Michela Taufer (The University of Tennessee), Stephen Thomas (The University of Tennessee), Michael Wyatt (The University of Tennessee), Tu Mai Anh Do (University of Southern California), Loïc Pottier (University of Southern California), Rafael Ferreira da Silva (University of Southern California), Harel Weinstein (Cornell University), Michel A. Cuendet (Cornell University; Lausanne University Hospital), Trilce Estrada (University of New Mexico), and Ewa Deelman (University of Southern California)
Molecular Dynamics (MD) simulations executed on state-of-the-art supercomputers are producing data at a rate faster than it can be written out to disk. In situ and in transit analysis of data produced by MD simulations reduce the original volume of information by several orders of magnitude, thereby alleviating the negative impact of I/O bottleneck. This work focuses on characterizing the impact of in situ and in transit analytics on the overall MD workflow performance, and the capability for capturing rapid, rare events in the simulated molecular system. The MD simulation and analysis processes share data via remote direct memory access (RDMA) using Dataspaces. Our metrics of interest are time spent waiting in I/O, or lost frames by the MD simulation, and idle time by the analysis. We measure these metrics for a diverse set of molecular systems, characterize their trends for in situ and in transit configurations, and model which frames are dropped and which ones are analyzed for a real use case. The insights gained from this study are generally applicable for in situ and in transit workflows that require optimization of parameters to minimize loss in workflow performance and analytic accuracy.
