Complexity analysis of matrix products on multicore architectures

Mathias Jacquelin; Loris Marchal; Yves Robert

Reports

Complexity analysis of matrix products on multicore architectures

Mathias Jacquelin ^{1, 2} Loris Marchal ^{1, 2} Yves Robert ^{1, 2}

1 LIP - Laboratoire de l'Informatique du Parallélisme

2 ENS Lyon - École normale supérieure - Lyon

Abstract : The multicore revolution is underway. Classical algorithms have to be revisited in order to take hierarchical memory layout into account. In this paper, we aim at minimizing the number of cache misses paid during the execution of the matrix product kernel on a multicore processor, and we show how th achieve the best possible trade-off between shared and distributed caches.

Keywords : Multicore processors Complexity Matrix products

Document type :

Reports

Domain :

Computer Science [cs]

Complete list of metadatas

https://hal-lara.archives-ouvertes.fr/hal-02102826
Contributor : Colette Orange <>
Submitted on : Wednesday, April 17, 2019 - 4:33:52 PM
Last modification on : Wednesday, November 20, 2019 - 2:52:53 AM

LIP-RR_08-41.pdf

Files produced by the author(s)

Complexity analysis of matrix products on multicore architectures

File

Identifiers

Collections

Citation

Export

Metrics

41

33

Complexity analysis of matrix products on multicore architectures

File

Identifiers

Collections

Citation

Export

Share

Metrics

41

33