Announcement

Collapse
No announcement yet.

Intel HD 4000 Ivy Bridge Graphics On Linux

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

  • #46
    Thanks for the great article, Michael!

    For what it's worth, the VDrift stable release has a few bugs---it tries to use the texture2DLod function in the fragment shader, which isn't available unless you enable the GL_ARB_shader_texture_lod extension or use GLSL 1.30. Which it doesn't, so we say "no", and they get bad rendering. I went to go submit a patch for that (it is open source after all!), and it turned out that they already fixed it; they just haven't released an updated version. Git snapshots of VDrift seem to work just fine on Sandybridge/Ivybridge.
    Free Software Developer .:. Mesa and Xorg
    Opinions expressed in these forum posts are my own.

    Comment


    • #47
      This is one part of what we were waiting for.

      The other one is: We know that in Windows the Brazos platform destroys Atom. I'd like to see a comparison between Brazos and Atom, with both Catalyst and free drivers. I think Atom could destroy Brazos in Linux, thanks to better drivers.

      Comment


      • #48
        Originally posted by mikkl View Post
        I'm surprised how close AMD and Intel are in some of the tests. I thought AMD is much faster.
        The Intel HD4000 is a year newer then the tested AMD 6550D and still comes up short, in a few weeks AMD's new parts in the same price bracket will be out, with the even faster HD7660D http://www.legitreviews.com/news/12666/ So again to Intel, better luck next time guys.

        Comment


        • #49
          Well maybe compare intel vaapi against amd xvba (if you like xbmc fernet menta or via xvba vaapi wrapper) - then you know what chip is better...

          Comment


          • #50
            Originally posted by Kano View Post
            Well maybe compare intel vaapi against amd xvba (if you like xbmc fernet menta or via xvba vaapi wrapper) - then you know what chip is better...
            intel prolly wins hand down, well ofc unless michael finds an combination of settings and a video that xvba can actually render without quality loss or creepy render error or kernel lockups, but even then since the cpu parts is a lot faster than llano i think is hard to determine which one is more effective since cpu usage in IB should be shockingly low compared to llano even if the gpu part is more efficient in llano. so dunno it probably will be hard to tell

            Comment


            • #51
              mpeg2 is not accellerated with xvba, h264 l5.1 is also not possible with xvba. if you select other testfiles xvba should work. in theory there is a h264 encoder you can use via (intel) vaapi es well but i don't know if there is an app using is yet (besides the test tools from libva).

              Comment


              • #52
                Originally posted by Alejandro Nova View Post
                I think Atom could destroy Brazos in Linux, thanks to better drivers.
                By Atom, do you mean GMA3150 graphics? Not a chance. Even with the better drivers. GMA3150 is Gen3 hardware! When ValleyView arrives, then it'll get interesting. But only then.

                Originally posted by Kano View Post
                Well maybe compare intel vaapi against amd xvba (if you like xbmc fernet menta or via xvba vaapi wrapper) - then you know what chip is better...
                This ^
                If I were buying a laptop right now, I'd go with Intel. Strictly because of the better driver situation.

                Comment


                • #53
                  Originally posted by Gusar View Post
                  By Atom, do you mean GMA3150 graphics? Not a chance. Even with the better drivers. GMA3150 is Gen3 hardware! When ValleyView arrives, then it'll get interesting. But only then.

                  This ^
                  If I were buying a laptop right now, I'd go with Intel. Strictly because of the better driver situation.
                  GMA3150, with free drivers, versus Brazos, with free drivers, and with less than 1/10 of its theoretical performance, thanks to crappy free drivers.

                  I think it's perfectly possible. Brazos only wins over GMA3150 when using Catalyst.

                  Comment


                  • #54
                    I think you're seriously underestimating how much Gen3 graphics suck. I should know, I have a GMA950 in my netbook . I'm definitely looking forward to ValleyView.

                    Also, you can clock the Brazos GPU up when using the open radeon driver, can you not? That's the big issue in this test, Michael didn't clock up the Llano GPU.

                    Comment


                    • #55
                      my question about this tropic is simple: why in hell is the radeon driver 10 time slower than the Catalyst ?

                      50% slower ok... 70% slower maybe ok 80% slower OMG.... but 90+% slower? LOL HELL?--

                      whats going wrong in the radeon driver team ?

                      Comment


                      • #56
                        Originally posted by Qaridarium View Post
                        i just do have a question wen intel will jump on the galium3D train ?
                        Unless anything unforeseeable happens, I don't think this will happen.

                        Comment


                        • #57
                          Wow, the Trinity APUs should blow this thing away graphics-wise. And that's with the crappy AMD drivers. Assuming there are no major problems with it, of course.

                          Also, perhaps I missed it, but, why wasn't the Llano temperature shown? EDIT: Just realized this is probably due to the lack of driver support.

                          Comment


                          • #58
                            Originally posted by fuzz View Post
                            Wow, the Trinity APUs should blow this thing away graphics-wise. And that's with the crappy AMD drivers. Assuming there are no major problems with it, of course.

                            Also, perhaps I missed it, but, why wasn't the Llano temperature shown? EDIT: Just realized this is probably due to the lack of driver support.
                            Not sure if the CPU temperature is available/usable (http://www.kernel.org/doc/Documentation/hwmon/k10temp says it's supported, but maybe the kernel driver wasn't loaded), but GPU temp on my Llano is discoverable:

                            me@myLlanoMachine:/sys/class/drm/card0/device/hwmon/hwmon2$ cat temp1_input
                            31000

                            Comment


                            • #59
                              Originally posted by Qaridarium View Post
                              my question about this tropic is simple: why in hell is the radeon driver 10 time slower than the Catalyst ?

                              50% slower ok... 70% slower maybe ok 80% slower OMG.... but 90+% slower? LOL HELL?--

                              whats going wrong in the radeon driver team ?
                              has been explained like 50 times already just in this post, plz read the thread before ninja asking stupid question or maybe you are just trolling

                              Comment


                              • #60
                                Originally posted by Alejandro Nova View Post
                                GMA3150, with free drivers, versus Brazos, with free drivers, and with less than 1/10 of its theoretical performance, thanks to crappy free drivers.

                                I think it's perfectly possible. Brazos only wins over GMA3150 when using Catalyst.
                                And that'd be delusional, The Atom N series is paired with the 200Mhz version of the GMA3150, so thats 2 200Mhz OpenGL2 Pixel Pipelines and only support for MPEG2 acceleration vs 80 280Mhz OpenGL4.2/OpenCL1.1 shaders, even at 1/10th optimal performance the GMA3150 a POS. Especially when you look at the CPUs, the AMD Z-01 and C-50 are both real dual core 64-bit CPUs at 1Ghz, All the Pineview series save for the 2 top end N550 and N570 are single core with hyperthreading and as such they are the only ones that come close to the E-350, E-450 and E2-1800 in terms of raw CPU power.


                                As for MPEG2 performance, it's still not all that relevant since my decade old Pentium4 can handle it. Just rip your DVDs already, the optical drive is eating more of your battery on the current crop of low end CPUs.

                                Comment

                                Working...
                                X