Performance analysis of HPC applications on low-power embedded platforms

Authors:
Luka Stanisic;Brice Videau;Johan Cronsioe;Augustin Degomme;Vania Marangozova-Martin;Arnaud Legrand;Jean-François Méhaut
Affiliations:
Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France;Université de Grenoble, UJF, CNRS, CEA, France
Venue:
Proceedings of the Conference on Design, Automation and Test in Europe
Year:
2013

Citing 3
Cited 1

A genetic algorithms approach to modeling the performance of memory-bound computations

Proceedings of the 2007 ACM/IEEE conference on Supercomputing
Automatic Evaluation of the Computation Structure of Parallel Applications

PDCAT '09 Proceedings of the 2009 International Conference on Parallel and Distributed Computing, Applications and Technologies
The low-power architecture approach towards exascale computing

Proceedings of the second workshop on Scalable algorithms for large-scale systems

Analysis of computing and energy performance of multicore, NUMA, and manycore platforms for an irregular application

IA^3 '13 Proceedings of the 3rd Workshop on Irregular Applications: Architectures and Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents performance evaluation and analysis of well-known HPC applications and benchmarks running on low-power embedded platforms. The performance to power consumption ratios are compared to classical x86 systems. Scalability studies have been conducted on the Mont-Blanc Tibidabo cluster. We have also investigated optimization opportunities and pitfalls induced by the use of these new platforms, and proposed optimization strategies based on auto-tuning.