IV Escola Regional de Alto Desempenho do Rio de Janeiro
09 a 11 de Maio - UFF
Local:
Instituto de Computação - IC-UFF
Universidade Federal Fluminense (UFF)
Endereço:
Av. Gal. Milton Tavares de Souza, s/nº
São Domingos
CEP: 24210-346
Niterói - RJ
Foto divulgação : cortesia do Sr. Saint-Clair Mello.
Palestrantes Convidados
Claude Tadonki
MINES ParisTech Institute
Cristiana Bentes
Universidade do Estado do Rio de Janeiro
Alba Cristina M. A. Melo
Universidade de Brasília
Edson Borin
Universidade Estadual de Campinas (Unicamp)Claude Tadonki, MINES ParisTech Institute (Paris/France)
Claude Tadonki is currently senior researcher and lecturer at MINES ParisTech Institute (Paris/France). He holds a PhD and a Habilitation degree in computer science from University of Rennes and from Paris-Sud University respectively . After six years of cutting-edge research in operational research and theoretical computer science at the University of Geneva (Switzerland), he relocated to France to work for EMBL, University of Paris-Sud, LAL-CNRS and then MINES ParisTech. His main research topics included High Performance Computing, Combinatorial algorithms, and Operational Research. Claude Tadonki has worked at/with several laboratories and universities, has initiated various scientific projects and national/international collaborations, has given significant number of CS courses in different contexts including industries. He acts as a reviewer for high-impact international journals and major conferences, and he has published numerous papers in journals and conferences. He has actively participated and co-organized number of international HPC conferences.
Cutting-edge HPC Techniques through Case Studies
High Performance Computing (HPC) aims at providing reasonably fast computing solutions to scientific and real life problems. Many efforts have been made on the way to powerful supercomputers, including generic and customized configurations. The advent of multicore architectures is noticeable in the HPC history, because it has brought the underlying parallel programming concept into common considerations. Based on multicore processors, probably enhanced with acceleration units, current generation of supercomputers is rated to deliver an increasing peak performance, the Exascale era being the current horizon. However, getting a high fraction of the available peak performance is more and more difficult. The Design of an efficient code that scales well on a supercomputer is a non-trivial task. Manycore processors are now common, and the scalability issue in this context is crucial. Code optimization requires advanced programming techniques, taking into account the specificities and constraints of the target architecture. Many challenges are to be considered from the standpoint of efficiency and expected performances. This talk will provide a synopsis of the key aspects related to parallel processing efficiency (parallel programming paradigms, code transformations, code optimization), driven by selected case studies (image processing, particles physics, combinatorial algorithms).
| Realização | Organização e Execução | Patrocínio |
|
|
|