Improving the accuracy vs. speed tradeoff for simulating shared-memory multiprocessors with ILP processors
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Previous simulators for shared-memory architectures have imposed a large tradeoff between simulation accuracy and speed. Most such simulators model simple processors that do not exploit common instruction-level parallelism (ILP) features, consequently exhibiting large errors when used to model current systems. A few newer simulators model current ILP processors in detail, but we find them to be about ten times slower. We propose a new simulation technique, based on a novel adaptation of direct execution, that alleviates this accuracy vs. speed tradeoff. We compare the speed and accuracy of our new simulator, DirectRSIM, with three other simulators-RSIM (a detailed simulator for multiprocessors with ILP processors) and two representative simple-processor based simulators. Compared to RSIM, on average, DirectRSIM is 3.6 times faster and exhibits a relative error of only 1.3% in total execution time. Compared to the simple-processor based simulators, DirectRSIM is far superior in accuracy, and yet is only 2.7 times slower.Keywords
This publication has 9 references indexed in Scilit:
- Cross-profiling as an efficient technique in simulating parallel computer systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A direct-execution framework for fast and accurate simulation of superscalar processorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The impact of instruction-level parallelism on multiprocessor performance and simulation methodologyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The SPLASH-2 programs: characterization and methodological considerationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Wisconsin Wind Tunnel II: a fast, portable parallel architecture simulatorIEEE Concurrency, 2000
- Fast out-of-order processor simulation using memoizationPublished by Association for Computing Machinery (ACM) ,1998
- Using the SimOS machine simulator to study complex computer systemsACM Transactions on Modeling and Computer Simulation, 1997
- Application and architectural bottlenecks in large scale distributed shared memory machinesPublished by Association for Computing Machinery (ACM) ,1996
- SPLASHACM SIGARCH Computer Architecture News, 1992