Re: [Gems-users] Functional Unit latencies on Ruby

["Abhishek Ranjan" <absk82@xxxxxxxxx>]

thanks a lot Mike!

 

This means that ruby will give us the memory accesses and the number of cycles assuming that computational units all have single cycles latency and no resource constraint.

 

If we have a code like this:

for( some condition)

{

 memory access

 FP Add

 FP Add

 FP Mul

}

 

then the number of cycles elapsed between two consecutive memory accesses will be three as given by ruby though it will depends a lot on the functional unit latencies. Is that correct? If yes, I think I would be better off using Opal with ruby.

the number of cycles which we get as the output of dump stats are simics cycles right? which will be twice that of ruby cycles if SIMICS_RUBY_MULTIPLIER if set to 2.

 

Thanks a lot,

Abhishek

 

 

On 5/26/06, Mike Marty <mikem@xxxxxxxxxxx> wrote:

> Mike Marty wrote:
>
> >>I think I can use both Ruby or opal to get this (assuming I can simulate
> >>uniprocessor on them).
> >>
> >>
> >>
> >
> >When using just Ruby, the "in-order" processor model is just Simics'
> >functional execution where each non-memory instruction executes in
> >1-cycle.
> >
> >
>
> Also this assumes a SIMICS_RUBY_MULTIPLIER set as 1.  You can make the
> Simics processor faster relative to Ruby by increasing this value.
>
> --Mike
>
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users