An Evolutionary Algorithm to Optimize Log/Restore Operations within Optimistic Simulation Platforms

In this work we address state recoverability in advanced optimistic simulation systems by proposing an evolutionary algorithm to optimize at run-time the parameters associated with state log/restore activities. Optimization takes place by adaptively selecting for each simulation object both (i) the best suited log mode (incremental vs non-incremental) and (ii) the corresponding optimal value of the log interval. Our performance optimization approach allows to indirectly cope with hidden effects (e.g., locality) as well as cross-object effects due to the variation of log/restore parameters for different simulation objects (e.g., rollback thrashing). Both of them are not captured by literature solutions based on analytical models of the overhead associated with log/restore tasks. More in detail, our evolutionary algorithm dynamically adjusts the log/restore parameters of distinct simulation objects as a whole, towards a well suited configuration. In such a way, we prevent negative effects on performance due to the biasing of the optimization towards individual simulation objects, which may cause reduced gains (or even decrease) in performance just due to the aforementioned hidden and/or cross-object phenomena. We also present an application-transparent implementation of the evolutionary algorithm within the ROme OpTimistic Simulator (ROOT-Sim), namely an open source, general purpose simulation environment designed according to the optimistic synchronization paradigm.