HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909446620315648 |
|---|---|
| author | Hossain, Abrar Badawy, Abdel-Hameed A. Islam, Mohammad A. Patki, Tapasya Ahmed, Kishwar |
| author_facet | Hossain, Abrar Badawy, Abdel-Hameed A. Islam, Mohammad A. Patki, Tapasya Ahmed, Kishwar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01057 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach Hossain, Abrar Badawy, Abdel-Hameed A. Islam, Mohammad A. Patki, Tapasya Ahmed, Kishwar Performance Machine Learning Systems and Control 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. |
| title | HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach |
| topic | Performance Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2501.01057 |