Kunle Olukotun
ABSTRACT
Advances in IC processing allow for more microprocessor design options. The increasing gate density and cost of wires in advanced integrated circuit technologies require that we look for new ways to use their capabilities effectively. This paper shows that in advanced technologies it is possible to implement a single-chip multiprocessor in the same area as a wide issue superscalar processor. We find that for applications with little parallelism the performance of the two microarchitectures is comparable. For applications with large amounts of parallelism at both the fine and coarse grained levels, the multiprocessor microarchitecture outperforms the superscalar architecture by a significant margin. Single-chip multiprocessor architectures have the advantage in that they offer localized implementation of a high-clock rate processor for inherently sequential applications and low latency interprocessor communication for parallel applications.
- 1.S.P. Amarasinghe, J. M. Anderson, M. S. Lam, and C.-W. Tseng, "An overview of the SUIF compiler for scalable parallel machines," Proceedings of the Seventh SIAM Conference on Parallel Processing for Scientific Compiler, San Francisco, 1995.Google Scholar
- 2.S. Amarasinghe et.al., "Hot compilers for future hot chips," presented at Hot Chips VII, Stanford, CA, 1995.Google Scholar
- 3.D.W. Anderson, F. J. Sparacio, and R. M. Tomasulo, "The IBM System/360 model 91: Machine philosophy and instruction-handling," IBM Journal of Research and Development, vol. 11, pp. 8-24, 1967.Google ScholarDigital Library
- 4.W. Bowhill et. al., "A 300MHz 64b quad-issue CMOS microprocessor," IEEE International Solid-State Circuits Conference Digest of Technical Papers, pp. 182-}L 83, San Francisco, CA, 1995.Google Scholar
- 5.E. Bugnion, J. Anderson, T. Mowry, M. Rosenblum, and M. Lam. "Compiler-Directed Page Coloring for Multiprocessors," Proceedings Seventh International Syrnp. Architectural Support for Programming Languages and Operating Systems (ASPLOS VII), October 1996. Google ScholarDigital Library
- 6."Chart watch: RISC processors," Microprocessor Report, vol. 10, no. 1, p. 22, January, 1996.Google Scholar
- 7.T. Conte, K. Menezes, P. Mills, and B. Patel, "Optimization of instruction fetch mechanisms for high issue rates," Proceedings of the 22nd Annual International Symposium on Computer Architecture, pp. 333-344, Santa Margherita Ligure, Italy, June, 1996. Google ScholarDigital Library
- 8.D. Dobberpuhl et. al., "A 200-MHz 64-b dual-issue CMOS microprocessor," IEEE Journal of Solid-State Circuits, vol. 27, pp. 1555-1557, 1992.Google ScholarCross Ref
- 9.Don Drappper, "The interconnect nightmare,'" IEEE International Solid-State Circuits Conference Digest of Technical Papers, p. 278, San Francisco, CA, 19!}6.Google Scholar
- 10.K. Farkas, N. Jouppi, and P. Chow, "Register file considerations in dynamically scheduled processors," Proceedings of the 2nd Int. Syrup. on High-Perfi~rmance Computer Architecture, pp. 40-51, San Jose, CA, February, 1996. Google ScholarDigital Library
- 11.J. Hennessy and N. Jouppi, "Computer technology and architecture: an evolving interaction," IEEE Computer Magazine, vol. 24, no. 1, pp. 18-29, 1991. Google ScholarDigital Library
- 12.J.L. Hennessy and D. A. Patterson, Computer Architecture A Quantitative Approach 2nd Edition. San Francisco, California: Morgan Kaufman Publishers, Inc., 1996. Google ScholarDigital Library
- 13.M. Johnson, Superscalar Microprocessor Design. Englewood Cliffs, NJ: Prentice Hall, Inc., 1991Google Scholar
- 14.J. Lotz, G. Lesartre, S. Naffzinger, and D. Kipp, "A quad issue out-of-order RISC CPU," IEEE International Solid-State Circuits Conference Digest of Technical Papers, }pp. 210- 211, San Francisco, CA, 1996.Google Scholar
- 15.S. McFarling, "Combining branch predictors," WRL Technical Note TN-36, Digital Equipment Corporation, 1993.Google Scholar
- 16.B. A. Nayfeh, L. Hammond, and K. Olukotun, "Evaluating alternatives for a multiprocessor microprocessor," Proceedings of 23rd Int. Symp. Computer Architecture, pp. 66-77, Philadelphia, PA, 1996. Google ScholarDigital Library
- 17.J. Ousterhout. "Why aren't operating systems getting faster as fast as hardware?," Summer 1990 USENIX Conference, pp. 247-256, June 1990.Google Scholar
- 18.M. Rosenblum, S. Herrod, E. Witchel, and A. Gupta, "The SimOS approach," IEEE Parallel and Distributed Technology, vol. 4, no. 3, 1995.Google Scholar
- 19.M. Rosenblum, E. Bugnion, S. Herrod, E. Witchel, and A. Gupta, "The impact of architectural trends on operating system performance," Proceedings of 15th ACM symposium on Operating Systems Principles, Colorado, December, 1995. Google ScholarDigital Library
- 20.G. Sohi and M. Franklin, "High Bandwidth Data Memory Systems for Superscalar Processors," Proceedings of 4th Int. Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS-IV), pp. 53- 62, April, 1991. Google ScholarDigital Library
- 21.J.E. Thornton, "Parallel operation in the Control Data 6600," Proceedings of Spring Joint Computer Conference, 1964.Google Scholar
- 22.D.W. Wall, "Limits of Instruction-Level Parallelism," Digital Western Research Laboratory, WRL Research Report 93/ 6, November 1993.Google Scholar
- 23.S.C. Woo, M. Ohara, E. Torrie, J.P. Singh and A. Gupta, "The SPLASH-2 Programs: Characterization and Methodological Considerations", 22nd Annual Int. Syrup. Computer Architecture, Santa Margherita, Italy, June 1995. Google ScholarDigital Library
- 24.K. Yeager et. al., "R10000 Superscalar Microprocessor," presented at Hot Chips VII, Stanford, CA, 1995.Google Scholar
- 25.J. Zurawski, J. Murray and P. Lemmon, '~the design and verification of the AlphaStation 600 5-series workstation," Digital Technical Journal, vol. 7, no. 1, pp. 89-99, 1995. Google ScholarDigital Library
Index Terms
- The case for a single-chip multiprocessor
Recommendations
The case for a single-chip multiprocessor
Advances in IC processing allow for more microprocessor design options. The increasing gate density and cost of wires in advanced integrated circuit technologies require that we look for new ways to use their capabilities effectively. This paper shows ...
The case for a single-chip multiprocessor
Advances in IC processing allow for more microprocessor design options. The increasing gate density and cost of wires in advanced integrated circuit technologies require that we look for new ways to use their capabilities effectively. This paper shows ...
Comments