Sequences of Sparse Matrix-Vector Multiplication on Fugaku’s A64FX processors - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Sequences of Sparse Matrix-Vector Multiplication on Fugaku’s A64FX processors

Résumé

We implement parallel and distributed versions of the sparse matrix-vector product and the sequence of matrixvector product operations, using OpenMP, MPI, and the ARM SVE intrinsic functions, for different matrix storage formats. We investigate the efficiency of these implementations on one and two A64FX processors, using a variety of sparse matrices as input. The matrices have different properties in size, sparsity and regularity. We observe that a parallel and distributed implementation shows good scaling on two nodes for cases where the matrix is close to a diagonal matrix, but the performances degrade quickly with variations to the sparsity or regularity of the input.
Fichier principal
Vignette du fichier
paper.pdf (239.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03450283 , version 1 (25-11-2021)

Identifiants

Citer

Jérôme Gurhem, Maxence Vandromme, Miwako Tsuji, Serge G Petiton, Mitsuhisa Sato. Sequences of Sparse Matrix-Vector Multiplication on Fugaku’s A64FX processors. CLUSTER 2021 - IEEE International Conference on Cluster Computing, Sep 2021, Portland, United States. pp.751-758, ⟨10.1109/Cluster48925.2021.00111⟩. ⟨hal-03450283⟩
83 Consultations
269 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More