DocumentCode :
1916179
Title :
Using utility prediction models to dynamically choose program thread counts
Author :
Moore, Ryan W. ; Childers, Bruce R.
Author_Institution :
Comput. Sci. Dept., Univ. of Pittsburgh, Pittsburgh, PA, USA
fYear :
2012
fDate :
1-3 April 2012
Firstpage :
135
Lastpage :
144
Abstract :
Multithreaded applications can simultaneously execute on a chip multiprocessor computer, starting and stopping without warning or pattern. The behavior of each program can be different, interacting in unexpected ways, including causing competition for CPU cycles, which harms performance.
Keywords :
multi-threading; multiprocessing systems; CPU cycles; chip multiprocessor computer; multithreaded application; program thread counts; utility prediction model; Aggregates; Computational modeling; Instruction sets; Linear regression; Predictive models; Quality of service; Throughput; CMP; multicore; multiprocessor; multithreaded; performance; prediction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Performance Analysis of Systems and Software (ISPASS), 2012 IEEE International Symposium on
Conference_Location :
New Brunswick, NJ
Print_ISBN :
978-1-4673-1143-4
Electronic_ISBN :
978-1-4673-1145-8
Type :
conf
DOI :
10.1109/ISPASS.2012.6189220
Filename :
6189220
Link To Document :
بازگشت