[prev in list] [next in list] [prev in thread] [next in thread]
List: gmp-bugs
Subject: multi-core ARM configuration
From: hannes () mehnert ! org (Hannes Mehnert)
Date: 2014-10-23 12:39:00
Message-ID: 5448F6E4.7000907 () mehnert ! org
[Download RAW message or body]
(sorry, I didn't cc the mailing list in my reply, thus resending the mail)
On 10/23/2014 14:08, Niels M?ller wrote:
> Hannes Mehnert <hannes at mehnert.org> writes:
>
>> This is a cubieboard2
>> (http://docs.cubieboard.org/products/start#cubieboard2).
>>
>> mirage at cubieboard2:~$ cat /proc/cpuinfo
>> processor : 0
>> model name : ARMv7 Processor rev 4 (v7l)
>> Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3
>> tls vfpv4 idiva idivt vfpd32 lpae evtstrm
>> CPU implementer : 0x41
>> CPU architecture: 7
>> CPU variant : 0x0
>> CPU part : 0xc07
>> CPU revision : 4
>>
>> processor : 1
>> model name : ARMv7 Processor rev 4 (v7l)
>> Features : swp half thumb fastmult vfp edsp thumbee neon vfpv3
>> tls vfpv4 idiva idivt vfpd32 lpae evtstrm
>> CPU implementer : 0x41
>> CPU architecture: 7
>> CPU variant : 0x0
>> CPU part : 0xc07
>> CPU revision : 4
>>
>> Hardware : Allwinner sun7i (A20) Family
>> Revision : 0000
>> Serial : 0000000000000000
>
> I see. I wonder why I get different output from my board, if it's just
> that you use a more recent kernel or something.
>
> Using the first CPU part line seems reasonable, as you do in your patch.
> Hopefully, they'll be identical. But I guess in principle, it's possible
> to have a system with two cpu sockets populated with slightly different
> cpus? Torbj?rn, do we care about that case for other archs?
When adjusting config.guess I read through it, and there is at least
for rs6* / powerpc* a very similar code part (line 449):
x=`grep "^cpu[ ]" /proc/cpuinfo | head -n 1`
I'm not sure what a SoC with SMP and heterogeneous CPUs outputs in
/proc/cpuinfo.
Cheers,
Hannes
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic