rCUDA 4: GPGPU as a Service in HPC Clusters

News · 09-17-12, 06:00 PM

www.youtube.com/watch?v=fzRMXoyaRLQ

In this video, Antonio J. PeÃ±a from the Technical University of Valencia and Rafael Mayo from Jaume University present: rCUDA 4: GPGPU as a Service in HPC Clusters.

With rCUDA, GPU-accelerated applications are enabled to seamlessly interact with any GPU of a cluster independently of its exact physical location. This provides the possibility of sharing accelerators among different nodes, thus reducing power requirements. Decoupling GPUs from nodes, creating pools of accelerators, brings additional flexibility to cluster deployments.'

Recorded at the HPC Advisory Council Spain Workshop 2012 in Malaga. Download the slides (PDF).

09-17-12, 06:00 PM	#1
News Registered User Join Date: Jun 2009 Posts: 34,698	rCUDA 4: GPGPU as a Service in HPC Clusters www.youtube.com/watch?v=fzRMXoyaRLQ In this video, Antonio J. PeÃ±a from the Technical University of Valencia and Rafael Mayo from Jaume University present: rCUDA 4: GPGPU as a Service in HPC Clusters. With rCUDA, GPU-accelerated applications are enabled to seamlessly interact with any GPU of a cluster independently of its exact physical location. This provides the possibility of sharing accelerators among different nodes, thus reducing power requirements. Decoupling GPUs from nodes, creating pools of accelerators, brings additional flexibility to cluster deployments.' Recorded at the HPC Advisory Council Spain Workshop 2012 in Malaga. Download the slides (PDF). Related posts: Video: rCUDA, An Approach to Provide Remote Access to GPU Computational Power Video: Programming Models for Heterogeneous Computing Video: GPGPU Compute On AMD More...