Dense Linear Algebra Kernels on Heterogeneous Platforms: Redistribution Issues

Olivier Beaumont 1 Arnaud Legrand 1 Fabrice Rastello 1 Yves Robert 1
1 REMAP - Regularity and massive parallel computing
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : In this paper, we deal with redistribution issues for dense linear algebra kernels on heterogeneous platforms. In this context, processors speeds may well vary during the execution of a large kernel, which requires efficient strategies for redistributing the data along the computations. The strategy that we propose is to redistribute data after some well identified static phases and therefore, it is neither fully static nor fully dynamic. We present an optimal algorithm (under some assumptions) for redistributing data when performing matrix matrix multiplication.
Complete list of metadatas

https://hal.inria.fr/hal-00856640
Contributor : Equipe Roma <>
Submitted on : Monday, September 2, 2013 - 10:21:55 AM
Last modification on : Friday, April 20, 2018 - 3:44:24 PM

Identifiers

  • HAL Id : hal-00856640, version 1

Collections

Citation

Olivier Beaumont, Arnaud Legrand, Fabrice Rastello, Yves Robert. Dense Linear Algebra Kernels on Heterogeneous Platforms: Redistribution Issues. [Research Report] 2000-45, 2000. ⟨hal-00856640⟩

Share

Metrics

Record views

225