Page 3 of 5 FirstFirst 12345 LastLast
Results 21 to 30 of 49

Thread: AMD Radeon Gallium3D More Competitive With Catalyst On Linux

  1. #21
    Join Date
    Jan 2009
    Posts
    1,438

    Default

    Quote Originally Posted by phoronix View Post
    Phoronix: AMD Radeon Gallium3D More Competitive With Catalyst On Linux

    With the ever-changing state of Linux graphics drivers -- both for the open and closed-source drivers -- new tests have been conducted to compare the OpenGL graphics performance on Linux with AMD Radeon graphics. In this article are benchmarks of nine different Radeon HD graphics cards when being tested on the very latest AMD Catalyst (13.3 Beta 3) graphics driver as well as the open-source AMD Radeon driver consisting of Mesa 9.2-devel and the yet-to-be-released Linux 3.9 kernel.

    http://www.phoronix.com/vr.php?view=18654
    What games make use of OGL4+? For that matter, what games make use of OGL3.3+?
    What's the big bottleneck with Doom 3?

  2. #22
    Join Date
    Jun 2009
    Posts
    2,932

    Default

    Quote Originally Posted by przemoli View Post
    3.2 is more important. OSX use 3.2 excessively, and apps on Win are using DX (more likely). So people will tend to have 3.2 code paths for the sake of OSX compa. Games also should pick 3.2 (as this give 95% of Steam market...), while 4.x will still for some time be add-on, as it require up to date drivers on win, mean no osx support, and binarys on Lin.

    Yes 3.3 will mark "full" OpenGL support for class-DX11 hw, but otherwise 3.2 support is more important (and we will get them both in same mesa release at least for intel & r600g)
    Yeah, with GL 3.3, that generation is "done", and devs can concentrate on OpenGL 4.

    But the reason I wrote 3.3 is that it's mostly done. As soon as the missing parts of GL 3.2 are finished, 3.3 will come automatically.

  3. #23

    Default

    Quote Originally Posted by liam View Post
    What games make use of OGL4+? For that matter, what games make use of OGL3.3+?
    What's the big bottleneck with Doom 3?
    I'm not sure Doom 3 is bottlenecked, just in the catalyst, the windows history of tweaking performance for it is just brought back. So if you could put the same tweaks in the open source driver, I think you can get closer (ideally 70/80%, just like in the other games).

  4. #24
    Join Date
    Nov 2007
    Posts
    1,353

    Default

    You make a good point. I'm sure that in that games heyday it was probably optimized by AMD extensively. As when it was new it was used extensively in mainstream benchmarketing sites. not going to name names here, but....

    The chances of the OSS driver ever getting per application performance tuning is slim. Mainly because it is a waste of time. If the game plays at decent framerates then it shouldnt really matter too much. The definition of what decent framerates is exactly is another issue entirely.

  5. #25
    Join Date
    Jan 2010
    Location
    Somewhere in Kansas.
    Posts
    282

    Default

    Quote Originally Posted by duby229 View Post
    The definition of what decent framerates is exactly is another issue entirely.
    If the framerate is equal to or greater than your monitor refresh speed, then it is enough (no point of having it higher than your screen's refresh rate, you won't see them). For most monitors that is 60fps.

  6. #26
    Join Date
    Aug 2012
    Location
    Pennsylvania, United States
    Posts
    1,911

    Default

    Quote Originally Posted by ua=42 View Post
    If the framerate is equal to or greater than your monitor refresh speed, then it is enough (no point of having it higher than your screen's refresh rate, you won't see them). For most monitors that is 60fps.
    Higher framerates ARE useful for a different reason though. If a game runs at 300 FPS and during major effect / lots of people areas it drops to 150FPS, you're gold. The GPU cant render as much, the framerate drops, but no one knows, it still looks fluid. If you're at 60FPS and during high effect moment it drops to 30FPS, then you've got a problem-- it can be jarring.

    (The number of frames needed for the human eye to not care varies on whether or not Motion Blur is in effect. If there's motion blur then you can have a number like 24 or 25 without it being 'jarring.' If there isn't then I think its equal to the refresh rate for no jarring-ness. EG: Old Quake games dont have Motion Blur, you need more FPS to avoid a jarring effect)

  7. #27
    Join Date
    Apr 2013
    Posts
    221

    Default steam games

    i really like a comparation with steam games, one of this days i put my 4850 on use to see the diference =) the worst from radeon fss drivers is the power management at this point

  8. #28
    Join Date
    Jun 2009
    Posts
    566

    Default

    and as usual, Michael conveniently leaves out any 7XXX series card from the tests because he knows (and I'm very sure he does) that including it will make the open drivers look downright loserrific.

  9. #29
    Join Date
    Oct 2011
    Location
    Rural Alberta, Canada
    Posts
    1,030

    Default

    He mentions in the article that RadeonSI is not quite there yet. What more do you want? Or is this another blind allegation of favouritism on Larabel's part?

    I am already quite happy with my 4670's performance. It will be interesting to see how things look when I can update.

  10. #30
    Join Date
    Oct 2008
    Posts
    3,176

    Default Doom 3

    I seem to remember when Doom 3 came out, the engine was quite a bit different than other games at the time. Something about a trick to use the stencil to create shadows? I don't think many games afterwards used that either, so it's very possible Doom3 represents an engine doing something that hasn't been well optimized yet. The proprietary drivers all probably made sure to get those optimizations in because it was an important benchmark back in the day.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •