Page 1 of 7 123 ... LastLast
Results 1 to 10 of 68

Thread: Likely Radeon Gallium3D Regression On Linux 3.14 + Mesa 10.2

  1. #1
    Join Date
    Jan 2007
    Posts
    14,645

    Default Likely Radeon Gallium3D Regression On Linux 3.14 + Mesa 10.2

    Phoronix: Likely Radeon Gallium3D Regression On Linux 3.14 + Mesa 10.2

    For anyone currently experiencing a slowdown of their Radeon Gallium3D open-source driver stack or are interested in helping out track down a new performance issue, it appears the Linux 3.14 + Mesa 10.2 configuration is regressing on Ubuntu 14.04 LTS in place of Linux 3.13 + Mesa 10.1.

    http://www.phoronix.com/vr.php?view=19941

  2. #2

    Default

    Quote Originally Posted by phoronix View Post
    Phoronix: Likely Radeon Gallium3D Regression On Linux 3.14 + Mesa 10.2

    For anyone currently experiencing a slowdown of their Radeon Gallium3D open-source driver stack or are interested in helping out track down a new performance issue, it appears the Linux 3.14 + Mesa 10.2 configuration is regressing on Ubuntu 14.04 LTS in place of Linux 3.13 + Mesa 10.1.

    http://www.phoronix.com/vr.php?view=19941
    HyperZ is disabled by default since this commit:
    http://cgit.freedesktop.org/mesa/mes...afe60faff48d84

  3. #3
    Join Date
    Oct 2008
    Posts
    3,102

    Default

    Quote Originally Posted by AnonymousCoward View Post
    HyperZ is disabled by default since this commit:
    http://cgit.freedesktop.org/mesa/mes...afe60faff48d84
    Aww, you beat me to it.

    I hope this is what Marek works on next. It'd be nice to finally get this working well.

  4. #4
    Join Date
    Oct 2011
    Location
    Rural Alberta, Canada
    Posts
    1,030

    Default

    I do understand the reason for the change. I myself got bit by this one:
    https://bugs.freedesktop.org/show_bug.cgi?id=64471

    Let's hope these issues can be resolved so it can be re-enabled by default again.

  5. #5
    Join Date
    Nov 2010
    Posts
    366

    Default

    Whatever happened to those memory optimizations by curaga? No tests?

  6. #6
    Join Date
    Sep 2010
    Posts
    683

    Default

    curaga & Marek patches (both work on memory management code), are not in Mesa yet.

    Marek just posted patchset, while curaga have something cooking for this week or next. (Or thats what I read from comments below article about Marek patchset )

    In other words we may see that work done for 3.15/Mesa 10.2/10.3

  7. #7
    Join Date
    Jan 2012
    Posts
    29

    Default

    So now you write articles on testing and live versions of software? Maybe you should take a break instad, and improve articles that actually matter.

  8. #8
    Join Date
    Sep 2010
    Posts
    683

    Default

    Quote Originally Posted by genstorm View Post
    So now you write articles on testing and live versions of software? Maybe you should take a break instad, and improve articles that actually matter.
    Yeah. Because major regressions in performance are nobody concerns.

    STFU. And go play Angry Birds or something. Demanding that BENCHMARKING website stop BENCHMARKING is ....

  9. #9
    Join Date
    Oct 2013
    Posts
    195

    Default

    Quote Originally Posted by genstorm View Post
    So now you write articles on testing and live versions of software?
    Why not? I was also wondering what is causing the performance drop, thanks to Michael and other people who made it clear, now I know the reason behind that.

  10. #10
    Join Date
    Jan 2012
    Posts
    29

    Default

    Quote Originally Posted by przemoli View Post
    Yeah. Because major regressions in performance are nobody concerns.
    When they matter, e.g. in final versions, yes. Have YOU ever used software based on live sources? Regressions may happen on any commit, might be fixed in one of the following commits. In that case, where HyperZ has been disabled, you will get a fine Changelog entry with the final announcement, and all of those costly benchmarking and wondering 'what the heck degraded here' moments have been a waste of time. Time that is so badly missing to improve the poor average quality of other articles.

    You can keep your insults to yourself.

Posting Permissions

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