1 |
"Hemmann, Volker Armin" <volker.armin.hemmann@××××××××××××.de> posted |
2 |
200608131915.18375.volker.armin.hemmann@××××××××××××.de, excerpted below, |
3 |
on Sun, 13 Aug 2006 19:15:18 +0200: |
4 |
|
5 |
> 2d is open - from nvidia... and you don't need more, if you just have some |
6 |
> servers running or only need basic desktop. ATI does not even has that. |
7 |
> And Intel.. I just don't trust them. It would be typical for them to open |
8 |
> their drivers and forbid the others to do the same, just to get some |
9 |
> advantage in the market place. About the ogp - as long as there is no |
10 |
> hardware, I don't even consider them. Even in very future plannings. |
11 |
|
12 |
The thing is... the 2D hardware is deprecated and on the way out. It's |
13 |
just a corner of most video chips now, and with all major platforms (incl. |
14 |
Linux/X) going 3D on the desktop, 2D is on the way out. With the |
15 |
generation of hardware matching Panorama-of-MSWormOS, 3D is fully |
16 |
integrated, to the point where even 2D is drawn using the 3D algorithms. |
17 |
It won't be long until there's no 2D hardware to have drivers FOR! |
18 |
|
19 |
As for AMD, here's what I skipped over in the previous post. They've |
20 |
already teamed up with various third parties to develop and sell physics |
21 |
and floating point processors slotted into additional CPU sockets, linked |
22 |
directly to the multi-core CPUs via Cohesive HyperTransport. The next |
23 |
step is doing the same thing with full video processors, a decent portion |
24 |
of which are physics processors anyway. There are however a couple issues |
25 |
with the idea, including the fact that getting video folks to commit to an |
26 |
AMD specific platform when they already have PCI-E would have been rather |
27 |
difficult. This is supposedly one of the big reasons they bought ATI -- |
28 |
to give AMD the where-with-all to follow up on that idea. Now, in ordered |
29 |
to fully populate the ecosystem, they'll /have/ to open things up. Keep |
30 |
in mind that Intel is designing similar stuff with it's integrated |
31 |
solutions, and if AMD didn't get in the game, it wouldn't be long until |
32 |
they were no more relevant than Via in the x86 CPU market. AMD can do it, |
33 |
and can continue to define the rules and the market place much as they did |
34 |
with amd64 aka x86_64 and HyperTransport, but in ordered to do it, they |
35 |
have to define open standards much as they did with x86_64. Should they |
36 |
fail, Intel won't be far behind and will end up ahead, and AMD could very |
37 |
soon be an also-ran. |
38 |
|
39 |
The flip side, as you mentioned, is the possibility of stomping on the |
40 |
patents of someone else and getting nicked for it. However, AMD has |
41 |
enough trade secrets and patents of its own that taking them down will be |
42 |
far more complex than trying to take down ATI alone. Even someone like |
43 |
Rambus can't afford to play the game exclusively, because any practical |
44 |
application, thus everyone they would be attempting to license to, is |
45 |
going to be using an AMD technique as well, so they can't directly attack |
46 |
AMD without nuking the market for their own product in the process. AMD, |
47 |
like Intel and IBM, is big enough one has to cross-license, because |
48 |
anything else ends up being MAD (Mutually Assured Destruction, a reference |
49 |
to the cold war, but you likely know that already). |
50 |
|
51 |
So... I think AMD/ATI /could/ open their video specs. However, it's still |
52 |
an open question of whether they /will/, tho I think the chances are |
53 |
pretty good, as Intel will have them between a rock and a hard place if |
54 |
they don't. |
55 |
|
56 |
(My sources for much of this were articles at ArsTechnica and the |
57 |
Register, in turn quoting trade mags and industry analysts, plus AMD's own |
58 |
PR.) |
59 |
|
60 |
-- |
61 |
Duncan - List replies preferred. No HTML msgs. |
62 |
"Every nonfree program has a lord, a master -- |
63 |
and if you use the program, he is your master." Richard Stallman |
64 |
|
65 |
-- |
66 |
gentoo-amd64@g.o mailing list |