An Adaptive Distributed Stencil Abstraction for GPUs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhosale, Aditya, Kale, Laxmikant
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914394557906944
author Bhosale, Aditya
Kale, Laxmikant
author_facet Bhosale, Aditya
Kale, Laxmikant
contents The scientific computing ecosystem in Python is largely confined to single-node parallelism, creating a gap between high-level prototyping in NumPy and high-performance execution on modern supercomputers. The increasing prevalence of hardware accelerators and the need for energy efficiency have made resource adaptivity a critical requirement, yet traditional HPC abstractions remain rigid. To address these challenges, we present an adaptive, distributed abstraction for stencil computations on multi-node GPUs. This abstraction is built using CharmTyles, a framework based on the adaptive Charm++ runtime, and features a familiar NumPy-like syntax to minimize the porting effort from prototype to production code. We showcase the resource elasticity of our abstraction by dynamically rescaling a running application across a different number of nodes and present a performance analysis of the associated overheads. Furthermore, we demonstrate that our abstraction achieves significant performance improvements over both a specialized, high-performance stencil DSL and a generalized NumPy replacement.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19851
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Adaptive Distributed Stencil Abstraction for GPUs
Bhosale, Aditya
Kale, Laxmikant
Distributed, Parallel, and Cluster Computing
The scientific computing ecosystem in Python is largely confined to single-node parallelism, creating a gap between high-level prototyping in NumPy and high-performance execution on modern supercomputers. The increasing prevalence of hardware accelerators and the need for energy efficiency have made resource adaptivity a critical requirement, yet traditional HPC abstractions remain rigid. To address these challenges, we present an adaptive, distributed abstraction for stencil computations on multi-node GPUs. This abstraction is built using CharmTyles, a framework based on the adaptive Charm++ runtime, and features a familiar NumPy-like syntax to minimize the porting effort from prototype to production code. We showcase the resource elasticity of our abstraction by dynamically rescaling a running application across a different number of nodes and present a performance analysis of the associated overheads. Furthermore, we demonstrate that our abstraction achieves significant performance improvements over both a specialized, high-performance stencil DSL and a generalized NumPy replacement.
title An Adaptive Distributed Stencil Abstraction for GPUs
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2512.19851