----------------------------------------------------------------------------------------------------------------------------
>
> *Do i need  to hack configs/example/se.py  or use the use the patch by 
> Jiayuan Meng ?*
>
> Thanks
> HARI

You need to do both. Jiayuan's patch is designed to run a single 
benchmark with a mesh model. If you want to run a workload, you need to 
assign each process to a different core in configs/example/se.py.
>
>
>
>
>
>
>
>
>
>
>
>
>
> On Wed, Feb 4, 2009 at 5:32 PM, Rick Strong <[email protected] 
> <mailto:[email protected]>> wrote:
>
>     If this is system emulation mode, then Pal is not the cause. How
>     many cpus have results? My theory is that you are not assigning a
>     thread to each CPU.  As most of the m5 scripts in configs/example
>     are setup now, you will only see all cpus being used if the
>     process creates multiple threads. It seems that in your case, you
>     might be trying to assign one process with one thread to multiple
>     CPUs. The result is a bunch of idle cores. You will need to hack
>     configs/example/se.py (assuming this is what you are using) when
>     it assigns the process to the core to assign one process to a
>     number of cores equal to the number of threads it will create.
>
>
>     Best,
>     -Rick
>
>     Hari Kiran wrote:
>
>         hi Rick
>
>            I am using Syscall Emulation mode, how to make sure all the
>         cpus boot successfully and could you please let me know what
>         is pal code and how to update it.
>
>         Thanks,
>         Hari
>
>         On Wed, Feb 4, 2009 at 4:59 PM, Rick Strong
>         <[email protected] <mailto:[email protected]>
>         <mailto:[email protected] <mailto:[email protected]>>> wrote:
>
>            If you are using full system alpha mode, make sure all the
>         cpus boot
>            successfully. If not, you might need updated pal code.
>
>            Best,
>            -Rick
>
>            Hari Kiran wrote:
>            >
>            > hi
>            >
>            > I am running eight-core system simulation for integer
>            benchmarks. But
>            > i am getting some 0 values for some cores in m5stat.txt.
>            > After  exchanging the benchmarks to different cpu's I am
>         getting the
>            > results. What might be the problem I don't understand. So
>         please
>            help
>            > me out regarding this problem.
>            >
>            > Thanks
>            > HARI
>            >
>          
>          
> ------------------------------------------------------------------------
>            >
>            > _______________________________________________
>            > m5-users mailing list
>            > [email protected] <mailto:[email protected]>
>         <mailto:[email protected] <mailto:[email protected]>>
>
>            > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
>
>            _______________________________________________
>            m5-users mailing list
>            [email protected] <mailto:[email protected]>
>         <mailto:[email protected] <mailto:[email protected]>>
>
>            http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
>
>
>
>
>         -- 
>         Regards
>         H A R I
>
>
>
>
>
> -- 
> Regards
> H A R I

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

Reply via email to