SC17 Denver, CO

P20: Facilitating the Scalability of ParSplice for Exascale Testbeds

Authors: Vinay B. Ramakrishnaiah (University of Wyoming), Jonas L. Landsgesell (University of Stuttgart), Ying Zhou (Loughborough University), Iris Linck (University of Colorado, Denver), Mouad Ramil (National School of Bridges and Roads - ParisTech), Joshua Bevan (University of Illinois), Danny Perez (Los Alamos National Laboratory), Louis J. Vernon (Los Alamos National Laboratory), Thomas D. Swinburne (Los Alamos National Laboratory), Robert S. Pavel (Los Alamos National Laboratory), Christoph Junghans (Los Alamos National Laboratory)

Abstract: Parallel trajectory splicing (ParSplice) is an attempt to solve the enduring challenge of simulating the evolution of materials over long time scales for complex atomistic systems. A novel version of ParSplice is introduced with features that could be useful in its scaling to exascale architectures. A two-pronged approach is used. First, latent parallelism is exploited by extending support to heterogeneous architectures, including GPUs and KNLs. Second, the efficiency of the Kinetic Monte Carlo predictor is improved, allowing enhanced parallel speculative execution. The key idea in these predictor modifications is to include statistics from higher temperature simulations. The issue of inherent uncertainty in the prediction model was addressed in order to improve the performance, as the current predictor only takes into account the previous observations to formulate the problem. The predictor was also improved by using a hybrid approach of message-passing + multi-threading. (LA-UR-17-26181​)
Award: Best Poster Finalist (BP): no

Poster: pdf
Two-page extended abstract: pdf

Poster Index