Hello again,

Ali you were right with getCpuNum now I can see the core that is trying to
access, thank you so much, without your help guys my work will be much
hardar, thank you.

2008/11/5 Lisa Hsu <[EMAIL PROTECTED]>

> the very latest and greatest m5 has been changed to contextId() as opposed
> to getCpuNum().  and there's a check now.
>
> lisa
>
>
>
>
> On Wed, Nov 5, 2008 at 3:55 PM, Ali Saidi <[EMAIL PROTECTED]> wrote:
>
>> pkt->req->getCpuNum()/getThreadNum(). However, they will only work if
>> the request came from a CPU and not from an I/O device. We seem to be
>> lacking a cpuThreadValid() method, so you may want to add one to the
>> request and test it before you grab your data.
>>
>> Ali
>>
>>
>>
>> On Nov 5, 2008, at 3:46 PM, Bob Nagel wrote:
>>
>> > I just need the src number to make stats about number of access per
>> > core. I will check the information give it by Clint, to access to
>> > the cpuid I have tried pkt->getCpuid bit it does not work, can you
>> > tell me the exact method?. Thanks so much.
>> >
>> > Bob
>> >
>> > 2008/11/5 Ali Saidi <[EMAIL PROTECTED]>
>> > Why do you need the src number of the cores? The Request object
>> > contains a cpuid/threadid that you can use for identifying which
>> > requests come from a CPU and what cpu that is.
>> >
>> > Ali
>> >
>> > On Nov 5, 2008, at 3:09 PM, Bob Nagel wrote:
>> >
>> > > Hi Steve thanks for your answer, how can I know the src number of
>> > > the cores?, I have been trying to identify them by the access but I
>> > > only see dfierent src number accesing to the bus without a clear
>> > > pattern, do you know where is the source code in which is assigned
>> > > the src number to the cores?. Thank you.
>> > >
>> > > 2008/11/5 Steve Reinhardt <[EMAIL PROTECTED]>
>> > > The bus IDs are essentially arbitrary... they're assigned by the bus
>> > > as devices are connected to it, which happens in an uncontrolled
>> > > fashion as the simulation objects are created.
>> > >
>> > > Note that the each object attached to the bus gets its own ID as
>> > well,
>> > > so for example if you have split I and D caches then each of those
>> > > caches will have its own ID.
>> > >
>> > > Steve
>> > >
>> > > On Wed, Nov 5, 2008 at 10:43 AM, Bob Nagel <[EMAIL PROTECTED]>
>> > wrote:
>> > > > Hello,
>> > > >
>> > > > I am exploring the information that I get when I put the option
>> > > > --trace-flags="bus", but I do not understand the criterium that it
>> > > is used
>> > > > to assign a src number to the packets. If I do a simulation with 1
>> > > core, The
>> > > > src number can have this values: 0,1,2, for 2 cores: 0,1,2,3,
>> > for 4
>> > > > cores:0,1,3,5,7.
>> > > >
>> > > > Can anyone explain me what is the criterium to assign a source
>> > > number for
>> > > > the cores, I am just interested in the packets that come from the
>> > > cores.
>> > > > Thank you.
>> > > >
>> > > >
>> > > >
>> > > > _______________________________________________
>> > > > 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
>> > >
>> > > _______________________________________________
>> > > 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
>> >
>> > _______________________________________________
>> > 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
>>
>>
>
> _______________________________________________
> 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