Denoising Application Performance Models with Noise-Resilient Priors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: de Morais, Gustavo, Geiß, Alexander, Calotoiu, Alexandru, Corbin, Gregor, Tarraf, Ahmad, Hoefler, Torsten, Mohr, Bernd, Wolf, Felix
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916911643623424
author de Morais, Gustavo
Geiß, Alexander
Calotoiu, Alexandru
Corbin, Gregor
Tarraf, Ahmad
Hoefler, Torsten
Mohr, Bernd
Wolf, Felix
author_facet de Morais, Gustavo
Geiß, Alexander
Calotoiu, Alexandru
Corbin, Gregor
Tarraf, Ahmad
Hoefler, Torsten
Mohr, Bernd
Wolf, Felix
contents As parallel codes are scaled to larger computing systems, performance models play a crucial role in identifying potential bottlenecks. However, constructing these models analytically is often challenging. Empirical models based on performance measurements provide a practical alternative, but measurements on high-performance computing (HPC) systems are frequently affected by noise, which can lead to misleading predictions. To mitigate the impact of noise, we introduce application-specific dynamic priors into the modeling process. These priors are derived from noise-resilient measurements of computational effort, combined with domain knowledge about common algorithms used in communication routines. By incorporating these priors, we effectively constrain the model's search space, eliminating complexity classes that capture noise rather than true performance characteristics. This approach keeps the models closely aligned with theoretical expectations and substantially enhances their predictive accuracy. Moreover, it reduces experimental overhead by cutting the number of repeated measurements by half.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10996
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Denoising Application Performance Models with Noise-Resilient Priors
de Morais, Gustavo
Geiß, Alexander
Calotoiu, Alexandru
Corbin, Gregor
Tarraf, Ahmad
Hoefler, Torsten
Mohr, Bernd
Wolf, Felix
Performance
Distributed, Parallel, and Cluster Computing
As parallel codes are scaled to larger computing systems, performance models play a crucial role in identifying potential bottlenecks. However, constructing these models analytically is often challenging. Empirical models based on performance measurements provide a practical alternative, but measurements on high-performance computing (HPC) systems are frequently affected by noise, which can lead to misleading predictions. To mitigate the impact of noise, we introduce application-specific dynamic priors into the modeling process. These priors are derived from noise-resilient measurements of computational effort, combined with domain knowledge about common algorithms used in communication routines. By incorporating these priors, we effectively constrain the model's search space, eliminating complexity classes that capture noise rather than true performance characteristics. This approach keeps the models closely aligned with theoretical expectations and substantially enhances their predictive accuracy. Moreover, it reduces experimental overhead by cutting the number of repeated measurements by half.
title Denoising Application Performance Models with Noise-Resilient Priors
topic Performance
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2504.10996