Date:

04/06/2012 - 2:00pm to 3:00pm

Speaker:

Kirk E. Jordan

Speaker affiliation:

IBM T.J. Watson Research

Location:

78-2130

As industry scientists and engineers tackle more complex problems involving

multiphysics and multiscales and then seek to solve these problems through

computation, the math formulations which incorporate and more closely

approximate the complex physical or biological phenomena being modeled will

also be important to unlocking the approach taken on future computer

systems. I will describe some of the challenges that will need to be

considered in designing Petascale and eventually Exascale systems. Through

the combination of High Performance Computing (HPC) hardware coupled with

novel mathematical and algorithmic approaches emerging from the original

formulations some efforts toward breakthroughs in industrial strength

science and engineering are described. While there is progress, many

challenges for the mathematical and computational science community to apply

HPC to science problems of industry with impact on society remain. In

conclusion, some discussion not only on the most obvious way to use

ultra-scale, multi-core HPC will be given but also some thoughts on

incorporating more physics in the algorithms derived from the math models

and a glimpse at how to make such systems more accessible which might allow

us to better use them to tackle previously intractable problems.

Home | Links | Credits | Search | Terms of Use | Disclaimer | My Account

Rochester Institute of Technology,

One Lomb Memorial Drive, Rochester, New York 14623, USA

Phone: (585) 475-7752

Fax: (585) 475-7340

Education - This is a contributing Drupal Theme

Design by WeebPal.

Design by WeebPal.