Announcement

Collapse
No announcement yet.

AMD Driver Support State For Radeon HD 7000 Series, Trinity

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

  • #16
    Originally posted by Qaridarium View Post
    for R600 amd can't go this way because they are 5 years to late.
    but the new architecture is different they start with the open source driver 1 year before release.

    with the same staff for example 4 Dev's work 5 years longer on 1 driver and the result is? (only dump people think 4 dev's do nothing in 5 years).
    but why the same staff? now calculate with a bigger staff because of the windows port of the radeon driver +5years extra.
    and now imagine this: AMD's next gen Opteron Architecture is a "APU" based on this graphic architecture.
    AMD CPU company side makes up to 30% of there turnover on the Linux market.
    sure only 1-2% on the Desktop but much more on the server market and the next "Opteron" is a APU.
    do you think the server Linux (CPU) customers start to use closed source ? never! many CPU customers will not use a driver like catalyst.

    they focus on the opensource driver or the CPU customers will not use this Opteron-APU.
    Well, Bridgman said in a previous comment: "The current plan is to start a new driver for GCN, based on a stripped-down copy of the r600g code.".
    I.e. they didn't start the driver yet. It is the plan. So don't be so excited. I want this to be true also, but I don't want to be disappointed like the bulldozer fiasco.

    Comment


    • #17
      Originally posted by Drago View Post
      Well, Bridgman said in a previous comment: "The current plan is to start a new driver for GCN, based on a stripped-down copy of the r600g code.".
      I.e. they didn't start the driver yet. It is the plan. So don't be so excited. I want this to be true also, but I don't want to be disappointed like the bulldozer fiasco.
      "I.e. they didn't start the driver yet"

      You are just a ignorance person.
      I know they do have 2 devs coding on GCN for months.

      Also Bridgman is a liar if he claim they don't have already started to code the GCN driver.

      so please stop to be naive.

      Comment


      • #18
        Even if they did start the driver a while ago

        Mesa itself is years behind.

        I don't see AMD pushing a driver that doesn't even support OpenGL 4 for their brand new cards.

        Now, there may be something where they announce more support. Maybe in particular for Android - I could see how Mesa might be far enough along for that, and it would probably be a nightmare to try and port fglrx to it and slim it down enough to fit on a phone.

        Let's hope they announce they are opening up UVD, open sourcing their OpenCL work, adding a bunch of OSS developers, and committing to having the OSS drivers available at hardware launch time. All 4 of those would be pretty major announcements. I'd be very happy if any single one of those was the big announcement coming up.

        Comment


        • #19
          Originally posted by Qaridarium View Post
          You are just a ignorance person.
          I know

          ...

          Also Bridgman is a liar

          ...

          so please stop to be naive.

          Comment


          • #20
            Originally posted by Qaridarium View Post
            Also Bridgman is a liar if he claim they don't have already started to code the GCN driver.
            ???

            I said what the plan is. I didn't say if execution of the plan had started yet or not. Please don't call me a liar for something I didn't say.

            Originally posted by Qaridarium View Post
            I know they do have 2 devs coding on GCN for months.
            As I said earlier nearly all of the work has been on the kernel drivers. This discussion is about the userspace Gallium3D drivers.
            Last edited by bridgman; 12-08-2011, 11:46 AM.

            Comment


            • #21
              Originally posted by bridgman View Post
              ???
              I said what the plan is. I didn't say if execution of the plan had started yet or not. Please don't call me a liar for something I didn't say.
              read the word "if" i know you don't do this "stupid" claim.
              he claim that by trying to quote you and trying to interpret your words.

              In fact the execution of the plan had started month ago.

              thats the real point!

              Originally posted by bridgman View Post
              As I said earlier nearly all of the work has been on the kernel drivers. This discussion is about the userspace Gallium3D drivers.
              for me the kernel part is a part of this driver.

              Comment


              • #22
                Originally posted by Qaridarium View Post
                read the word "if" i know you don't do this "stupid" claim. he claim that by trying to quote you and trying to interpret your words.
                That was how I interpreted your post as well, but could you find another way to deliver that explanation ? Preferably one which does not involve even "conditionally" calling me a liar

                Originally posted by bridgman View Post
                As I said earlier nearly all of the work has been on the kernel drivers. This discussion is about the userspace Gallium3D drivers.
                Originally posted by Qaridarium View Post
                for me the kernel part is a part of this driver.
                I don't know how to respond to this
                Last edited by bridgman; 12-08-2011, 01:26 PM.

                Comment


                • #23
                  Originally posted by bridgman View Post
                  That was how I interpreted your post as well, but could you find another way to deliver that explanation ? Preferably one which does not involve even "conditionally" calling me a liar
                  Writing English is hard work for me. Write a valid conditionally sentence is even harder for me. I do not have the skill to write in your Public Relations fashion way.

                  Sorry if i conditionally hurt you.


                  Originally posted by bridgman View Post
                  I don't know how to respond to this
                  For me as a consumer there is no difference between different parts of the radeon driver in mesa and kernel because all parts must be completed.

                  And in fact compared to an hd2900 amd start 5 year earlier.

                  also the on next fusion apu is build with the new architecture.

                  and i'm sure the Opteron in 2013 will be this kind of APU.

                  Comment


                  • #24
                    Originally posted by Qaridarium View Post
                    Writing English is hard work for me. Write a valid conditionally sentence is even harder for me. I do not have the skill to write in your Public Relations fashion way. Sorry if i conditionally hurt you.
                    I try to write more "simply", ie if I disagree with something I say that and nothing more. Your English is probably as good as mine these days -- but if I tried to write as colourfully as you do I would probably have trouble too

                    Originally posted by Qaridarium View Post
                    For me as a consumer there is no difference between different parts of the radeon driver in mesa and kernel because all parts must be completed.
                    Agreed, but you were disagreeing with someone who said that work on the *mesa* driver might not have started.

                    Originally posted by Qaridarium View Post
                    And in fact compared to an hd2900 amd start 5 year earlier.
                    It's more like a couple of years, isn't it ? The HD2900 came out in mid-2007 and by mid-2008 we had started working on r6xx acceleration. I agree that it is a really important change though... starting before launch rather than 12-18 months after launch makes a *big* difference.
                    Last edited by bridgman; 12-08-2011, 02:30 PM.

                    Comment


                    • #25
                      Originally posted by bridgman View Post
                      I try to write more "simply", ie if I disagree with something I say that and nothing more. Your English is probably as good as mine these days -- but if I tried to write as colourfully as you do I would probably have trouble too
                      really? thank you. however the biggest different is i can't do this without help wikipedia/google/translator/spell checking in fact i use my computer as a brain prosthesis.

                      "colourfully" In Anbetracht der Tatsache dass mein Deutsch um ein vielfaches facettenreicher und komplexer ist, so erscheint es für mich traurig zu beobachten wie stümperhaft ich mich im englischem Sprachraum auszudrücken vermag, was dazu führt das dies der deinige Einwurf bezüglich des farbenfrohen Schreibens wie eine surrealistische Parodie auf mich wirkt in der es wohl kein platz für eine würdevolle selbst Reflexion gibt ohne vor Scham in den Boden zu versinken. (yes this is one single sentence in german)

                      Originally posted by bridgman View Post
                      Agreed, but you were disagreeing with someone who said that work on the *mesa* driver might not have started.
                      however all modern future graphic architectures are ray-tracing based over openCL this means mesa doesn't matter.

                      Originally posted by bridgman View Post
                      It's more like a couple of years, isn't it ? The HD2900 came out in mid-2007 and by mid-2008 we had started working on r6xx acceleration.
                      we talk about the architecture not the graphic cards.
                      wikipedia claims other facts than you:

                      german wikipedia translatet with google translate: "The architecture of the R600 graphics processors and their derivatives, which are used in the Radeon HD 2000-series are used, although it was never used in graphics cards for PCs, not entirely new. It is based in principle on the architecture of the Xenos GPU of the Xbox 360, which carried the codename R400."
                      about xbox360: "At the Game Developers Conference in March 2005 the unit was first introduced to the broad audience. [2] The official presentation took place on the 12th of the console May 2005 on the American television channel MTV, including the band The Killers instead. [3]"

                      also the radeonHD was a failure this means you should calculate with the radeon instead.

                      this means the architecture come out 2005 and you start the radeon driver in 2009-20010.

                      also the driver work for the Xenos GPU was done in 2004!!!!!

                      this means if you calculate the worst case its 5 years!

                      Originally posted by bridgman View Post
                      I agree that it is a really important change though... starting before launch rather than 12-18 months after launch makes a *big* difference.
                      yes you are right.

                      But please calculate again with the Xenos-GPU as the first gpu on the hd2000 architecture. and the driver work for the xenos back in 2004

                      In fact the new next gen GPU architecture will get 5 years more love.

                      Comment


                      • #26
                        I'm pretty sure xenos is something much closer to x800.... I could be wrong, but it definitely does not have a unified shader architecture. It definitely has pixel shaders, and I'm almost positive it has vertex shaders too.

                        EDIT: Well, I looked into it, and I guesss it does use a unified shader architecture. So I was wrong.
                        Last edited by duby229; 12-08-2011, 04:34 PM.

                        Comment


                        • #27
                          Originally posted by duby229 View Post
                          I'm pretty sure xenos is something much closer to x800.... I could be wrong, but it definitely does not have a unified shader architecture. It definitely has pixel shaders, and I'm almost positive it has vertex shaders too.

                          EDIT: Well, I looked into it, and I guesss it does use a unified shader architecture. So I was wrong.
                          LOOOOOOOOOOOOL nice try and funny to read

                          in fact i beat bridgman in this rhetorical battle !!!
                          the hd2000 architecture is the Xenos-GPU architecture.
                          this means there is more than 5 years different between starting the architecture and starting the opensource driver.

                          the next gen architecture coming in 1 month is the same new as the XENOS-GPU architecture was back in 2004.

                          this means 5 years earlier start in the opensource driver.

                          i like to push Bridgman

                          Comment


                          • #28


                            opensource friendly hd7970 is coming.

                            Comment


                            • #29
                              Its funny Bridgman stop writing instantly every time i make a good point.



                              my analysis:
                              the lifetime of the (Xenos/R600) architecture was from 2005-2011
                              and the development time was from 2004-2011 (in my point of view 2003)
                              the Dev time overall = 7 years.

                              claimed open source dev time 2008-2011 (in my point of view the radeonHD failure and the galium3D rewrite eat 1 year)

                              this means the new architecture are from 2012-2018 (dev time 2011-2018)
                              No RadeonHD delay and no galium3D rewrite PLUS some parts from the r600g driver is used. this save 1 year.
                              this means in real 8 years of dev time with twice as great team.

                              instead of the r600 2 years (3years) of dev time with the half as great team.

                              this means the next gen hardware driver will do have a 8 time bigger impact.

                              and I'm sure they will increase the dev team to focus on openCL for the Opteron customers. .

                              Comment


                              • #30
                                Originally posted by Qaridarium View Post
                                Its funny Bridgman stop writing instantly every time i make a good point.
                                It's too hard to type and facepalm at the same time

                                Seriously, if you're talking about the *last* GPU/APU in the GCN family I guess I sort of agree with your numbers, although you are ignoring the contributions of non-AMD developers which IMO invalidates the numbers completely.

                                I was talking about the *first* chip in the GCN family not the *last* chip and there the difference is smaller, although still significant.

                                RadeonHD and radeon always shared the kernel and 3D drivers, so I wouldn't take time off for that, but I agree that we don't need to go through the classic=>Gallium3D transition again so that does save some time.

                                This is all academic until I see triangles though...

                                http://www.phoronix.com/scan.php?pag...item&px=NjY3OQ
                                Last edited by bridgman; 12-09-2011, 06:45 PM.

                                Comment

                                Working...
                                X