Announcement

Collapse
No announcement yet.

This Is What Started AMD's Open-Source Strategy

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • This Is What Started AMD's Open-Source Strategy

    Phoronix: This Is What Started AMD's Open-Source Strategy

    While AMD's open-source strategy was announced on Phoronix on 7 September 2007, it was on 17 September of the same year that the Novell/SUSE developers did their first public release of their xf86-video-radeonhd driver. This was the X.Org driver created by the Novell Linux engineers in months prior for R500 and R600 GPUs. Here is some special reading -- a letter that was volleyed from Novell to AMD that kicked off this entire process -- to celebrate what would have been the fourth birthday of this open-source Linux driver.

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Ok, now forward that email to nvidia.

    Comment


    • #3
      now make a good an fast drivers so i can play quake live on 4850 on open drivers... now it is 60 fps, but screen is choppy.

      i can use my computer as beta test machine

      Comment


      • #4
        All I would like is power management, especially for my E-350-based notebook...

        Comment


        • #5
          Originally posted by Qaridarium
          active power management isn't the problem its the default setting that its the problem.
          You're wrong.

          Originally posted by Qaridarium
          "high" mode as a default hurt the most people
          Yeah, but dynpm/low are too buggy to be default, so there's nothing we can do.

          Originally posted by Qaridarium
          KDE for example can turn of 3D desktop if a full screen game starts why not turn the power management profile to high if a full screen game starts ?
          That's what dynpm will do in the future (clock dependend on the workload). It's not really working yet. And low has problems even on the desktop.

          Originally posted by Qaridarium
          or yes in my point of view it makes no sense to dev a open source driver but not the automatic power management.
          Power Management is hard to do but I agree its priority should be higher than it is right now.

          Originally posted by Qaridarium
          in real you can't only use passive cooled cards for the open source driver but there is no passive cooled notebook at all.
          Not sure if serious...? Power management is important because of the power consumption. The fan in my subnotebook is quiet enough (totally different story with my desktop, powered by a 6870).

          Comment


          • #6
            The drivers default to "default" because that is the only thing that runs reliably on all systems so far.
            Test signature

            Comment


            • #7
              Originally posted by bridgman View Post
              The drivers default to "default" because that is the only thing that runs reliably on all systems so far.
              Lets say your claim is true.
              Then what decides the "default profile"?
              The BIOS that lacks it?
              Some non-existing user setting?
              Hardware defined?
              Basiacally what needs to be done is to:
              1. Set low or medium as default profile
              2. Fix dynpm!

              Comment


              • #8
                Originally posted by Qaridarium
                or maybe you are blind or just a ignorance person.
                I'll take "blind" for $300, Alex.

                I read that thread a few more times but didn't see any indication of default not running on the user's system. It didn't reduce power, obviously, but it also didn't crash at boot which is the problem on some systems if the driver defaults to mid, low, dynpm or anything else. As long as the system boots up (which it does with "default") the user can adjust power levels; if the system crashes at boot that's a lot harder.

                Originally posted by del_diablo View Post
                Lets say your claim is true. Then what decides the "default profile"?
                The BIOS that lacks it? Some non-existing user setting? Hardware defined?
                The video BIOS contains a power settings table, with one or more entries. One of those entries is marked as "default". The VBIOS uses that entry when setting up the hardware, and IIRC "default" in the driver means "don't mess with whatever the VBIOS set".

                When you say "The BIOS that lacks it", what does "it" refer to ?
                Last edited by bridgman; 17 September 2011, 12:06 PM.
                Test signature

                Comment


                • #9
                  agd5f has mentioned it here a couple of times IIRC, also discussion on #radeon over the last couple of years
                  Test signature

                  Comment


                  • #10
                    @quaridium if you are too lazy to google up the IRC logs why should anyone help you.

                    Comment

                    Working...
                    X