A Code Transformation Framework for Scientific Applications on Structured Grids

Pei-Hung Lin, Jagan Jayaraj, Paul Woodward, Pen-chung Yew
Department of Computer Science and Engineering, University of Minnesota, 4-192 Keller Hall, 200 Union Street SE, Minneapolis, MN 55455-0159 USA
University of Minnesota, Computer Science and Engineering, Technical report TR 11-021, 2011


   title={A Code Transformation Framework for Scientific Applications on Structured Grids},

   author={Lin, Pei-Hung and Jayaraj, Jagan and Woodward, Paul and Yew, Pen-chung},



Download Download (PDF)   View View   Source Source   



The combination of expert-tuned code expression and aggressive compiler optimizations is known to deliver the best achievable performance for modern multicore processors. The development and maintenance of these optimized code expressions is never trivial. Tedious and error-prone processes greatly decrease the code developer’s willingness to adopt manually-tuned optimizations. In this paper, we describe a pre-compilation framework that will take a code expression with a much higher programmability and transform it into an optimized expression that would be much more difficult to produce manually. The user-directed, source-to-source transformations we implement rely heavily on the knowledge of the domain expert. The transformed output, in its optimized format, together with the optimizations provided by an available compiler is intended to deliver exceptionally high performance. Three computational fluid dynamics (CFD) applications are chosen to exemplify our strategy. The performance results show an average of 7.3x speedup over straightforward compilation of the input code expression to our pre-compilation framework. Performance of 7.1 Gflops/s/core on the Intel Nehalem processor, 30% of the peak performance, is achieved using our strategy. The framework is seen to be successful for the CFD domain, and we expect that this approach can be extended to cover more scientific computation domains.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: