Abstract
This paper addresses the performance problems caused by high memory access latencies and their effect on the scalability of shared-memory multiprocessor systems. We propose to take full advantage of weak ordering through lockup-free caches and delayed consistency protocols and to interconnect processors with point-to-point links. Simulation results show that these approaches are promising.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Selected References
Dubois, M., Scheurich, C., “Memory Access Dependencies in Shared Memory Multiprocessors,” IEEE Trans. on Soft. Eng., 16(6), pp. 660–674, June 1990.
Scheurich, C. Access Ordering and Coherence in Shared-Memory Multiprocessors. PhD thesis, Univ. of Southern California, May 1989 (also U.S.C. Tech. Rep. CENG 89-19)
Scheurich, C. and Dubois, M., “Correct Memory Operation of Cache-based Multiprocessors,” Proc. of the 14th Int. Symp. on Comp. Arch, pp. 234–243, June 1987.
Lenoski, D., et al., “The Directory-based Cache Coherence Protocol for the DASH Multiprocessor,” Proc. of the 17th Ann. Int. Symp. on Comp. Arch., pp. 148–159, June 1990.
Gharachorloo, K., Gupta, A, and J. Hennessy, “Performance Evaluation of Memory Consistency Models for Shared-memory Multiprocessors,” ASPLOS IV, Apr 1991.
Kowalik, J. S. Parallel MIMD Computation: HEP Supercomputer and its Applications. The MIT Press, 1985.
Dubois, M., “A Cache-based Multiprocessor with High Efficiency,” IEEE Trans. on Comp., pp. 968–972, Oct. 1985.
Agarwal, A., et al., “APRIL: A Processor Architecture for Multiprocessing,” Proc. of the 17th Ann. Int. Symp. on Comp. Arch., pp. 104–114, June 1990.
Jouppi, N. J., and Wall, D., “Available Instruction-level Parallelism for Superscalar and Superpipelined Machines,” ASPLOS III, pp. 272–282, Apr 1989.
Amdahl, G. M., “Validity of the Single Processor Approach to Achieving Large-scale Computing Capabilities,” Proc. AFIPS, Vol. 30, pp.483–465, 1967.
Scheurich, C. and Dubois, M., “Lockup-free Caches in High-Performance Multiprocessors,” J. of Par. and Dist. Comp., Jan. 1991.
Kroft, D., “Lockup-free Instruction Fetch/Prefetch Cache Organization,” Proc. of the 8th Ann. Int. Symp. on Comp. Arch., pp. 81–87, June 1981.
Kogge, P. M. The Architecture of Pipelined Computers. Mc Graw-Hill, 1981.
McMahon, F. H. LLNL Fortran Kernels: MFlops. Technical Report, Lawrence Livermore Laboratories, Livermore, CA, March 1984.
Zima, H. and Chapman, B. Supercompilers for Parallel and Vector Computers. Addison-Wesley Publishing Company. 1990.
Porterfield, A. K. Software Methods for Improvement of Cache Performance on Supercomputer Applications. PhD dissertation, RICE COMP TR 89-93, May 1989.
Eggers, S. J., and Jeremiassen, T. E., “Eliminating False Sharing,” Proc. of the 1991 Int. Conf. on Par. Processing, pp. I-377–I-381, Aug. 1991.
Dubois, M., et al., “Delayed Consistency and its Effects on the Miss Rate of Parallel Programs,” Supercomputing' 91, pp. 197–206, Nov. 1991.
Censier, L. M. and Feautrier, P., “A New Solution to Coherence Problems in Multicache Systems,” IEEE Trans. on Computers, Vol. C-27, No. 12, pp. 1112–1118, Dec. 1978.
Gustavson, D. B., “The Scalable Coherent Interface and Related Standards Projects”, IEEE Micro, Vol. 12, No. 1, pp. 10–22, February 1992.
Barroso, L. A. and Dubois, M., “Cache Coherence on a Slotted Ring”, Proceedings of the 1991 International Conference on Parallel Processing, pp. 1230–1237, August 1991.
Schwetman, H., “CSIM: A C-Based, Process-Oriented Simulation Language”, Proceedings of the 1986 Winter Simulation Conference, pp. 387–396, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dubois, M., Barroso, L., Chen, YS., Öner, K. (1992). Scalability problems in multiprocessors with private caches. In: Etiemble, D., Syre, JC. (eds) PARLE '92 Parallel Architectures and Languages Europe. PARLE 1992. Lecture Notes in Computer Science, vol 605. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55599-4_90
Download citation
DOI: https://doi.org/10.1007/3-540-55599-4_90
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55599-5
Online ISBN: 978-3-540-47250-6
eBook Packages: Springer Book Archive