Acceleration of the Implicit-Explicit Non-hydrostatic Unified Model of the Atmosphere (NUMA) on Manycore Processors

TL;DR

This paper demonstrates significant speedups in atmospheric modeling by implementing IMEX methods on manycore processors, outperforming explicit methods through various optimizations and scalable solutions.

Contribution

The paper introduces optimized IMEX schemes for atmospheric models on GPUs and MIC architectures, achieving high speedups and scalability over explicit methods.

Findings

4X speedup at Courant number 15 with 3D-IMEX

100X speedup at Courant number 150 with 1D-IMEX

Effective scalability on thousands of GPUs and processors

Abstract

We present the acceleration of an IMplicit-EXplicit (IMEX) non-hydrostatic atmospheric model on manycore processors such as GPUs and Intel's MIC architecture. IMEX time integration methods sidestep the constraint imposed by the Courant-Friedrichs-Lewy condition on explicit methods through corrective implicit solves within each time step. In this work, we implement and evaluate the performance of IMEX on manycore processors relative to explicit methods. Using 3D-IMEX at Courant number C=15 , we obtained a speedup of about 4X relative to an explicit time stepping method run with the maximum allowable C=1. In addition, we demonstrate a much larger speedup of 100X at C=150 using 1D-IMEX due to the unconditional stability of the method in the vertical direction. Several improvements on the IMEX procedure were necessary in order to outperform our results with explicit methods: a) reducing the number of degrees of freedom of the IMEX formulation by forming the Schur complement; b) formulating a horizontally-explicit vertically-implicit (HEVI) 1D-IMEX scheme that has a lower workload and potentially better scalability than 3D-IMEX; c) using high-order polynomial preconditioners to reduce the condition number of the resulting system; d) using a direct solver for the 1D-IMEX method by performing and storing LU factorizations once to obtain a constant cost for any Courant number. Without all of these improvements, explicit time integration methods turned out to be difficult to beat. We discuss in detail the IMEX infrastructure required for formulating and implementing efficient methods on manycore processors. Finally, we validate our results with standard benchmark problems in NWP and evaluate the performance and scalability of the IMEX method using up to 4192 GPUs and 16 Knights Landing processors.