Forgot your password?
typodupeerror
AMD Graphics Open Source

AMD's Open Source Linux Driver Trounces NVIDIA's 147

Posted by timothy
from the hari-seldon dept.
An anonymous reader writes "In a 15-way graphics card comparison on Linux of both the open and closed-source drivers, it was found that the open-source AMD Linux graphics driver is much faster than the open-source NVIDIA driver on Ubuntu 13.04. The open-source NVIDIA driver is developed entirely by the community via reverse-engineering, but for Linux desktop users, is this enough? The big issue for the open-source 'Nouveau' driver is that it doesn't yet fully support re-clocking the graphics processor so that the hardware can actually run at its rated speeds. With the closed-source AMD Radeon and NVIDIA GeForce results, the drivers were substantially faster than their respective open-source driver. Between NVIDIA and AMD on Linux, the NVIDIA closed-source driver was generally doing better than AMD Catalyst."
This discussion has been archived. No new comments can be posted.

AMD's Open Source Linux Driver Trounces NVIDIA's

Comments Filter:
  • Nice heading (Score:5, Informative)

    by Desler (1608317) on Thursday May 02, 2013 @11:33AM (#43610491)

    NVIDIA doesn't have an open source graphics driver... Nice misleading title there, timmy.

    • by somersault (912633) on Thursday May 02, 2013 @11:36AM (#43610529) Homepage Journal

      We're going to need another Timmy

    • by npridgeon (784063) on Thursday May 02, 2013 @11:38AM (#43610555)
      http://www.youtube.com/watch?v=IVpOyKCNZYw [youtube.com] Linus Torvalds explaining how much he loves Nvidia.
    • Re: (Score:2, Insightful)

      by Anonymous Coward

      yeah, i kind of read that as "nouveau" but you're right and that really needs to be changed because that would make people think Nvidia has an open source driver. I would also add "with no help from nvidia" or similar after "The open-source NVIDIA driver is developed entirely by the community via reverse-engineering," in the story to make their crapulence perfectly clear.

      • because that would make people think Nvidia has an open source driver

        Technically they do. They've got one for Tegra, and if you're really pedantic they've got an old abandoned one called nv.

    • Re: (Score:2, Insightful)

      by Tough Love (215404)

      "The open source driver for NVidia". Nouveau. NVidia does not need to "have" this driver for it to be open source. The contrary if anything. I can't for the life of me imagine a reason for your troll.

      • Re:Nice heading (Score:4, Insightful)

        by Desler (1608317) on Thursday May 02, 2013 @12:27PM (#43611081)

        You're the troll. The headline says:

        AMD's Open Source Linux Driver Trounces NVIDIA's

        This is elementary school level reading comrephension you failed at. There is no "for" in it at all.

        • by Anonymous Coward

          NVIDIA's what? Driver? what driver? Windows? OSX? Android? Oh, we're suppose to assume Linux Driver? What about Open Source Linux Driver? Does NVIDIA even have an Open Source Linux Driver? There is plenty of ambiguity in the statement and is simply not "elementary school level reading comrephension" fail. The failure is in your response.

      • by Desler (1608317)

        And to add the phrase "for NVidia" doesn't even appear in the summary. You invented that quote out of whole cloth.

      • by AdamWill (604569)

        The point is that AMD is writing an open source driver for its own hardware, about which it obviously knows everything. The Nouveau driver is being reverse engineered. It would be amazing if a third-party reverse engineered driver performed better than a first-party one. So the comparison is pretty unfair to the Nouveau devs, who are doing an excellent job given the limitations they're working with.

        It would just be a lot clearer if the summary noted these nuances and gave the story "AMD pretty good; Nouveau

    • Not only that, the Open Source drivers are basically slower in every way, despite what the summary seems to imply. This particular line from the article is especially depressing:

      "Sadly, the Nouveau kernel driver seems to regress quite frequently, still making it like a game of Russian Roulette in between major Linux kernel releases."

      Who knows what they are doing.

      • Re:Nice heading (Score:5, Insightful)

        by Kjella (173770) on Thursday May 02, 2013 @01:48PM (#43612039) Homepage

        Who knows what they are doing.

        Guessing. AMD provides specs, nVidia doesn't nor do they offer developer help. The hardware interface of graphics cards changes a lot since what people care about is compliance with DirectX and OpenGL, what happens behind the scenes between the driver and hardware isn't important. Lots of weird interfaces, lots of magic values, lots of bugs that don't appear in the closed source drivers because the driver and hardware team have agreed on just the right order to set it up and call it. Nouveau is fueled by "if you refuse to support open source, by god we'll make it work with open source" and all credit for that but it seems this is a tough enough mountain to climb without the blindfold. Personally I'd rather get behind one of the companies that actually support open source, but everybody do what they want. That's how it works.

        • I'm a pragmatist... I get behind the company who best supports their hardware on Linux, regardless of if the driver is open or closed source... I just want it to work dammit, and in my experience nVidia has always had more "just works" on Linux. AMD might "support" open source drivers and such, but I've always been very disappointed by the end result. So, if I want it to work on Linux, I buy nVidia, end of story.

          • Re:Nice heading (Score:5, Interesting)

            by Anonymous Coward on Thursday May 02, 2013 @02:14PM (#43612257)

            You know, there's more than just two video card vendors in the world.

            Intel's graphics are supported better on linux than either nVidia or AMD. Intel hired Keith Packard [wikipedia.org], for chrissakes, what more could you want in support?

            Now it's true nVidia's hardware is faster & more powerful - at the moment. But you didn't mention that, you just claimed (incorrectly) that "nVidia has always had more 'just works' on linux" with is completely false. Matrox cards worked better than nVidia in the old days, and Intel 'just works' better now.

            I'm a pragmatist - I use Intel graphics chips in my linux boxen - and I suggest you do the same. They just work.

            • by Anonymous Coward

              I'm a pragmatist - I use Intel graphics chips in my linux boxen - and I suggest you do the same. They just work.

              Sure, let me just run down to my local computer parts store and grab an Intel video card. Oh, what's that? Intel doesn't make discrete video cards? Guess I'm stuck with my onboard AMD/NVidia chip, then.

            • Except that Intel's GPUs just don't support some of their functionality on Linux. Like OpenCL. Or a modern OpenGL version.

              Right, you might not care, if your usage pattern is mostly about websites and text files. For me, nVidia GPUs are the *only* thing that both brings the functionality I need (as a GPGPU software developer) and actually works.

              AMD linux drivers are in a habit of losing functionality over time. Like all functionality (happened to me once). Others have complained that after updating the drive

              • OpenCL [phoronix.com] is coming (not that there's much point, even their Windows version seems slower than just running OpenCL on the CPU from what I've read [tomshardware.com]), and they're catching up with OpenGL version support. What apps do you use on Linux that actually require the newer versions of OpenGL?
            • > what more could you want in support?

              Let's see, 3D Performance on a Discrete card. For all the billions they make they STILL can't make a discrete (or mobile) GPU worth a crap. Also, OpenCL on Windows, OSX, and Linux.

              Meanwhile, almost everybody else in Scientific Computing is using (nVidia's) CUDA across all 3 platforms. /Oblg. Sad but true.
              http://media.bestofmicro.com/V/6/233106/original/feature_image09.jpg [bestofmicro.com]

              • For all the billions they make they STILL can't make a discrete (or mobile) GPU worth a crap

                HD 4000 is fairly decent for a mobile chip, and Iris from Haswell is looking pretty good from the previews.

                Also, OpenCL on Windows, OSX, and Linux.

                Ivy Bridge does OpenCL on Windows, Linux support is coming. Performance isn't worthwhile [tomshardware.com] though.

          • by kasperd (592156)

            I get behind the company who best supports their hardware on Linux, regardless of if the driver is open or closed source... I just want it to work dammit

            The only way to get hardware which "just works" with Linux is if the driver is in the mainline kernel. And to be in the mainline kernel it has to be open source. There is no such thing as a closed source driver which "just works", because part of the requirement for earning that label is that it also works after kernel interfaces have been changed in a way,

        • None of that explains why their drivers break between kernel versions.
          • The kernel changing explains why the drivers break between kernel versions...
            • Except the NVidia drivers don't have the same problem. I've looked at the graphics driver section of the kernel, and I don't think it changes THAT much. I could be wrong, though.
    • Re:Nice heading (Score:5, Insightful)

      by abrotman (323016) on Thursday May 02, 2013 @01:06PM (#43611587)

      And who is to blame for that? nVidia could release specs and work with the OSS community.

  • 1) unfair comparison
    2) old news
    3) 100% nvidia's fault

  • Same old shit as always (DNRTFA).

    I'm tainting my pure and virgin kernels since about 10 years with the evil corporate drivers from Nvidia, because it works and performs. Sorry Gnu!

    • No shit. Fact is, Nvidia, with their closed-source binary-blob driver, STILL supports Linux better than ATI/AMD did/does. "Purity" is overrated, and variable, depending on who's doing defining it.
      • by KugelKurt (908765)

        No shit. Fact is, Nvidia, with their closed-source binary-blob driver, STILL supports Linux better than ATI/AMD did/does. "Purity" is overrated, and variable, depending on who's doing defining it.

        "Purity" means that the drivers work out of the box under all Linux distributions. The proprietary drivers must be re-installed every time a kernel upgrade is done which, depending on the Linux distribution, can be quite often.

    • Re:In other words: (Score:5, Interesting)

      by Andy Dodd (701) <atd7&cornell,edu> on Thursday May 02, 2013 @12:06PM (#43610863) Homepage

      Yup. I still buy NVidia cards because they ACTUALLY WORK and they do a reasonable quality control effort on their drivers.

      As opposed to AMD/ATI's drivers. Every time I've gone near a Radeon it's been nightmare driver hell, whether the platform is Linux or Windows. (Yeah, they can't even get their Windows drivers right. It should be the exception and not the norm that game A requires driver version Y and above, but game B requires drivers Z and below, where Z Y, because AMD/ATI don't comprehend regression testing - but every time I've worked with an AMD/ATI graphics chipset, that shit is normal.)

      • by Torp (199297) on Thursday May 02, 2013 @12:27PM (#43611075)

        Agreed. There's no point in looking at anything but NVidia with their proprietary drivers if you want 3D performance and stability on Linux.

      • Re:In other words: (Score:4, Insightful)

        by hairyfeet (841228) <bassbeast1968@ g m a i l.com> on Thursday May 02, 2013 @02:52PM (#43612611) Journal

        I'm sorry but I have to call bullshit as the Windows drivers have been nothing but rock solid since AMD bought them out and cleaned up the cruft. if you are talking pre-buyout? Then sure i agree 100% as ATI couldn't write a driver to save their lives but AMD fixed the messes (requiring .NET bullshit for the driver GUI? Really ATI?) and since then I've been using AMD cards exclusively in the shop and they have been nothing but stable.

        If anybody could tell you if there was a problem with the drivers it would be me as I've put everything from the low end 3200 and 4200 IGPs to the X2s to the 7770s through their paces at the shop and its been nothing but blue skies and rainbows and at home me and both the boys have HD4850s and they just purr like kittens, not a complaint one.

      • by KugelKurt (908765)

        Yup. I still buy NVidia cards because they ACTUALLY WORK and they do a reasonable quality control effort on their drivers.

        Really? So the 310.x and newer NVidia drivers don't actually crash when trying to initialize OpenGL on my GeForce 9200?

  • fine, don't open source the drivers but at least open up the video card hardware so dev's can write their own drivers. Intel and amd cpu's are open why not gpu's.

    • Re:hum (Score:4, Funny)

      by Narcocide (102829) on Thursday May 02, 2013 @11:51AM (#43610705) Homepage

      Probably because that's where Hoffa's body is buried or something.

    • Those are excellent questions to ponder every now and then. Would releasing full specs of the hardware to OSS coders reveal too much of secrets about the hardware? Would having an full-feature open source driver actually hurt or improve business? Why does Intel have no problem having a relatively open driver development?
      • Re:hum (Score:5, Interesting)

        by Anonymous Coward on Thursday May 02, 2013 @12:12PM (#43610915)

        I work for a semiconductor company, not one of the three mentioned above. I've worked on video drivers for our GPU as well.
        nVidia won't open source their drivers because it opens them up to patent lawsuits.
        Undoubtedly nVidia is using some crap that is patented by someone else in their hardware and software. Only a fool thinks they won't be sued by someone, even if it's bogus. AMD and Intel have been very careful on how they release and what they release. It's an expensive (in lawyer time) proposition and nVidia doesn't care to spend the money.

      • Re:hum (Score:4, Insightful)

        by westlake (615356) on Thursday May 02, 2013 @12:19PM (#43610985)

        Would having an full-feature open source driver actually hurt or improve business?

