MPIGDB: A Flexible Debugging Infrastructure for MPI Programs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

MPIGDB: A Flexible Debugging Infrastructure for MPI Programs

Robert Underwood
Bogdan Nicolae

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Licence

Attribution

Identifiers

Cite

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⟩
4 View
6 Download

Altmetric

Share

Gmail Facebook X LinkedIn More