Page 5 of 18 FirstFirst ... 3456715 ... LastLast
Results 41 to 50 of 180

Thread: More Radeon Power Management Improvements

  1. #41
    Join Date
    Dec 2007
    Posts
    1,970

    Default

    You can manually select a power state and clock mode:
    echo 3.0 > /sys/class/drm/card0/device/power_state
    will select power state 3, clock mode 0.

  2. #42
    Join Date
    Aug 2009
    Posts
    122

    Default

    yeah, thats what I did, I was asking, is it possible to make dynpm to use state 3, not state 1

  3. #43
    Join Date
    Dec 2007
    Posts
    1,970

    Default

    You'd need to adjust the power state selection algo in r600_get_power_state() in r600.c

  4. #44
    Join Date
    Aug 2009
    Posts
    122

    Default

    hm, i guess this should be enough then

    if (rdev->pm.num_power_states > 2)
    - min_power_state_index = 1;
    + min_power_state_index = 3;

  5. #45
    Join Date
    Apr 2008
    Posts
    26

    Default

    Quote Originally Posted by agd5f View Post
    You can manually select a power state and clock mode:
    echo 3.0 > /sys/class/drm/card0/device/power_state
    will select power state 3, clock mode 0.
    Uhm, somehow this does not exist here:

    Code:
    2.6.34-0.38.rc5.git0.fc14.i686 #1 SMP
    Which is the latest Kernel from Fedora and should hold all the pm-stuff in it. Latest drm, mesa and ddx and I booted with dynpm=1 and

    Code:
    [drm] radeon: power management initialized
    indicates that power management is working. However, I saw no improvement on lowered GPU temperatures whatsoever.

    What did I miss?

  6. #46
    Join Date
    Dec 2007
    Posts
    1,970

    Default

    You need the drm-radeon-testing branch of the drm:
    http://git.kernel.org/?p=linux/kerne...radeon-testing

  7. #47
    Join Date
    May 2010
    Posts
    2

    Default

    Quote Originally Posted by agd5f View Post
    You need the drm-radeon-testing branch of the drm:
    http://git.kernel.org/?p=linux/kerne...radeon-testing
    It is not enough to use drm-radeon-testing kernel. Some X parts must be rebuilt as well: http://www.phoronix.com/forums/showthread.php?t=20484

    Anyway I am using drm-radeon-testing. Everything seems to be working. I can change profiles in sysfs but my GPU is still getting hot (Currently 89 degrees). I was trying to change profiles but nothing has helped. As well I see following messages in log:

    [ 1223.517620] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1325.118109] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1328.719790] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1433.991376] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1489.719272] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1576.114701] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 1975.846892] radeon 0000:01:05.0: efd38000 reserve failed for wait
    [ 2022.020323] radeon 0000:01:05.0: efd38000 reserve failed for wait

  8. #48
    Join Date
    Jul 2009
    Posts
    78

    Default

    Quote Originally Posted by daliusd View Post
    It is not enough to use drm-radeon-testing kernel. Some X parts must be rebuilt as well: http://www.phoronix.com/forums/showthread.php?t=20484
    Huh, what makes you think so?

    Neither the DDX nor mesa do interface with the pm AFAIK, so why would it be necessary to rebuild X components?

  9. #49
    Join Date
    Aug 2009
    Posts
    122

    Default

    since alex's last commit ( http://git.kernel.org/?p=linux/kerne...86c041340079db )

    messages about changing clocks arent displaying in dmesg now, is there any way to check if reclocking actualy works and not failing due to - gui not idle ?

  10. #50
    Join Date
    Aug 2009
    Posts
    122

    Default

    I run glxgears then change profile from high to low, and doesnt see any noticable fps change

Posting Permissions

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