Re: [Gems-users] Which matrices should be used to compare CMP coherence protocols?

["lopamudra chatterjee" <lopamudralopa@xxxxxxxxxxxxxx>]

 RUBY_CYCLES is indeed lower on the supposedly better performance
protocol i.e. MOESI_CMP_directory. Is there any other metrices that I
should consider?

Sorry for double message. Initially didn't realize how I should reply.

Thanks,
Lopamudra

On Tue, 23 Mar 2010 22:44:36 +0530  wrote
>What does RUBY_CYCLES say?
>
>

On Tue, Mar 23, 2010 at 12:06 PM, lopamudra chatterjee <lopamudralopa@xxxxxxxxxxxxxx> wrote:
>

Hi,
>
>I am trying to compare the performance of 2 CMP cache coherence protocols by running a benchmark. Could anyone please give me an idea about which matrices from the ruby stats file will be good for performance comparison? Because according to the wiki MOESI_CMP_directory is supposed to give better performance than MSI_MOSI_CMP_directory. But I found that the miss_latency of my run says otherwise.
>
>Thanks,
>Lopamudra 
>
>_______________________________________________
>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.
>
>