[an error occurred while processing this directive]

Domain-specific Abstractions for Compiler Optimization

It is rarely feasible to achieve a significant fraction of the peak performance of a multicore processor from programs written in general-purpose high-level programming languages like C/C++.  Although optimizing compilers have made significant advances in implementing loop transformations, most are based on simple, local-cost models. The use of DSLs and effective domain-specific abstractions enables more global compiler optimization strategies because of the additional semantic information. This talk will present examples of domain-specific compiler optimization for stencil computations.

Bio

Sadayappan is a Professor in the Department of Computer Science and Engineering at The Ohio State University. His primary research interests center around performance optimization and compiler/runtime systems for high-performance computing, with special emphasis on high-performance frameworks that enable high productivity for application developers in scientific computing. Two recent projects include a polyhedral framework for automatic parallelization and data locality optimization, and the Tensor Contraction Engine - a domain-specific compiler/runtime system to automatically transform high-level specifications into efficient parallel programs, for a class of high accuracy ab initio models in quantum chemistry. Sadayappan obtained a B.Tech from the Indian Institute of Technology, Madras, and an M.S. and Ph.D. from Stony Brook University, all in Electrical Engineering.
Saday Sadayappan

Speaker

Saday Sadayappan

Date

Tuesday, May 20, 2014

Time

2:30 pm - 3:30 pm

Location

Computer Science Bldg, Room 2311