DocumentCode :
1920953
Title :
On the Use of Term Rewriting for Performance Optimization of Legacy HPC Applications
Author :
Panyala, A. ; Chavarria-Miranda, D. ; Krishnamoorthy, S.
Author_Institution :
Pacific Northwest Nat. Lab., Louisiana State Univ., Baton Rouge, LA, USA
fYear :
2012
fDate :
10-13 Sept. 2012
Firstpage :
399
Lastpage :
409
Abstract :
Preparing codes for next generation supercomputer systems is anticipated to require significant changes to the optimization strategies employed in established HPC applications. In this paper, we present our experience in applying term rewriting transformations for the optimization of such applications. We have designed application-specific term rewriting transformations to improve the scalability, enhance locality and reduce the communication overhead of the Self-Consistent Field computational chemistry benchmark. We present the rationale for the use of term rewriting in this manner, the design of our transformations, and the much enhanced performance of the resulting code.
Keywords :
optimisation; parallel machines; rewriting systems; software maintenance; application specific term rewriting transformation; legacy HPC application; next generation supercomputer system; performance optimization; scalability; self-consistent field computational chemistry benchmark; Abstracts; Benchmark testing; Heuristic algorithms; Kernel; Semantics; Syntactics; Tiles; Global Arrays; TASCEL; load balancing; term rewriting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel Processing (ICPP), 2012 41st International Conference on
Conference_Location :
Pittsburgh, PA
ISSN :
0190-3918
Print_ISBN :
978-1-4673-2508-0
Type :
conf
DOI :
10.1109/ICPP.2012.44
Filename :
6337601
Link To Document :
بازگشت