A Task Parallel Orthonormalization Multigrid Method For Multiphase Elliptic Problems

TL;DR

This paper introduces a task-parallel version of the K-cycle orthonormalization multigrid method, enhancing scalability and performance for solving large-scale multiphase elliptic PDE problems on modern high-performance computing systems.

Contribution

It develops an asynchronous, task-parallel implementation of the K-cycle orthonormalization multigrid method, addressing scalability limitations of traditional bulk-synchronous approaches.

Findings

Improved scalability on high-performance computing systems.

Maintains robustness and efficiency for anisotropic problems.

Achieves faster convergence in large-scale simulations.

Abstract

Multigrid methods have been a popular approach for solving linear systems arising from the discretization of partial differential equations (PDEs) for several decades. They are particularly effective for accelerating convergence rates with optimal complexity in terms of both time and space. K-cycle orthonormalization multigrid is a robust variant of the multigrid method that combines the efficiency of multigrid with the robustness of Krylov-type residual minimalizations for problems with strong anisotropies. However, traditional implementations of K-cycle orthonormalization multigrid often rely on bulk-synchronous parallelism, which can limit scalability on modern high-performance computing (HPC) systems. This paper presents a task-parallel variant of the K-cycle orthonormalization multigrid method that leverages asynchronous execution to improve scalability and performance on large-scale parallel systems.