        In the high-end consumer market who cares about the open source driver other than the open source purist?

        • by SuseLover (996311)

          Would having an full-feature open source driver actually hurt or improve business?

          In the high-end consumer market who cares about the open source driver other than the open source purist?

          Hmm, "who cares about the high end consumer market"? What about the high end professional market? I have worked in several engineering departments where ALL development is done on Linux/Unix boxes and high end graphics are a must (EDA IC design tools for instance). I'm sure there are many more (closed source) applications that run on open source systems that need high end graphics performance and the engineers demanded the performance/features needed.

          Every time I have tried to use the Nouveau drivers,

        • by MrHanky (141717)

          Anyone who cares about simplicity, reliability and stability.

      • Well the last question is answered easily enough. Intel doesn't compete for features or performance in the GPU market, just price per unit and to some extent energy efficiency. They have no secrets that open drivers would reveal.

      • by Desler (1608317)

        Intel has no problem because their business isn't selling GPUs.

      • by Kjella (173770)

        Would releasing full specs of the hardware to OSS coders reveal too much of secrets about the hardware?

        The internal documentation would reveal way too much about the hardware, not just where they are but where they're going, so could the driver code and comments. It only takes one /* Will be done through/fixed by XYZ in next gen */ to potentially reveal important information on unreleased products. Could you strip it down to something terse that only says exactly what needs to be said in order to use it and nothing more? Maybe, but that's a lot of lawyer food. Instead AMD has mostly chosen the opposite appro

      • Closed or controlled-as-in-android OS means forced obsolescence is way easier. Do you think hardware makers would keep subjecting themselves to MS Apple and Google now that alternative ecosystems cover A LOT of use cases?
        This explains 3d, secure boot, acpi and other annoying problems that were not present when I was installing ppc linux on a powerbook in 2003.

    • by xaoslaad (590527)
      Probably because the 8 cents of PCB and 12 cents of metal on a new $500 GPU is not justified, even after R&D costs. Imagine if other people could enter the market and make $100 or $200 dollar top of the line cards. They're just trying to keep things status quo for their Oligopoly.
      • by kermidge (2221646)

        Curious where you got those numbers.

        As of 1 May, copper spot was, what, $3.12/lb. That's down from when I bought my nVidia 460GTX, which surely has more than an ounce of copper in the heat sink/radiator alone. Add in all the metal in all the other parts. Add in actual cost of parts, including processor and memory, assembly, I'm guessing there's easily more than 20 cents worth of stuff.

        I realize you may have been using those numbers for hyperbole, but still seems off-kilter to me.

        But now you've got me won

  • I would have preferred benchmarks on Windows game performance in WINE. Sure, that would have added some extra configuration problems to the benchmarks, but those are the numbers I really care about as a Linux user that keeps a Windows boot around just for games. From my experience, that's also where AMD cards take a shit, whether using open or closed source drivers (sometimes it's performance, sometimes it's game-breaking bugs that don't affect nvidia cards).
  • Maybe the Open Source driver does not support all the same features the NVidia one does?

    I mean who can see from their screen if the GPU really did all of the 100+ flashy named video processing tasks and whatever else it was supposed to do?
    Maybe it flunked on a certain texture-whatever effect and did a faster, almost as good one?
    Maybe NVidia puts more auxillery tasks on the GPU, like physics stuff?

    How can we compare the 2 drivers, when one of them is closed? And they dont even run on the same cards for AMD/NVidia...

    • by Hatta (162192)

      If you can't see the difference, does it matter?

    • by KugelKurt (908765)

      Every NVidia owner who uses Ubuntu, Fedora, etc. for at least one session.
      Most distributions don't bundle proprietary drivers.

  • by DMJC (682799) on Thursday May 02, 2013 @12:48PM (#43611343)
    I'm going to weigh in here. The Nouveau drivers are better than the open source ATi drivers. Simply because, the performance doesn't matter. It's the feature completeness of the drivers that matters. The Nouveau drivers have been very steadily working towards a point where all previous generation cards and the current generation cards have the same feature set at the same time. If you check out the nouveau feature matrix it's a stunning achievement how rapidly they've come to the point they're at. People don't seem to realise that aside from SLI, OpenCL and the hardware reclocking support. The Nouveau drivers are basically feature complete. Noone uses TV out anymore since HDMI/digital video has taken over. Within 2-5 kernel revisions, the reclocking stuff is going to be completed. When that hits, the Nouveau drivers are going to shatter the AMD ones for performance. Already in preliminary testing where reclocking was enabled, the Nvidia cards were performing at or above the level of the nvidia binary blob. When the reclocking support is turned on these cards are going to be running OpenGL 3.3 and probably pushing a lot of GL4 features. The interesting thing is if you check the status matrix, the same level of support exists in current high-end leading Nvidia graphics cards as in the previous generation's cards. This means that the nouveau driver appears to be similar to the Nvidia blob in that it's adapted to support multiple graphics card models easily.
    • I very much hope you are right.
    • by Rich0 (548339)

      Noone uses TV out anymore since HDMI/digital video has taken over.

      I was using it on an Nvidia mini-ITX motherboard only a few months ago. It won't be obsolete until the last analog TV dies. Considering that TVs last about a decade and HD only really took over a few years ago I'd say that TV-out has at least a few years left in it. That said, other than 2D codec support I doubt there is that much need for acceleration. The main use case for TV-out is to hook a PC up to a TV as a media player.

    • by antdude (79039)

      I still use TV out with my 19.5" CRT Sharp TV from January 1996! As for monitors, they're all old and LCD.

    • by higuita (129722)

      the most advanced open 3D drivers are from intel.
      AMD takes the common parts (like most of the mesa code) from intel and add support for radeon GPUs. This helps a lot the driver development.
      Nouveau people have to that also, but they have first to do guess work to enable the features.

      So you are saying that nouveau, with years of missing work and many missing features, compared to the other two GPUs will have more and better features in a few months/years? are you on drugs? :)
      the other drivers will not stop wa

  • Nothing has changed in a couple of years regarding the relative performance of the open source kernel drivers for NVidia and ATI cards and their closed source binary counterparts.

    Given similar and modern hardware, the open source ATI driver is much better in several areas including general performance and ease of installation. I believe this is due to ATI publishing specs to a much greater extent, and I think they even have (had?) employee(s) dedicated to developing the OSS driver that ships w/the kernel
    • Re: (Score:3, Interesting)

      by Lonewolf666 (259450)

      That's not entirely true.

      In some individual tests in the benchmarks on Phoronix.com, the latest open source ATI drivers reach now 80-90% of the performance of the closed source drivers (most are still at something like 30%).

      Maybe 2 years ago, the best individual test results were something like 30% of the performance of the closed source drivers. Benchmarks that would not run at all on the open source side were a lot more common that today (although Phoronix may since have settled on tests that are known to

  • It's just too bad that both open source drivers are still nowhere close to matching their proprietery couterparts.
  • I gave up on reading Phoronix because they report on nothing but benchmarks when those are very uninteresting from a Linux perspective unless things fall way behind. There are plenty of non-Linux sites benchmarking hardware. What we need in a Linux review site is someone focuesed on compatibility, stability and ease of configuration.

    • by KugelKurt (908765)

      I agree that the Phoronix benchmarks are mostly stupid but the site also covers lots of stories other publications don't. Michael reads through git commit logs, has subscriptions to mailing lists of exotic Linux-related projects, etc. and he reports what he finds.

      Filtering out the benchmark stories is still easier than to subscribe to all those mailing lists and search for useful info.

      I take Phoronix over OSNews any day...

    • by cas2000 (148703)

      I stopped reading Phoronix because he never fucking links to external sites. Lots of links to other articles on phoronix but almost never a link to the original source of whatever he's crapping on about. it's just one big fucking circle-jerk.

      also, the constant stream of pointless benchmarks and articles about i-am-so-great-because-i-guessed-about-steam-on-linux-first are just plain boring.

  • I see nobody has mentioned FreeBSD and Kernel Mode Switching. Problem is that some time ago in a galaxy not far away the authors of opensource Radeon driver decided to abandon UMS in favor to KMS which obviously required card-specific code in OS kernel of every OS that uses the card. FreeBSD folks work hard, but my Radeon supermeganotebook that costs me a fortune still collects dust, and I have been forced to sell my Radeon, buy Geforce and use proprietary drivers. They suck - they have some issue with fram

"In matters of principle, stand like a rock; in matters of taste, swim with the current." -- Thomas Jefferson

Working...