Re: [2.1.105] Cyrix 6x86 reduced to 486

Mike Jagdis (mike@roan.co.uk)
Wed, 10 Jun 1998 10:29:50 +0100 (GMT/BST)


On Tue, 9 Jun 1998, Phil's Kernel Account wrote:

> On Tue, 9 Jun 1998, Adam Sulmicki wrote:
>
> #AFAIK, it is b/c cyrix probing and Intel's BX chipsets did not like
> #each other.
>
> No. Intel designed BX so that probing for their competitors would break
> the OS.

It's even worse. Simply putting the chipset registers in the same
place that Cyrix chips have their config registers wasn't sufficient.
Why? Because Cyrix chips set their flags slightly differently
on certain division operations and this difference was commonly
used to detect the presence of a Cyrix chip initially (it is part
of the standard CPU detection code supplied by Cyrix). So Intel
also seem to have changed their processors - Pentium IIs appear
to exhibit the Cyrix flags behaviour rather than the Intel
behaviour which all previous Intel CPUs had. It takes both changes
to break things. Coincidence?

Mike

-- 
.----------------------------------------------------------------------.
|  Mike Jagdis                  |  Internet:  mailto:mike@roan.co.uk   |
|  Roan Technology Ltd.         |                                      |
|  54A Peach Street, Wokingham  |  Telephone:  +44 118 989 0403        |
|  RG40 1XG, ENGLAND            |  Fax:        +44 118 989 1195        |
`----------------------------------------------------------------------'

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