research-article

GViM: GPU-accelerated virtual machines

Authors:

Vishakha Gupta,

Ada Gavrilovska,

Karsten Schwan,

Harshvardhan Kharche,

Parthasarathy RanganathanAuthors Info & Claims

HPCVirt '09: Proceedings of the 3rd ACM Workshop on System-level Virtualization for High Performance Computing

Pages 17 - 24

https://doi.org/10.1145/1519138.1519141

Published: 31 March 2009 Publication History

Abstract

The use of virtualization to abstract underlying hardware can aid in sharing such resources and in efficiently managing their use by high performance applications. Unfortunately, virtualization also prevents efficient access to accelerators, such as Graphics Processing Units (GPUs), that have become critical components in the design and architecture of HPC systems. Supporting General Purpose computing on GPUs (GPGPU) with accelerators from different vendors presents significant challenges due to proprietary programming models, heterogeneity, and the need to share accelerator resources between different Virtual Machines (VMs).

To address this problem, this paper presents GViM, a system designed for virtualizing and managing the resources of a general purpose system accelerated by graphics processors. Using the NVIDIA GPU as an example, we discuss how such accelerators can be virtualized without additional hardware support and describe the basic extensions needed for resource management. Our evaluation with a Xen-based implementation of GViM demonstrate efficiency and flexibility in system usage coupled with only small performance penalties for the virtualized vs. non-virtualized solutions.

References

[1]

AAD J. van der Steen and Jack J. Dongarra. Overview of recent supercomputers. http://www.top500.org/resources/orsc.

[2]

Alam, S. R., Agarwal, P. K., Smith, M. C., Vetter, J. S., and Caliga, D. Using fpga devices to accelerate biomolecular simulations. Computer 40, 3 (2007), 66--73.

Digital Library

[3]

AMD Corporation. Amd white paper: The industry-changing impact of accelerated computing. http://www.amd.com/us/Documents/AMD_fusion_Whitepaper.pdf, 2009.

[4]

Black, F., and Scholes, M. The pricing of options and corporate liabilities. In Journal of Political Economy (1973), pp. 81:637--659.

[5]

Chisnall, D. The Definitive Guide to the Xen Hypervisor, 1st ed. Prentice Hall Open Source Software Development Series, 2008.

Digital Library

[6]

Cray Inc. Cray xd1, 2.2 ghz. http://www.top500.org/system/7657.

[7]

Diamos, G., and Yalamanchili, S. Harmony: An execution model and runtime for heterogeneous many core systems. In HPDC Hot Topics.

Digital Library

[8]

Fraser, K., H, S., Neugebauer, R., Pratt, I., et al. Safe hardware access with the xen virtual machine monitor. In I Workshop on Operating System and Architectural Support for on demand IT InfraStructure (OASIS (Oct. 2004).

[9]

Gavrilovska, A., Kumar, S., Raj, H., Schwan, K., et al. High-performance hypervisor architectures: Virtualization in hpc systems. In HPCVirt (2007), pp. 1--8.

[10]

Gupta, V., Xenidis, J., and Schwan, K. Cellule: Virtualizing cell/b.e. for lightweight execution. Georgia Tech STI Cell/B.E. Workshop, June 2007.

[11]

Hofstee, H. P. Power efficient processor architecture and the cell processor. In HPCA (2005), pp. 258--262.

Digital Library

[12]

IBM. Accelerated library framework for cell broadband engine programmers guide and api reference. http://tinyurl.com/c2z4ze, October 2007.

[13]

Intel Corporation. Enabling consistent platform-level services for tightly coupled accelerators. http://tinyurl.com/cler3n.

[14]

Khronos OpenCl Working Group. The opencl specification. http://www.khronos.org/registry/cl/specs/opencl--1.0.29.pdf, December 2008.

[15]

Kumar, S., Talwar, V., Ranganathan, P., and Ripal Nathuji, K. S. M-channels and m-brokers: Coordinated management in virtualized systems. In Workshop on Managed Multi-Core Systems (June 2008).

[16]

Lagar-Cavilla, H. A., Tolia, N., Satyanarayanan, M., and de Lara, E. Vmm-independent graphics acceleration. In VEE (2007), pp. 33--43.

Digital Library

[17]

Linderman, M. D., Collins, J. D., Wang, H., and Meng, T. H. Merge: a programming model for heterogeneous multi-core systems. In ASPLOS (2008), pp. 287--296.

