1 |
Andrey Falko wrote: |
2 |
> On 11/20/08, *Nikos Chantziaras* <realnc@×××××.de |
3 |
> <mailto:realnc@×××××.de>> wrote: |
4 |
> |
5 |
> As it happens, upgrading to kernel 2.6.27 was not the only change; I |
6 |
> switched from xf86-video-radeonhd to the proprietary ATI Catalyst |
7 |
> drivers. Didn't think that this has anything to do with it though. |
8 |
> |
9 |
> |
10 |
> I have a hunch that this is the problem. Have you tried 2.6.27 without |
11 |
> the proprietary ATI drivers? |
12 |
|
13 |
I'll be running tests on this with various combinations |
14 |
(2.6.26/2.6.27/Catalyst/open source radeonhd) and see what happens. |
15 |
Re-emerging a bunch of stuff should do it. |
16 |
|
17 |
|
18 |
> This is the first thing I would suspect |
19 |
> because ATI drivers are not reputed --- or so I believe --- for being |
20 |
> the best quality software out there. |
21 |
|
22 |
They are reputed to be one of the most broken (from packaging, install |
23 |
scripts up to the actual binary blobs) ever produced ;P Too bad they're |
24 |
the *only* choice on modern cards. No 3D (or even accelerated 2D) |
25 |
support with any open source driver for HD4xxx series cards. It's one |
26 |
of those things you hate to the bone but can't do without due to AMD's |
27 |
refusal to open source them so we can fix them. |
28 |
|
29 |
|
30 |
> Either way, we need to eliminate as |
31 |
> many factors as possible and one of these factors is your ATI driver |
32 |
> change. I don't know much about Prime95, but if it won't simulate a |
33 |
> subtlety in your video drivers, especially how proprietary ATI drivers |
34 |
> will play with kernel 2.6.27. |
35 |
|
36 |
Yes, Prime doesn't touch the GPU. It stresses CPU, northbridge and RAM |
37 |
only. |