Accuracy of profiling

Mahmood N <[email protected]>
Newsgroups gmane.linux.oprofile
Message-ID <[email protected]>
Hi,I have a concern over the accuracy of profiling. I profiled two executions immediately. The second execution took less time than the first one. That is correct in real world because of caching. However, I don't expect to see such an effect in profiling. 

Events were actively counted for 37.9 seconds.
Event counts (actual) for /home/mahmood/spec-cpu2006-x86_64/benchspec/CPU2006/401.bzip2/exe/bzip2_base.amd64-m64-gcc44-nn:
        Event                        Count                    % time counted
        CPU_CLK_UNHALTED             109,637,705,266          100.00
        RETIRED_INSTRUCTIONS         108,789,176,110          100.00
Events were actively counted for 35.9 seconds.
Event counts (actual) for /home/mahmood/spec-cpu2006-x86_64/benchspec/CPU2006/401.bzip2/exe/bzip2_base.amd64-m64-gcc44-nn:
        Event                        Count                    % time counted
        CPU_CLK_UNHALTED             107,924,858,901          100.00
        RETIRED_INSTRUCTIONS         108,708,808,686          100.00



Another thing is that I expect the same number of RETIRED_INSTRUCTIONS  since bzip2 has a number of fixed static instructions (input file in the same in both runs) and doesn't matter how many times it is executed.
 Regards,
Mahmood

------------------------------------------------------------------------------

_______________________________________________
oprofile-list mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/oprofile-list
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.