MPIGDB: A Flexible Debugging Infrastructure for MPI Programs - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

MPIGDB: A Flexible Debugging Infrastructure for MPI Programs

Robert Underwood
Bogdan Nicolae

Résumé

The advent of flexible science workflows that span traditional HPC, the cloud, and beyond requires more than ever efficient, scalable, portable, featureful debugging tools. This work presents the design and implementation of MPIGDB a flexible debugging infrastructure for MPI programs. MPIGDB is designed to be highly capable at scale, available across platforms, easily interactive, and an extensible way to debug distributed MPI programs. This work demonstrates the scalability of this our approach to 128 processes on debugging memory access violations in a heat diffusion code as an example use case while providing features competitive with proprietary debugging tools such as GPU kernel debugging, mixed language support, and scripting abilities. Together these tools allow users to debug quickly challenges wherever their science is run.
Fichier principal
Vignette du fichier
MPIGDB.pdf (687.89 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04343674 , version 1 (14-12-2023)

Licence

Identifiants

Citer

Robert Underwood, Bogdan Nicolae. MPIGDB: A Flexible Debugging Infrastructure for MPI Programs. FlexScience’23: The 13th Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures (with HPDC'23), Jun 2023, Orlando, United States. pp.11-18, ⟨10.1145/3589013.3596675⟩. ⟨hal-04343674⟩
17 Consultations
91 Téléchargements

Altmetric

Partager

More