Différences
Ci-dessous, les différences entre deux révisions de la page.
| Les deux révisions précédentes Révision précédente Prochaine révision | Révision précédente | ||
| outils_analyse:perfsuite [2016/12/06 15:56] – [Basic usage] admin | outils_analyse:perfsuite [2016/12/06 19:21] (Version actuelle) – admin | ||
|---|---|---|---|
| Ligne 1: | Ligne 1: | ||
| + | ~~NOTOC~~ | ||
| ====== Perfsuite ====== | ====== Perfsuite ====== | ||
| PerfSuite is a collection of tools, utilities, and libraries for software performance analysis. It is relatively easy to use and is targeted to users at all levels of expertise. | PerfSuite is a collection of tools, utilities, and libraries for software performance analysis. It is relatively easy to use and is targeted to users at all levels of expertise. | ||
| Ligne 36: | Ligne 37: | ||
| </ | </ | ||
| - | <note tip>The psrun command uses an XML configuration file to determine the mode of operation (counting or profiling). If you do not specify an XML configuration file, the default file itimer.xml will be used. | + | < |
| + | <note tip> | ||
| </ | </ | ||
| + | |||
| + | For post-processing the output, use the '' | ||
| + | <code bash> | ||
| + | $ psprocess a.out.pid.hostname.xml | ||
| + | </ | ||
| + | |||
| + | ==== Example ==== | ||
| + | Execute Matmul ('' | ||
| + | |||
| + | **Execute: | ||
| + | <code bash> | ||
| + | $ export OMP_NUM_THREADS=8 | ||
| + | $ psrun ./ | ||
| + | </ | ||
| + | |||
| + | The output file is '' | ||
| + | |||
| + | **Postprocessing: | ||
| + | <code bash> | ||
| + | $ psprocess omp_matmul_03.exe.49333.mesoshared.xml | ||
| + | </ | ||
| + | |||
| + | **Statistic output: | ||
| + | <code bash> | ||
| + | PerfSuite Hardware Performance Summary Report | ||
| + | |||
| + | Version | ||
| + | Created | ||
| + | Generator | ||
| + | XML Source | ||
| + | |||
| + | Execution Information | ||
| + | ============================================================================================ | ||
| + | Collector | ||
| + | Date : Tue Dec 6 16:37:47 2016 | ||
| + | Host : mesoshared | ||
| + | Process ID : 49333 | ||
| + | Thread | ||
| + | User : kmazouzi | ||
| + | Command | ||
| + | |||
| + | Processor and System Information | ||
| + | ============================================================================================ | ||
| + | Node CPUs : 32 | ||
| + | Vendor | ||
| + | Brand : Intel(R) Xeon(R) CPU | ||
| + | CPUID : family: 6, model: 46, stepping: 6 | ||
| + | CPU Revision | ||
| + | Clock (MHz) : 2000.180 | ||
| + | Memory (MB) : 64409.21 | ||
| + | Pagesize (KB) : 4 | ||
| + | |||
| + | Cache Information | ||
| + | ============================================================================================ | ||
| + | Cache levels | ||
| + | -------------------------------- | ||
| + | Level 1 | ||
| + | Type : instruction | ||
| + | Size (KB) : 32 | ||
| + | Linesize (B) : 64 | ||
| + | Assoc : 4 | ||
| + | Type : data | ||
| + | Size (KB) : 32 | ||
| + | Linesize (B) : 64 | ||
| + | Assoc : 8 | ||
| + | -------------------------------- | ||
| + | Level 2 | ||
| + | Type : unified | ||
| + | Size (KB) : 256 | ||
| + | Linesize (B) : 64 | ||
| + | Assoc : 8 | ||
| + | -------------------------------- | ||
| + | Level 3 | ||
| + | Type : unified | ||
| + | Size (KB) : 18432 | ||
| + | Linesize (B) : 64 | ||
| + | Assoc : 24 | ||
| + | |||
| + | Index Description | ||
| + | ============================================================================================ | ||
| + | 1 Conditional branch instructions.................................. | ||
| + | 2 Branch instructions.............................................. | ||
| + | 3 Conditional branch instructions mispredicted..................... | ||
| + | 4 Conditional branch instructions taken............................ | ||
| + | 5 Floating point operations........................................ | ||
| + | 6 Level 1 data cache accesses...................................... | ||
| + | 7 Level 1 data cache misses........................................ | ||
| + | 8 Level 1 instruction cache accesses............................... | ||
| + | 9 Level 1 instruction cache misses................................. | ||
| + | 10 Level 2 instruction cache accesses............................... | ||
| + | 11 Level 2 instruction cache misses................................. | ||
| + | 12 Level 2 total cache accesses..................................... | ||
| + | 13 Level 2 cache misses............................................. | ||
| + | 14 Load instructions................................................ | ||
| + | 15 Cycles stalled on any resource................................... | ||
| + | 16 Store instructions............................................... | ||
| + | 17 Data translation lookaside buffer misses......................... | ||
| + | 18 Instruction translation lookaside buffer misses.................. | ||
| + | 19 Total cycles..................................................... | ||
| + | 20 Instructions issued.............................................. | ||
| + | 21 Instructions completed........................................... | ||
| + | |||
| + | Event Index | ||
| + | ============================================================================================ | ||
| + | 1: PAPI_BR_CN | ||
| + | 5: PAPI_FP_OPS | ||
| + | 9: PAPI_L1_ICM | ||
| + | 13: PAPI_L2_TCM | ||
| + | 17: PAPI_TLB_DM | ||
| + | 21: PAPI_TOT_INS | ||
| + | |||
| + | Statistics | ||
| + | ============================================================================================ | ||
| + | Counting domain........................................................ | ||
| + | Multiplexed............................................................ | ||
| + | Floating point operations per cycle.................................... | ||
| + | Floating point operations per graduated instruction.................... | ||
| + | Graduated instructions per cycle....................................... | ||
| + | Issued instructions per cycle.......................................... | ||
| + | Graduated instructions per issued instruction.......................... | ||
| + | Issued instructions per level 1 instruction cache miss................. | ||
| + | Graduated instructions per level 1 instruction cache miss.............. | ||
| + | Level 1 data cache accesses per graduated instruction.................. | ||
| + | % cycles stalled on any resource....................................... | ||
| + | Graduated loads and stores per floating point operation................ | ||
| + | Level 1 instruction cache misses per issued instruction................ | ||
| + | Level 1 cache miss ratio (data)........................................ | ||
| + | Level 1 cache miss ratio (instruction)................................. | ||
| + | Level 2 cache miss ratio (data), data cache miss and access counts derived | ||
| + | Level 2 cache miss ratio (instruction)................................. | ||
| + | Bandwidth used to level 2 cache (MB/ | ||
| + | MFLOPS (cycles)........................................................ | ||
| + | MFLOPS (wall clock).................................................... | ||
| + | MIPS (cycles).......................................................... | ||
| + | MIPS (wall clock)...................................................... | ||
| + | CPU time (seconds)..................................................... | ||
| + | Wall clock time (seconds).............................................. | ||
| + | % CPU utilization...................................................... | ||
| + | |||
| + | </ | ||
| + | |||
| + | |||
| + | ====== PerfSuite Command-Line Tools ====== | ||
| + | Command-Line Utilities | ||
| + | * '' | ||
| + | * '' | ||
| + | * '' | ||
| + | * '' | ||
| + | |||
| + | |||
| + | <note warning> | ||
| + | ====== Links ====== | ||
| + | * http:// | ||
| + | * https:// | ||