Half-Life 2 On Wine Is Faster On AMD R600g Over Catalyst

[drag]

I have noticed this with starcraft2. The open source drivers tend to work better then the catalyst. At least for me.

..

I think that part of the deal is that the 'highly optimized' nature of catalyst is often on a per-app basis. In order to look good in benchmarks AMD has spent considerably money profiling and creating optimized code paths for specific applications. If you are not using a particular gaming engine or application that AMD didn't anticipate or put a lot of effort into optimizing then the open source drivers are going to be more competitive.

[dhewg]

@przemoli, dhewg, Drago
As clearly stated in the article, the Catalyst result is the one at the right end of the graphs. Glsl and arb have nothing to do with the driver. The text makes perfect sense to me...

Oh, now I see it. Still confusing though :P

[Drago]

I doubt that. r600g doesn't have a shader optimizer, how possibly it can beat Catalyst?

I think that part of the deal is that the 'highly optimized' nature of catalyst is often on a per-app basis. In order to look good in benchmarks AMD has spent considerably money profiling and creating optimized code paths for specific applications. If you are not using a particular gaming engine or application that AMD didn't anticipate or put a lot of effort into optimizing then the open source drivers are going to be more competitive.

[Drago]

I very doubt that, either. In clear_d3d test text below is saying r600g has much better performance than Catalyst, but all see is virtually overlapping grapths. WTF?

Oh, now I see it. Still confusing though :P

[AJenbo]

I very doubt that, either. In clear_d3d test text below is saying r600g has much better performance than Catalyst, but all see is virtually overlapping grapths. WTF?

The two graphs are not r600g vs Catalys, it's two modes in Wine, the Catalyst is the spike at the end of the graph, the rest of it is r600g on different versions of Wine.

[smitty3268]

ati-glsl and ati-arb are wine settings.

just look at the far right for the catalyst results, all the others are r600g.

[FireBurn]

What a useless bunch of crap! Why Michael decided to post this is beyond me. He could have at least took the results and reformatted them to make some sense in the graphs

So far there have been more comments on the terrible graphs than when they're supposed to be displaying

[_ONH_]

I'm sorry, but "clearly" is wrong wording. The labeling is very confusing and also: the last two result seemed to be Catalyst, according to the first page, not only the last one.

No, the two points rows in the first page are for the two lines with arb and glsl so just one point of the x axis is the catalyst driver, eg the last one.

[Gusar]

So far there have been more comments on the terrible graphs than when they're supposed to be displaying

Which boggles my mind completely. Because I don't see how

What we are looking at is the result on the far right side, which is the fglrx/Catalyst performance while the rest of the results are from Wine on the Radeon Gallium3D open-source driver.

could've been written any clearer.

[crazycheese]

800x600 as res used for all tests? Most be a joke or?

"As far as why the open-source driver is outperforming the highly optimized closed-source driver, Stefan wrote, "I don't have an explanation for this yet, especially considering that fglrx beats r600g by a factor of 5 in most of your Linux-native tests. A possible cause is that my test setup is heavily CPU limited (usually 800x600 resolution, no multisampling). This was a conscious decision when I set up the tests because Wine's main performance issues are on the CPU side, not the GPU side. However, at least r300g's main problems seem to be GPU-related (not sure about r600g).""

Unless he means, WINE has CPU issues when using AMD drivers, I disagree. WINE had no CPU bottlenecks in all games I played (NOLF2 and stuff).
Still, even with 800x600 this shows open driver has no resolution-associated CPU issues, which is good.
Running 1920 parallel would be good though, even if opensource looses.