Re: 2.1.119 and Cyrix detection

Kurt Garloff (garloff@kg1.ping.de)
Fri, 4 Sep 1998 03:10:48 +0200


On Thu, Sep 03, 1998 at 06:42:12PM -0400, Gregory McLean wrote:

> Yep 2.1.119 still fails to detect this cyrix chip properly.
>
> CPU 6x86MX PR 233+
> Calibrating delay loop... 156.88 BogoMIPS
> CPU: Cyrix 6x86MX 2.5x Core/Bus Clock stepping 2.6
>
> Ok the initial check gets it right (somewhat it gets the stepping wrong)
>
> then /proc/cpuinfo has the same incorrect info
> processor : 0
> cpu family : 4
> model : 6x86MX 2.5x Core/Bus Clock
> vendor_id : CyrixInstead
> stepping : 2.6
> ..
> cpuid level : -1
> wp : yes
> flags :
> bogomips : 156.88

What's wrong about this? You CPU does 2.5 x 66 MHz = 166 MHz -> you should
see about 165 BogoMips ...
CPUID seems to be off by default on your CPU, though I was believing 6x86MX
has it turned on by default. Strange. That's why you CPU family of 4.

> [gregm@tweetie gregm]$ uname -a
> Linux tweetie 2.1.119 #17 Thu Aug 27 22:09:07 EDT 1998 i486 unknown
> [gregm@tweetie gregm]$

And this is the consequence of cpu family == 4.

I remeber having read a posting, where somebody claimed that egcs optimizes
some routines for CPU recignition which causes the 6x86 not to be detected
correctly. Don't know if this is the case for you. I also remeber that it
only happened with kernels configured for 586 and 686. ?

-- 
Kurt Garloff, Dortmund 
<K.Garloff@ping.de>
PGP key on http://student.physik.uni-dortmund.de/homepages/garloff

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/faq.html