SMARTS is a framework for using rigorous statistical sampling to accelerate microarchitecture simulation. It employs systematic sampling to measure only a very small portion of the entire application being simulated. Between measurement periods, a functional model is invoked, greatly speeding the overall simulation.
With accelerated simulation rates, researchers can simulate entire benchmarks, thus generating more representative results. Since SMARTS applies well-known statistical sampling techniques, it can be used to evaluate any property - such as CPI or power consumption - to the desired accuracy and confidence level.
The SMARTS sample design.
TurboSMARTS: Simulation Sampling with Live-points
TurboSMARTS is a simulation-sampling framework that replaces functional warming with live-points without sacrificing accuracy. A live-point stores the bare minimum of functionally-warmed state for accurate simulation of a limited execution window while placing minimal restrictions on microarchitectural configuration. Live-points can be processed in random rather than program order, allowing simulation results and their statistical confidence to be reported while simulations are in progress.
Download the TurboSMARTS simulator (includes SMARTS).