The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - July/August (2011 vol.31)
pp: 74-78
Richard Vuduc , Georgia Institute of Technology
Kent Czechowski , Georgia Institute of Technology
ABSTRACT
<p>This column examines how GPU computing might affect the architecture of future exascale supercomputers. Specifically, the authors argue that a system with slower but better-balanced processors might yield higher performance and consume less energy than a system with very fast but imbalanced processors.</p>
INDEX TERMS
GPU, CPU, exascale, supercomputers, system balance, data-intensive processing
CITATION
Richard Vuduc, Kent Czechowski, "What GPU Computing Means for High-End Systems", IEEE Micro, vol.31, no. 4, pp. 74-78, July/August 2011, doi:10.1109/MM.2011.78
REFERENCES
1. P. Kogge et al., Exascale Computing Study: Technology Challenges in Achieving Exascale Systems, tech. report, DARPA, 2008.
2. H. Simon et al., Modeling and Simulation at the Exascale for Energy and the Environment, tech. report, US Department of Energy, Office of Science, 2007.
3. J. Nickolls and W.J. Dally, "The GPU Computing Era," IEEE Micro, vol. 30, no. 2, 2010, pp. 56-69.
4. R. Bordawekar, U. Bondhugula, and R. Rao, "Believe It or Not! Multi-core CPUs Can Match GPU Performance for a FLOP-Intensive Application!" Proc. 19th Int'l Conf. Parallel Architectures and Compilation Techniques, ACM Press, 2010, p. 537-538.
5. E.S. Chung et al., "Single-Chip Heterogeneous Computing: Does the Future Include Custom Logic, FPGAs, and GPUs?" Proc. 43rd IEEE/ACM Int'l Symp. Microarchitecture, IEEE CS Press, 2010, pp. 225-236.
6. V.W. Lee et al., "Debunking the 100X GPU vs. CPU Myth: An Evaluation of Throughput Computing on CPU and GPU," ACM SIGARCH Computer Architecture News, vol. 38, no. 3, 2010, pp. 451-460.
7. R. Vuduc et al., "On the Limits of GPU Acceleration," Proc. USENIX Workshop Hot Topics in Parallelism, USENIX Assoc., 2010, http://www.usenix.org/events/hotpar10tech .
8. K. Czechowski et al., "Balance Principles for Algorithm-Architecture Co-design," Proc. USENIX Workshop Hot Topics in Parallelism, Usenix Assoc, 2011, http://www.usenix.org/eventshotpar11.
9. H.T. Kung, "Memory Requirements for Balanced Computer Architectures," Proc. ACM Int'l Symp. Computer Architecture, ACM Press, 1986, pp. 49-54.
10. J. McCalpin, "Memory Bandwidth and Machine Balance in High Performance Computers," IEEE Technical Committee Computer Architecture, newsletter, Dec. 1995.
11. S. Williams, A. Waterman, and D. Patterson, "Roofline: An Insightful Visual Performance Model for Multicore Architectures," Comm. ACM, vol. 52, no. 4, 2009, pp. 65-76.
12. K. Czechowski et al., Prospects for Scalable 3D FFTs on Heterogeneous Exascale Systems, tech. report GT-CSE-11-02, Georgia Institute of Technology, 2011.
13. G.H. Loh and Y. Xie, "3D Stacked Microprocessor: Are We There Yet?" IEEE Micro, vol. 30, no. 3, 2010, pp. 60-64.
14. G. Bell, "Bell's Law for the Birth and Death of Computer Classes," Comm. ACM, vol. 51, no. 1, 2008, pp. 86-94.
15. T. Anderson, D. Culler, and D. Patterson, "A Case for NOW (Networks of Workstations)," IEEE Micro, vol. 15, no. 1, 1995, pp. 54-64.
16. J. Markoff, "The iPad in Your Hand: As Fast as a Supercomputer of Yore," blog, New York Times,9 May 2011; http://bits.blogs.nytimes.com/2011/05/09 the-ipad-in-your-hand-as- fast-as-a-supercomputer-of-yore .
17. V.J. Reddi et al., "Web Search Using Mobile Cores: Quantifying and Mitigating the Price of Efficiency," ACM SIGARCH Computer Architecture News, vol. 38, no. 3, 2010, pp. 215-314.
18 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool