Azzam Haidar : September 15, 2010

On the future of the HPC: How to think Exascale? How the HPC community addresses this challenge, which direction they propose?

Azzam Haidar, Innovative Computing Laboratory at University of Tennessee, USA

Wednesday, September 15, 2:30 p.m. in the CERFACS conference room

Abstract:

The roadmap of this talk is the result of more than a year of coordinated effort within the global software community for high end scientific computing. The goal is to develop plan to overcomes the obstacles of modern science, such as
1) the increase of the computing power by orders of magnitude;
2) the inadequacy of the current high end software infrastructure, in all its component areas; and
3) the near complete lack of planning and coordination in the global scientific software community.
At the beginning of 2009, a large group of collaborators from this worldwide community initiated the International Exascale Software Project (IESP) to carry out the planning and the organization building necessary to solve this vitally important problem.

In this talk, I will present a set of first steps taken by the Innovative Computing Laboratory under the direction of Jack Dongarra, at the University of Tennessee to address this critical challenge that now confronts modern science. The ICL as well as the CERFACS and the INRIA are partners of the IESP project. The ultimate goal of the ICL projects is to provide a common strategy that could be used to support the severe constraints that the above trends in technology and applications will impose.