Simulation Framework for Asynchronous Iterative Methods
Evan Coleman, Erik J. Jensen, Masha Sosonkina · ODU Digital Commons (Old Dominion University) · 2018
As high-performance computing (HPC) platforms progress towards exascale, computational methods must be revamped to successfully leverage them. In particular, (1) asynchronous methods become of great importance because synchronization becomes prohibitively expensive and (2) resilience of computations must be achieved, e.g., using checkpointing selectively which may otherwise become prohibitively expensive due to the sheer scale of the computing environment. In this work, a simulation framework for asynchronous iterative methods is proposed and tested on HPC accelerator (shared-memory) architecture. The design proposed here offers a lightweight alternative to existing computational frameworks to allow for easy experimentation with various relaxation iterative techniques, solution updating schemes, and predicted performance. The simulation framework is implemented in MATLAB® using function handles which offers a modular, easily extensible design. An example of a case study using the simulation framework is presented to examine the efficacy of different checkpointing schemes for asynchronous relaxation methods.