Announcement

Collapse
No announcement yet.

AMD R600g Still Tackling Hierarchical Z

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

  • #16
    Originally posted by TemplarGR View Post
    "For free"? Seriously? And i thought i had payed for the hardware... And it didn't have a sticker "It only works for Windows" on the box...
    you buyed the hardware not the opensource radeon driver you also buyed the "catalyst" and you buyed 3-4 opensource devs from AMD.

    but the point is the Radeon driver do have ~140 opensource devs

    this means you payed maybe 1-2% of the radeon driver and you get 98% for free.

    now what is more true you payed for the radeon driver 2% or you get it for free 98% ?

    Comment


    • #17
      Originally posted by TemplarGR View Post
      This is one of the rare times i want to complain to opensource devs, but i can't help it. While you have are gratitude for your work, there are some things that shouldn't be happening.

      Why HD2000-4000 are second rate citizens? First AMD drops support in Catalyst for them. And while it would make sense to have a focused opensource driver for these generations to provide legacy support, it seems that the opensource driver makes a priority Evergreen and above generations too... A while ago it was the news that Evergreen would have official OpenGl 3.0 support on by default, earlier than the older generations(?), and now from what agd5f says:

      [truncated because entire argument is BS]
      I'd like you to read two things here

      http://www.phoronix.com/scan.php?pag...0_hyperz&num=1

      http://www.x.org/wiki/RadeonFeature

      Do you happen to notice something? Oh what's that say? that pre-evergreen hardware has had Hyper-Z first, and that it's largely stabilized whereas Evergreen and above is still in heavy development? :shock: Could it be this man is either A. Trolling, or B. Hasn't the slightest clue what he's talking about because he clearly failed to do his research? :horror:

      seriously though.. Quit trolling or at least do some research before you try doing so.

      Comment


      • #18
        What about R500 Hi-Z instead? Any plan to enable it?
        ## VGA ##
        AMD: X1950XTX, HD3870, HD5870
        Intel: GMA45, HD3000 (Core i5 2500K)

        Comment


        • #19
          Originally posted by darkbasic View Post
          What about R500 Hi-Z instead? Any plan to enable it?
          in my knowelege the HIZ engine in r500 do have bugs and need "application profiles" with dirty "hacks"

          because of this its disabled.

          Comment


          • #20
            r300 also need hacks ? How to enable hiz for default (for all apps)?
            Last edited by Tommy666; 06-06-2012, 05:26 AM.

            Comment


            • #21
              Originally posted by TemplarGR View Post
              This is one of the rare times i want to complain to opensource devs, but i can't help it. While you have are gratitude for your work, there are some things that shouldn't be happening.

              Why HD2000-4000 are second rate citizens? First AMD drops support in Catalyst for them. And while it would make sense to have a focused opensource driver for these generations to provide legacy support, it seems that the opensource driver makes a priority Evergreen and above generations too... A while ago it was the news that Evergreen would have official OpenGl 3.0 support on by default, earlier than the older generations(?), and now from what agd5f says:

              a) Either evergreen will have support for hiz first

              b) Or hiz support for hd2000-4000 was fine but there were issues on Evergreen so they decided to hold it back...

              Either way, it is a bad attitude towards older generation users. Why Evergreen and newer are a priority, when they can use the Catalyst and are much newer chips? Seriously, i own a 3870 and it is about 2 year older than the Evergreen family. When i see that Evergreen matures to OpenGL 3.0 first or gets Hyper-Z(a really important feature) first (not to mention other performance improvements etc) i feel cheated. It is like AMD showing us older generation users to buy newer cards. Well, if that is what they want, it would be better to just ask for it, not this way... And why upgrade? My 3870 does its job perfectly...
              I think you are forgetting how the developers work and assuming conspiracy where none exists. In general they will work on a new feature for all generations (in this case 2xxx through NI) but things will start working on one generation before others as a consequence of generation-to-generation quirks. The developers don't choose this, it just works out that way.

              If you are saying "developers should be forbidden from working on newer generations until everything is finished on older generations" then the overall rate of progress would drop dramatically, since it's generally a lot faster to write code for a new feature designed to work across all the generations supported by the driver than to only look at older parts. In this case hyper-z and the backend work are pretty interdependent IIRC and both were happening at the same time, so it seems to make sense that Jerome would have had an Evergreen card in his system when it all came together.

              Anyways, key point here is that most of these features are implemented for multiple generations at the same time, and it's luck of the draw which generation starts working first. If you assume conspiracy or lack of care for older hardware each time that happens you're going to be whipsawing between happiness and misery for no good reason. You probably owe the developers a bit of an apology.

              Comment


              • #22
                I tried the patch, but unlike kernel 3.5 which gives me a huge performance improvement, I don't see any performance improvements with this patch.

                Comment


                • #23
                  Originally posted by AnonymousCoward View Post
                  I tried the patch, but unlike kernel 3.5 which gives me a huge performance improvement, I don't see any performance improvements with this patch.
                  Looking through the patch, it looks like the patch disables HyperZ by default:

                  Code:
                  diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
                  index e0ee823..7004ff9 100644
                  --- a/src/gallium/drivers/r600/r600_pipe.c
                  +++ b/src/gallium/drivers/r600/r600_pipe.c
                  @@ -942,6 +942,7 @@ struct pipe_screen *r600_screen_create(struct radeon_winsys *ws)
                   
                   	rscreen->use_surface_alloc = debug_get_bool_option("R600_SURF", TRUE);
                   	rscreen->glsl_feature_level = debug_get_bool_option("R600_GLSL130", TRUE) ? 130 : 120;
                  +	rscreen->use_hyperz = debug_get_bool_option("R600_HYPERZ", FALSE);
                  If you run your program (example = glxgears) with
                  Code:
                  R600_HYPERZ=1 glxgears
                  , then maybe performance will change...

                  From the Bug thread on FD.o, it sounds like all of the kernel patches are upstream, but I haven't checked if the DDX patches have all made it there yet. If this doesn't work, or throws errors, you might want to check that.
                  Last edited by Veerappan; 06-06-2012, 09:05 AM.

                  Comment


                  • #24
                    Originally posted by TemplarGR View Post
                    This is one of the rare times i want to complain to opensource devs, but i can't help it. While you have are gratitude for your work, there are some things that shouldn't be happening.

                    Why HD2000-4000 are second rate citizens? First AMD drops support in Catalyst for them. And while it would make sense to have a focused opensource driver for these generations to provide legacy support, it seems that the opensource driver makes a priority Evergreen and above generations too... A while ago it was the news that Evergreen would have official OpenGl 3.0 support on by default, earlier than the older generations(?), and now from what agd5f says:

                    a) Either evergreen will have support for hiz first

                    b) Or hiz support for hd2000-4000 was fine but there were issues on Evergreen so they decided to hold it back...

                    Either way, it is a bad attitude towards older generation users. Why Evergreen and newer are a priority, when they can use the Catalyst and are much newer chips? Seriously, i own a 3870 and it is about 2 year older than the Evergreen family. When i see that Evergreen matures to OpenGL 3.0 first or gets Hyper-Z(a really important feature) first (not to mention other performance improvements etc) i feel cheated. It is like AMD showing us older generation users to buy newer cards. Well, if that is what they want, it would be better to just ask for it, not this way... And why upgrade? My 3870 does its job perfectly...
                    The Hiz patches add support for all asics supported by r600g (6xx, 7xx, evergreen, NI). Most of the code is shared since the programming model is very similar across generations (in fact it works very similarly in SI). There were various issues with chips from all generations which have finally been solved. It just happened that the last remaining issue was an evergreen one. There was no conscious decision to hold back certain asics.

                    Also, all r600g chips can support OpenGL 3, no one has said it would be evergreen only.

                    Comment


                    • #25
                      Originally posted by Veerappan View Post
                      From the Bug thread on FD.o, it sounds like all of the kernel patches are upstream, but I haven't checked if the DDX patches have all made it there yet. If this doesn't work, or throws errors, you might want to check that.
                      You no longer need the ddx patch. It's now self contained in mesa.

                      Comment


                      • #26
                        Originally posted by Veerappan View Post
                        Looking through the patch, it looks like the patch disables HyperZ by default:

                        If you run your program (example = glxgears) with
                        Code:
                        R600_HYPERZ=1 glxgears
                        , then maybe performance will change...
                        Okay thanks. I didn't bother to look at the patch, just applied it . glxgears works, but that's not really a benchmark. So I tried the benchmark within FEAR. But with R600_HYPERZ=1 it puts the GPU in a state of infinite GPU resets. So no performance data here.

                        Comment


                        • #27
                          Originally posted by TemplarGR View Post
                          This is one of the rare times i want to complain to opensource devs, but i can't help it. While you have are gratitude for your work, there are some things that shouldn't be happening.

                          Why HD2000-4000 are second rate citizens? First AMD drops support in Catalyst for them. And while it would make sense to have a focused opensource driver for these generations to provide legacy support, it seems that the opensource driver makes a priority Evergreen and above generations too... A while ago it was the news that Evergreen would have official OpenGl 3.0 support on by default, earlier than the older generations(?), and now from what agd5f says:

                          a) Either evergreen will have support for hiz first

                          b) Or hiz support for hd2000-4000 was fine but there were issues on Evergreen so they decided to hold it back...

                          Either way, it is a bad attitude towards older generation users. Why Evergreen and newer are a priority, when they can use the Catalyst and are much newer chips? Seriously, i own a 3870 and it is about 2 year older than the Evergreen family. When i see that Evergreen matures to OpenGL 3.0 first or gets Hyper-Z(a really important feature) first (not to mention other performance improvements etc) i feel cheated. It is like AMD showing us older generation users to buy newer cards. Well, if that is what they want, it would be better to just ask for it, not this way... And why upgrade? My 3870 does its job perfectly...
                          HD2000-HD4000 are not second class citizen, the evergreen fix also apply to R7XX generation (HD4xxx). And all the kernel work on the backend stuff was needed and also impact R7XX and in smaller way R6XX GPU. The commit message might have more emphasis on evergreen but it's just due to the fact that at the time i was on an evergreen. You need to understand that we have many GPU and we keep switching btw generation and sometimes when things start to come into shape we might not stress what it does on all generations.

                          Comment


                          • #28
                            Originally posted by AnonymousCoward View Post
                            Okay thanks. I didn't bother to look at the patch, just applied it . glxgears works, but that's not really a benchmark. So I tried the benchmark within FEAR. But with R600_HYPERZ=1 it puts the GPU in a state of infinite GPU resets. So no performance data here.
                            What GPU ? Where can i download FEAR ?

                            Comment


                            • #29
                              Originally posted by glisse View Post
                              What GPU ?
                              Juniper (5750)

                              Where can i download FEAR ?
                              You can download a demo here

                              http://www.gamershell.com/download_10167.shtml

                              It's a Windows game, but works fine on Linux with wine and r600 drivers, except when run with R600_HYPERZ=1.

                              Comment


                              • #30
                                I do some tests
                                HD 6770

                                lightsmark 1024
                                w/o patch | with patch
                                240 | 330
                                lightsmark 1920
                                130 | 180
                                But mesa with this patch 90% of time shows me black screen, only text and one scene is rendered correctly.

                                R600_HYPERZ=1\0 don't change anything for lightsmark.

                                Comment

                                Working...
                                X