Optimizing transformations of stencil operations for parallel cache-based architectures [electronic resource]
Parallel Stencil Operations; Optimizing Transformation; Parallel Cache-based Architectures.
Saved in:
| Online Access: |
Online Access |
|---|---|
| Corporate Author: | |
| Format: | Government Document Electronic eBook |
| Language: | English |
| Published: |
Washington, D.C : Oak Ridge, Tenn. :
United States. Dept. of Energy ; distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy,
1999.
|
| Subjects: |
| Summary: | Parallel Stencil Operations; Optimizing Transformation; Parallel Cache-based Architectures. |
|---|---|
| Abstract: | This paper describes a new technique for optimizing serial and parallel stencil- and stencil-like operations for cache-based architectures. This technique takes advantage of the semantic knowledge implicity in stencil-like computations. The technique is implemented as a source-to-source program transformation; because of its specificity it could not be expected of a conventional compiler. Empirical results demonstrate a uniform factor of two speedup. The experiments clearly show the benefits of this technique to be a consequence, as intended, of the reduction in cache misses. The test codes are based on a 5-point stencil obtained by the discretization of the Poisson equation and applied to a two-dimensional uniform grid using the Jacobi method as an iterative solver. Results are presented for a 1-D tiling for a single processor, and in parallel using 1-D data partition. For the parallel case both blocking and non-blocking communication are tested. The same scheme of experiments has bee n performed for the 2-D tiling case. However, for the parallel case the 2-D partitioning is not discussed here, so the parallel case handled for 2-D is 2-D tiling with 1-D data partitioning. |
| Item Description: | Published through the Information Bridge: DOE Scientific and Technical Information. 06/28/1999. "LA-UR-99-1119" 1999 International Conference on Parallel and Distributed Processing Techniques and Applications, Monte Carlo Resort, Las Vegas, NV (US), 06/28/1999--07/01/1999. Davis, K.; Bassetti, F. |
| Physical Description: | 5 pages. |