Autonomic Log/Restore for Advanced Optimistic Simulation Systems

In this paper we address state recoverability in optimistic simulation systems by presenting an autonomic log/restore architecture. Our proposal is unique in that it jointly provides the following features: (i) log/restore operations are carried out in a completely transparent manner to the application programmer, (ii) the simulation-object state can be scattered across dynamically allocated non-contiguous memory chunks, (iii) two differentiated operating modes, incremental vs non-incremental, coexist via transparent, optimized run-time management of dual versions of the same application layer, with dynamic selection of the best suited operating mode in different phases of the optimistic simulation run, and (iv) determination of the best suited mode for any time frame is carried out on the basis of an innovative modeling/optimization approach that takes into account stability of each operating mode vs variations of the model execution parameters.