Slashdot Mirror
AMD Releases 900+ Pages Of GPU Specs
An anonymous reader writes "Ending off the X Developer Summit this year, Matthew Tippett handed off ATI's GPU specifications to David Airlie on a CD. However, the specifications are also now available on the X.org site. Right now there is the RV630 Register Reference Guide and M56 Register Reference Guide. Expect more documentation (and 3D specifications) to arrive shortly. The new open-source R500/600 driver will be released early next week."
AMD ie recently making more moves toward the open source community than either it or ATI did prior to the merger.It seems to me that AMD has realized that there is value in not only having the right products rolling off the lines, but also having a greater mindshare.
Google realized this early, and bought off a great amount of geek awe by using Linux as the basis for its computing grid. This popularity among geeks turned into word of mouth advertising which turned into huge market share (having a great product didn't hurt either). Google still tries to maintain the "we're just a benign bunch of geeks" image (an image which is eroding, as it becomes more apparent that they are more akin to a lovechild of M$ and the NSA than a giant sushi eating LAN party). This appeal to mindshare by making steps toward the community, genuine or not, may be part of what AMD is trying to do, at least to an extent.
There are other genuine benefits to being more open about its specs, most clearly highlighted by the use of ATI GPUs to process Folding@Home. Therefore it is conceivable that AMD GPUs and GPU/CPU combo chips in the future may, if more openly specced, be used in a wider variety of HPC applications.
Disclaimer: I am an AMD fanboi.
I hate printers.
One can hope that it actually had the specifications for modern GPUs... and not just stuff you might find in scrap piles or in 15+ year old government computers. Otherwise, it will be like when the RIAA gave a crap-ton of Whitney Houston Christmas CDs as a settlement for their price-fixing practices... technically within the letter of the law, but violating the spirit of the law all to hell...
Actually this is the fun part. Governments have been "enforcing" open source as gimmicks. The only way to show there is a REAL market is to have an actual producer get involved and actually PROVIDE the goods and support. Red Hat did its part, various OSS groups did their part, etc.
:)
:) (Or build another one.)
They weren't tax supported, but they did a better job than all the tax supported wealth consuming agencies out there
I agree, once the cards hit my neck of the woods, if they're well implemented in hardware, I'll gladly supplant my 7800's in my SLI rig
" What luck for rulers that men do not think" - Adolf Hitler
Is it really though? That's not rhetorical. Without RTFAing, I want the slashdot opinion - is this or is this not the proof that ATI is the solution for linux graphics? I was almost certain that my next card would be an nvidia, but this may change that.
Evidently, the key to understanding recursion is to begin by understanding recursion. The rest is easy.
I've got a new in the box nVidia card I was going to put in my new tower I'm building. It's off to e-bay for it and back to the store for an Ati card. amiga3D
I retract my previous statement, it looks incredibly likely my next card will be an ATI.
Looking like I'm going to be becoming an ATI fanboi.
I am not a hardware hacker, so I was wondering what cards would benefit from this first release.
Well, one time where people were left high and dry, was when voodoo went under. Lots of people had voodoo3s and its brethren. In this case, 3dfx had already released specs for linux (and I believe provided an open source driver at one time? can't recall). Yet with the specs released, the open source driver never achieved the same performance of what the card was capable of (comparing it to windows drivers' performance) and problems with some functionality.
When investigating for info on updated drivers the general feeling was no one is working on them because none of the devs bother with using 3dfx anymore and most users have moved on so there is lack of interest in further support. And this was only shortly after 3dfx folded. I thought this was a perfect situation for the strength of open sourcee. I actually still have that same v3 and when putting together a myth box last year, I thought it might be good enough for basic video. But in xorg, hardware overlay has been broken for quite sometime, so I couldn't control the brightness/contrast etc of videos. And opengl was pretty shaky.
I don't think the same thing would happen here, as ati is still doing fine and lots of people have their cards, now. But when a card becomes old and outdated, it will interesting to so how long it's really supported.
is this or is this not the proof that ATI is the solution for linux graphics?
For those of us who absolutely refuse to use closed sourced drivers their older cards have already proven to be the best solution for desktops.
Time is what keeps everything from happening all at once.
ATI have historically always had excellent features on their cards for supporting media playback. The downside was that accessing them in Linux has always been much harder than using the equivalent features on nvidia hardware.
If these specs allow a good stable XVMC driver to be written for ATI hardware, ATI could become the top choice for Linux media centre boxes.
NVidia have been stalwart protectors of their hardware designs, mostly due to historical accident. A few of the principals at NVidia used to work at Sun, where they designed the GX graphics chip. As it turns out, a version of SunOS was released with a header file describing the chip's registers. Using that -- and a logic analyzer -- a company called Weitek successfully created a functional clone of the chip that was good enough such that Sun's own drivers worked on it. This stuck in the craw of the Sun guys, and evidently vowed no such thing would happen again.
Another historical accident was that NVidia did, in fact, have a few source code releases way back. And every time they did, so it seemed, they got hit a few weeks later with a patent infringement lawsuit, usually from SGI. NVidia solved this latter problem largely through the expedient of buying SGI.
So, no, I don't think they're going to do it, and certainly not within six months. And yes, I would be perfectly tickled to be wrong about that.
Schwab
Editor, A1-AAA AmeriCaptions
The last time I bought a computer, I went with AMD because I was mad at Intel. I still am, though less so. It fades over time.
... solely because they had an open source video driver. This will soon eliminate that benefit.
Last year I did an evaluation, and Intel came out on top
N.B.: For me to choose Intel it must be 5% better than the competition. This is due to various corporate actions that I dislike. (Two years ago it was 10%...I use a time decaying function.) If they were up against a competitor that didn't support DRM, they'd need to be 50% better, but I don't see one, so that part of the playing field is level.
I think we've pushed this "anyone can grow up to be president" thing too far.
I have been buying nVidia video cards for forever for their... let's say less bad support for GNU/Linux and I recomended them to my Windows-using friends. But this changes everything: from now on I know that I can buy ATI cards and be sure that they'll work and have good software support. Thanks AMD, thanks ATI: you have made a new loyal customer today.
There's a hidden treasure in Python 3.x: __prepare__()
The thing that gets me is that Wikipedia seems to know more about the ATI chips than ATI. Of course this can't actually be the case, but I think it is somewhat telling that ATI is not the authoritative reference for even their own hardware. There seems to be some uneasiness with releasing the full product specs, which suggests to me that they don't have a real committment to openness.
Well, if I can't get specs, my next video card will be an nVidia. Why should I suffer because my HW vendor wants to hide something from me? Do they really believe that non-functional hardware gains them any marketshare?
With Windows hopelessly insecure, my only real option is to either buy a Mac, which is too expensive for my taste, or to use Linux. Which means that if ATI doesn't provide the documentation that I - or somebody - needs to write open drivers, I'm just not going to buy their HW. Period. That super-secret, proprietary graphics pipeline won't sell ATI cards if no one can use it. Do they really think that I'm going to run Windows just to get video to work?
The society for a thought-free internet welcomes you.
That's why Ubuntu and others do not upgrade the kernel with every new release. Only new releases of Ubuntu have a new kernel. [Ubuntu does put in patches for security, of course.] And Ubuntu makes their own package for Nvidia and ATI drivers, so it-will-work with their kernel. No need to go to www.amd.com for drivers, etc.
Right,
We will all take your word for this. 1 1.4GHz processor.
My laptop for work, a dual core at 2GHz with 2 Gb crawls. It's a pristine Vista install.
Please, my old single core laptop with 1/2 as much ram but still at 2GHz with Linux runs incredibly fast compared to it.
Yes! I'm happy stupid close source drivers break. Break break break, I hope they break them even more often. This will teach hardware companies something that they should have learned a long time ago but somehow missed out. They're hardware companies! They gain nothing by screwing with software.
Oh really? Service packs for windows don't break driver support? You're clearly living in an alternate reality. I've even seen nightly updates break patches, which is a lot more fun with the close-source nature of the whole thing. At least with Linux I can fix the bugs in a few hours generally.
Thank god I only have to see windows at work and this will all be over in a few months. Never again.
(And seriously, won't there be a Windows version of the open source driver? And if so, might it not surpass AMD's own Windows driver? And might this not be a part of AMD's strategy, out of recognition that everyone disses their drivers and that their coders cost them too many salaries? Probably not, but this will certainly do a lot to make people finally reconsider the undying meme that ATi cards are better but their drivers suck.)
If this were really happening, what would you think?
Amusingly, when I bought my Ubuntu PC from Dell's UK site a few weeks back the graphics card section had a giant ATi banner above it but only offered an NVidia card as an option. I assume that this is because right now NVidia's linux drivers are better, though neither are open source. Hopefully this'll change soon.
(Interestingly, the system shipped without NVidia's drivers installed, so I had to explicitly install NVidia's driver using the Restricted Driver Manager. I suppose you could argue that NVidia's driver has no business on a system being sold as an "Open Source" computer, but this is an annoying extra barrier for the potential non-technical user.)