Power Consumption of GPUs from a Software Perspective

Caroline Collange (1) , David Defour (1) , Arnaud Tisserand (2)

1 LP2A - Laboratoire de Physique Appliquée et d'Automatique
2 CAIRN - Energy Efficient Computing ArchItectures with Embedded Reconfigurable Resources

GPUs are now considered as serious challengers for high-performance computing solutions. They have power consumptions up to 300 W. This may lead to power supply and thermal dissipation problems in computing centers. In this article we investigate, using measurements, how and where modern GPUs are using energy during various computations in a CUDA environment.

Keywords: GPGPU; Power consuption; CUDA; Nvidia

Domains: Hardware Architecture [cs.AR]; Distributed, Parallel, and Cluster Computing [cs.DC]

Caroline Collange, David Defour, Arnaud Tisserand. Power Consumption of GPUs from a Software Perspective. 9th International Conference on Computational Science, May 2009, Baton Rouge, Louisiana, United States. pp.914-923, ⟨10.1007/978-3-642-01970-8_92⟩. ⟨hal-00348672⟩