Increasing the Efficiency of Your GPU-enabled Cluster with rCUDA

Print Friendly, PDF & Email

In this video from the 2014 HPC Advisory Council Europe Conference, Federico Silla from the Universitat Politècnica de Valèncian presents: Increasing the efficiency of your GPU-enabled cluster with rCUDA.

The use of GPUs to accelerate applications is mainstream nowadays, but their adoption in current high performance computing clusters is primarily impaired by the trend of including accelerators in all the nodes of the cluster, as this presents several drawbacks related with increased costs. In this talk we introduce the remote GPU virtualization mechanism, intended to address the drawbacks of GPU computing. The rCUDA remote GPU virtualization framework will also be presented.”

Download the Slides (PDF) * See more talks from the HPCAC Europe Conference Video Gallery