Thank you for a timely response, Jack.

I have one additional question regarding the ASPLOS tutorial. In the
tutorial with gcc_integrated benchmark, the tutorial shows the following
command line:

m5.fast configs/example/se.py --bench=gcc_integrate --take-checkpoint=0
--simpoint

It looks like we are taking the simpoint from the interval 0, yet in the
ucsd:

http://cseweb.ucsd.edu/~calder/simpoint/points/standard/spec2000-single-std-100M.html

They show that the simpoint is taken at the interval 4 for the
gcc_integrated workload. Is there any specific reason for taking it at the
interval 0 or it was just 0 for an example purpose? Thank you.

Jee Ho Ryoo

2012/6/21 Jack Harvard <[email protected]>

> It's possible to run simpoint on any architecture, there's no reason
> it should be architecture-dependent.
>
> Jack Harvard
>
>
> On Wed, Jun 20, 2012 at 10:43 PM, Jee Ho Ryoo <[email protected]> wrote:
> > Hi,
> >
> > In the ASPLOS tutorial, it says that the simpoint is only implemented in
> > alpha. Has there been any progress in this towards ARM or X86
> architecture?
> > Is it possible to run simpoint on either of two ISAs? Thank you.
> >
> > Jee Ho Ryoo
> >
> > _______________________________________________
> > gem5-users mailing list
> > [email protected]
> > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
> _______________________________________________
> gem5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to