Task-based adaptive multiresolution for time-space multi-scale reaction-diffusion systems on multi-core architectures

TL;DR

This paper introduces a new parallel implementation of an adaptive multiresolution solver for reaction-diffusion systems, significantly improving efficiency and scalability on multi-core architectures through a novel data structure and task-based parallelism.

Contribution

It presents a fully redesigned data structure and parallel implementation for an existing adaptive solver, enhancing performance and scalability on multi-core systems.

Findings

High scalability demonstrated on multi-core architectures

Efficient handling of large multidimensional reaction-diffusion problems

Improved parallel performance over previous tree-based implementations

Abstract

A new solver featuring time-space adaptation and error control has been recently introduced to tackle the numerical solution of stiff reaction-diffusion systems. Based on operator splitting, finite volume adaptive multiresolution and high order time integrators with specific stability properties for each operator, this strategy yields high computational efficiency for large multidimensional computations on standard architectures such as powerful workstations. However, the data structure of the original implementation, based on trees of pointers, provides limited opportunities for efficiency enhancements, while posing serious challenges in terms of parallel programming and load balancing. The present contribution proposes a new implementation of the whole set of numerical methods including Radau5 and ROCK4, relying on a fully different data structure together with the use of a specific library, TBB, for shared-memory, task-based parallelism with work-stealing. The performance of our implementation is assessed in a series of test-cases of increasing difficulty in two and three dimensions on multi-core and many-core architectures, demonstrating high scalability.