Skip to Main content Skip to Navigation
Habilitation à diriger des recherches

Instruments of Productivity for High Performance Computing

Olivier Aumage 1, 2 
2 STORM - STatic Optimizations, Runtime Methods
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest
Abstract : High performance computing (HPC) is now well established as the cornerstone for building and conducting software simulations in numerous scientific and industrial fields. The hardware complexity of supercomputers is steadily increasing, however, to deliver ever improved computing performance, causing the complexity of HPC application development to increase as well. As a result, the need for tools and methodologies to compensate the development complexity by reducing the costs it induces —that is, the need for instruments to improve productivity in HPC development— has never been so pressing. This manuscript builds on the experience I have gathered while being involved in the design of several of such instruments of productivity for HPC, over the course of my academic career in computer science research, to study the technical choices made, the lessons learnt, and to discuss upcoming challenges and priorities.
Complete list of metadata

https://hal.inria.fr/tel-03105625
Contributor : Olivier Aumage Connect in order to contact the contributor
Submitted on : Monday, January 11, 2021 - 3:50:04 PM
Last modification on : Sunday, June 26, 2022 - 3:03:26 AM
Long-term archiving on: : Monday, April 12, 2021 - 6:42:25 PM

Identifiers

  • HAL Id : tel-03105625, version 1

Collections

Citation

Olivier Aumage. Instruments of Productivity for High Performance Computing. Distributed, Parallel, and Cluster Computing [cs.DC]. Université de Bordeaux (UB), France, 2020. ⟨tel-03105625⟩

Share

Metrics

Record views

162

Files downloads

500