Complexity analysis and performance evaluation of matrix product on multicore architectures - ENS de Lyon - École normale supérieure de Lyon Access content directly
Preprints, Working Papers, ... Year :

Complexity analysis and performance evaluation of matrix product on multicore architectures

Abstract

The multicore revolution is underway, bringing new chips introducing more complex memory architectures. Classical algorithms must be revisited in order to take the 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 to achieve the best possible tradeoff between shared and distributed caches. Comprehensive simulation results confirm the analytical performance predictions and fully establish the practical significance of our new algorithms.
Fichier principal
Vignette du fichier
rr_lip.pdf (246.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

ensl-00381458 , version 1 (05-05-2009)

Identifiers

  • HAL Id : ensl-00381458 , version 1

Cite

Mathias Jacquelin, Loris Marchal, Yves Robert. Complexity analysis and performance evaluation of matrix product on multicore architectures. 2009. ⟨ensl-00381458⟩
108 View
231 Download

Share

Gmail Facebook Twitter LinkedIn More