Hello,

I tried the patch and the problem persists.
As *Shehab Elsayed* said, the problem is more likely to arise when the
number of CPUs increases.
For me, the simulation ends with only *one CPU* and I have to set a
large *L2cache_size
(4MB)* for the simulation to end with *2 CPUs*. From *3 CPUs* upwards the
simulation does not end (*or takes very very long time but i don't know
because i stopped the simulation after 2 hours*).
It is as if the simulation time increases exponentially with the number of
CPUs.

kind regards,
Armel
--
*JEATSA TOULEPI Armel*
Étudiant En Génie Informatique
Tel: +237 650771894 / 655296800


Le ven. 19 juil. 2019 à 09:01, Armel Jeatsa <[email protected]> a
écrit :

> Hello,
>
> Thank you for your reply. I will try the patch.
> I think the command line is deterministic.
> I realized that when I set the number of cpu to 1 or 2, the simulation
> runs normally but from 3 it freezes in line *"brought up x cpu"*.
>
> kind regards,
> Armel.
> --
> *JEATSA TOULEPI Armel*
> Étudiant En Génie Informatique
> Tel: +237 650771894 / 655296800
>
>
> Le jeu. 18 juil. 2019 à 23:35, Jason Lowe-Power <[email protected]> a
> écrit :
>
>> Hmm... that's strange. I would expect that command line to be completely
>> deterministic.
>>
>> However, Brandon just submitted a patch that fixes an undefined behavior
>> error for x86. It should be merged soon, but if you'd like to try it now
>> see https://gem5-review.googlesource.com/c/public/gem5/+/19568
>>
>> Cheers,
>> Jason
>>
>> On Thu, Jul 18, 2019 at 11:55 AM Armel Jeatsa <[email protected]>
>> wrote:
>>
>>> Hello,
>>> I use the command : *build/X86/gem5.opt configs/example/fs.py
>>> --disk-image=$(pwd)/full-system-images/disks/linux-x86.img
>>> --kernel=$(pwd)/full-system-images/binaries/x86_64-vmlinux-2.6.22.9.smp
>>>  --cpu-type=TimingSimpleCPU -n 4 --caches --l1i_size=8kB --l1d_size=8kB
>>> --l2cache --l2_size=256kB*
>>> and it seems to freeze at line : *"Brought up 4 CPUs"*
>>>
>>> kind regards,
>>> Armel
>>> --
>>> *JEATSA TOULEPI Armel*
>>> Étudiant En Génie Informatique
>>> Tel: +237 650771894 / 655296800
>>>
>>>
>>> Le lun. 15 juil. 2019 à 17:22, Jason Lowe-Power <[email protected]> a
>>> écrit :
>>>
>>>> Hi Armel,
>>>>
>>>> It's unlikely the performance of the host machine. gem5 should be
>>>> deterministic, and the underlying host machine shouldn't make a difference.
>>>>
>>>> Since you're seeing non-deterministic behavior, you should ask "what
>>>> about the simulation is changing?". Is it some configuration options (e.g.,
>>>> size of caches)? Is it the CPU pipeline design (e.g., size of ROB)? This
>>>> might give a hint as to the problem.
>>>>
>>>> If you could give us details about your configuration (e.g., Ruby vs
>>>> classic caches, what CPU model, etc.) we may be able to help more.
>>>>
>>>> Cheers,
>>>> Jason
>>>>
>>>> On Mon, Jul 15, 2019 at 1:39 AM Armel Jeatsa <[email protected]>
>>>> wrote:
>>>>
>>>>> Hello everyone,
>>>>>
>>>>> Sometimes when i launch full system simulation, the process seems to
>>>>> be freezing at line "*Brought up 2 CPUs*" or at line "*Freeing unused
>>>>> kernel memory: 248k freed*", and other times it launches well and
>>>>> show the m5 terminal. What can be the cause of the problem??  could it be
>>>>> related to the performance of my machine?
>>>>>
>>>>> Kind regards,
>>>>> Armel.
>>>>> --
>>>>> *JEATSA TOULEPI Armel*
>>>>> Étudiant En Génie Informatique
>>>>> Tel: +237 650771894 / 655296800
>>>>> _______________________________________________
>>>>> 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
>
>
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to