Performance-Monitoring Counters Library, for Intel/AMD Processors and Linux

This example introduces
   rabbit command-line option -Clean n

Return to Main Menu


Command-Line Options

-Clean n

  Make n attempts to determine the overhead associated with a call to
  pmc_read(), and subtract this value from the measured cycles and events
  when pmc_accumulate() is used.

  The default is n = 0, so the measurements are not "corrected".  Usually
  n = 10 should be sufficient.


Notes

  The overhead calculation is done when pmc_select() is first invoked.  To
  avoid overcorrecting, the minimum of n trials is used, and pmc_accumulate()
  will not subtract more than the measurement.