Slashdot Mirror
AMD's Open Source Linux Driver Trounces NVIDIA's
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."
NVIDIA doesn't have an open source graphics driver... Nice misleading title there, timmy.
wow, what a subject line. for the oss community to be able to get hw acceleration through reverse engineering is impressive!
this isn't network/disk i/o hardware. opengl is a very complex api. it took nvidia years to get their ogl drivers into stable working order (without reverse engineering).
Access to the documentation of the hardware you are writing a driver for helps when writing the driver. If the OSS driver programmers are as good as the manufacturer's, or even slightly better, you'd still expect the manufacturer to produce better drivers simply because they don't have to waste their time to figure out how to access the hardware. Instead of experimenting some extended time, they just have a look in the internal hardware manual.
If the OSS drivers are better than the manufacturer's without the manufacturer opening up the relevant documentation, it usually means that either the hardware is outdated, or the manufacturer's programmers did a really bad job, or both.
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?
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.
Not entirely.
AMD's main drivers are proprietary, but they have open specs making it much easier for the community to write open source drivers, and they also assist the community in making those drivers.
NVIDIA neither opens their specs or assists in the development of the open source drivers.
That the open source AMD drivers would trounce the open source NVIDIA drivers is about as surprising as the Daily Mail finding something causes cancer.
I stole this Sig
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.)
retrorocket.o not found, launch anyway?
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...
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.
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?
I've never had a problem with the Nvidia driver. I don't know about AMD's driver because it sucked so bad back a few years ago that I didn't bother ever trying it again. I might buy an AMD board and try it again now.
Agreed. There's no point in looking at anything but NVidia with their proprietary drivers if you want 3D performance and stability on Linux.
I apologize for the lack of a signature.
More than that, the actual headline should have been:
Drivers with complete support for hardware features outperform drivers with partial support.
Even the summary says that the Nvidia reverse-engineered driver doesn't support adjusting the GPU's clock, and since Nvidia's firmware has the thing clocked to "barely running" when it starts up, it's hardly a shock that you get piss poor performance.
Obligatory car analogy: reverse engineering the ECU firmware on an engine, except in your version the rev limit is set to 1500 RPM, when the engine redlines at 8000; and then you wonder why you're short on horsepower and torque.
Slashdot still doesnâ(TM)t support Unicode after it was added to the HTML standard in 1997.
The complexity of OpenGL itself may or may not be the issue. To the best of my understanding; both nouveau and the AMD OSS drivers use Gallium3d and Mesa(which can also provide an openGL implementation entirely in software, if you don't mind a lot of waiting). Actually taking advantage of the specialized hardware in a fast and stable way, though, is device specific.
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.
He's talking about on Linux. The old ATI Linux drivers were notoriously bad for years, and while they've gotten better since AMD bought them, they still fall short of nVidia's reliability and capability, regardless of the performance of the hardware itself. If you just want a graphics card to drive a monitor or two, AMD hardware is fine. If you want something that will do OpenGL or video playback well, you want nVidia, or at the very least Intel.
The open source drivers support the older cards. ATI's plan is to dump support for legacy cards on to the community driver when it's too much of a pain in thte ass to keep the code going in their closed driver.
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, it breaks my windowing system in some way I must tweak just to get working again (Ubuntu 12.04, CentOS, and a few others that I run).
I must be one of the rare instances where AMD drivers/cards just worked well for me.
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.
ACs don't waste your time replying, your posts are never seen by me.
I'm sure you got downmodded because you forgot the "???" step. ;-)
The Tao of math: The numbers you can count are not the real numbers.
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 run on open source, so take this with a grain of salt).
So on ATI cards the open source drivers have come closer, but they still have a way to go.
In the case of the noveau driver for nVidia, I find it impressive that the developers got it to run by reverse engineering at all. Performance, however, looks like that of the open source ATI driver 1-2 years ago.
C - the footgun of programming languages