ABSTRACT
One critical aspect in designing set-associative cache at high clock rate is deriving timely results from directory lookup. In this paper we investigate the possibility of accurately approximating the results of conventional directory search with faster matches of few partial address bits. Such fast and accurate approximations may be utilized to optimize cache access timing, particularly in a customized design environment. Through analytic and simulation studies we examine the trade-offs of various design choices. We also discuss few other applications of partial address matching to computer designs.
- 1.C.J. Conti, "Concepts for Buffer Storage," IEEE Comp. Group News, 2, 8, (March 1969), pp. 9-13.Google Scholar
- 2.A. J. Smith, "A Comparative Study of Set Associative Memory Mapping Algorithms and Their Use for Cache and Main Memory," IEEE Trans. on Software Engineering, SE-4, 2 (March 1978).Google Scholar
- 3.A. J. Smith, "Cache Memories," Computing Surveys, 14, 3 (September 1982), pp. 473-530. Google ScholarDigital Library
- 4.M. Hill "A Case for Direct-Mapped Caches," IEEE Computer, 21,12 (December 1988). Google ScholarDigital Library
- 5.S. Przybylski, M. Horowitz and J. Hennessy, "Performance Tradeoffs in Cache Design," Proc. 15th International Symp. on Computer Architecture (June 1988). Google ScholarDigital Library
- 6.T. Wada, S. Rajan and S. A. Pryzybylski, "An Analytic Access Time Model for On-Chip Cache Memories," IEEE Journal of Sohd-State Czrcu~ts, Vol. 27, No. 8 (August 1992) pp. 1147-1156.Google ScholarCross Ref
- 7.J. J. Losq, G. S. Rao and H. E. Sachar, "Decode History Table for Conditional Branch instructions,'' U.S. Patent No. 4,477,872 (October 16, 1984).Google Scholar
- 8.R. E Kessler, R. Jooss, A. Lebeck and M. Hill, "Inexpensive Implementations of Set- Associativity," Proc. 16th {nternatzonal Syrup. on Computer Architecture, (June 1989). Google ScholarDigital Library
- 9.L. Liu, "Partial Address Directory for Cache Access,'' IBM Research Report, RC18803 (February 1993). Also published in IEEE Trans. on VLSI Systems, Vol. 2, No. 2 (June 1994) pp. 226-240.Google Scholar
- 10.J. M. Lee and A. Weinberger, "A Solution to the Synonym Problem," IBM Technical D~sclosure Bulletin, 22, 8A (January 1980), pp. 3331-3333.Google Scholar
- 11."3033 Processor Complex, Theory of Operation/Diagrams Manual (Vol. 4), Processor Storage Control Function (15SCF),'' IBM, Poughkeepsie, New York (1978).Google Scholar
- 12.A. J. Smith, "Characterizing the Storage Process and Its Effect on the Update of Memory for Write-Through," Journal of A CM, 26, 1 (January 1979). Google ScholarDigital Library
- 13.J. H. Chang, H. Chao and K. So, "Cache Design of a Sub-Micron CMOS System/370," Proc. ljth International Syrup. on Computer Architecture, (June 1987). Google ScholarDigital Library
- 14.K. Hun, A. Hunt, L. Liu, J. Peir, D. Pruett and J. Temple, "Early Resolution of Address Translation in Cache Design," Proc. 1990 IEEE International Conf. on Computer Design (September 1990)Google Scholar
- 15.S. G. Tucker, "The IBM 3090 Systems: An Overview," IBM Systems Journal, 25, 6 (January 1986).Google ScholarDigital Library
- 16.J. R. Goodman. "Using Cache Memory to Reduce Processor Memory Traffic," Proc. l Oth Intl. Symp. on Computer Archztecture (May 1983) pp. 124-131. Google ScholarDigital Library
Index Terms
- Cache designs with partial address matching
Recommendations
Partial address directory for cache access
In most high performance computers the speeds of cache accessing are critical in determining the cycle times. A classical method for designing set-associative caches is to late-select array data based on the results of cache directory Iookups. The ...
Location cache: a low-power L2 cache system
ISLPED '04: Proceedings of the 2004 international symposium on Low power electronics and designWhile set-associative caches incur fewer misses than direct-mapped caches, they typically have slower hit times and higher power consumption, when multiple tag and data banks are probed in parallel. This paper presents the location cache structure which ...
Comments