar, V.: A survey of sparse matrix-vector multiplication performance on large matrices. CoRR abs/1608.00636 (2016). http://arxiv.org/abs/1608.00636
Liu, W., Vinter, B.: CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS 2015, pp. 339–350. ACM, New York (2015)
Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. SIAM, Philadelphia (2003)
Acknowledgements
This work was partially sponsored by the EU H2020 project 732631 OPRECOMP and project TIN2017-82972-R of the Spanish MINECO. Hartwig Anzt and Yuhsiang M. Tsai were supported by the “Impuls und Vernetzungsfond” of the Helmholtz Association under grant VH-NG-1241 and by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of the U.S. Department of Energy Office of Science and the National Nuclear Security Administration. The authors would like to thank the Steinbuch Centre for Computing (SCC) of the Karlsruhe Institute of Technology for providing access to an NVIDIA A100 GPU.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Aliaga, J.I., Anzt, H., Quintana-Ortí, E.S., Tomás, A.E., Tsai, Y.M. (2021). Balanced and Compressed Coordinate Layout for the Sparse Matrix-Vector Product on GPUs. In: Balis, B., et al. Euro-Par 2020: Parallel Processing Workshops. Euro-Par 2020. Lecture Notes in Computer Science(), vol 12480. Springer, Cham. https://doi.org/10.1007/978-3-030-71593-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-71593-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71592-2
Online ISBN: 978-3-030-71593-9
eBook Packages: Computer ScienceComputer Science (R0)