Lightweight Task Offloading Exploiting MPI Wait Times for Parallel Adaptive Mesh Refinement

TL;DR

This paper introduces a lightweight, reactive MPI wait time-based task migration technique that improves load balancing in adaptive mesh refinement simulations, achieving significant speed-ups without code modifications.

Contribution

It presents a novel non-blocking, asynchronous load balancing method using MPI idle time measurements to dynamically migrate tasks in parallel simulations.

Findings

Achieved up to 2-3x speed-up in seismic simulations.

Effectively reacts to workload and performance fluctuations.

No changes needed in existing code base.

Abstract

Balancing the workload of sophisticated simulations is inherently difficult, since we have to balance both computational workload and memory footprint over meshes that can change any time or yield unpredictable cost per mesh entity, while modern supercomputers and their interconnects start to exhibit fluctuating performance. We propose a novel lightweight balancing technique for MPI+X to accompany traditional, prediction-based load balancing. It is a reactive diffusion approach that uses online measurements of MPI idle time to migrate tasks temporarily from overloaded to underemployed ranks. Tasks are deployed to ranks which otherwise would wait, processed with high priority, and made available to the overloaded ranks again. This migration is non-persistent. Our approach hijacks idle time to do meaningful work and is totally non-blocking, asynchronous and distributed without a global data view. Tests with a seismic simulation code developed in the ExaHyPE engine uncover the method's potential. We found speed-ups of up to 2-3 for ill-balanced scenarios without logical modifications of the code base and show that the strategy is capable to react quickly to temporarily changing workload or node performance.