An efficient implementation of GPU virtualization in high performance clusters

Authors:
José Duato;Francisco D. Igual;Rafael Mayo;Antonio J. Peña;Enrique S. Quintana-Ortí;Federico Silla
Affiliations:
Departamento de Informática de Sistemas y Computadores, Universidad Politécnica de Valencia, Valencia, Spain;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain;Departamento de Informática de Sistemas y Computadores, Universidad Politécnica de Valencia, Valencia, Spain;Depto. de Ingeniería y Ciencia de Computadores, Universidad Jaume I, Castellón, Spain;Departamento de Informática de Sistemas y Computadores, Universidad Politécnica de Valencia, Valencia, Spain
Venue:
Euro-Par'09 Proceedings of the 2009 international conference on Parallel processing
Year:
2009

Citing 9
Cited 1

Rethinking the TCP Nagle algorithm

ACM SIGCOMM Computer Communication Review
Brook for GPUs: stream computing on graphics hardware

ACM SIGGRAPH 2004 Papers
Congestion control in IP/TCP internetworks

ACM SIGCOMM Computer Communication Review
Guest Editors' Introduction: Resource Virtualization Renaissance

Computer
VMM-independent graphics acceleration

Proceedings of the 3rd international conference on Virtual execution environments
Accelerating advanced mri reconstructions on gpus

Proceedings of the 5th conference on Computing frontiers
Benchmarking GPUs to tune dense linear algebra

Proceedings of the 2008 ACM/IEEE conference on Supercomputing
Solving Dense Linear Systems on Graphics Processors

Euro-Par '08 Proceedings of the 14th international Euro-Par conference on Parallel Processing
VELO: A Novel Communication Engine for Ultra-Low Latency Message Transfers

ICPP '08 Proceedings of the 2008 37th International Conference on Parallel Processing

VGRIS: virtualized GPU resource isolation and scheduling in cloud gaming

Proceedings of the 22nd international symposium on High-performance parallel and distributed computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Current high performance clusters are equipped with high bandwidth/low latency networks, lots of processors and nodes, very fast storage systems, etc. However, due to economical and/or power related constraints, in general it is not feasible to provide an accelerating coprocessor -such as a graphics processor (GPU)- per node. To overcome this, in this paper we present a GPU virtualization middleware, which makes remote CUDA-compatible GPUs available to all the cluster nodes. The software is implemented on top of the sockets application programming interface, ensuring portability over commodity networks, but it can also be easily adapted to high performance networks.