This Article 
 Bibliographic References 
 Add to: 
Performance Implications of Tolerating Cache Faults
March 1993 (vol. 42 no. 3)
pp. 257-267

The authors investigate how much cache miss ratios increase when blocks are disabled. It is shown how the mean miss ratio increase can be characterized as a function of the miss ratios of related caches, an efficient approach is developed for calculating the exact distribution of miss ratio increases from all fault patterns, and this approach is applied to the ATUM traces. Results reveal that the mean relative miss ratio increase from a few faults decreases with increasing cache size and is negligible (>2% per defect) unless a set is completely disabled by faults. The maximum relative increase is also acceptable (5% per fault) if no set is entirely disabled.

[1] A. Agarwal, R.L. Sites, and M. Horowitz, "ATUM: A New Technique for Capturing Address Traces Using Microcode,"13th Int'l Symp. Computer Architecture, 1986, IEEE Computer Soc. Press, Los Alamitos, Calif., pp. 119-127.
[2] A. Agarwal, M. Horowitz, and J. Hennessy, "An analytical cache model,"ACM Trans. Comput. Syst., vol. 7, pp. 184-215, May 1989.
[3] A. D. Berenbaum, B. W. Colbry, D. R. Ditzel, R. D. Freeman, H. R. McLellan, K. J. O'Connor, and M. Shoji, "CRISP: A pipelined 32- bit microprocessor with 13-kbit of cache memory,"IEEE J. Solid-State Circuits, vol. SC-22, no. 5, pp. 776-782, Oct. 1987.
[4] J.R. Goodman, "Using Cache Memory to Reduce Processor Memory Traffic,"Proc. 10th Symp. Computer Architecture, IEEE CS Press, Los Alamitos, Calif., Order No. 473 (microfiche only), 1983, pp. 124-131.
[5] M. D. Hill and A. J. Smith, "Evaluating associativity in CPU caches,"IEEE Trans. Comput., vol. C-38, no. 12, pp. 1612-1630, Dec. 1989.
[6] M. Horowitz, P. Chow, D. Stark, R. T. Simoni, A. Salz, S. Przybylski, J. Hennessy, G. Gulak, A. Agarwal, and J. M. Acken, "MIPS-X: A 20-MIPS peak, 32-bit microprocessor with on-chip cache,"IEEE J. Solid-State Circuits, vol. SC-22, no. 5, pp. 790-799, Oct. 1987.
[7] N.P. Jouppi, "Improving Direct-Mapped Cache Performance by the Addition of a Small Fully-Associative Cache and Prefetch Buffers,"Proc. 17th Int'l Symp. Computer Architecture, CS Press, Los Alamitos, Calif., May 1990, pp. 364-373.
[8] H. Kadota, J. Miyake, I. Okabayashi, T. Maeda, T. Okamoto, M. Nakajima, and K. Kagawa, "A 32-bit CMOS microprocessor with on-chip cache and TLB,"IEEE J. Solid-State Circuits, vol. SC-22, no. 5, pp. 800-807, Oct. 1987.
[9] M. J. Litzkow, M. Levy, and M. W. Mutka, "Condor--a hunter of idle workstations," inProc. IEEE Int. Conf. on Distributed Comput. Syst., 1988, pp. 104-111.
[10] R. L. Mattson, J. Gecsei, D. R. Schultz, and I. L. Traiger, "Evaluation techniques for storage hierarchies,"IBM Syst. J., vol. 9, no. 2, pp. 78-117, 1970.
[11] D. Patterson et al., "Architecture of a VLSI Instruction Cache,"Proc. 10th Ann. Symp. Computer Architecture, ACM SIGarch, Vol. 11, No. 3, June 1983, pp. 108-116.
[12] D. Phillips, "The Z80000 Microprocessor,"IEEE Micro, pp. 23-36, Dec. 1985.
[13] F. Pour and M. D. Hill, "Performance implications of tolerating cache faults," Comput. Sci. Tech. Rep. 991, Univ. of Wisconsin, Jan. 1991.
[14] A. Smith, "Cache Memories,"Computing Surveys, Vol. 14, No. 3, Sept. 1982, pp. 473- 530.
[15] G. Sohi, "Cache memory organization to enhance the yield of high-performance VLSI processors,"IEEE Trans. Comput., vol. 38, no. 4, pp. 484-492, Apr. 1989.

Index Terms:
performance implications; cache faults; fault patterns; ATUM traces; buffer storage; fault tolerant computing; performance evaluation.
A.F. Pour, M.D. Hill, "Performance Implications of Tolerating Cache Faults," IEEE Transactions on Computers, vol. 42, no. 3, pp. 257-267, March 1993, doi:10.1109/12.210168
Usage of this product signifies your acceptance of the Terms of Use.