[an error occurred while processing this directive]

Tradeoffs in the Design of High-Performance Computational Simulations in Science and Engineering

Scientific simulation comprises a complex mixture of mathematical components, such as models for scientific and engineering problems, discretization algorithms, and software libraries interacting with a computer science software stack that is our interface to the hardware. In this talk, I will look at how we have navigated this complex system in the case of numerical methods for partial differential equations on structured grids to obtain successful simulations across a broad range of fields. I will also discuss how the coming changes in processor architecture due to power limitations is causing the approach we have taken over the last 20 years to break down, and describe some new ideas we would like to use to remedy this problem. 

Bio

Dr. Phillip Colella received his A.B. (1974), M.A. (1976) and Ph.D. (1979) degrees from the University of California at Berkeley, all in applied mathematics. He has been a staff scientist at the Lawrence Berkeley National Laboratory and at the Lawrence Livermore National Laboratory, and a Professor in the Mechanical Engineering Department at the University of California at Berkeley. He is currently a Senior Scientist and Group Leader for the Applied Numerical Algorithms Group in the Computational Research Division at the Lawrence Berkeley National Laboratory, and a Professor in Residence in the Electrical Engineering and Computer Science Department at UC Berkeley.

Speaker

Phillip Colella

Date

Thursday, April 2, 2015

Time

1 pm - 2 pm

Location

Laufer Center, Room 101

Media

Video Recordings