DocumentCode :
3016746
Title :
Impact of Compiler-based Data-Prefetching Techniques on SPEC OMP Application Performance
Author :
Tian, Xinmin ; Krishnaiyer, Rakesh ; Saito, Hideki ; Girkar, Milind ; Li, Wei
Author_Institution :
Intel Compiler Labs., Intel Corp., Santa Clara, CA, USA
fYear :
2005
fDate :
04-08 April 2005
Abstract :
In this paper, we evaluate the benefits achievable from software data-prefetching techniques for OpenMP* C/C++ and Fortran benchmark programs, using the framework of the Intel production compiler for the Intel® Itanium® 2 processor. Prior work on software data-prefetching study has primarily focused on benchmark performance in the context of a few software data-prefetching schemes developed in research compilers. In contrast, our study is to examine the impact of an extensive set of software data-prefetching schemes on the performance of multi-threaded execution using a full set of SPEC OMPM2001 applications with a product compiler on a commercial multiprocessor system. This paper presents performance results showing that compiler-based software data-prefetching supported in the Intel compiler results in significant performance gain, viz., 11.88% to 99.85% gain for 6 out of 11 applications, 3.83% to 6.96% gain for 4 out of 11 applications, with only one application obtaining less than 1% gain on an IntelR Itanium® 2 processor based SGI Altix* 32-way sharedmemory multiprocessor system.
Keywords :
C++ language; FORTRAN; multi-threading; open systems; optimising compilers; parallelising compilers; shared memory systems; software performance evaluation; storage management; C++; Fortran benchmark program; Intel production compiler; Intel® Itanium® 2 processor; OpenMP* C; SGI Altix* 32-way shared-memory multiprocessor system; SPEC OMPM2001 application performance; compiler-based software data-prefetching; multithreaded execution; Application software; Delay; Information analysis; Multiprocessing systems; Optimizing compilers; Performance gain; Phased arrays; Production; Program processors; Software performance; OpenMP; Thread-level parallelism; compiler optimization; performance evaluation; prefetching;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel and Distributed Processing Symposium, 2005. Proceedings. 19th IEEE International
Print_ISBN :
0-7695-2312-9
Type :
conf
DOI :
10.1109/IPDPS.2005.248
Filename :
1419874
Link To Document :
بازگشت