CRIHAN  - Mars 2001
Outils d’optimisation - Page 43
4- F. application : ADI
•résultat de perfex -a -y -x
•                                                                           Typical      Minimum      Maximum
•   Event Counter Name                                      Counter Value   Time (sec)   Time (sec)   Time (sec)
•===============================================================================================================
• 0 Cycles..................................................    473543376     2.428428     2.428428     2.428428
•16 Cycles..................................................    473543376     2.428428     2.428428     2.428428
•25 Primary data cache misses...............................     13666112     0.631444     0.197633     0.631444
•22 Quadwords written back from primary data cache..........     23456192     0.463109     0.377705     0.535282
•26 Secondary data cache misses.............................      1168832     0.452548     0.295864     0.503497
• 7 Quadwords written back from scache......................      7385600     0.242399     0.160211     0.242399
•21 Graduated floating point instructions...................     30300896     0.155389     0.077695     8.080239
•23 TLB misses..............................................        65264     0.022789     0.022789     0.022789
• 9 Primary instruction cache misses........................         8832     0.000816     0.000255     0.000816
•10 Secondary instruction cache misses......................          768     0.000297     0.000194     0.000331
•Statistics
•=====================================================================================
•Graduated instructions/cycle............................................     0.583375
•Graduated floating point instructions/cycle.............................     0.063988
•Graduated loads & stores/cycle..........................................     0.247853
•Graduated loads & stores/floating point instruction.....................     3.873448
•L1 Cache Line Reuse.....................................................     7.588320
•L2 Cache Line Reuse.....................................................    10.692110
•L1 Data Cache Hit Rate..................................................     0.883563
•L2 Data Cache Hit Rate..................................................     0.914472
•Time accessing memory/Total time........................................     0.703613
•L1--L2 bandwidth used (MB/s, average per process).......................   334.625857
•Memory bandwidth used (MB/s, average per process).......................   110.268924
•MFLOPS (average per process)............................................    12.477579