Announcement

Collapse
No announcement yet.

Rich Geldreich: A Bad Catalyst GL Driver Is Bad For Everyone

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

  • #16
    What all of you little ignorant posters from the outer space don't know or don't probably think is that the next OpenGL iteration will probably be what Mantle is now. AMD is a big supporter and developer in Khronos Group. Their driver tries to closely follow the standard (although with not much success) and has promoted a lot of ARB extensions.

    OpenGL 5 "Mantle profile" and that profile currently has some engines supporting it.

    Comment


    • #17
      Originally posted by stalkerg View Post
      I wrote about workers.
      They say several times they will not drop Catalyst driver for Linux because they have enterprise customers who use it, the same goes with the opensource driver, etc... so workers will have what to do: like supporting next generation hardware, Mantle maybe, etc. But OK i guess they can manage some devs time for the opensource driver if help is wanted/needed .

      Comment


      • #18
        Graham Sellers (AMD's OpenGL guy) said this in a recent tweet (about the Phoronix article with the benchmark):

        Originally posted by Graham Sellers
        Point completely missed, I guess. This was never about vendor vs. vendor, but about technique vs. technique.
        My lesson learned... "Don't tell developers how to optimize their applications unless you also beat NV."
        Full conversation: https://twitter.com/thatjimblack/sta...15058634014720

        Comment


        • #19
          I wish GL detractors would also mention that the problem is multiplied by the orthogonal OpenCL support-- and I do mean right angles. It's the same driver and the different companies have different non-overlapping priorities, again.

          Comment


          • #20
            Originally posted by dungeon View Post
            Devs just needs reliable API which fast & reliable on most vendor implementation, common thing as they can target majority of people with no problem, etc... so they want just that to be easy and easy supportible for them, with not so much vendor diversity included .
            DirectX: Window only api slower than Mantle and New Opengl methods, Dx12 would be faster but is not out yet.

            Mantle: It's faster than DX but only works on WINDOWS using AMD GCN hardware, is not open and even the documentation is under nda.

            Opengl: Open, works on almost everything (Operating systems and hardware from desktop to mobile devices) is as fast as Mantle on Nvidia cards but too slow on Intel and AMD hardware.

            Metal: Not enough information yet...

            And sadly the more "reliable" api for AMD, Intel and Nvidia hardware is DirectX.

            Comment


            • #21
              Sdar: I thought Mantle was only on AMD gpus for now, how could you compare it to OpenGL on nVidia GPUs? Even then, comparing APIs can be somewhat difficult if you aren't familiar with all the API specific optimizations.

              Comment


              • #22
                Originally posted by dungeon View Post
                They say several times they will not drop Catalyst driver for Linux because they have enterprise customers who use it, the same goes with the opensource driver, etc... so workers will have what to do: like supporting next generation hardware, Mantle maybe, etc. But OK i guess they can manage some devs time for the opensource driver if help is wanted/needed .

                Ok, will not drop Catalyst but need freeze.

                Comment


                • #23
                  I remember there being talk of merging as much code as possible into the open source AMD driver and then anything else would be an optional closed-source module or something, any word on that? I'll try finding the article.

                  EDIT: Well that wasn't hard to find: http://www.phoronix.com/scan.php?pag...atalyst_kernel
                  Last edited by chinoto; 06-17-2014, 11:38 AM.

                  Comment


                  • #24
                    Originally posted by Sdar View Post
                    DirectX: Window only api slower than Mantle and New Opengl methods, Dx12 would be faster but is not out yet.

                    Mantle: It's faster than DX but only works on WINDOWS using AMD GCN hardware, is not open and even the documentation is under nda.

                    Opengl: Open, works on almost everything (Operating systems and hardware from desktop to mobile devices) is as fast as Mantle on Nvidia cards but too slow on Intel and AMD hardware.

                    Metal: Not enough information yet...

                    And sadly the more "reliable" api for AMD, Intel and Nvidia hardware is DirectX.
                    Being fast is not the same as being reliable . For example, most reliable OpenGL implementation and close to the OpenGL specs is Mesa actually .

                    In all those implementation and APIs you mentioned something is fast, something is slow and something is unavailable (and there are bugs of course, in diferent implementation bugs are in different areas - that happens all the time) . Question about which most users care: is it supported, and if it is - is it smooth, and in the and is it working acceptible fast on my chip in scenario I need to use .
                    Last edited by dungeon; 06-17-2014, 12:02 PM.

                    Comment


                    • #25
                      Originally posted by Filiprino View Post
                      What all of you little ignorant posters from the outer space don't know or don't probably think is that the next OpenGL iteration will probably be what Mantle is now. AMD is a big supporter and developer in Khronos Group. Their driver tries to closely follow the standard (although with not much success) and has promoted a lot of ARB extensions.

                      OpenGL 5 "Mantle profile" and that profile currently has some engines supporting it.
                      Are you making an informed comment here, or an educated guess? What Mantle profile are you talking about?

                      Comment


                      • #26
                        Originally posted by chinoto View Post
                        Sdar: I thought Mantle was only on AMD gpus for now, how could you compare it to OpenGL on nVidia GPUs? Even then, comparing APIs can be somewhat difficult if you aren't familiar with all the API specific optimizations.
                        read my post again:
                        Originally posted by Sdar View Post
                        Mantle: It's faster than DX but only works on WINDOWS using AMD GCN hardware, is not open and even the documentation is under nda.
                        I already know is only for AMD GCN cards and that is only working on WINDOWS.

                        But it's a graphical api as dx is even if they don't support all the Operating systems or hardware.

                        Originally posted by dungeon View Post
                        Being fast is not the same as being reliable .
                        And that's why i said that DX is the most reliable api for all three major vendors (AMD, Intel and Nvidia) even if it's slower than mantle, Opengl and probably metal and it's a windows only api.

                        Comment


                        • #27
                          i like too see something

                          directx drivers by amd suck too, blame amd not opengl or others

                          Comment


                          • #28
                            Originally posted by sarmad View Post
                            Are you making an informed comment here, or an educated guess? What Mantle profile are you talking about?
                            I'm making an educated guess. Their API continues being high level, they've added more control to the programmer but you're still calling hardware independent functions, like in a console.
                            AMD will get this API tested with some games and could end being standardized as a new version of OpenGL once it's mature enough.

                            Comment


                            • #29
                              Originally posted by haplo602 View Post
                              The test is not relevant to anything byt high-end gamers.
                              Gosh, and who'd have thought that someone from a game development background might be interested in being able to reliably support high-end gamers?

                              Comment


                              • #30
                                I am not a programmer, but Mr. "Moneyrich" is starting to sound pretty profane.

                                They are "implementations", per definition they will differ. Throw any other, especially closed source, API performing via, especially closed source, driver, on a, especially proprietary hardware - they will outcome with different quality.
                                I never heard AMD and Nvidia has joined effort to make their driver peform at equal speed, why the heck they even make hidden micro-optimizations/shortcuts.......
                                My face is like -____________________- now

                                Comment

                                Working...
                                X