loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
14th International Conference on Parallel Architectures and Compilation Techniques (PACT'05)
Automatic Selection of Compiler Options Using Non-parametric Inferential Statistics
St. Louis, Missouri
September 17-September 21
ISBN: 0-7695-2429-X
ASCII Text
x 
 
M. Haneda, P.M.W. Knijnenburg, H.A.G. Wijshoff, "Automatic Selection of Compiler Options Using Non-parametric Inferential Statistics," Parallel Architectures and Compilation Techniques, International Conference on, pp. 123-132, 14th International Conference on Parallel Architectures and Compilation Techniques (PACT'05), 2005.
 
 
BibTex
x
 
@article{ 10.1109/PACT.2005.9,
author = {M. Haneda and P.M.W. Knijnenburg and H.A.G. Wijshoff},
title = {Automatic Selection of Compiler Options Using Non-parametric Inferential Statistics},
journal ={Parallel Architectures and Compilation Techniques, International Conference on},
volume = {0},
year = {2005},
issn = {1089-795X},
pages = {123-132},
doi = {http://doi.ieeecomputersociety.org/10.1109/PACT.2005.9},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Parallel Architectures and Compilation Techniques, International Conference on
TI - Automatic Selection of Compiler Options Using Non-parametric Inferential Statistics
SN - 1089-795X
SP123
EP132
A1 - M. Haneda,
A1 - P.M.W. Knijnenburg,
A1 - H.A.G. Wijshoff,
PY - 2005
KW - null
VL - 0
JA - Parallel Architectures and Compilation Techniques, International Conference on
ER -
 
M. Haneda, LIACS, Leiden University The Netherlands
P.M.W. Knijnenburg, LIACS, Leiden University The Netherlands
H.A.G. Wijshoff, LIACS, Leiden University The Netherlands

In this paper, we propose a statistical method to determine the setting of compiler options. Conventionally, programmers use standard -Ox settings which are provided by compiler developers. However, in order to obtain maximal performance, it is necessary to tune the compiler setting for the application as well as the underlying architecture. In this paper, we propose a methodology to con?gure compiler options automatically using pro?le information. We apply non-parametric statistical analysis, in particular the Mann-Whitney test, to decide whether to turn on or to turn off compiler flags. This approach produces compiler settings of gcc 3.3.1 for the SPEC2000 benchmark suite that outperform the standard -Ox switches on a Pentium 4 processor.

Citation:
M. Haneda, P.M.W. Knijnenburg, H.A.G. Wijshoff, "Automatic Selection of Compiler Options Using Non-parametric Inferential Statistics," pact, pp.123-132, 14th International Conference on Parallel Architectures and Compilation Techniques (PACT'05), 2005
Usage of this product signifies your acceptance of the Terms of Use.