Re: [Gems-users] High IFETCH ratio

[Edward Lee <edwl202@xxxxxxxxx>]

Thanks, again. I actually had followed all those standard procedures.
I will post back if I find anything useful.

Regards,

Ed

On Fri, Apr 16, 2010 at 9:42 AM, Dan Gibson <degibson@xxxxxxxx> wrote:
> I have no idea what ruby0.tracer does, actually.
> Now that I think about it, I'm not sure if Ruby even sees IFETCH for every
> instruction when running under Simics, or just every cache line. I would
> think the former, because Simics shouldn't know what a 'cache line' is, but
> you never know.
>
> Did you run with these magic lines?
> instruction-fetch-mode instruction-fetch-trace
> istc-disable
> dstc-disable
>
> Failure to use those lines would probably cause problems.
>
> Did you invoke simics with the -stall flag? You should, if you want to see
> ifetches. (I think its required for Simics 3 anyway, but I don't use it
> myself, so again I am not sure).
>
> Regards,
> Dan
>
> On Thu, Apr 15, 2010 at 8:00 PM, Edward Lee <edwl202@xxxxxxxxx> wrote:
>>
>> Thanks Dan for the prompt answer although you make me more worried now :)
>>
>> Pretty much rest of the kernels have ~1-2% IFETCH ratio out of all
>> events for the parallel section. Would that be because I only captured
>> the parallel section trace? Also, just to make sure ruby0.tracer
>> captures all the events that are issued from the processors right?
>>
>> Regards,
>>
>> Ed
>>
>> On Thu, Apr 15, 2010 at 9:12 PM, Dan Gibson <degibson@xxxxxxxx> wrote:
>> > I would be worried if IFETCH wasn't quite high... seeing as every LD or
>> > ST
>> > requires an IFETCH... as do all the non-memory instructions.
>> >
>> > Regards,
>> > Dan
>> >
>> > On Thu, Apr 15, 2010 at 6:12 PM, Edward Lee <edwl202@xxxxxxxxx> wrote:
>> >>
>> >> Hi,
>> >>
>> >> I collected traces from (parallel sections only) my SPLASH2 runs.
>> >> Couple of the benchmarks (namely Barnes-16k and raytrace) show 40%
>> >> IFETCH count and pretty much ~1% STORE count and the rest is LOADs. Is
>> >> having this large IFETCH counts normal, as the rest of the suite has
>> >> less than 1% ratio for IFETCH events?
>> >>
>> >> Regards,
>> >>
>> >> Ed
>> >> _______________________________________________
>> >> Gems-users mailing list
>> >> Gems-users@xxxxxxxxxxx
>> >> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
>> >> Use Google to search the GEMS Users mailing list by adding
>> >> "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>> >>
>> >
>> >
>> >
>> > --
>> > http://www.cs.wisc.edu/~gibson [esc]:wq!
>> >
>> > _______________________________________________
>> > Gems-users mailing list
>> > Gems-users@xxxxxxxxxxx
>> > https://lists.cs.wisc.edu/mailman/listinfo/gems-users
>> > Use Google to search the GEMS Users mailing list by adding
>> > "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>> >
>> >
>> >
>> _______________________________________________
>> Gems-users mailing list
>> Gems-users@xxxxxxxxxxx
>> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
>> Use Google to search the GEMS Users mailing list by adding
>> "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>>
>
>
>
> --
> http://www.cs.wisc.edu/~gibson [esc]:wq!
>
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> Use Google to search the GEMS Users mailing list by adding
> "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>
>
>