Re: [Gems-users] Different CPI's for Ruby and Opal

["Min Xu (Hsu)" <xu@xxxxxxxxxxx>]

Looks like this question should be the FAQ. :-)

Bradford Beckmann wrote:

> The OPAL_RUBY_MULTIPLIER is simply a frequency multiplier between Ruby's
> and Opal's frequencies.  If you set it to 1, Opal and Ruby have the same
> frequency, higher Opal will have a faster frequency.
>
> The multiplier was added as a performance enhancement.  The assumption is
> Opal needs a high frequency to model a fast out-of-order processor, but
> Ruby can use a lower frequency because it models the relatively slow
> memory system.  Since Ruby is an eventqueue driven simulator, having a
> slower frequency in Ruby results in less 'wakeup' cycles and thus reduces
> simulation time.
>
> However, when using a non-unit multiplier, you need to remember the
> relation when analyzing the stats.
>
>
> On Thu, 28 Apr 2005, Jonathan Brooks wrote:
>
>  
>
> > Yes, they are off exactly by a factor of two!  Ok, but what is the
> > purpose OPAL_RUBY_MULTIPLIER?  Can I set it to 1 without affecting
> > something else?
> >
> > -----Original Message-----
> > From: gems-users-bounces@xxxxxxxxxxx
> > [mailto:gems-users-bounces@xxxxxxxxxxx] On Behalf Of Mike Marty
> > Sent: Thursday, April 28, 2005 6:39 PM
> > To: Gems Users
> > Subject: Re: [Gems-users] Different CPI's for Ruby and Opal
> >
> > Are they off by a factor of 2?  If so, this is due to the
> > OPAL_RUBY_MULTIPLIER setting in ruby/config/rubyconfig.defaults
> >
> > --Mike
> >
> >
> >    
> >
> > > I am running a CMP system (2 procs on 1 chip) with Serengeti/Solaris
> > > target (mostly default configuration).  I use both Opal and Ruby for a
> > > simulation of running a few binaries for 1 million steps.  When I look
> > > at the statistics in Ruby, I see Instructions per cycle per processor,
> > > which I assume I can take the inverse to get Cycles Per Instruction).
> > > However these numbers do not match the CPI's I get in Opal's report.
> > > Why are they different?
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >
> > >      
> > _______________________________________________
> > Gems-users mailing list
> > Gems-users@xxxxxxxxxxx
> > https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> >
> >
> >
> > _______________________________________________
> > Gems-users mailing list
> > Gems-users@xxxxxxxxxxx
> > https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> >
> >    
>
> -----------------------------------------------------------------
> Department of Computer Science         Residence
> University of Wisconsin
> 1210 W. Dayton St. #6366               918 E. Dayton St. #4
> Madison, WI 53706                      Madison, WI 53703
> (608)265-2702				(608)442-0187
> -----------------------------------------------------------------
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
>  


--
That is what makes time travel into our past impossible and thereby
explains, as those who say it is possible cannot explain, why it will
never happen - as we know it will not, since we know it never has.
 -- D. H. Mellor, Emeritus Professor of Philosophy, University of Cambridge