On the benefits of the remote GPU virtualization mechanism: The rCUDA case

Concurrency and Computation: Practice and Experience

Volumn 29, Issue 13, 2017, Pages

  Silla, Federico ^a   Iserte, Sergio ^b   Reaño, Carlos ^a   Prades, Javier ^a  

^a UNIVERSITAT POLITÈCNICA DE VALÈNCIA   (Spain)

^b UNIVERSITAT JAUME I   (Spain)

Author keywords

CUDA; GPU migration; GPU virtualization; InfiniBand; Slurm; Xen

Indexed keywords

CLOUD COMPUTING; CLUSTER COMPUTING; COMPUTER GRAPHICS; ENERGY UTILIZATION; NETWORK SECURITY; PROGRAM PROCESSORS; VIRTUAL ADDRESSES; VIRTUAL MACHINE; VIRTUALIZATION;

COMPUTING FACILITIES; CUDA; EXASCALE COMPUTING; INFINIBAND; SERVER CONSOLIDATION; SLURM; SPACE REQUIREMENTS; TOTAL ENERGY CONSUMPTION;

GRAPHICS PROCESSING UNIT;

EID: 85012118571     PISSN: 15320626     EISSN: 15320634     Source Type: Journal    
DOI: 10.1002/cpe.4072     Document Type: Conference Paper

References (40)

1. NVIDIA. CUDA C Programming Guide 7.5. https://docs.nvidia.com/cuda/cuda-c-programming-guide/; 2016.
2. Wu H, Diamos G, Sheard T, et al. Red Fox: An execution environment for relational query processing on GPUs. Proceedings of Annual IEEE/ACM International Symposium on Code Generation and Optimization, CGO '14. Orlando, FL, USA: ACM; 2014:44:44–44:54.
3. Playne DP, Hawick KA. Data parallel three-dimensional cahn-hilliard field equation simulation on GPUs with CUDA. Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA, Las Vegas, Nevada, USA; 2009.
4. Yamazaki I, Dong T, Solc R, Tomov S, Dongarra J, Schulthess T. Tridiagonalization of a dense symmetric matrix on multiple GPUs and its application to symmetric eigenvalue problems. Concurrency Computat: Pract Exper. 2014;26(16):2652–2666.
5. Yuancheng Luo D. Canny edge detection on NVIDIA CUDA. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008. CVPRW '08. Anchorage, AK, USA: IEEE; 2008:1–8.
6. Surkov V. Parallel option pricing with fourier space time-stepping method on graphics processing units. Parallel Comput. 2010;36(7):372–380.
7. Agarwal PK, Hampton S, Poznanovic J, Ramanthan A, Alam SR, Crozier PS. Performance modeling of microsecond scale biological molecular dynamics simulations on heterogeneous architectures. Concurrency Computat: Pract Exper. 2013;25(10):1356–1375.
8. Yoo AB, Jette MA, Grondona M. Slurm: Simple linux utility for resource management. Job Scheduling Strategies for Parallel Processing: 9th International Workshop, JSSPP 2003, Seattle, WA, USA, June 24, 2003. Revised Paper. Berlin, Heidelberg: Springer Berlin Heidelberg; 2003:44–60.
9. Silla F, Prades J, Iserte S, Reaño C. Remote GPU virtualization: Is it useful. The 2nd IEEE International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era. Barcelona, Spain: IEEE Computer Society; 2016:41–48.
10. Liang TY, Chang YW. GridCuda: A grid-enabled CUDA programming toolkit. 2011 IEEE Workshops of International Conference on Advanced Information Networking and Applications (WAINA). Biopolis, Singapore: IEEE; 2011:141–146.
11. Oikawa M, Kawai A, Nomura K, Yasuoka K, Yoshikawa K, Narumi T. DS-CUDA: A middleware to use many GPUs in the cloud environment. Proceedings of the 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC '12. IEEE Computer Society, Washington, DC, USA; 2012:1207–1214.
12. Giunta G, Montella R, Agrillo G, Coviello G. A GPGPU transparent virtualization component for high performance computing clouds. Euro-Par 2010 - Parallel Processing. Ischia, Italy: Springer; 2010.
13. Shi L, Chen H, Sun J. vCUDA: GPU accelerated high performance computing in virtual machines. IEEE International Symposium on Parallel & Distributed Processing, 2009. IPDPS 2009. Rome, Italy: IEEE; 2009:1–11.
14. Gupta V, Gavrilovska A, Schwan K, et al. GViM: GPU-accelerated virtual machines. Proceedings of the 3rd ACM Workshop on System-level Virtualization for High Performance Computing, Nuremberg, Germany: ACM; 2009:17–24.
15. Peña AJ, Reaño C, Silla F, Mayo R, Quintana-Orti ES, Duato Jose. A complete and efficient CUDA-sharing solution for HPC clusters. Parallel Comput. 2014;40:574–588.
16. CUDA API Reference Manual 7.5. https://developer.nvidia.com/cuda-toolkit; 2016. Accessed July 1, 2016.
17. Merritt AM, Gupta V, Verma A, Gavrilovska A, Schwan K. Shadowfax: Scaling in heterogeneous cluster systems via GPGPU assemblies. Proceedings of the 5th International Workshop on Virtualization Technologies in Distributed Computing, VTDC '11. ACM, New York, NY, USA; 2011:3–10.
18. Shadowfax II - scalable implementation of GPGPU assemblies. http://keeneland.gatech.edu/software/keeneland/kidron, Accessed May 20, 2015.
19. NVIDIA. The NVIDIA GPU Computing SDK Version 5.5; 2013.
20. iperf3: A TCP, UDP, and SCTP network bandwidth measurement tool. https://github.com/esnet/iperf; 2016. Accessed July 1, 2016.
21. Reaño C, Silla F, Shainer G, Schultz S. Local and remote GPUs perform similar with EDR 100G InfiniBand. Proceedings of the Industrial Track of the 16th International Middleware Conference, Middleware Industry '15, Vancouver, Canada; 2015.
22. Reaño C, Silla F, Castello A, et al. Improving the user experience of the rCUDA remote GPU virtualization framework. Concurrency Computat: Pract Exper. 2015;27(14):3746–3770.
23. Iserte S, Castelló A, Mayo R, et al. Slurm support for remote GPU virtualization: Implementation and performance study. 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD); 2014:318–325.
24. Vouzis PD, Sahinidis NV. GPU-BLAST: Using graphics processors to accelerate protein sequence alignment. Bioinformatics. 2011;27(2):182–188.
25. Brown WM, Kohlmeyer A, Plimpton SJ, Tharrington AN. Implementing molecular dynamics on hybrid high performance computers: Particle-particle particle-mesh. Comput Phys Commun. 2012;183(3):449–459.
26. Liu Y, Schmidt B, Liu W, Maskell DL. CUDA-MEME: Accelerating motif discovery in biological sequences using CUDA-enabled graphics processing units. Pattern Recogn Lett. 2010;31(14):2170–2177.
27. Pronk S, Páall S, Schulz R, et al. Gromacs 4.5: A high-throughput and highly parallel open source molecular simulation toolkit. Bioinformatics. 2013;29(7):845–854.
28. Klus P, Lam S, Lyberg D, et al. Barracuda - a fast short read sequence aligner using graphics processing units. BMC Res Not. 2012;5(1):27.
29. Kurtz S, Phillippy A, Delcher AL, et al. Versatile and open software for comparing large genomes. Genome Biol. 2004;5(2):R12.
30. Chang C-C, Lin C-J. Libsvm: A library for support vector machines. ACM Trans Intell Syst Technol. May 2011;2(3):27:1–27:27.
31. Phillips JC, Braun R, Wang W, et al. Scalable molecular dynamics with namd. J Comput Chem. 2005;26(16):1781–1802.
32. NVIDIA Popular GPU-Accelerated Applications Catalog. http://www.nvidia.es/content/tesla/pdf/gpu-accelerated-applications-for-hpc.pdf; 2016. Accessed July 1, 2016.
33. Walters JP, Younge AJ, Kang D-I, et al. GPU-passthrough performance: A comparison of KVM, Xen, VMWare ESXi, and LXC for CUDA and OpenCL applications. 7th IEEE International Conference on Cloud Computing (CLOUD 2014), Anchorage, AK, USA; 2014.
34. Yang C-T, Wang H-Y, Ou W-S, Liu Y-T, Hsu C-H. On implementation of GPU virtualization using PCI pass-through. 2012 IEEE 4th International Conference on Cloud Computing Technology and Science (CLOUDCOM), Taipei, Taiwan: IEEE; 2012:711–716.
35. Pérez F, Reaño C, Silla F. Providing CUDA acceleration to KVM virtual machines in InfiniBand clusters with rCUDA. Proceedings of the International Conference on Distributed Applications and Interoperable Systems, Crete, Greece; 2016.
36. Jo H, Jeong J, Lee M, Choi DH. Exploiting GPUs in virtual machine for BioCloud. BioMed Res Int. vol. 2013, Article ID 939460, 11 pages, 2013. doi:10.1155/2013/939460.
37. Prades J, Reaño C, Silla F. CUDA acceleration for Xen virtual machines in Infiniband clusters with rCUDA. Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP '16, Barcelona, Spain; 2016.
38. Mellanox. Mellanox OFED for Linux User Manual; 2015.
39. Liu Y, Wirawan A, Schmidt B. CUDASW++ 3.0: Accelerating Smith-Waterman protein database search by coupling CPU and GPU SIMD instructions. BMC Bioinformatics. 2013;14(1):1–10.
40. Takizawa H, Sato K, Komatsu K, Kobayashi H. CheCUDA: A checkpoint/restart tool for CUDA applications. Proceedings of the 2009 International Conference on Parallel and Distributed Computing, Applications and Technologies, Hiroshima, Japan; 2009.