DocumentCode :
2407321
Title :
PAPI deployment, evaluation, and extensions
Author :
Moore, Shirley ; Terpstra, Daniel ; London, Kevin ; Mucci, Philip ; Teller, Patricia ; Salayandia, Leonardo ; Bayona, Alonso ; Nieto, Manuel
Author_Institution :
Tennessee Univ., Knoxville, TN, USA
fYear :
2003
fDate :
9-13 June 2003
Firstpage :
349
Lastpage :
353
Abstract :
PAPI is a cross-platform interface to the hardware performance counters available on most modern microprocessors. These counters exist as a small set of registers that count events, which are occurrences of specific signals related to processor functions. Monitoring these events has a variety of uses in application development, including performance modeling and optimization, debugging, and benchmarking. In addition to routines for accessing the counters, PAPI specifies a common set of performance metrics considered most relevant to analyzing and tuning application performance. These metrics include cycle and instruction counts, cache and memory access statistics, and functional unit and pipeline status, as well as relevant SMP cache coherence events. PAPI is becoming a de facto industry standard and has been incorporated into several third-party research and commercial performance analysis tools. As in any physical system, the act of measuring perturbs the phenomenon being measured. Discrepancies in hardware counts and counter-related profiling data can result from other causes as well. A PET-sponsored project is deploying PAPI and related tools on DoD HPC Center platforms and evaluating and interpreting performance counter data on those platforms.
Keywords :
application program interfaces; performance evaluation; PAPI; SMP cache coherence event; benchmarking; cross-platform interface; debugging; functional unit; hardware performance counter; instruction count; memory access statistics; microprocessor; optimization; performance analysis tool; performance application programmer interface; performance counter data; performance metrics; performance modeling; pipeline status; processor function; Counting circuits; Debugging; Hardware; Measurement; Microprocessors; Monitoring; Performance analysis; Registers; Signal processing; Statistics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
User Group Conference, 2003. Proceedings
Print_ISBN :
0-7695-1953-9
Type :
conf
DOI :
10.1109/DODUGC.2003.1253415
Filename :
1253415
Link To Document :
بازگشت