Skip to Main content Skip to Navigation
Conference papers

Analytical Cache Modeling and Tilesize Optimization for Tensor Contractions

Abstract : Data movement between processor and memory hierarchy is a fundamental bottleneck that limits the performance of many applications on modern computer architectures. Tiling and loop permutation are key techniques for improving data locality. However, selecting effective tile-sizes and loop permutations is particularly challenging for tensor contractions due to the large number of loops. Even state-of-the-art compilers usually produce sub-optimal tile-sizes and loop permutations, as they rely on naive cost models. In this paper we provide an analytical model based approach to multi-level tile size optimization and permutation selection for tensor contractions. Our experimental results show that this approach achieves comparable or better performance than state-of-theart frameworks and libraries for tensor contractions.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Fabrice Rastello Connect in order to contact the contributor
Submitted on : Thursday, December 19, 2019 - 10:53:57 AM
Last modification on : Saturday, July 23, 2022 - 3:53:09 AM
Long-term archiving on: : Friday, March 20, 2020 - 2:10:45 PM


Files produced by the author(s)



Rui Li, Aravind Sukumaran-Rajam, Richard Veras, Tze Meng Low, Fabrice Rastello, et al.. Analytical Cache Modeling and Tilesize Optimization for Tensor Contractions. SC 2019 - International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2019, Denver, United States. pp.1-13, ⟨10.1145/3295500.3356218⟩. ⟨hal-02418875⟩



Record views


Files downloads