EUVIMEDEUVIMED entdecken
Crossref

Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs

Khalid Ahmad, Cris Cecka, Michael Garland, Mary Hall

ACM Transactions on Architecture and Code Optimization · 31.03.2024 · 21 (1) · 1-20

DOI: 10.1145/3633462 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 15.02.2024. Verfasst von Khalid Ahmad und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An important sparse tensor computation is sparse-tensor-dense-matrix multiplication (SpTM), which is used in tensor decomposition and applications. SpTM is a multi-dimensional analog to sparse-matrix-dense-matrix multiplication (SpMM). In this article, we employ a hierarchical tensor data layout that can unfold a multidimensional tensor to derive a 2D matrix, making it possible to compute SpTM using SpMM kernel implementations for GPUs. We compare two SpMM implementations to the state-of-the-art PASTA sparse tensor contraction implementation using: (1) SpMM with hierarchical tensor data layout; and, (2) unfolding followed by an invocation of cuSPARSE’s SpMM. Results show that SpMM can outperform PASTA 70.9% of the time, but none of the three approaches is best overall. Therefore, we use a decision tree classifier to identify the best performing sparse tensor contraction kernel based on precomputed properties of the sparse tensor.

Zitieren

APA

Ahmad, K., Cecka, C., Garland, M., & Hall, M. (2024). Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs. ACM Transactions on Architecture and Code Optimization, 21(1), 1-20. https://doi.org/10.1145/3633462

Vancouver

Ahmad K, Cecka C, Garland M, Hall M. Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs. ACM Transactions on Architecture and Code Optimization. 2024;21(1):1-20. doi:10.1145/3633462

BibTeX
@article{Ahmad2024,
  author = {Ahmad, Khalid and Cecka, Cris and Garland, Michael and Hall, Mary},
  title = {Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs},
  journal = {ACM Transactions on Architecture and Code Optimization},
  year = {2024},
  volume = {21},
  number = {1},
  pages = {1--20},
  doi = {10.1145/3633462}
}
Kostenlos starten →