I'm trying to analyse an execution on an Intel IvyBridge CPU (Xeon E5-2620 V2) with the Top-down Microarchitecture Analysis Method, described in Chapters B of the Intel® 64 and IA-32 Architectures Optimization Reference Manual.
Therefore I perform performance counter events measurements with Perf (perf stat -e rNNN), There are some results I don’t understand:
CPU_UNHALTED.TREAD_P(0x003C) < CYCLE_ACTIVITY.STALLS_LDM_PENDING(Event A3H, Umask 06H)
I can not understand which it means?
- CYCLE_ACTIVITY.CYCLES_L2_PENDING > CYCLE_ACTIVITY.CYCLES_L1D_PENDING and CYCLE_ACTIVITY.STALLS_L2_PENDING > CYCLE_ACTIVITY.STALLS_L1D_PENDING