Efficient Tiled Sparse Matrix Multiplication through Matrix Signatures - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Efficient Tiled Sparse Matrix Multiplication through Matrix Signatures

Süreyya Emre
  • Function : Author
  • PersonId : 1089194
Aravind Sukumaran-Rajam
  • Function : Author
  • PersonId : 1089195


Tiling is a key technique to reduce data movement in matrix computations. While tiling is well understood and widely used for dense matrix/tensor computations, effective tiling of sparse matrix computations remains a challenging problem. This paper proposes a novel method to efficiently summarize the impact of the sparsity structure of a matrix on achievable data reuse as a one-dimensional signature, which is then used to build an analytical cost model for tile size optimization for sparse matrix computations. The proposed model-driven approach to sparse tiling is evaluated on two key sparse matrix kernels: Sparse Matrix-Dense Matrix Multiplication (SpMM) and Sampled Dense-Dense Matrix Multiplication (SDDMM). Experimental results demonstrate that model-based tiled SpMM and SDDMM achieve high performance relative to the current state-of-the-art.
Fichier principal
Vignette du fichier
main.pdf (624.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03117491 , version 1 (21-01-2021)


  • HAL Id : hal-03117491 , version 1


Süreyya Emre, Aravind Sukumaran-Rajam, Fabrice Rastello, Ponnuswamy Sadayyapan. Efficient Tiled Sparse Matrix Multiplication through Matrix Signatures. SC 2020 - International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2020, virtual, United States. pp.1-13. ⟨hal-03117491⟩
160 View
1331 Download


Gmail Facebook X LinkedIn More