Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration
ACM Transactions on Architecture and Code Optimization · 31.03.2023 · 20 (1) · 1-26
DOI: 10.1145/3566054 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 16.12.2022. Verfasst von Tuowen Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: Exascale Computing Project, National Science Foundation.
Abstract (Originalsprache)
This article presents a code generator for sparse tensor contraction computations. It leverages a mathematical representation of loop nest computations in the sparse polyhedral framework (SPF), which extends the polyhedral model to support non-affine computations, such as those that arise in sparse tensors. SPF is extended to perform layout specification, optimization, and code generation of sparse tensor code: (1) We develop a polyhedral layout specification that decouples iteration spaces for layout and computation; and (2) we develop efficient co-iteration of sparse tensors by combining polyhedra scanning over the layout of one sparse tensor with the synthesis of code to find corresponding elements in other tensors through an SMT solver. We compare the generated code with that produced by a state-of-the-art tensor compiler, TACO. We achieve on average 1.63× faster parallel performance than TACO on sparse-sparse co-iteration and describe how to improve that to 2.72× average speedup by switching the find algorithms. We also demonstrate that decoupling iteration spaces of layout and computation enables additional layout and computation combinations to be supported.
Förderung
- Exascale Computing Project
- National Science Foundation
Zitieren
APA
Zhao, T., Popoola, T., Hall, M., Olschanowsky, C., & Strout, M. (2023). Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration. ACM Transactions on Architecture and Code Optimization, 20(1), 1-26. https://doi.org/10.1145/3566054
Vancouver
Zhao T, Popoola T, Hall M, Olschanowsky C, Strout M. Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration. ACM Transactions on Architecture and Code Optimization. 2023;20(1):1-26. doi:10.1145/3566054
BibTeX
@article{Zhao2023,
author = {Zhao, Tuowen and Popoola, Tobi and Hall, Mary and Olschanowsky, Catherine and Strout, Michelle},
title = {Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2023},
volume = {20},
number = {1},
pages = {1--26},
doi = {10.1145/3566054}
}
EUVIMED