85 citations · 92 across the 6 of their papers we have counts for
6 papers · 1 filter
Controlled Periodic Synchronization for Efficient Data-Parallel Training
Imane Ettifouri, Mostapha Zbakh, Claude Tadonki
Data-parallel training relies on frequent gradient synchronization across workers. Standard DDP synchronizes gradients at every iteration, which is effective on fast local-area net…
High Performance Optimization at the Door of the Exascale
Claude Tadonki
quest for processing speed potential. In fact, we always get a fraction of the technically available computing power (so-called {\em theoretical peak}), and the gap is likely to go…
Conceptual and Technical Challenges for High Performance Computing
Claude Tadonki
High Performance Computing (HPC) aims at providing reasonably fast computing solutions to scientific and real life problems. The advent of multicore architectures is noticeable in…
OpenMP Parallelization of Dynamic Programming and Greedy Algorithms
Claude Tadonki
Multicore has emerged as a typical architecture model since its advent and stands now as a standard. The trend is to increase the number of cores and improve the performance of the…
Basic Parallel and Distributed Computing Curriculum
Claude Tadonki
With the advent of multi-core processors and their fast expansion, it is quite clear that {\em parallel computing} is now a genuine requirement in Computer Science and Engineering…
HPC Curriculum and Associated Ressources in the Academic Context
Claude Tadonki
Hardware support for high-performance computing (HPC) has so far been subject to significant advances. The pervasiveness of HPC systems, mainly made up with parallel computing unit…