Pavlos,

That patch also prints the absolute values for the
hits/misses/accesses, and solves that misnomer issue. The only thing
it does not change is the member name profileMiss() of the CacheMemory
class because I wasn't sure what developers intend to do with the
naming convention.

You can look at the details/summary of the patch for more information.

Malek

On Tue, Nov 20, 2012 at 1:08 PM, Pavlos Maniotis <[email protected]> wrote:
> Now I understand, thanks a lot. I will try to install
> the patch and see what results I will get.
> But it is very strange that such a bug exists in gem5
> (you said "Currently, ruby counts (refers to) all cache accesses as
> 'misses' which..."). It would be also helpful to print
> cache accesses and cache misses as absolute values, I suppose
> someone could need them.
>
> Thanks again,
> Pavlos
>
> On Tue, 2012-11-20 at 12:37 -0500, Malek Musleh wrote:
>> Pavlos,
>>
>> Did you look at the changes in CacheProfiler.cc? Currently, ruby
>> counts (refers to) all cache accesses as 'misses' which is a bit
>> misleading. This patch changes that to correctly account for when a
>> cache access is a 'hit' versus a 'miss' (as in it has to go up to the
>> next level memory to satisfy the request). In doing so,
>> CacheProfiler.cc prints the ratio of misses/accesses:
>>
>>    out << description << "_miss_rate: " <<  100.0 * m_misses / m_accesses
>> 64
>>         << "%" << endl;
>>
>> If you notice, "out" in this case references the std::outstream, which
>> is the ruby.stats file.
>>
>> This is done on a per-cache basis, unless you want sum global
>> misses/accesses that accounts for all caches misses/accesses for every
>> cache into one value ?
>>
>> Malek
>>
>> On Tue, Nov 20, 2012 at 12:29 PM, Pavlos Maniotis <[email protected]> 
>> wrote:
>> > Hello Malek,
>> >
>> > Thanks for the reply.
>> > ruby.stats file reports the absolute number of cache misses but
>> > I need its proportion to all cache accesses. I can't understand
>> > how this patch will help me. Will it print the cache ratio (%) in
>> > ruby.stats file?
>> >
>> > Pavlos
>> >
>> > On Tue, 2012-11-20 at 11:38 -0500, Malek Musleh wrote:
>> >> Hi Pavlos,
>> >>
>> >> I have a patch posted here for this:
>> >>
>> >> http://reviews.gem5.org/r/1467/
>> >>
>> >> I only added support for MESI/MOESI Protocols, but you can extend to
>> >> the other ones also.
>> >>
>> >> Malek
>> >>
>> >> On Tue, Nov 20, 2012 at 11:09 AM, Pavlos Maniotis <[email protected]> 
>> >> wrote:
>> >> > Hello everyone,
>> >> >
>> >> > Is there anybody who knows how to calculate miss
>> >> > ratio using ruby? I think a step by step explanation
>> >> > would help a lot of us working on gem5.
>> >> >
>> >> > Thanks in advance,
>> >> > Pavlos
>> >> >
>> >> > _______________________________________________
>> >> > gem5-users mailing list
>> >> > [email protected]
>> >> > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>> >> _______________________________________________
>> >> gem5-users mailing list
>> >> [email protected]
>> >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>> >
>> >
>> > _______________________________________________
>> > gem5-users mailing list
>> > [email protected]
>> > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>> _______________________________________________
>> gem5-users mailing list
>> [email protected]
>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
>
> _______________________________________________
> gem5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to