Publicado em: 28/04/2014
Seminário com Prof. Vincent Danjean, University of Grenoble
No dia 30/4, quarta-feira, o Prof. Vincent Danjean ministrará o Seminário: Parallel Architectures: hardware and software evolution, às 13h30min, na Sala dos Conselhos (220), do Instituto de Informática.
O Prof. Vincent Danjean estará visitando o INF de 30 de abril à 6 de maio e, também, participará da banca de tese de doutorado de João Lima, doutorando do Prof. Nicolas Bruno Maillard.
QUARTA-FEIRA, 30 de abril de 2014
———————————————————
Horário: 13h30min
Duração: 1h
——————————————————–
Local: Sala do Conselho, 220 – 43412(65)
Instituto de Informática, UFRGS
Av Bento Gonçalves 9500, Bloco IV
——————————————————–
Palestrante: Prof. Vincent Danjean, University of Grenoble I, France
Título: Parallel Architectures: hardware and software evolution
For a long time, processors became more powerful by increasing their speed (frequency) and by adding internal resources (more registers, more computational units, more cache, etc.) These improvements immediately benefit to all applications: using an updated processor automatically enables the applications to run faster. However, over the last few years, we observe a great evolution of processors core architecture. Frequency does not increase any more and processors become multi-cores or even many-cores. To be efficient on such processors, applications must be rewritten to explicitly exhibit parallelism that can be exposed to processors (multi-threaded applications, etc.). In this talk, I will present an overview of the evolution of processor designs, and explain why such a path has been taken by hardware manufacturers. I will also present some middlewares, languages or tools that have been developed in order to help application programmers to easily exploits this new hardware, such as, for example, OpenCL, Cuda, OpenMP, Cilk, etc.
Short bio:
Vincent Danjean is assistant professor at the University of Grenoble I, France. He works in the MOAIS INRIA team in the Laboratoire d’Informatique de Grenoble (LIG). MOAIS team focuses on the programming of applications where increasing the number of resources is a key to improve performance. Beyond the optimization of the application itself, the effective use of a larger number of resources is expected to enhance the performance. In particular, Vincent Danjean is involved in the development of the XKaapi programming environment that aims at providing an easy but very efficient way to program many-cores processors (CPU but also accelerators such as NVidia GPU or Intel Xeon Phi). At the university, Vincent Danjean teaches various courses around programming languages and tools, hardware, operating systems.
