Sorry I don't have an answer off the top of my head for this, but
since no one else is speaking up, I'd suggest wading through the code
in configs/common/Simulation.py and see if you can figure out what's
going on, and then perhaps you can fix it to do what you want.

Steve

On Tue, Jul 6, 2010 at 10:31 PM, Sage <[email protected]> wrote:
> Hi, Gabe,
>
> Thanks a lot for your answer. Now I am hoping someone can answer my second
> question as follows.
>
> It seems that the two commands "--checkpoint-restore=XXX --at-instruction
> --warmup-insts=250000000 --max-inst=250000000" and "--checkpoint-restore=XXX
> --at-instruction --max-inst=250000000" produce the same simulation results,
> indicating that "-warmup-insts=250000000" does not take effect at all. I am
> wondering how I can warm up caches after recovering from a checkpoint???
>  However, using "--fast-forward" instead of "--checkpoint-restore" seems to
> work fine, but I 'd prefer to use ""--checkpoint-restore" to save time.
>
>
> Leonard
>
>
>
>
> On Tue, Jul 6, 2010 at 10:26 PM, Gabriel Michael Black
> <[email protected]> wrote:
>>
>> I'll answer your first question. All addresses outside of the CPU should
>> be physical. The TLB objects defined by the ISA do the translation, and
>> they're hooked in as internal components of the CPU. We've talked a little
>> bit about whether those should be pulled out into the memory system, but
>> that unfortunately introduces a lot of complications.
>>
>> Gabe
>>
>> Quoting Sage <[email protected]>:
>>
>>> Hi, everyone,
>>>
>>> I have two questions regarding the m5 simulator.
>>>
>>> The first question is whether or not the address seen by a cache module
>>> (e.g., the parameter "addr" passed to the cache function "accessBlock")
>>> is a
>>> virtual address. If it is, when does the virtual->physical translation
>>> take
>>> place?
>>>
>>> The second question is that it seems to me that the two commands
>>> "--checkpoint-restore=XXX --at-instruction --warmup-insts=250000000
>>> --max-inst=250000000" and "--checkpoint-restore=XXX --at-instruction
>>> --max-inst=250000000" produce the same simulation results, indicating
>>> that
>>> "-warmup-insts=250000000" does not take effect at all. I am wondering how
>>> I
>>> can warm up caches after recovering from a checkpoint???    However,
>>> using
>>> "--fast-forward" instead of "--checkpoint-restore" seems to work fine,
>>> but I
>>> 'd prefer to use ""--checkpoint-restore" to save time.
>>>
>>> Thanks in advance!
>>>
>>> Leonard
>>> --
>>> Give our ability to our work, but our genius to our life!
>>>
>>
>>
>> _______________________________________________
>> m5-users mailing list
>> [email protected]
>> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
>
>
>
> --
> Give our ability to our work, but our genius to our life!
>
> _______________________________________________
> m5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
>
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users

Reply via email to