On the acceleration of wavefront applications using distributed many-core architectures

Computer Journal

Volumn 55, Issue 2, 2012, Pages 138-153

  Pennycook, S J ^a   Hammond, S D ^a   Mudalige, G R ^b   Wright, S A ^a   Jarvis, S A ^a  

^a UNIVERSITY OF WARWICK   (United Kingdom)

^b UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

CUDA; GPU; many core computing; optimization; performance modelling; wavefront

Indexed keywords

APPLICATION PERFORMANCE; CUDA; DISTRIBUTED GRAPHICS; FUTURE PERFORMANCE; GPU; HIGH-PERFORMANCE COMPUTING; MANY-CORE ARCHITECTURE; MANY-CORE COMPUTING; NAS PARALLEL BENCHMARKS; PERFORMANCE MODEL; PERFORMANCE MODELLING; SCIENTIFIC AND ENGINEERING APPLICATIONS; THEORETICAL PERFORMANCE;

ALGORITHMS; COMPUTATION THEORY; COMPUTER GRAPHICS EQUIPMENT; COMPUTER SOFTWARE SELECTION AND EVALUATION; OPTIMIZATION; PROGRAM PROCESSORS; TEACHING; WAVEFRONTS;

BENCHMARKING;

EID: 84856898868     PISSN: 00104620     EISSN: 14602067     Source Type: Journal    
DOI: 10.1093/comjnl/bxr073     Document Type: Article

References (27)

1. RNR-94-007. (1994) The NAS Parallel Benchmarks. NASA Ames Research Center, Moffet Field, CA.
2. Mudalige, G.R., Vernon, M.K. and Jarvis, S.A. (2008) A Plugand-Play Model for Evaluating Wavefront Computations on Parallel Architectures. Proc. IEEE Int. Parallel and Distributed Processing Symp., Miami, FL, April 14-18. IEEE Computer Society, Los Alamitos, CA.
3. Hammond, S.D., Mudalige, G.R., Smith, J.A., Jarvis, S.A., Herdman, J.A. and Vadgama, A. (2009) WARPP: A Toolkit for Simulating High-Performance Parallel Scientific Codes. Proc. Int. Conf. Simulation Tools and Techniques, Rome, Italy, March 2-6, pp. 19:1-19:10. Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, Brussels, Belgium.
4. Hoisie, A., Lubeck, O.,Wasserman, H., Petrini, F. and Alme, H. (2000) A General Predictive Performance Model for Wavefront Algorithms on Clusters of SMPs. Proc. Int. Conf. Parallel Processing, Toronto, Canada, August 21-24, pp. 219-228. IEEE Computer Society, Los Alamitos, CA.
5. TR-08-24. (2008) Accelerating Data-Serial Applications on GPGPUs: A Systems Approach. Computer Science, Virginia Tech. Blacksburg, VA.
6. Munekawa, Y., Ino, F. and Hagihara, K. (2008) Design and Implementation of the Smith-Waterman Algorithm on the CUDA-Compatible GPU. Proc. IEEE Int. Conf. Bioinformatics and Bioengineering, Athens, Greece, October 8-10, pp. 1-6. IEEE Computer Society, Los Alamitos, CA.
7. Manavski, S. andValle, G. (2008) CUDA Compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment. BMC Bioinf., 9, S10.
8. Petrini, F., Fossum, G., Fernandez, J., Varbanescu, A.L., Kistler, N. and Perrone, M. (2007) Multicore Surprises: Lessons Learned from Optimizing Sweep 3D on the Cell Broadband Engine. Proc. IEEE Int. Parallel and Distributed Processing Symp., Long Beach, CA, March 26-30. IEEE Computer Society, LosAlamitos, CA.
9. Gong, C., Liu, J., Gong, Z., Qin, J. and Xie, J. (2010) Optimizing Sweep 3D for Graphic Processor Unit. Proc. Int. Conf. Algorithms and Architectures for Parallel Processing, Busan, Korea, May 21-23, pp. 416-426. Springer, Berlin.
10. (1995) The ASCI Sweep 3D Benchmark. Los Alamos National Laboratory. http://www.c3.lanl.gov/pal/software/sweep3d/sweep3d-readme.html (accessed May 12, 2011).
11. Boyer, M., Tarjan, D., Acton, S.T. and Skadron, K. (2009) Accelerating Leukocyte Tracking using CUDA:A Case Study in LeveragingManycore Coprocessors. Proc. IEEE Int.Parallel and Distributed Processing Symp., Rome, Italy, May 23-29. IEEE Computer Society, Los Alamitos, CA.
12. Govindaraju, N.K., Lloyd, B., Dotsenko, Y., Smith, B. and Manferdelli, J. (2008) High Performance Discrete Fourier Transforms on Graphics Processors. Proc. ACM/IEEE Conf. Supercomputing, Austin, TX, November 15-21, pp. 2:1-2:12. IEEE Press Piscataway, NJ.
13. Shimokawabe, T., Aoki, T., Muroi, C., Ishida, J., Kawano, K., Endo, T., Nukada, A., Maruyama, N. and Matsuoka, S. (2010) An 80-Fold Speedup, 15.0 TFlops Full GPUAcceleration of Non-Hydrostatic Weather Model ASUCA Production Code. Proc. ACM/IEEE Int. Conf. for High Performance Computing, Networking, Storage and Analysis, New Orleans, LA, November 13-19. IEEE Computer SocietyWashington, DC.
14. Jacobsen, D.A., Thibault, J.C. and Senocak, I. (2010) An MPICUDA Implementation for Massively Parallel Incompressible Flow Computations on Multi-GPU Clusters. Proc. 48th AIAA Aerospace Sciences Meeting, Orlando, FL, January 4-7. American Institute of Aeronautics and Astronautics, Reston,VA.
15. Lee,V.W. et al. (2010) Debunking the 100X GPU vs. CPU Myth: An Evaluation of Throughput Computing on CPU and GPU. Proc. ACM/IEEE Int. Symp. Computer Architecture, Saint-Malo, France, June 21-23, pp. 451-460. ACM NewYork, NY.
16. Vuduc, R., Chandramowlishwaran, A., Choi, J., Guney, M.E. and Shringarpure, A. (2010) On the Limits of GPU Acceleration. Proc. USENIXWorkshop on Hot Topics in Parallelism, Berkeley, CA, June 14-15. USENIX Association, Berkeley, CA.
17. RC24982. (2010) Believe it or Not! Multi-core CPUs Can Match GPU Performance for FLOP-Intensive Application!. IBM Research Division, Thomas J.Watson Research Center.Yorktown Heights, NY.
18. RC25033. (2010) Can CPUs Match GPUs on Performance with Productivity-: Experiences with Optimizing a FLOP-Intensive Application on CPUs andGPU. IBM Research Division, Thomas J.Watson Research Center.Yorktown Heights, NY.
19. Pennycook, S.J., Hammond, S.D., Mudalige, G.R. and Jarvis, S.A. (2011) Performance Analysis of a Hybrid MPI/CUDA Implementation of the NAS-LU Benchmark. SIGMETRICS Perform. Eval. Rev., 38, 23-29.
20. Lazou, C. (2010) Should I Buy GPGPUs or Blue Gene- HPC Wire. http://www.hpcwire.com/hpcwire/2010-11-04/should-i-buy-gpgpus-or-blue-gene.html (accessed November 4, 2010).
21. NAS-96-18. (1996) NAS Parallel Benchmark (Version 1.0) Results 11-96. NASA Ames Research Center, Moffet Field, CA.
22. Ryoo, S., Rodrigues, C.I., Baghsorkhi, S.S., Stone, S.S., Kirk, D.B. and Hwu, W.W. (2008) Optimization Principles and Application Performance Evaluation of a Multithreaded GPU Using CUDA. Proc. ACM SIGPLAN Symp. Principles and Practice of Parallel Programming, Salt Lake City, UT, February 20-23, pp. 73-82. ACM NewYork, NY.
23. Lamport, L. (1974) The parallel execution of DOloops. Commun. ACM, 17, 83-93.
24. Gharaibeh, A. and Ripeanu, M. (2010) Size Matters: Space/Time Tradeoffs to Improve GPGPU Applications Performance. Proc. ACM/IEEE Int. Conf. for High Performance Computing, Networking, Storage and Analysis, New Orleans, LA, November 13-19. IEEE Computer SocietyWashington, DC.
25. Reussner, R., Sanders, P., Prechelt, L. and Müller, M. (1998) SKaMPI: A detailed, accurate MPI benchmark. Recent Adv. Parallel Virtual Mach. Message Passing Interface, 1497, 52-59.
26. (2010) Livermore Computing Systems Summary. Lawrence Livermore National Laboratory. https://computing.llnl.gov/resources/systems-summary.pdf (accessed May 12, 2011).
27. Kerbyson, D.J., Hoisie, A. and Wasserman, H. (2005) A performance comparison between the earth simulator and other terascale systems on a characteristic ASCI workload. Concurrency Comput.: Pract. Exp., 17, 1219-1238. (Pubitemid 41092969)