
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
J.P. Singh, H.S. Stone, D.F. Thiebaut, "A Model of Workloads and its Use in MissRate Prediction for Fully Associative Caches," IEEE Transactions on Computers, vol. 41, no. 7, pp. 811825, July, 1992.  
BibTex  x  
@article{ 10.1109/12.256450, author = {J.P. Singh and H.S. Stone and D.F. Thiebaut}, title = {A Model of Workloads and its Use in MissRate Prediction for Fully Associative Caches}, journal ={IEEE Transactions on Computers}, volume = {41}, number = {7}, issn = {00189340}, year = {1992}, pages = {811825}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.256450}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  A Model of Workloads and its Use in MissRate Prediction for Fully Associative Caches IS  7 SN  00189340 SP811 EP825 EPD  811825 A1  J.P. Singh, A1  H.S. Stone, A1  D.F. Thiebaut, PY  1992 KW  model of workloads; missrate prediction; fully associative caches; mathematical model; behavior of programs; fully associative cache; leastrecentlyused replacement; spatial locality; temporal locality; buffer storage; contentaddressable storage; memory architecture. VL  41 JA  IEEE Transactions on Computers ER   
A mathematical model for the behavior of programs or workloads is presented and from it is extracted the miss ratio of a finite, fully associative cache (or other firstlevel memory) using leastrecentlyused replacement under those workloads. To obtain miss ratios, the function u(t, L), defined to be the number of unique lines of size L referenced before time t, is modeled. Empirical observations show that this function appears to have the form u(t, L)=(W L/sup a/t/sup b/) (d/sup log/ /sup L log t/) where W, a, b, d are constants that are related, respectively, to the working set size, locality of references to nearby addresses (spatial locality), temporal locality (locality in time not attributable to spatial locality), and interactions between spatial locality and temporal locality. The miss ratio of a finite fully associative cache can be approximated as the time derivative of u(t, L) evaluated where the function has a value equal to the size of the cache. When the miss ratios from this model are compared to measured miss ratios for a representative trace, the accuracy is high for large caches. For smaller caches, the model is close but not highly precise.
[1] A. Agarwal, private communication, Jan. 1989.
[2] A. Agarwal, M. Horowitz, and J. Hennessy, "An analytical cache model,"ACM Trans. Comput. Syst., vol. 7, pp. 184215, May 1989.
[3] C. K. Chow, "On optimization of storage hierarchy,"IBM J. Res. Develop., vol. 18, pp. 194203, May 1974.
[4] C. K. Chow, "Determining the optimum capacity of a cache memory,"IBM Tech. Discl. Bull., vol. 17, no. 10, pp. 31633166, Mar. 1975.
[5] C. K. Chow, "Determination of a cache's capacity and its matching storage hierarchy,"IEEE Trans. Comput., vol. C25, no. 2, pp. 157164, Feb. 1976.
[6] P. J. Denning and S. C. Schwartz, "Properties of the workingset model,"Commun. ACM, vol. 15, no. 3, pp. 191198, Mar. 1972.
[7] M. C. Easton, "Computations of coldstart miss ratios,"IEEE Trans. Comput., vol. C27, no. 5, pp. 404408, May 1978.
[8] M. C. Easton and R. Fagin, "Coldstart versus warmstart miss ratios,"Commun. ACM, vol. 21, no. 10, pp. 866872, Oct. 1978.
[9] J. E. Gillis and G. H. Weiss, "Expected number of distinct sites visited by a random walk with an infinite variance,"J. Math. Phys., vol. 11, no. 4, pp. 13071312, Apr. 1970.
[10] 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. 124131.
[11] M. D. Hill, "Correction to 'Evaluating associativity in caches',"IEEE Trans. Comput., vol. 40, no. 3, p. 371, Mar. 1991.
[12] M. D. Hill and A. J. Smith, "Evaluating associativity in caches,"IEEE Trans. Comput., vol. 38, no. 12, pp. 16121630, Dec. 1989.
[13] M. Kobayashi and M. H. MacDougall, "The stack growth function: Cache line reference models,"IEEE Trans. Comput., vol. 38, no. 6, pp. 798805, June 1989.
[14] B. Mandelbrot,The Fractal Geometry of Nature. San Francisco, CA: Freeman, 1983.
[15] G. S. Rao, "Performance analysis of cache memories,"J. ACM, vol. 25, no. 3, pp. 378385, July 1978.
[16] J. H. Saltzer, "A simple linear model of demand paging performance,"Commun. ACM, vol. 17, no. 4, pp. 181186, Apr. 1974.
[17] A. J. Smith, "A comparative study of setassociative memory mapping algorithms and their use for cache and main memory,"IEEE Trans. Software Eng., vol. SE4, no. 2, pp. 121130, Mar. 1978.
[18] A. J. Smith, "Line (block) size choice for CPU cache memories,"IEEE Trans. Computers, vol. 36, no. 9, pp. 10631074, 1987.
[19] W. D. Strecker, "Transient behavior of cache memories,"ACM Trans. Comput. Syst., vol. 1, no. 4, pp. 281293, Nov. 1983.
[20] D. Thiébaut, "Influence of program transients in computer cache memories, Ph.D. dissertation, Univ. of Massachusetts, Amherst, MA, Feb. 1988.
[21] D. F. Thiebaut, "On the fractal dimension of computer programs and its application to the prediction of the cache miss ratio,"IEEE Trans. Comput.vol. 38, no. 7, pp. 10121026, July 1989.
[22] D. F. Thiebaut and H. S. Stone, "Footprints in the cache,"ACM Trans. Comput. Syst., vol. 5, no. 4, pp. 305329, Nov. 1987.
[23] D. F. Thiebaut, H. S. Stone, and J. L. Wolf, "A theory of cache behavior," IBM Res. Rep. RC 13309, Nov. 1987.
[24] J. Voldmanet al., "Fractal nature of softwarecache interaction,"IBM J. Res. Develop., vol. 27, pp. 164170, Mar. 1983.