research-article

CUDA acceleration for Xen virtual machines in infiniband clusters with rCUDA

Authors:

Javier Prades,

Carlos Reaño,

Federico SillaAuthors Info & Claims

PPoPP '16: Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

Article No.: 35, Pages 1 - 2

https://doi.org/10.1145/2851141.2851181

Published: 27 February 2016 Publication History

Get Access

Abstract

Many data centers currently use virtual machines (VMs) to achieve a more efficient usage of hardware resources. However, current virtualization solutions, such as Xen, do not easily provide graphics processing unit (GPU) accelerators to applications running in the virtualized domain with the flexibility usually required in data centers (i.e., managing virtual GPU instances and concurrently sharing them among several VMs). Remote GPU virtualization frameworks such as the rCUDA solution may address this problem.

In this work we analyze the use of the rCUDA framework to accelerate scientific applications running inside Xen VMs. Results show that the use of the rCUDA framework is a feasible approach, featuring a very low overhead if an InfiniBand fabric is already present in the cluster.

References

[1]

NVIDIA GRID Technology. www.nvidia.com/object/grid-technology.html, 2015.

Google Scholar

[2]

J. Song et al. KVMGT: a full GPU virtualization solution. 2014.

Google Scholar

[3]

S. N. Laboratories. Lammps molecular dynamics simulator. lammps.sandia.gov/, 2013.

Google Scholar

[4]

Y. Liu et al. CUDA-MEME: Accelerating motif discovery in biological sequences using GPUs. Pattern Recognition Letters, 31(14), 2010.

Digital Library

Google Scholar

[5]

Y. Liu et al. CUDASWw++ 3.0: accelerating smith-waterman protein database search by GPUs. BMC Bioinformatics, 14(1), 2013.

Google Scholar

[6]

C. Reaño et al. Local and Remote GPUs Perform Similar with EDR 100G InfiniBand. Middleware Conference, 2015.

Digital Library

Google Scholar

[7]

P. D. Vouzis el at. GPU-BLAST: Using graphics processors to accelerate protein sequence alignment. Bioinformatics, 2010.

Digital Library

Google Scholar

Cited By

View all

Tan HTan YHe XLi KLi K(2019)A Virtual Multi-Channel GPU Fair Scheduling Method for Virtual MachinesIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2018.286534130:2(257-270)Online publication date: 1-Feb-2019
https://dl.acm.org/doi/10.1109/TPDS.2018.2865341
Xu MBuyya R(2019)Managing renewable energy and carbon footprint in multi-cloud computing environmentsJournal of Parallel and Distributed Computing10.1016/j.jpdc.2019.09.015Online publication date: Oct-2019
https://doi.org/10.1016/j.jpdc.2019.09.015
Gutiérrez-Aguado JClaver JPeña-Ortiz R(2019)Toward a transparent and efficient GPU cloudification architectureThe Journal of Supercomputing10.1007/s11227-018-2720-z75:7(3640-3672)Online publication date: 1-Jul-2019
https://dl.acm.org/doi/10.1007/s11227-018-2720-z
Show More Cited By

Recommendations

CUDA acceleration for Xen virtual machines in infiniband clusters with rCUDA
PPoPP '16

Many data centers currently use virtual machines (VMs) to achieve a more efficient usage of hardware resources. However, current virtualization solutions, such as Xen, do not easily provide graphics processing unit (GPU) accelerators to applications ...
On the effect of using rCUDA to provide CUDA acceleration to Xen virtual machines

Nowadays, many data centers use virtual machines (VMs) in order to achieve a more efficient use of hardware resources. The use of VMs provides a reduction in equipment and maintenance expenses as well as a lower electricity consumption. Nevertheless, ...
Providing CUDA Acceleration to KVM Virtual Machines in InfiniBand Clusters with rCUDA
Distributed Applications and Interoperable Systems
Abstract
There is a trend towards using graphics processing units (GPUs) not only for graphics visualization, but also for accelerating scientific applications. But their use for this purpose is not without disadvantages: GPUs increase costs and energy ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

PPoPP '16: Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

February 2016

420 pages

ISBN:9781450340922

DOI:10.1145/2851141

General Chair:
Rafael Asenjo
University of Málaga, Spain
,
Program Chair:
Tim Harris
Oracle Labs, Cambridge, UK

ACM SIGPLAN Notices Volume 51, Issue 8
PPoPP '16
August 2016
405 pages
ISSN:0362-1340
EISSN:1558-1160
DOI:10.1145/3016078
Editor:
Matthew Fluet
Issue’s Table of Contents

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 February 2016

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Generalitat Valenciana

Conference

PPoPP '16

Sponsor:

PPoPP '16: 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

March 12 - 16, 2016

Barcelona, Spain

Acceptance Rates

Overall Acceptance Rate 230 of 1,014 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
305
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)1

Reflects downloads up to 13 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Tan HTan YHe XLi KLi K(2019)A Virtual Multi-Channel GPU Fair Scheduling Method for Virtual MachinesIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2018.286534130:2(257-270)Online publication date: 1-Feb-2019
https://dl.acm.org/doi/10.1109/TPDS.2018.2865341
Xu MBuyya R(2019)Managing renewable energy and carbon footprint in multi-cloud computing environmentsJournal of Parallel and Distributed Computing10.1016/j.jpdc.2019.09.015Online publication date: Oct-2019
https://doi.org/10.1016/j.jpdc.2019.09.015
Gutiérrez-Aguado JClaver JPeña-Ortiz R(2019)Toward a transparent and efficient GPU cloudification architectureThe Journal of Supercomputing10.1007/s11227-018-2720-z75:7(3640-3672)Online publication date: 1-Jul-2019
https://dl.acm.org/doi/10.1007/s11227-018-2720-z
Iserte SPrades JReaño CSilla F(2019)Improving the management efficiency of GPU workloads in data centers through GPU virtualizationConcurrency and Computation: Practice and Experience10.1002/cpe.527533:2Online publication date: 10-Apr-2019
https://doi.org/10.1002/cpe.5275
Hong CSpence INikolopoulos D(2017)GPU Virtualization and Scheduling MethodsACM Computing Surveys10.1145/306828150:3(1-37)Online publication date: 29-Jun-2017
https://dl.acm.org/doi/10.1145/3068281
Montella RGiunta GLaccetti GLapegna MPalmieri CFerraro CPelliccia VHong CSpence INikolopoulos D(2017)On the Virtualization of CUDA Based GPU Remoting on ARM and X86 Machines in the GVirtuS FrameworkInternational Journal of Parallel Programming10.1007/s10766-016-0462-145:5(1142-1163)Online publication date: 1-Oct-2017
https://dl.acm.org/doi/10.1007/s10766-016-0462-1
Silla FIserte SReaño CPrades J(2017)On the benefits of the remote GPU virtualization mechanism: The rCUDA caseConcurrency and Computation: Practice and Experience10.1002/cpe.407229:13Online publication date: 8-Feb-2017
https://doi.org/10.1002/cpe.4072
Tan HTan YHe XLi KLi K(2019)A Virtual Multi-Channel GPU Fair Scheduling Method for Virtual MachinesIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2018.286534130:2(257-270)Online publication date: 17-Jul-2019
https://dl.acm.org/doi/10.1109/TPDS.2018.2865341
Li HKong XLiu W(2019)Dynamic Caustic Generation for Transparent Geometry in Virtualized GPU Environment2019 IEEE International Conferences on Ubiquitous Computing & Communications (IUCC) and Data Science and Computational Intelligence (DSCI) and Smart Computing, Networking and Services (SmartCNS)10.1109/IUCC/DSCI/SmartCNS.2019.00160(786-791)Online publication date: Oct-2019
https://doi.org/10.1109/IUCC/DSCI/SmartCNS.2019.00160

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Recommendations

CUDA acceleration for Xen virtual machines in infiniband clusters with rCUDA

On the effect of using rCUDA to provide CUDA acceleration to Xen virtual machines

Providing CUDA Acceleration to KVM Virtual Machines in InfiniBand Clusters with rCUDA