MPIGDB: A Flexible Debugging Infrastructure for MPI Programs
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.
Origine | Fichiers produits par l'(les) auteur(s) |
---|