| Date: | Tue, 23 Mar 2010 14:49:18 -0500 |
|---|---|
| From: | Dan Gibson <degibson@xxxxxxxx> |
| Subject: | Re: [Gems-users] Which matrices should be used to compare CMP coherence protocols? |
|
RUBY_CYCLES is time. It is pretty much THE performance metric. Everything else is, to some extent, informational. Regards, Dan On Tue, Mar 23, 2010 at 2:23 PM, lopamudra chatterjee <lopamudralopa@xxxxxxxxxxxxxx> wrote: 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? -- http://www.cs.wisc.edu/~gibson [esc]:wq! |
| [← Prev in Thread] | Current Thread | [Next in Thread→] |
|---|---|---|
| ||
| Previous by Date: | Re: [Gems-users] Which matrices should be used to compare CMP coherence protocols?, lopamudra chatterjee |
|---|---|
| Next by Date: | [Gems-users] Configuration of "heterogeneous multi core processor" with GEMS, dl kumar |
| Previous by Thread: | Re: [Gems-users] Which matrices should be used to compare CMP coherence protocols?, lopamudra chatterjee |
| Next by Thread: | [Gems-users] x86 patch on Gems 2.1 and Simics 3.0.31, Abhishek Moghe |
| Indexes: | [Date] [Thread] |