Communication Dans Un Congrès Année : 2025

Measuring and Interpreting Dependent Task-based Applications Performances

Résumé

Breaking down the parallel time into work, idleness, and overheads is crucial for assessing the performance of HPC applications, but difficult to measure in asynchronous dependent tasking runtime systems. No existing tools allow its measurement portably and accurately. This paper introduces POT: a tool-suite for dependent task-based applications performance measurement. We focus on its low-disturbance methodology consisting of task modeling, discrete-event tracing, and post-mortem simulation-based analysis. It supports the OMPT standard OpenMP specifications. The paper evaluates the precision of POT's parallel time breakdown analysis on LLVM and MPC implementations and shows that measurement bias may be neglected above 16µs workload per task, portably across two architectures and OpenMP runtime systems

Fichier principal
Vignette du fichier
article.pdf (1013.81 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04767262 , version 1 (05-11-2024)

Identifiants

  • HAL Id : hal-04767262 , version 1

Citer

Romain Pereira, Thierry Gautier, Adrien Roussel, Patrick Carribault. Measuring and Interpreting Dependent Task-based Applications Performances. 15th International Conference on Parallel Processing & Applied Mathematics, Sep 2024, Ostrava, Czech Republic. ⟨hal-04767262⟩
28 Consultations
23 Téléchargements

Partager

More