Announcement

Collapse
No announcement yet.

The State Of ARM SoC GPU Linux Drivers

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

  • The State Of ARM SoC GPU Linux Drivers

    Phoronix: The State Of ARM SoC GPU Linux Drivers

    Here's an interesting interview concerning the state of open-source Linux SoC graphics drivers...

    http://www.phoronix.com/vr.php?view=MTM1OTM

  • #2
    Interesting read, even if none of them go into great detail...

    I'm quite interested in this, having an Android cell phone with an Adreno200 gpu (and hard keyboard--a Venture, to be precise)
    ...anyone have an idea how you get X started from there? Or pointers towards where to look?

    Also, it's interesting to note the state of etna_viv, since it's now also targetting the JZ4760/4770, which is what all the cheap MIPS ICS/JB tablets have.

    Comment


    • #3
      How come we've never seen open GPU hardware? I understand that it wouldn't be easy, but is it at all feasable? Nvidia, ATI and the various SOC vendors offer poor OSS support, Intel is underpowered, why hasn't someone just made their own hardware for Linux which is completely open, maybe through Kickstarter or something?

      Comment


      • #4
        Originally posted by kaprikawn View Post
        How come we've never seen open GPU hardware? I understand that it wouldn't be easy, but is it at all feasable? Nvidia, ATI and the various SOC vendors offer poor OSS support, Intel is underpowered, why hasn't someone just made their own hardware for Linux which is completely open, maybe through Kickstarter or something?
        They tried: Project VGA and the Open Graphics Project. Michael wrote about it here. I'm not sure what's happening with the Open Graphics Project.

        Comment


        • #5
          It's great that there are people working on open drivers for most GPU archtectures, but at the same time I wonder if it wouldn't be more efficient to choose the most friendly one and have them all working on just this one in order to have something close to fully feature working really well. If this particular GPU gets more design wins or sells more because of that open driver, then the other hardware makers might be compeled to also embrace open source.

          Obviously most of them are working on their free time, so nobody gets to tell them what to do, and I guess they have a better chance at "making a name" for themselves if being the one and only developer o a certain component, instead of a member of a group. Anyway, just food for thought.

          Comment


          • #6
            Originally posted by Figueiredo View Post
            It's great that there are people working on open drivers for most GPU archtectures, but at the same time I wonder if it wouldn't be more efficient to choose the most friendly one and have them all working on just this one in order to have something close to fully feature working really well.
            For me, the reason why I started with Tegra instead of just helping out with Mali is that I'm NDA-contaminated. So helping out an existing project wasn't an option.

            Comment


            • #7
              Originally posted by Figueiredo View Post
              It's great that there are people working on open drivers for most GPU archtectures, but at the same time I wonder if it wouldn't be more efficient to choose the most friendly one and have them all working on just this one in order to have something close to fully feature working really well. If this particular GPU gets more design wins or sells more because of that open driver, then the other hardware makers might be compeled to also embrace open source.

              Obviously most of them are working on their free time, so nobody gets to tell them what to do, and I guess they have a better chance at "making a name" for themselves if being the one and only developer o a certain component, instead of a member of a group. Anyway, just food for thought.
              What makes you believe that we are not working on the most friendly GPUs?

              I picked the Mali early 2011 as i assumed this had the most promising future ahead of itself, being ARMs own GPU. Rob Clark, working for Ti and Linaro at the time, chose Adreno, as his legal position towards Mali was questionable (linaro being largely sponsored by ARM), and he, like me for my N9 work, had access to the PowerVR source and then some. Both Erik Faye-Lund and Wladimir J Van Der Laan first approached me with the intent to work on PowerVR. I successfully convinced them to look elsewhere. Erik was first, and the Tegra was the best candidate then. When Wladimir came round, Vivante was simply waiting for him.

              Yes, we might seem to be spreading resources around, but at the same time we are limiting ourselves to the 4 sane GPUs, and ignoring PowerVR and other implementations. What happened for Videocore happened outside my sphere of influence, i personally would never have touched that hw with a 10ft pole, and i must applaud the fearless Videocore guys for undertaking a job which is even an order of magnitude harder than what we have to deal with on the 4 normal GPUs.

              Why 4 and not 1? Well, each of the people tackling each of those GPUs wanted to take this insane task from start to finish, not just finish what someone else already did. Plus, these 4 GPUs all have decent positions in the market, and they are sane and nice and each worthy of an open source driver. By spreading around across just those 4, we have a good chance of some degree of success on some. The way things are looking now means that we will be successful on all 4, but that we just need a bit of time to finish the massive task that is REing a GPU, and then writing a proper driver for it.

              So don't blame us for being slow on delivering, we are tackling an unbelievably time-consuming task, in our spare time. Don't be impatient if all you intend to do is talk about us not having delivered yet.

