Modeling superscalar processors via statistical simulation

• Published in: Proceedings 2001 International Conference on Parallel Architectures and Compilation Techniques 2001, p.15-24
• Main Authors: Nussbaum, S., Smith, J.E.
• Format: Article
• Language: English
• Subjects: Analytical models; Computational modeling; Computer errors; Computer performance; Computer simulation; Convergence; Discrete event simulation; Predictive models; Space exploration; Statistics
• ISSN: 1089-796X
• DOI: 10.1109/PACT.2001.953284

Statistical simulation is a technique for fast performance evaluation of superscalar processors. First, intrinsic statistical information is collected from a single detailed simulation of a program. This information is then used to generate a synthetic instruction trace that is fed to a simple processor model, along with cache and branch prediction statistics. Because of the probabilistic nature of the simulation, it quickly converges to a performance rate. The simplicity and simulation speed make it useful for fast design space exploration; as such, it is a good complement to conventional detailed simulation. The accuracy of this technique is evaluated for different levels of modeling complexity. Both errors and convergence properties are studied in detail. A simple instruction model yields an average error of 8% compared with detailed simulation. A more detailed instruction model reduces the error to 5% but requires about three times as long to converge.