Re: [Gems-users] Ruby_cycles != opal0.cycle ?!


Date: Fri, 4 Mar 2005 11:48:12 -0600
From: "Min Xu (Hsu)" <xu@xxxxxxxxxxx>
Subject: Re: [Gems-users] Ruby_cycles != opal0.cycle ?!
On Fri, 04 Mar 2005 Min Xu (Hsu) wrote :
> Hi group,
> 
> Bk tells me both parameters are changed by milo in revision 1.28
> at Feb 03 2004. The comment simply says it "makes more sense" to
> have both MULTIPLIER be 2, instead of SIMICS_RUBY_MULTIPIER
> be 4 and OPAL_RUBY_MULTIPLIER be 1.

OK, I think I figured out what are the default values mean:

By default, we simulate a 2GHz out-of-order processor with a
1GHz memory hierarchy. Cache latency is 12ns, memory and directory
latencies are 80ns, network latency is 14ns. So in terms of
processor cycles, L1 caches are 2 cycle, L2 are 24 cycles.
memory is 160 cycles.

So the questions is, is this what we want?
[← Prev in Thread] Current Thread [Next in Thread→]