Predicting Computer Performance Dynamics
- 1.1k Downloads
Traditional approaches to the design and analysis of computer systems employ linear, stochastic mathematics—techniques that are becoming increasingly inadequate as computer architects push the design envelope. To work effectively with these complex engineered systems, one needs models that correctly capture their dynamics, which are deterministic and highly nonlinear. This is important not only for analysis, but also for design. Even an approximate forecast of the state variables of a running computer could be very useful in tailoring system resources on the fly to the dynamics of a computing application—powering down unused cores, for instance, or adapting cache configuration to memory usage patterns. This paper proposes a novel prediction strategy that uses nonlinear time-series methods to forecast processor load and cache performance, and evaluates its performance on a set of simple C programs running on an Intel Core® Duo.
KeywordsAverage Mutual Information Performance Trace Nonlinear Time Series Cache Performance Topological Conjugacy
Unable to display preview. Download preview PDF.
- 2.Armstrong, B., Eigenmann, R.: Performance forecasting: Towards a methodology for characterizing large computational applications. In: Proc. of the Int’l Conf. on Parallel Processing, pp. 518–525 (1998)Google Scholar
- 3.Bradley, E.: Analysis of time series. In: Berthold, M., Hand, D. (eds.) Intelligent Data Analysis: An Introduction, vol. 2, pp. 199–226. Springer, Heidelberg (2000)Google Scholar
- 4.Browne, S., Deane, C., Ho, G., Mucci, P.: PAPI: A portable interface to hardware performance counters. In: Proceedings of Department of Defense HPCMP Users Group Conference. Department of Defense (1999)Google Scholar
- 11.Mytkowicz, T.: Supporting experiments in computer systems research. Ph.D. thesis, University of Colorado (November 2010)Google Scholar
- 12.Mytkowicz, T., Diwan, A., Bradley, E.: Computer systems are dynamical systems. Chaos 19(3), 033124–033124–14 (2009)Google Scholar