              Comment


              • #8
                Originally posted by kaprikawn View Post
                How come we've never seen open GPU hardware? I understand that it wouldn't be easy, but is it at all feasable? Nvidia, ATI and the various SOC vendors offer poor OSS support, Intel is underpowered, why hasn't someone just made their own hardware for Linux which is completely open, maybe through Kickstarter or something?
                Isn't Intel HD4000 several times faster than any currently available GPU in any ARM SoC? The only reason to use ARM SoC is low power consumption.
                Honestly I don't see why would someone spend nights and days with reverse engineering of Mali, Adreno, PowerVR etc. when ValleyView is going to be available soon with Gen7 graphics and open source drivers.
                Last edited by atom01; 04-26-2013, 12:10 PM.

                Comment


                • #9
                  Man, Emmanuel Deloget should really spell-check his posts. That "powerfull" is really annoying...

                  Hmm, yea, the four projects are indeed distinct in some fashion. Etnaviv has a partially open-source driver to look at, Grate also has that now, Freedreno has radeon documents to look at. And Lima, well, it was first, I believe. And it got lucky with the whole optimised hardware deal. The Videocore drivers are there just because the Raspberry Pi uses it, and it was made with the idea of letting people tinker with things, so it's a natural target.

                  Comment


                  • #10
                    Originally posted by atom01 View Post
                    Isn't Intel HD4000 several times faster than any currently available GPU in any ARM SoC? The only reason to use ARM SoC is low power consumption.
                    Honestly I don't see why would someone spend nights and days with reverse engineering of Mali, Adreno, PowerVR etc. when ValleyView is going to be available soon with Gen7 graphics and open source drivers.
                    By that reasoning, why bother working on opensrc drivers other than for nv or radeon hw, since those gpu's are faster still ;-)

                    Comment


                    • #11
                      Originally posted by robclark View Post
                      By that reasoning, why bother working on opensrc drivers other than for nv or radeon hw, since those gpu's are faster still ;-)
                      Good question indeed.

                      Comment


                      • #12
                        Originally posted by atom01 View Post
                        Good question indeed.
                        I'm not entirely sure if you completely missed my point, or if you are just trolling.

                        Comment


                        • #13
                          Please don't mind. I assure you guys that the majority of us appreciate the hard work you guys are doing. I myself have several products with differing versions of Adreno, so I am very much looking forward to that driver.

                          Comment


                          • #14
                            Originally posted by libv View Post
                            What makes you believe that we are not working on the most friendly GPUs?

                            I picked the Mali early 2011 as i assumed this had the most promising future ahead of itself, being ARMs own GPU. Rob Clark, working for Ti and Linaro at the time, chose Adreno, as his legal position towards Mali was questionable (linaro being largely sponsored by ARM), and he, like me for my N9 work, had access to the PowerVR source and then some. Both Erik Faye-Lund and Wladimir J Van Der Laan first approached me with the intent to work on PowerVR. I successfully convinced them to look elsewhere. Erik was first, and the Tegra was the best candidate then. When Wladimir came round, Vivante was simply waiting for him.

                            Yes, we might seem to be spreading resources around, but at the same time we are limiting ourselves to the 4 sane GPUs, and ignoring PowerVR and other implementations. What happened for Videocore happened outside my sphere of influence, i personally would never have touched that hw with a 10ft pole, and i must applaud the fearless Videocore guys for undertaking a job which is even an order of magnitude harder than what we have to deal with on the 4 normal GPUs.

                            Why 4 and not 1? Well, each of the people tackling each of those GPUs wanted to take this insane task from start to finish, not just finish what someone else already did. Plus, these 4 GPUs all have decent positions in the market, and they are sane and nice and each worthy of an open source driver. By spreading around across just those 4, we have a good chance of some degree of success on some. The way things are looking now means that we will be successful on all 4, but that we just need a bit of time to finish the massive task that is REing a GPU, and then writing a proper driver for it.

                            So don't blame us for being slow on delivering, we are tackling an unbelievably time-consuming task, in our spare time. Don't be impatient if all you intend to do is talk about us not having delivered yet.
                            Please don't take my comments as criticism. I'm in no position to tell you guys what to do and I certainly apreciate your work. My point was just trying to discuss the politics behind it all. You do have very valid points.

                            Comment


                            • #15
                              Originally posted by GreatEmerald View Post
                              And Lima, well, it was first, I believe. And it got lucky with the whole optimised hardware deal.
                              Well, I think, based on what libv has said and my experience (working on shaders), that we got lucky with the command stream and unlucky with the shaders. As libv proved with the Q3A demo, it's (relatively) easy to write an efficient driver for the mali cmdstream format. What flatmush and I discovered, though, is that the vertex shader and fragment shaders ISA's are much more complex and difficult to write an optimizing shader compiler for. I'm working on it though, and at the very least it won't be that hard to take what we have and write a very basic compiler for a Gallium driver.

                              Comment

                              Working...
                              X