The Community for Technology Leaders
Quantitative Evaluation of Systems, International Conference on (2007)
Edinburgh, Scotland, UK
Sept. 17, 2007 to Sept. 19, 2007
ISBN: 0-7695-2883-X
pp: 273-274
S. Sbaraglia , IBM T.J. Watson Research Center, USA
I. Chung , IBM T.J. Watson Research Center, USA
G. Cong , IBM T.J. Watson Research Center, USA
S. Seelam , IBM T.J. Watson Research Center, USA
H. Wen , IBM T.J. Watson Research Center, USA
D. Klepacki , IBM T.J. Watson Research Center, USA
ABSTRACT
Our productivity centered performance tuning framework for HPC applications comprises of three main components: (1) a versatile source code, performance metrics, and performance data visualization and analysis graphical user interface, (2) a unique source code and binary instrumentation engine, and (3) an array of data collection facilities to gather performance data across various dimensions including CPU, message passing, threads, memory and I/O. We believe that the ability to decipher performance impacts at the source level and the ability to probe the application with different tools at the same time at varying granularities, while hiding the complications of binary instrumentation, leads to higher productivity of scientists in understanding and tuning the performance of associated computing systems and applications.
INDEX TERMS
null
CITATION
S. Sbaraglia, I. Chung, G. Cong, S. Seelam, H. Wen, D. Klepacki, "A Productivity Centered Tools Framework for Application Performance Tuning", Quantitative Evaluation of Systems, International Conference on, vol. 00, no. , pp. 273-274, 2007, doi:10.1109/QEST.2007.14
90 ms
(Ver 3.3 (11022016))