Applying StarPU runtime system to scientific applications: Experiences and lessons learned - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Applying StarPU runtime system to scientific applications: Experiences and lessons learned

Abstract

Task-based runtime systems are adopted by application developers for their valuable features including flexibility of execution and optimized resource management. However, the use of such advanced programming models in complex HPC applications often requires significant training time and programming effort. In this work, we share experiences and lessons learned from the use of StarPU in three independent projects of various complexity. We reach conclusions, with respect to training, programming effort, and existing challenges, that are useful to the communities of application developers, as well as to the developers of runtime systems. Finally, we suggest extensions to the runtime systems beneficial to application developers.
Fichier principal
Vignette du fichier
POMCO2020-camera-ready.pdf (784.43 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02985721 , version 1 (18-11-2020)

Identifiers

  • HAL Id : hal-02985721 , version 1

Cite

Georgios Tzanos, Vineet Soni, Charles Prouveur, Matthieu Haefele, Stavroula Zouzoula, et al.. Applying StarPU runtime system to scientific applications: Experiences and lessons learned. POMCO 2020 - 2nd International Workshop on Parallel Optimization using/for Multi- and Many-core High Performance Computing, Dec 2020, Barcelona / Virtual, Spain. ⟨hal-02985721⟩
239 View
370 Download

Share

Gmail Mastodon Facebook X LinkedIn More