Thanks for your reply, Korey. I meant I haven't found the source code in M5
(sorry for that).

Now I understand that the spec2k6 is not in the regression suite, thanks for
the explanation. I will try to look at implementation of this system call
and see whether I can implement it or not.

Thank you.

On Sun, Mar 27, 2011 at 12:18 AM, Korey Sewell <[email protected]> wrote:

> Hi Veydan,
> my intent in this email is definitely not to sound abrasive, but the
> note on the top of this page it says:
> "This is a work in-progress. Everyone should feel free to extend this
> page with their experiences to help new users get started."
>
> And then looking at the authors list from the history, I don't
> recognize any of the names who contributed this particular page. So
> it's not clear when you say "how did you run this?" that you are
> talking to any M5 developer in particular especially since spec2k6
> workloads aren't in the M5 regression suite.
>
> As such, we wouldn't know if any particular benchmark did or didn't
> work without it being in the regression suite or someone reporting
> that they got it to work for their studies. The note on the bottom of
> that page seems to suggest the latter:
> "If you have any questions, please email to M5 Mailing-List or contact
> Meng-Ju Wu at [email protected]"
>
> If you aren't able to figure it out through that reference, then
> you'll have to go down the route of implementing any unimplemented
> behavior yourself. (Btw, if you found this system call in the source
> code, then how can it be unimplemented?)
>
> On Sat, Mar 26, 2011 at 11:24 PM, Veydan Wu <[email protected]> wrote:
> > I referred to this page as well. I used Alpha CPU. From this page, seems
> > that M5 SE already support this benchmark, I just wonder why I
> encountered
> > such an unimplemented system call error. If I need to implement this
> system
> > call myself, I will try it. But how did you run "povray" successfully,
> given
> > that I have found this system call in the M5 source code. Thanks.
> >
> > On Sat, Mar 26, 2011 at 1:30 PM, Korey Sewell <[email protected]> wrote:
> >>
> >> what M5 page are you referring to that says it works?
> >>
> >> This page shows some starter info on running spec2k6:
> >> http://m5sim.org/wiki/index.php/SPEC2006_benchmarks
> >>
> >> What CPU model are you running?
> >>
> >> Have you tried implementing the system call yourself? You may be able
> >> to look at how other system calls are defined and form your own
> >> definition.
> >>
> >> On Wed, Mar 23, 2011 at 3:46 PM, Veydan Wu <[email protected]> wrote:
> >> > Hi, all. I ran spec2006 on M5 Alpha FS mode. The benchmark "povray"
> >> > encounters an error:
> >> > fatal: syscall chdir (#12) unimplemented.
> >> >  @ cycle 914691000
> >> > [unimplementedFunc:build/ALPHA_SE/sim/syscall_emul.cc, line 82]
> >> > However, the M5 website says this program runs OK on M5. I can't find
> >> > the
> >> > implementation of this system call in the latest m5 source code. Can
> >> > anyone
> >> > tell me how to solve this problem? Thanks in advance.
> >> > --
> >> > Regards,
> >> >
> >> > Veydan
> >> >
> >> > _______________________________________________
> >> > m5-users mailing list
> >> > [email protected]
> >> > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
> >> >
> >>
> >>
> >>
> >> --
> >> - Korey
> >> _______________________________________________
> >> m5-users mailing list
> >> [email protected]
> >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
> >
> >
> >
> > --
> > Regards,
> >
> > Veydan
> >
> > _______________________________________________
> > m5-users mailing list
> > [email protected]
> > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
> >
>
>
>
> --
> - Korey
> _______________________________________________
> m5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
>



-- 
Regards,

Veydan
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users

Reply via email to