Control Flow Modeling in Statistical Simulation for Accurate and Efficient Processor Design Studies

Designing a new microprocessor is extremely time-consuming.One of the contributing reasons is that computerdesigners rely heavily on detailed architectural simulations,which are very time-consuming. Recent workhas focused on statistical simulation to address this issue.The basic idea of statistical simulation is to measurecharacteristics during program execution, generate asynthetic trace with those characteristics and then simulatethe synthetic trace. The statistically generated synthetictrace is orders of magnitude smaller than the original programsequence and hence results in significantly fastersimulation.This paper makes the following contributions to the statisticalsimulation methodology. First, we propose the useof a statistical flow graph to characterize the control flow ofa program execution. Second, we model delayed update ofbranch predictors while profiling program execution characteristics.Experimental results show that statistical simulationusing this improved control flow modeling attainssignificantly better accuracy than the previously proposedHLS system. We evaluate both the absolute and the relativeaccuracy of our approach for power/performance modelingof superscalar microarchitectures. The results showthat our statistical simulation framework can be used to efficientlyexplore processor design spaces.