Re: [Gems-users] magic instructions profiling

[Dan Gibson <degibson@xxxxxxxx>]

The impact of the pre-sethi instructions and the sethi instruction 
itself should be very small when the number of magic instructions is 
small. Many simulations use only 1 magic call per sim (xactional 
simulations use more), thus the impact is determined by the length of 
the simulation.
Denisse Lin wrote:
> I'm sorry for the confusion. What I meant was the assembly 
> instructions added (to pass data values to Ruby) before the sethi 
> instruction. For example, mov %0, %%g1. Do those instructions have a 
> lot of impact on the outcome?
> Thanks,
>
> Denisse
>
> */Dan Gibson <degibson@xxxxxxxx>/* wrote:
>
>     Magic instructions do not themselves issue memory references.
>
>     Hence, I also do not understand Denisse's question.
>
>     郭锐 wrote:
> >     I’m afraid that I missed your point in my previous reply. But I
> >     think the magic instruction doesn’t make any memory reference,
> >     does it?
> >     ------------------------------------------------------------------------
> >     *From:* gems-users-bounces@xxxxxxxxxxx
> >     [mailto:gems-users-bounces@xxxxxxxxxxx] *On Behalf Of *Denisse Lin
> >     *Sent:* Wednesday, April 25, 2007 7:47 AM
> >     *To:* gems-users@xxxxxxxxxxx
> >     *Subject:* [Gems-users] magic instructions profiling
> >     Dear List,
> >
> >     When I pass some data values from the user program to Ruby via
> >     magic instructions, does Simics forward those data references to
> >     Ruby? In other words, do those data references within magic
> >     instructions get profiled by Ruby? If so, is it possible to
> >     exclude those data references from Ruby profiling?
> >
> >     Thank you,
> >
> >     Denisse
> >     ------------------------------------------------------------------------
> >     Ahhh...imagining that irresistible "new car" smell?
> >     Check out new cars at Yahoo! Autos.
> >     <http://us.rd.yahoo.com/evt=48245/*http:/autos.yahoo.com/new_cars.html;_ylc=X3oDMTE1YW1jcXJ2BF9TAzk3MTA3MDc2BHNlYwNtYWlsdGFncwRzbGsDbmV3LWNhcnM->
> >
> >     ------------------------------------------------------------------------
> >      _______________________________________________ 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.
> >
> >       
>     _______________________________________________
>     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.
>
>
> ------------------------------------------------------------------------
> Ahhh...imagining that irresistible "new car" smell?
> Check out new cars at Yahoo! Autos. 
> <http://us.rd.yahoo.com/evt=48245/*http://autos.yahoo.com/new_cars.html;_ylc=X3oDMTE1YW1jcXJ2BF9TAzk3MTA3MDc2BHNlYwNtYWlsdGFncwRzbGsDbmV3LWNhcnM-> 
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> 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!