Re: AMD vs. Intel
On Wednesday 07 April 2004 12:44, martin f krafft wrote:
> Recently, however, I have experienced random crashes on two machines
> that run AMDs. The crashes seem to be related to IO and happen
> usually when there is a lot of disk activity.
This has nothing to do with CPU. Things to check:
1. Hard drive/CD-ROM data cable. Especially if it is the thin (ATA-66 and up)
- they damage very easily around the connectors. I've also seen I/O errors
and data corruption a lot with those cables if there is the slightest bit of
isolation damaged, life if the cable scratched against a sharp edge in the
box.
2. Hard drive - although you can verify this easily by putting it in another
machine.
3. Controller. What controller is it? Onboard or PCI? What chipset? Older
VIA chipsets can be a bit buggy if the manufacturer of the motherboard didn't
take care when implementing it.
> from you success and failure stories of AMD processors and Linux.
AMD always have and still make excellent quality processors (although
performance, like beauty, is in the eye of the beholder). The only funny
behaviour you would get that has anything to do with the CPU itself is if the
CPU overheats. AMD K6 CPUs became unstable when they overheat. Same for All
Intels up to the last P-III CPUs. Athlons and Durons too, although they can
stably much higher temperatures than anything before them - I've seen a Duron
(Spitfire core) run Windows stably at just over 100 degrees celcius. This
was a worst case scenario where the heatsink's clasp was put on the wrong way
around and heatsink didn't make proper contact with the CPU die. No, it
didn't burn out - it just slowed down but ran stably for about three months
until I got my hands on it and figured out what was wrong. I also frequently
see Durons and Athlons (of various cores) that run stably well into the 80
and 90 degrees when their fans quit.
So, my guess is your problems isn't CPU related.
Hans
--
Kind regards
Hans du Plooy
Newington Consulting Services
hansdp at newingtoncs dot co dot za
Reply to: