HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach

TL;DR

This paper presents LASP, a lightweight, bandit learning-based autotuning method for HPC applications on resource-constrained edge devices, achieving significant performance improvements through dynamic parameter optimization.

Contribution

LASP introduces a novel bandit learning approach for adaptive, efficient parameter autotuning tailored for edge devices with limited resources.

Findings

LASP effectively optimizes HPC application parameters on edge devices.

Significant performance improvements were achieved with LASP.

LASP adapts dynamically to changing environments.

Abstract

The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices.