Messages in this thread | | | Date | Wed, 2 May 2012 13:14:33 +0200 | Subject | Re: [BUG] perf stat: useless output for raw events with new event parser | From | Stephane Eranian <> |
| |
Peter,
I will try to experiment with: cpu/event=INST_RETIRED:ANY:c=1/ But for now with libpfm4 as it is. Then will try to come up with an external file format that encapsulates what I already have in the C-table. There is more than just what the hardware exports. You have to encode certain constraints, e.g., how umasks can be combined. I don't even use the same format for all arch. On X86 the AMD and Intel formats are different.
On Mon, Apr 23, 2012 at 12:45 PM, Stephane Eranian <eranian@google.com> wrote: > Hi, > > With the new event parser, one can express raw events field by field: > > $ perf stat -e cpu/event=0x3c,umask=0x0/,cpu/event=0xc5,umask=0x0/ noploop 1 > > The problem with this is that the output of perf stat becomes useless: > > $ perf stat -e cpu/event=0x3c,umask=0x0/,cpu/event=0xc5,umask=0x0/ noploop 1 > noploop for 1 seconds > > Performance counter stats for 'noploop 1': > > 2395038678 pmu > 10787 pmu > ^^^^^^ > 1.000802603 seconds time elapsed > > We lose the event names or encoding completely. Now for all events > expressed via this > new syntax , all we see is 'pmu'. That is pretty useless. It is hard > to decrypt the results > without some serious scripting. > > Not sure how to solve this given how the parser works. This looks like > a regression to me. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |