Slashdot Mirror
AMD Releases Open-Source R600/700 3D Code
Michael writes "AMD has just released code that will allow for open-source 3D acceleration on their ATI R600 and R700 graphics cards, including all of their newest Radeon HD 4xxx products. This code consists of a demo program that feeds the commands to the hardware, updates to their RadeonHD driver, and a Direct Rendering Manager update. With this code comes working 2D EXA acceleration support for these newer ATI graphics processors as well as basic X-Video support. AMD will be releasing sanitized documentation for these new ATI GPUs in the coming weeks. Phoronix has an article detailing what's all encompassed by today's code drop as well as the activities that led to this open-source code coming about for release."
Don't forget to pay your $699 licensing fee, you cock-smoking teabaggers!
Thats true, but this sounds far more complex and useful that what has been released in the past, perhaps they are getting more serious. I would love to see good ATI drivers on OSolaris/ BSD and Linux. There is no reason we- the OSS community, can't have the best drivers, like we have the best web browsers.
Or just good economical sense.
"Hey Bob, these kids on the Internet want to write Linux drivers for our cards."
"Oh really? Have we had any customer requests for Linux drivers lately?"
"Yeah, a couple."
"Send 'em that dev code we did last week, see what they come up with."
"Ok."
Shocking!
How we know is more important than what we know.
I had almost forgotten to pay my $699 licensing fee. Makes me feel like such a cock-smoking teabagger!
This seems to confirm what people have been predicting all along, that OSS philosophy is driving competition between vendors to cater to their customers' needs. Nvidia, Intel, and now ATI all providing increasing levels of documentation and code support in competitive volleys. I for one welcome our new 3d accelerated overlords.
-*The above statement is printed entirely on recycled electrons*-
AMD doing nice shit just makes it all the more heartbreaking when Intel releases better chips. I hope they get their shit together soon, I feel dirty with a Core 2 Duo.
The scenario you describe has one issue: last week's dev code is copyrighted by the company, not the developers. They probably needed to have some long conversations with the lawyers and accountants to get this done.
Every single 3D accelerator I have ever owned has been an NVidia, up until now. Not because I am an NVidia fan-boy, but because that's what I started with (TNT!) and (since I switched over to Linux) because NVidia has always been the best choice for Linux support. I have never considered ATI since their Linux drivers have been craptastic. But in between what I've heard of ATI drivers having improved lately, and now with these drivers being open source, I will definitely be giving ATI a look when I build my next PC in a few months. Thanks ATI!
I chose ATI over Nvidia in my most recent graphics card purchase because of ATI's policy.
Thanks ATI; it's the right thing, and it will help your revenue.
I am looking forward to see what this means for Linux, OpenCL and other GP-GPU goodies. With OpenCL working along side OpenGL, a tightly integrated kernel ATI driver that handles the GP-GPU/OpenCL stuff we will really see some interesting stuff come our way. To my understanding OpenCL allows someone who is writing an algorithm to implement it in OpenCL and let OpenCL take care of diving up the work load between GPU's and CPU cores. Damn I am really excited to see the OSS community tie all this stuff together and release the computing power of the GPU to more general yet compute intense applications.
A system with a quad core CPU and four ATI cards would be a force to be reckoned with! Fast trans-coding/cracking of Blu-ray, rapid key sniffing for air crack, even networked applications could be sped up like IPsec and SSH. We could have fast rendering in blender and ray tracing can be done with high precision as well as speed (maybe even real time!). Gimp plug-ins can be given a boost in speed and video editing a breeze. Even a laptop with a slower dual core could benefit from its on board GPU's number crunching power. Useful for cracking WEP/WPA keys.
And AMD/ATI arent the only ones getting on board the OpenCL bandwagon, Apple developed it, and Intel along with Nvidia are also going to support it. So OpenCL will allow us to run our apps on the hardware of our choice.
I think they know how to write off such a contribution as charity.
Based on what's been on IRC in the past few hours.
Q: Wait, what?
A: Code for radeonhd and the kernel providing acceleration for Radeon HD 2400 and newer. Kernel parts are already pretty much integrated; radeonhd is integrated as well, although stuff still needs to be copied to radeon.
Q: So what does this mean for the user?
A: EXA means faster GUI responsiveness. Xv means fast video. Kernel DRM is the basis for all acceleration unification (OpenGL, etc.)
Q: Speaking of OpenGL...
A: Lawl, no. Not for another few months. Most of the code we're gonna write will target Gallium, so--
Q: Gallium?
A: Gallium is the next generation of GPU acceleration. Once we get drivers ready, it'll be awesome. Linky to TG: http://www.tungstengraphics.com/wiki/index.php/Gallium3D
Q: So this is just docs and some basic code?
A: Nope, no docs. AMD couldn't agree on docs before their vacation time, so I guess we'll see those in a month or so. On the other hand, we've got enough here to do a lot of stuff. It'd be nice if we had more devs, though. :3
Q: So why is there only code for radeonhd? Will radeon support this too? Why two separate drivers?
A: The reason for two separate drivers is a very long and largely silly story. I don't feel like repeating it, and I probably couldn't tell it fairly anyway.
I'll get radeonhd code ported over to radeon once my vacation's over, assuming nobody does it sooner. I can't do the HDMI audio setup without testing hardware, though; does anybody want to donate an HDMI audio-enabled monitor? :3
~ C.
~ C.
Why can't it be both? I'd say the Gates Foundation has been far more successful at promoting Microsoft than some of their more direct efforts.
We all joke about his billions of dollars, but to see them put to use attempting to vaccinate an entire continent, I gotta tell ya that is a pretty damned impressive thing to do.
Don't get me wrong, donations of time and money to Open Source projects are also good and noble things, and they provide infinitely-copyable and long-lasting amounts of good. But if someone asked me "who did more good, the guy who saved x-hundred-thousand kids or the guy who donated an improved scheduler algorithm to the Linux core?" there's only one way a human being could answer that question. There is a different question in there, and that is "who donated more overall effort?" Gates' money made him rich enough that he may not even feel the pinch of spending $37 billion, but the coder likely sweated over his efforts for months, sacrificing evenings and dinners with his S.O., etc. And I suspect its part of the job of the foundation to ensure the first form of the question is asked on camera, and not the second.
John
It's been about 8 years since I last immersed myself in the world of video cards and of course everything has changed since then. (Except that nVidia and AMD (was: ATI) are still on top.) Since then, whenever I've needed a video card, I've just gone to newegg and bought whichever nVidia card was priced around $50.
But pretend for a moment that I want to congratulate AMD on their open source stance and buy one of their cards. I don't need eye-blistering speed, but I want something that's going to be able to acceptably play a game released a year to six months ago. And obviously it has to work well on Linux. Would be nice if it was under $100 and dual-head, but I'll take any suggestions I can get. Is there such a card? If so, which drivers does it use?
Yeah... is there a catch?
No. You can be forgiven for asking the question, given history, but... no.
TFA:
The microcode for the newest GPUs has also been released.
This is the real deal. Actual specifications about how the hardware interfaces actually work in a format that can't be encumbered by copyrights or patents. NVidia and Intel will follow with their own release announcements within weeks, or watch their proprietary crap die. This is "a race to the bottom" where the "bottom" is "fully open". The funny thing is that the "bottom" is a door to a whole new world of opportunity.
To be fair Intel has been fairly open, and Nvidia has been opening up. Windows only video drivers are soon to be a legacy best forgotten. Please hold a moment of silence for the brave chairs that are about to lose their integrity in Redmond.
Help stamp out iliturcy.
Well, Nvidia could afford not to follow Intel open-source drivers, since they share just a small part of the market, but it is doubtfull if they can ignore ATI open-sourcing their drivers.
The race here is exactly for the future of graphic cards, both Intel and ATI/AMD want to get rid of it, replacing them by some SIMD massively multi-core general processors (forget about those physics engines you heard about recently, it is going to be replaced by your general porpouse GPU). They think that this configuration is what the consumers want, and they may be right, but Nvidia has no route to get there. Now, Nvidia face a harsh future, both because of this change and because they have being losing quality/competitiveness/reputation recently. I really don't know how they can survive, but open-sourcing the drivers look like a good help, even if it canibilizes some product lines.
By the way, I'm delaying buying a video card since AMD brought ATI, because I trusted them to release open source drivers for their line. Before that, I'd buy Nvidia (I did buy a Nvidia card just before that), now I'll go get an ATI.
Rethinking email
We all joke about his billions of dollars, but to see them put to use attempting to vaccinate an entire continent, I gotta tell ya that is a pretty damned impressive thing to do.
Sounds good on the face of it doesn't it? But look a little closer. The entire vaccination program is about intellectual property - countries have to forgo local pharma factories that produce medicine without paying royalties - despite it being perfectly legal to do so since most of those countries do not recognize foreign patents anyway.
But if someone asked me "who did more good, the guy who saved x-hundred-thousand kids or the guy who donated an improved scheduler algorithm to the Linux core?" there's only one way a human being could answer that question.
If you are going to cherry pick the question, then of course the outcome is predetermined. But what about taking into account the source of all that money in the first place? How much of the world's GDP has microsoft skimmed off the top? Money that would have been re-invested into the domestic economies all around the world, resulting in improved economic and living conditions without having to go through all the fat-cat middlemen, each taking their cut of that money before it eventually comes back around in the form of a "charity?"
When information is power, privacy is freedom.
I have an R350 chipset, you insensitive clod!
Seriously though, I'm not seeing much progress with respect to older processors. FTFA,
Two weeks after the initial R500 3D documentation release, AMD had released an R300 3D register guide. This programming guide concerning their older graphics hardware was previously only available through Non-Disclosure Agreements to select developers.
Well, so far my experience with the open source R350 drivers is lukewarm. They do work to an extent, in that they can run Tux Racer and its forks, but FlightGear remains beyond their capabilities.
Why not just buy a R600 or R700 card?
Yours
AMD Marketing.
echo -e 'global _start\n _start:\n mov eax, 2\n int 80h\n jmp _start' > a.asm; nasm a.asm -f elf; ld a.o -o a;
I can remember reading from John Carmack, that he hated the ATi drivers, because they were so crappy. The impression that I got from his description was, that it's kind of like the Internet Explorer of graphics drivers. They did seem to not be able to conform to the OpenGL or DirectX specifications at all, and had weird bugs when rendering in a specific condition.
Does anyone who is programming actual 3D and shader code know if this has changed? I can imagine that nowadays, everything is written as shaders, so the actual implementation of higher level functionality (like the OpenGL default rendering model) does not matter anymore.
Any sufficiently advanced intelligence is indistinguishable from stupidity.
True or not, they're still giving the Linux community exactly what they've been asking for: documentation to write good drivers for their devices. It's win-win for everyone.
I get the impression that the most vocal group asks for "Linux drivers", even less ask for "open source Linux drivers". Just a few ask for documentation. I'm glad they released the documentation. There are more OS's than Linux and maintaining an undocumented driver will probably be a hell.
Well, the sanitized docs for the R300/R500 chips lead to very usable opensource 2D/3D drivers in less than half a year. Let's give AMD the benefit of the doubt here, they've proven to deliver useful documentation in the past.
Problem is that the drivers you're referencing and the Carmack's comments on them date from around 2000. Lots has changed in the meantime. FWIW, the Carmack was referring to Rage128 era hardware/software, which was one unusable ball of software workarounds for hardware bugs and hardware workarounds of legacy software bugs. ATI threw it all away and started fresh roughly around the time they ditched the Rage architecture and had released drivers on the newer codebase when they released the second-gen Radeons. The hardware wasn't fully new-gen and pretty until roughly Radeon 9700.
They repeated the process on a smaller scale again roughly the time the X1K cards were released (software restart) and around the time the HD2K cards came out (completely new hardware generation).
This is all just a lot more info than you needed, but the simple answer is 'Yes, everything has changed since the paleolithic quote's time. Twice'.
The current quality of ATI/AMD's Windows drivers is debatable, but I'd be entirely comfortable saying 'they are very comparable in quality to Nvidia's current drivers'.
The preceding comment is my own, and in no way construes an opinon of the Emperor of Mankind.
But how can I be the youngest X.org member if I don't act cute?
Or, on a more serious note, why complain? I'm the only X.org member to actually comment here, and with a nice, big, juicy, informative FAQ, no less.
~ C.
Lots of good information in parent's post that I've sort of imagined to be true but had no evidence - wish I had mod points for you.
As for my experience between the two sets of drivers, I've been switching back and forth between ATI and Nvidia graphics cards for the past 4-5 computers that I've built. Feature-wise, (recently) both of them are pretty smooth about dual monitors, setting up custom resolutions/refresh rates without needing programs like reforce, and all sorts of bells and whistles that I'll never use.
The only noticeable difference between the two that I've seen is that when the graphics card is having issues, ATI has a "VPU recovery" feature that is likely to prevent your computer from getting a BSOD, whereas Nvidia will just BSOD.
I had an MSI motherboard (RS480-M2, iirc) that was having all sorts of issues despite replacing literally every piece of hardware in the tower. Turns out that any time I had a video card in the PCI-E slot, it would do weird things - and I even RMA'd the motherboard before figuring this out. Of course, I discovered this way too late. On-Board video worked fine, but my Nvidia card would BSOD (but worked fine in other computers), and the ATI card would go to black screens in games, then eventually reset itself and give me the VPU recovery error message.
That feature alone seems like a major improvement over Nvidia's cards, but given that it rarely happens, it isn't a determining factor in which card I will select. Since that POS MSI board, I've only had one VPU recovery error, and I'm not even sure why that one happened yet...
Whatever their motivations happen to be, they are doing exactly what the kernel developers have been asking them to do.
If it saves ATI/AMD money, even better. Maybe other companies will see the light and follow suit.
*sigh* back to work...
Well. The few who ask for documentation want to write open source drives which will provide drivers to the first group.
You present the last group as a fringe group of fanatics... It is quite understandable that very few people will want documentation on graphic cards, for there are in fact very few people in the world who can understand it. And youseem to imply that because they are few, they are mostly negligible: that's a pretty absurd position.
Who said Opera? I was refering to Gecko and KHTML/ Webkit.