Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kashi, Aditya, Koukpaizan, Nicholson, Lu, Hao, Matheson, Michael, Oral, Sarp, Wang, Feiyi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.11512
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916844793757696
author Kashi, Aditya
Koukpaizan, Nicholson
Lu, Hao
Matheson, Michael
Oral, Sarp
Wang, Feiyi
author_facet Kashi, Aditya
Koukpaizan, Nicholson
Lu, Hao
Matheson, Michael
Oral, Sarp
Wang, Feiyi
contents Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by dense matrix operations have seen substantial speedups by utilizing low precision formats such as FP16. However, a majority of scientific simulation applications are memory bandwidth limited. Beyond preliminary studies, the practical gain from using mixed-precision algorithms on a given HPC system is largely unclear. The High Performance GMRES Mixed Precision (HPG-MxP) benchmark has been proposed to measure the useful performance of a HPC system on sparse matrix-based mixed-precision applications. In this work, we present a highly optimized implementation of the HPG-MxP benchmark for an exascale system and describe our algorithm enhancements. We show for the first time a speedup of 1.6x using a combination of double- and single-precision on modern GPU-based supercomputers.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling the memory wall using mixed-precision -- HPG-MxP on an exascale machine
Kashi, Aditya
Koukpaizan, Nicholson
Lu, Hao
Matheson, Michael
Oral, Sarp
Wang, Feiyi
Distributed, Parallel, and Cluster Computing
Numerical Analysis
Performance
65Y10
G.4; C.4
Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by dense matrix operations have seen substantial speedups by utilizing low precision formats such as FP16. However, a majority of scientific simulation applications are memory bandwidth limited. Beyond preliminary studies, the practical gain from using mixed-precision algorithms on a given HPC system is largely unclear. The High Performance GMRES Mixed Precision (HPG-MxP) benchmark has been proposed to measure the useful performance of a HPC system on sparse matrix-based mixed-precision applications. In this work, we present a highly optimized implementation of the HPG-MxP benchmark for an exascale system and describe our algorithm enhancements. We show for the first time a speedup of 1.6x using a combination of double- and single-precision on modern GPU-based supercomputers.
title Scaling the memory wall using mixed-precision -- HPG-MxP on an exascale machine
topic Distributed, Parallel, and Cluster Computing
Numerical Analysis
Performance
65Y10
G.4; C.4
url https://arxiv.org/abs/2507.11512