Digital Library

[18]

Manz, J. A sequency-ordered fast walsh transform. In IEEE Transactions on Audio and Electroacoustics (August 1972).

[19]

Nathuji, R., and Schwan, K. Virtualpower: coordinated power management in virtualized enterprise systems. In SOSP (2007).

Digital Library

[20]

NVIDIA. Nvidia cuda compute unified device architecture - programming guide. http://tinyurl.com/cx3t13, June 2007.

[21]

Raj, H., and Schwan, K. High performance and scalable i/o virtualization via self-virtualized devices. In HPDC (2007).

Digital Library

[22]

Ranadive, A., Kesavan, M., Gavrilovska, A., and Schwan, K. Performance implications of virtualizing multicore cluster machines. In HPCVirt (2008), pp. 1--8.

Digital Library

[23]

Rodrguez, M., Tapiador, D., et al. Dynamic provisioning of virtual clusters for grid computing. In 3rd Workshop on Virtualization in High-Performance Cluster and Grid Computing Euro-Par (2008).

[24]

Santos, J. R., Turner, Y., Janakiraman, G. J., and Pratt, I. Bridging the gap between software and hardware techniques for i/o virtualization. In USENIX Annual Technical Conference (June 2008).

Digital Library

[25]

Santos, J. R., Turner, Y., and Mudigonda, J. Taming heterogeneous nic capabilities for i/o virtualization. In Workshop on I/O Virtualization (Dec. 2008).

Digital Library

[26]

Seiler, L., Carmean, D., Sprangle, E., et al. Larrabee: a many-core x86 architecture for visual computing. ACM Transactions on Graphics 27, 3 (2008), 1--15.

Digital Library

[27]

Stratton, J., Stone, S., and mei Hwu, W. Mcuda: An efficient implementation of cuda kernels on multi-cores. Tech. Rep. IMPACT-08-01, University of Illinois at Urbana-Champaign, March 2008.

Digital Library

[28]

Sun Microsystems. The tsubame grid redefining supercomputing. http://www.top500.org/lists/2006/11.

[29]

Turner, J. A. The los alamos roadrunner petascale hybrid supercomputer: Overview of applications, results, and programming, March 2008.

[30]

Volkov, V., and Demmel, J. Lu, qr and cholesky factorizations using vector capabilities of gpus. Tech. Rep. UCB/EECS-2008-49, May 2008.

[31]

Yu, W., and Vetter, J. S. Xen-based hpc: A parallel i/o perspective. In CCGRID (2008), pp. 154--161.

Digital Library

Cited By

Teguia DChen JBitchebe SBalmau OTchana ASchiavoni VEdinger JCao JJin Z(2024)vPIM: Processing-in-Memory VirtualizationProceedings of the 25th International Middleware Conference10.1145/3652892.3700782(417-430)Online publication date: 2-Dec-2024
https://dl.acm.org/doi/10.1145/3652892.3700782
Xiang YTang DHuang RYao YXie CShi QXu RHaghighat MBao CGu YQi ZGuan H(2024)CARE: Cloudified Android With Optimized Rendering PlatformIEEE Transactions on Multimedia10.1109/TMM.2023.327430326(958-971)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3274303
Fingler HTarte IYu HSzekely AHu BAkella ARossbach CAamodt TJerger NSwift M(2023)Towards a Machine Learning-Assisted Kernel with LAKEProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 210.1145/3575693.3575697(846-861)Online publication date: 27-Jan-2023
https://dl.acm.org/doi/10.1145/3575693.3575697
Show More Cited By

GViM: GPU-accelerated virtual machines
1. General and reference
  1. Cross-computing tools and techniques

Recommendations

GPU virtualization for high performance general purpose computing on the ESX hypervisor
HPC '14: Proceedings of the High Performance Computing Symposium

Graphics Processing Units (GPU) have become important components in high performance computing (HPC) systems for their massively parallel computing capability and energy efficiency. Virtualization technologies are increasingly applied to HPC to reduce ...
On the Efficacy of a Fused CPU+GPU Processor (or APU) for Parallel Computing
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance Computing

The graphics processing unit (GPU) has made significant strides as an accelerator in parallel computing. However, because the GPU has resided out on PCIe as a discrete device, the performance of GPU applications can be bottlenecked by data transfers ...
Optimized HPL for AMD GPU and multi-core CPU usage

The installation of the LOEWE-CSC ( http://csc.uni-frankfurt.de/csc/__ __51 ) supercomputer at the Goethe University in Frankfurt lead to the development of a Linpack which can fully utilize the installed AMD Cypress GPUs. At its core, a fast DGEMM for ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

HPCVirt '09: Proceedings of the 3rd ACM Workshop on System-level Virtualization for High Performance Computing

March 2009

42 pages

ISBN:9781605584652

DOI:10.1145/1519138

General Chair:
Stephen L. Scott
Oak Ridge National Laboratory
,
Program Chair:
Geoffroy Vallée
Oak Ridge National Laboratory

Copyright © 2009 ACM.

