Hierarchical cache/bus architecture for shared memory multiprocessors

ABSTRACT

A new, large scale multiprocessor architecture is presented in this paper. The architecture consists of hierarchies of shared buses and caches. Extended versions of shared bus multicache coherency protocols are used to maintain coherency among all caches in the system. After explaining the basic operation of the strict hierarchical approach, a clustered system is introduced which distributes the memory among groups of processors. Results of simulations are presented which demonstrate that the additional coherency protocol overhead introduced by the clustered approach is small. The simulations also show that a 128 processor multiprocessor can be constructed using this architecture which will achieve a substantial fraction of its peak performance. Finally, an analytic model is used to explore systems too large to simulate (with available hardware). The model indicates that a system of over 1000 usable MIPS can be constructed using high performance microprocessors.

REFERENCES

• 1: George A. Anderson , E. Douglas Jensen, Computer Interconnection Structures: Taxonomy, Characteristics, and Examples, ACM Computing Surveys (CSUR), v.7 n.4, p.197-213, Dec. 1975 [doi>10.1145/356654.356658]
• 2: J. L. Baer, A Survey of Some Theoretical Aspects of Multiprocessing, ACM Computing Surveys (CSUR), v.5 n.1, p.31-80, March 1973 [doi>10.1145/356612.356615]
• 3: Censier, L.M. and Feautrier, P., "A New Solution to Coherence Problems in Muticache Systems," IEEE Transactions on Computers (C-27), December, 1978.
• 4: Dubois, Michael, and Briggs, F.A., "Effects of Cache Coherency in Multiiprocessors," IEEE Transactions on Computers C-31(11), November, 1982.
• 5: Feng, T., "A Survey of Interconnection Networks," Computer 14(12):12-27, December, 1981.
• 6: Frank, S.J., "A Tightly Coupled Muhiprocessor System Speeds Memory-Access Times," Electronics 164-169, January, 1984.
• 7: James R. Goodman, Using cache memory to reduce processor-memory traffic, Proceedings of the 10th annual international symposium on Computer architecture, p.124-131, June 13-17, 1983, Stockholm, Sweden
• 8: Haynes, L.S., Lau, R.L., Siewiorek, D.P., and Mitzell, D.W., "A Survey of Highly Parallel Computing," Computer 9-24, January, 1982.
• 9: Mark S. Papamarcos , Janak H. Patel, A low-overhead coherence solution for multiprocessors with private cache memories, Proceedings of the 11th annual international symposium on Computer architecture, p.348-354, January 1984
• 10: Pohm, A.V., and Agrawal, O.P., High-Speed Memory Systems, Reston Publishing Company, Inc. 1983.
• 11: Larry Rudolph , Zary Segall, Dynamic decentralized cache schemes for mimd parallel processors, Proceedings of the 11th annual international symposium on Computer architecture, p.340-347, January 1984
• 12: P. Sweazey , A. J. Smith, A class of compatible cache consistency protocols and their support by the IEEE futurebus, Proceedings of the 13th annual international symposium on Computer architecture, p.414-423, June 02-05, 1986, Tokyo, Japan
• 13: Tang, C.K., "Cache System Design in the Tightly Coupled Muhiprocessor System," In National Computer Conference, Proceedings, AFIPS, 1976.
• 14: Thurber, K.J., "Interconnection Networks-A Survey and Assessment," In National Computer Conference, Proceedings, AFIPS, 1974.
• 15: Andrew Wilkins Wilson, Jr., Organization and statistical simulation of hierarchical multiprocessors, 1985

INDEX TERMS

Primary Classification:
  B. Hardware
  B.3 MEMORY STRUCTURES
      B.3.2 Design Styles
          Subjects: Cache memories

Additional Classification:
  C. Computer Systems Organization

General Terms:
Algorithms, Design, Measurement, Performance