Title :
Parallel performance visualization using moments of utilization data
Author :
Godin, T.J. ; Quinn, Michael J. ; Pancake, C.M.
Author_Institution :
Dept. of Comput. Sci., Oregon State Univ., Corvallis, OR, USA
fDate :
30 Mar-3 Apr 1998
Abstract :
We propose a new parallel performance visualization scheme, based on a simple moment analysis of processor utilization data. This method combines the scalability advantages of statistical summaries with the more revealing processor utilization information of Gantt charts. It scales well to large numbers of processors, requiring only storage constant in execution time
Keywords :
data analysis; data visualisation; parallel processing; performance evaluation; statistical analysis; Gantt charts; execution time; moment analysis; parallel performance visualization; processor utilization data; scalability; statistical summaries; storage; Clocks; Computer displays; Computer science; Concurrent computing; Data visualization; Performance analysis; Programming profession; Scalability; Synchronization; User-generated content;
Conference_Titel :
Parallel Processing Symposium, 1998. IPPS/SPDP 1998. Proceedings of the First Merged International ... and Symposium on Parallel and Distributed Processing 1998
Conference_Location :
Orlando, FL
Print_ISBN :
0-8186-8404-6
DOI :
10.1109/IPPS.1998.670015
