OpenMP scheduling on ARM big.LITTLE architecture

Single-ISA heterogeneous multicore systems are emerging as a promising direction to achieve a more suitable balance between performance and energy consumption. However, a proper utilization of these architectures is essential to reach the energy benefits. In this paper, we demonstrate the ineffectiveness of popular OpenMP scheduling policies executing Rodinia benchmark on the Exynos 5 Octa (5422) SoC, which integrates the ARM big.LITTLE architecture.

Domains

Micro and nanotechnologies/Microelectronics

Fichier principal

multiprog-18.pdf (191.99 Ko)

Origin	Files produced by the author(s)

Florent Bruguier : Connect in order to contact the contributor

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01377630

Submitted on : Friday, October 7, 2016-11:52:09 AM

Last modification on : Friday, March 24, 2023-2:53:02 PM

Long-term archiving on : Friday, February 3, 2017-7:12:23 PM

Dates and versions

lirmm-01377630 , version 1 (07-10-2016)

Identifiers

HAL Id : lirmm-01377630 , version 1

Cite

Anastasiia Butko, Louisa Bessad, David Novo, Florent Bruguier, Abdoulaye Gamatié, et al.. OpenMP scheduling on ARM big.LITTLE architecture. MULTIPROG 2016 - 9th International Workshop on Programmability and Architectures for Heterogeneous Multicores, HIPEAC, Jan 2016, Prague, Czech Republic. ⟨lirmm-01377630⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CNRS SYSMIC LIRMM LIRMM_MIC MIC MIPS UNIV-MONTPELLIER

567 View

983 Download