If you look at configs/common/Simulation.py you can see what each options
does.

-Tony

On Mon, Oct 1, 2012 at 8:23 PM, Mahshid Sedghi <[email protected]>wrote:

> Thanks for the quick response. What about standard switch (-s)? This is
> not also working?
>
>
> Mahshid
>
>
>
> On Mon, Oct 1, 2012 at 7:50 PM, Anthony Gutierrez <[email protected]>wrote:
>
>> The "switchcpu" pseudo op only calls m5 exit, i.e., it's not fully
>> implemented. You could add a call to m5 exit to your rcS script right
>> before it launches your benchmark, then have the config script do a drain
>> and switch out the cpus.
>>
>> -Tony
>>
>> On Mon, Oct 1, 2012 at 7:47 PM, Mahshid Sedghi 
>> <[email protected]>wrote:
>>
>>> Hello all,
>>>
>>> I am trying to run a benchmark in full system mode on X86 and I am using
>>> Ruby. I want to load the kernel with some simple CPU and then switch to the
>>> detailed cpu to run my benchmark. I tried two options:
>>>
>>>
>>>    - I used "switchcpu" in my script, but gem5 exits after loading the
>>>    kernel.
>>>    - I also tried fast forwarding, but apparently gem5 uses atomic cpu
>>>    to run the instructions before switching to the other cpu which happens
>>>    when it hits the specified instruction count. And since Ruby does not
>>>    support atomic operations, it failed to run.
>>>
>>> I'll appreciate it If anybody can help me figure out a solution.
>>>
>>> Regards,
>>> Mahshid
>>>
>>>
>>> _______________________________________________
>>> 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
>
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to