Performance Evaluation of Mixed-Precision Runge-Kutta Methods
Numerical Analysis
2021-07-08 v1 Numerical Analysis
Performance
Abstract
Additive Runge-Kutta methods designed for preserving highly accurate solutions in mixed-precision computation were proposed and analyzed in [8]. These specially designed methods use reduced precision or the implicit computations and full precision for the explicit computations. We develop a FORTRAN code to solve a nonlinear system of ordinary differential equations using the mixed precision additive Runge-Kutta (MP-ARK) methods on IBM POWER9 and Intel x86\_64 chips. The convergence, accuracy, runtime, and energy consumption of these methods is explored. We show that these MP-ARK methods efficiently produce accurate solutions with significant reductions in runtime (and by extension energy consumption).
Cite
@article{arxiv.2107.03357,
title = {Performance Evaluation of Mixed-Precision Runge-Kutta Methods},
author = {Ben Burnett and Sigal Gottlieb and Zachary J. Grant and Alfa Heryudono},
journal= {arXiv preprint arXiv:2107.03357},
year = {2021}
}
Comments
IEEE HPEC 2021 submission