Actions
  • shareshare
  • link
  • cite
  • add
add
auto_awesome_motion View all 2 versions
Publication . Research . Other literature type . 2019

Tuning Alya for Energy Eciency with READEX

Venkatesh Kannan; Ricard Borrell; Myles Doyle; Guillaume Houzeaux;
Open Access
English
Published: 16 Mar 2019
Publisher: Zenodo
Abstract
High Performance Computing (HPC) applications are highly complex and demand ecient execution. Energy require- ment of current petascale and future exascale systems is a major cause for concern, and it is crucial to improve the energy-eciency of the applications that run on these systems. A signi cant source of improvement for applications is that they commonly exhibit dynamic resource requirements. Consequently, such dynamism in an application presents opportunity to tailor the utilisation of resources in the HPC system based on the requirements of the application at runtime. READEX (Runtime Exploitation of Application Dynamism for Energy-ecient eXascale computing) is a EU Horizon 2020 FET-HPC project whose objective is to exploit the dynamism found in HPC applications at runtime to achieve ecient computation on exascale systems. Alya is a high performance computational mechanics application that is present in the Uni ed European Application Benchmark Suite and the PRACE Accelerator Benchmark Suite. In this paper, we apply the READEX methodology on Alya to identify and exploit any dynamism that is exhibited. We report on the potential energy savings and the e ects on the application runtime, where we observe 5-20% reduction in the energy consumed by the application.
Subjects

HPC, REDAEX, Horizon 2020

Funded by
EC| PRACE-5IP
Project
PRACE-5IP
PRACE 5th Implementation Phase Project
  • Funder: European Commission (EC)
  • Project Code: 730913
  • Funding stream: H2020 | RIA
moresidebar