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]

Sponsors

SIGOPS: ACM Special Interest Group on Operating Systems

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 31 March 2009

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

EuroSys '09

Sponsor:

SIGOPS

EuroSys '09: Fourth EuroSys Conference 2009

March 31, 2009

Nuremburg, Germany

Upcoming Conference

EuroSys '25

Sponsor:
sigops

Twentieth European Conference on Computer Systems

March 30 - April 3, 2025

Rotterdam , Netherlands

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

190
Total Citations
View Citations
1,632
Total Downloads

Downloads (Last 12 months)60
Downloads (Last 6 weeks)5

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Teguia DChen JBitchebe SBalmau OTchana ASchiavoni VEdinger JCao JJin Z(2024)vPIM: Processing-in-Memory VirtualizationProceedings of the 25th International Middleware Conference10.1145/3652892.3700782(417-430)Online publication date: 2-Dec-2024
https://dl.acm.org/doi/10.1145/3652892.3700782
Xiang YTang DHuang RYao YXie CShi QXu RHaghighat MBao CGu YQi ZGuan H(2024)CARE: Cloudified Android With Optimized Rendering PlatformIEEE Transactions on Multimedia10.1109/TMM.2023.327430326(958-971)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3274303
Fingler HTarte IYu HSzekely AHu BAkella ARossbach CAamodt TJerger NSwift M(2023)Towards a Machine Learning-Assisted Kernel with LAKEProceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 210.1145/3575693.3575697(846-861)Online publication date: 27-Jan-2023
https://dl.acm.org/doi/10.1145/3575693.3575697
Park MBhardwaj KGavrilovska AFedorova ANarayanan DDi Luna GQuerzoni L(2023)Pocket: ML Serving from the EdgeProceedings of the Eighteenth European Conference on Computer Systems10.1145/3552326.3587459(46-62)Online publication date: 8-May-2023
https://dl.acm.org/doi/10.1145/3552326.3587459
Yao JLu QTian RLi KGuan H(2023)An Economy-Oriented GPU Virtualization With Dynamic and Adaptive OversubscriptionIEEE Transactions on Computers10.1109/TC.2022.319999872:5(1371-1383)Online publication date: 1-May-2023
https://doi.org/10.1109/TC.2022.3199998
Bhat AAhmed I(2023)A Simulation Environment for enhancing the student experience in advanced networking conceptsSHS Web of Conferences10.1051/shsconf/202315607003156(07003)Online publication date: 13-Jan-2023
https://doi.org/10.1051/shsconf/202315607003
Tang DMao MYao YBao CShi QXie CXu RHaghighat MWang YQi ZGuan HCao X(2023)rShareJournal of Systems Architecture: the EUROMICRO Journal10.1016/j.sysarc.2023.103009145:COnline publication date: 1-Dec-2023
https://dl.acm.org/doi/10.1016/j.sysarc.2023.103009
Cecilia JMorales-García JImbernón BPrades JCano JSilla F(2023)Using remote GPU virtualization techniques to enhance edge computing devicesFuture Generation Computer Systems10.1016/j.future.2022.12.038142(14-24)Online publication date: May-2023
https://doi.org/10.1016/j.future.2022.12.038
Fingler HZhu ZYoon EJia ZWitchel ERossbach C(2022)DGSF: Disaggregated GPUs for Serverless Functions2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS)10.1109/IPDPS53621.2022.00077(739-750)Online publication date: May-2022
https://doi.org/10.1109/IPDPS53621.2022.00077
Lee MAhn HHong CNikolopoulos D(2022)gShareFuture Generation Computer Systems10.1016/j.future.2021.12.016130:C(181-192)Online publication date: 1-May-2022
https://dl.acm.org/doi/10.1016/j.future.2021.12.016
Show More Cited By

View Options

Login options

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

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten