Re: 2.1.104/105 misdetection of Cyrix CPU

Phil's Kernel Account (kernel@eiterra.nls.net)
Wed, 10 Jun 1998 10:08:21 -0400 (EDT)


On Wed, 10 Jun 1998, Steven N. Hirsch wrote:

#On Tue, 9 Jun 1998, josh wrote:
#> I hope no one has commented on this already, but the 2.1.105 kernel
#> seems to misdetect Cyrix 6x86MXes --- mine is reported as a "Cx486SLC"
#> I first noticed the bug w/ 2.1.104, the kernel I was using prior to that
#> (a snapshot of vger's cvs repository circa 2.1.103) worked OK.
#I'm seeing this as well. Also, after a long period of stability Bogomips
#are not being measured properly. A 6x86MMX PR20 shows up with 166
#Bogomips on all earlier kernels. 2.1.105 reports 133.

I don't know how many times I've addressed this, but suffice to say, far
too many.

First off; I don't know why, but some kernels report the actual clocking
of the processor instead of the PR. This is NORMAL operation.

Some kernels drop ~33-66 bogomips off of Cyrix processors for unknown
reasons.

But it's all moot, since bogomips are just that; bogus.

-Phil R. Jaenke (kernel@nls.net / prj@nls.net)
TheGuyInCharge(tm), Ketyra Designs - We get paid to break stuff :)
Linux pkrea.ketyra.INT 2.0.33 #15 Sat Apr 18 00:40:21 EDT 1998 i586
Linux eiterra.nls.net 2.1.98 #15 Fri May 1 18:21:00 EDT 1998 i586
- Linus says for 'brave people only.' I say 'keep a backup.' - :)
! I reserve the right to bill spammers for my time and disk space !

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu