The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - July/August (2008 vol.28)
pp: 51-70
Mei Wen , National University of Defense Technology, China
Nan Wu , National University of Defense Technology, China
Chunyuan Zhang , National University of Defense Technology, China
Qianming Yang , National University of Defense Technology, China
Jun Ren , National University of Defense Technology, China
Yi He , National University of Defense Technology, China
Wei Wu , National University of Defense Technology, China
Jun Chai , National University of Defense Technology, China
Maolin Guan , National University of Defense Technology, China
Changqing Xun , National University of Defense Technology, China
ABSTRACT
With the extension of application domains, hardware-managed memory structures such as caches are drawing attention for dealing with irregular stream applications. However, since a real application usually has both regular and irregular stream characteristics, conventional stream register files, caches, or combinations thereof have shortcomings. This article focuses on combining software- and hardware-managed memory structures and presents a new syncretic memory system based on the FT64 stream accelerator.
INDEX TERMS
stream architecture, cache, stream register file, irregular stream, scientific accelerator
CITATION
Mei Wen, Nan Wu, Chunyuan Zhang, Qianming Yang, Jun Ren, Yi He, Wei Wu, Jun Chai, Maolin Guan, Changqing Xun, "On-Chip Memory System Optimization Design for the FT64 Scientific Stream Accelerator", IEEE Micro, vol.28, no. 4, pp. 51-70, July/August 2008, doi:10.1109/MM.2008.56
REFERENCES
1. J.H. Ahn et al., "Evaluating the Imagine Stream Architecture," Proc. 31st Int'l. Symp. Computer Architecture (ISCA 04), IEEE CS Press, 2004, pp. 14-25.
2. http://www.streamprocessors.com/streamprocessors/ Home/ProductsStorm-1Family.html 2007.
3. W.J. Dally et al., "Merrimac: Supercomputing with Streams," Proc. ACM/IEEE Supercomputing Conf. (SC 03), IEEE Press, 2003, pp. 35-35.
4. X. Yang et al., "A 64-Bit Stream Processor for Scientific Applications," ACM SigArch Computer Architecture News, 2007, vol. 35, no. 2, May 2007, pp. 210-219.
5. S. Williams et al., "The Potential of the Cell Processor for Scientific Computing," Proc. 3rd Conf. Computing Frontiers, ACM Press, 2006, pp. 9-20.
6. K. Kitagawa et al., "A Hardware Overview of SX-6 and SX-7 Supercomputer," NEC Research and Development J., vol. 44, no. 1, Jan. 2003, pp. 2-7.
7. J.W. Sheaffer, D.P. Luebke, and K. Skadron, "A Hardware Redundancy and Recovery Mechanism for Reliable Scientific Computation on Graphics Processors," Proc. 22nd Siggraph/Eurographics Symp. Graphics Hardware (GH 07), ACM Press, 2007, pp. 55-64.
8. J.D. Owens et al., "A Bandwidth-Efficient Architecture for Media Processing," Proc. 31st Ann. ACM/IEEE Int'l Symp. Microarchitecture (Micro 98), IEEE CS Press, 1998, pp. 3-13.
9. M. Erez et al., "Executing Irregular Scientific Applications on Stream Architectures," Proc. 21st Ann. Int'l Conf. Supercomputing (ICS 07), ACM Press, 2007, pp. 93-104.
10. K. So and V. Zecca, "Cache Performance of Vector Processors," Proc. 15th Ann. Int'l Symp. Computer Architecture (ISCA 88), IEEE Press, 1988, pp. 261-268.
11. J. Wawrzynek et al., "Spert II: A Vector Microprocessor System," Computer, vol. 29, no. 3, Mar. 1996, pp. 79-86.
12. C. Kozyrakis, Scalable Vector Media-Processors for Embedded Systems, PhD thesis, Computer Science Dept., Univ. of California, Berkeley, 2002.
13. U.J. Kapasi et al., "Stream Scheduling," Proc. 3rd Workshop Media and Streaming Processors (MSP 01), 2001, pp. 101-106, http://cva.stanford.edu/publications/2002 stream_scheduling_TR122.pdf.
14. A. Das and W.J. Dally, "Stream Scheduling: A Framework to Manage Bulk Operations in a Memory Hierarchy," Proc. 16th Int'l Conf. Parallel Architecture and Compilation Techniques (PACT 07), IEEE CS Press, 2007, p. 405.
15. J. Leverich et al., "Comparing Memory Systems for Chip Multiprocessors," Proc. 34th Int'l Symp. Computer Architecture (ISCA 07), ACM Press, 2007, pp. 358-368.
16. P.R. Mattson, A Programming System for the Imagine Media Processor, PhD thesis, Computer Science Dept., Stanford Univ., 2002.
17. M. Wen et al., "Analysis and Performance Results of a Fluid Dynamics Application on MASA Stream Processor," Proc. Int'l Conf. Information Systems (ICIS 06), IEEE Press, 2006, pp. 350-354.
18. Z. Tian, Numerical Simulations of Multiplex Unsteady Flow in Hypersonic Free Stream, master's thesis, Dept. of Aerospace and Material Engineering, Nat'l Univ. of Defense Technology, China, 2003.
28 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool