Accession Number : ADA181716

Title :   An Analytical Cache Model.

Descriptive Note : Technical rept.,

Corporate Author : STANFORD UNIV CA COMPUTER SYSTEMS LAB

Personal Author(s) : Agarwal, Anant ; Horowitz, Mark ; Hennessy, John

PDF Url : ADA181716

Report Date : Sep 1986

Pagination or Media Count : 49

Abstract : Trace driven simulation and hardware measurement are the techniques most often used to obtain accurate performance figures for caches. The former requires a large amount of simulation time to evaluate each cache configuration while the latter is restricted to measurements of existing caches. An analytical cache model that uses parameters extracted from address traces of programs can provide estimates of cache performance and show the effects of varying cache parameters. By representing the factors that affect cache performance, the authors develop an analytical model that gives miss rates for a given trace as a function of cache-size, degree of associativity, block-size multiprogramming level, task switch interval, and observation interval. The predicted values closely approximate the results of trace drive simulations while requiring only a small fraction of the computation cost. Keywords: run length; start up.

Descriptors :   *MEMORY DEVICES, COMPUTATIONS, COSTS, DRIVES, INTERVALS, MATHEMATICAL MODELS, MEASUREMENT, SWITCHES, TIME, COMPUTERIZED SIMULATION, CONFIGURATIONS

Subject Categories : Computer Hardware

Distribution Statement : APPROVED FOR PUBLIC RELEASE