Identification and Characterization of Memory Allocation Anomalies in High-Performance Computing Applications - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Identification and Characterization of Memory Allocation Anomalies in High-Performance Computing Applications

Résumé

A memory allocation anomaly occurs when the allocation of a set of heap blocks imposes an unnecessary overhead on the execution of an application. In this paper, we propose a method for identifying, locating, characterizing and fixing allocation anomalies, and a tool for developers to apply the method. We experiment our method and tool with a numerical simulator aimed at approximating the solutions to partial differential equations using a finite element method. We show that taming allocation anomalies in this simulator reduces the memory footprint of its processes by 37.27% and the execution time by 16.52%. We conclude that the developer of high-performance computing applications can benefit from the method and tool during the software development cycle.
Fichier principal
Vignette du fichier
paper.pdf (282.68 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02197277 , version 1 (30-07-2019)

Identifiants

  • HAL Id : hal-02197277 , version 1

Citer

Antônio Tadeu Azevedo Gomes, Enzo Molion, Roberto Pinto Souto, Jean-François Méhaut. Identification and Characterization of Memory Allocation Anomalies in High-Performance Computing Applications. Simpósio de Sistemas Computacionais de Alto Desempenho (WSCAD), Oct 2019, Campo Grande, Brazil. ⟨hal-02197277⟩
69 Consultations
250 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More