Learn how easy it is to sync an existing GitHub or Google Code repo to a SourceForge project! See Demo

Close

#145 core_2 unit_mask/events nits

closed-fixed
nobody
None
5
2007-07-16
2006-09-20
Dean Gaudet
No

this is based off the 0.9.2.1rc1 core_2 events file...

the default mask for L2_RQSTS is 0xcf -- this double
counts references because oprofile is generally running
on all cores. the default should probably be 0x4f.
i've verified this with a multithreaded microbenchmark
issuing random walks on all processors and the results
for 0x4f are more in-line with what i'd expect.

i've attached a patch to correct this and several other
unit_mask problems.

-dean

Discussion

  • Dean Gaudet
    Dean Gaudet
    2006-09-20

    fix some unit_mask nits

     
  • Dean Gaudet
    Dean Gaudet
    2006-09-21

     
    Attachments
  • Dean Gaudet
    Dean Gaudet
    2006-09-21

    Logged In: YES
    user_id=408455

    in 0.9.2.1rc1 there are two L2_RQSTS events listed for
    core_2. one is with um:core_mesi, the other with
    um:core_prefetch_mesi... unfortunately since the prefetch
    one comes second you can't specify prefetch masks for L2_RQSTS.

    the patch i've attached also renames the two
    L2_RQSTS.SELF.etcetc events to match what the ISA calls the
    two events -- LLC_REFS and LLC_MISSES... this seems like it
    would be preferred on the assumption they may some day add
    an L3 cache and the architectural "LLC" events would
    probably then refer to L3.

    unfortunately it seems opreport only looks at the first 0x2e
    event when decoding things so it doesn't display the handy
    LLC_REFS/LLC_MISSES monikers.

    anyhow, either this patch or one supporting
    core_prefetch_mesi for L2_RQSTS would be nice...

    thanks
    -dean

     
  • Dean Gaudet
    Dean Gaudet
    2006-09-21

    • summary: core_2 unit mask nits --> core_2 unit_mask/events nits
     
  • John Levon
    John Levon
    2006-09-21

    • status: open --> open-fixed
     
  • John Levon
    John Levon
    2006-09-21

    Logged In: YES
    user_id=53034

    I've applied both after bcrl reviewed them.

    The multiple events with the same number must be fixed by
    adding synthetic event numbers and decoding them in-kernel.

     
    • status: open-fixed --> closed-fixed