Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Graphics Hardware Hacking Upgrades Build Hardware Linux

Open Source Graphics Card Available For Advance Orders 262

mollyhackit writes "The Open Graphics Project, which we've been following since it first started looking for experts four years ago, has just announced that the OGD1 is available for preorder now. The design features 2 DVI, 256MB RAM, PCI-X, and a Xilinx Spartan-3 FPGA along with a nonvolatile FPGA for programming on boot. FPGAs are reprogrammable hardware which means the graphics card can be optimized for specific tasks and execute them faster than a general purpose CPU. The card could be programmed for certain codecs to speed up encoding or decoding. An open hardware design means potential for better driver support. Of course you could always use the FPGA for something else... say crypto cracking."
This discussion has been archived. No new comments can be posted.

Open Source Graphics Card Available For Advance Orders

Comments Filter:
  • Pretty crappy FPGA (Score:4, Informative)

    by Anonymous Coward on Wednesday May 21, 2008 @06:24PM (#23498306)
    The SPARTAN 3 is a hobbyist FPGA. Cheap, and a lot of gates, but slow. A Virtex 4 would've been nicer :)
  • by FranTaylor ( 164577 ) on Wednesday May 21, 2008 @06:37PM (#23498440)
    At this stage of their development.

    This is not a finished product by any stretch of the imagination. These are prototypes. Back in the day prototypes were wirewrapped nightmares and they cost a lot more than $1500!
  • by fpgaprogrammer ( 1086859 ) on Wednesday May 21, 2008 @06:51PM (#23498562) Homepage
    you might be getting ripped off if you're paying $1500 for a Spartan-3 board.

    I guess they don't really have the board volume to get low prices. But If you want a graphics card for $1500 that's probably less functional than an NVidia commodity card, I'm not gonna stop you.

    OTOH, If you're interested in FPGA programming and a novice at it, you'll want to get a MUCH MUCH MUCH cheaper Spartan board (like 50 to 150). See http://digilentinc.com/ [digilentinc.com] for good starter boards.
    If you're serious about FPGA programming (or just willing to pay $1500 to $3000) you will definitely want to get a board with a Virtex or Stratix on board:
    http://www.xilinx.com/products/devkits/HW-V5-ML501-UNI-G.htm [xilinx.com]

    If you want to have it on PCIx:
    http://www.xilinx.com/products/devkits/HW-V5-ML555-G.htm [xilinx.com]

    You can also get FPGAs socketted for AMD's Hypertransport bus and Intel's FSB:
    http://xtremedatainc.com/ [xtremedatainc.com] (Altera FPGAs)
    http://drccomputer.com/ [drccomputer.com] (Xilinx FPGAs)
    http://nallatech.com/ [nallatech.com]
    http://celoxica.com/ [celoxica.com]

    (some of these vendors also sell PCI solutions)

    FPGA programming environments still mostly suck. it's a market impeded by proprietary standards and a whole lot of NP-Hard algorithms. We're working on it...
  • by Uncle Focker ( 1277658 ) on Wednesday May 21, 2008 @06:55PM (#23498596)

    I guess they don't really have the board volume to get low prices. But If you want a graphics card for $1500 that's probably less functional than an NVidia commodity card, I'm not gonna stop you.
    Because we all know that first generation prototypes are the most super powerful and cheap cards ever made.
  • by greg1104 ( 461138 ) <gsmith@gregsmith.com> on Wednesday May 21, 2008 @07:04PM (#23498682) Homepage
    There are two entries in the FAQ [traversaltech.com] about this. Short answer is "PCI is more popular with users of FPGA kits" and "PCI-X is backward compatible with your 32-bit 33MHz PCI slots".
  • Re:Uh...not for me! (Score:5, Informative)

    by RattFink ( 93631 ) on Wednesday May 21, 2008 @07:35PM (#23498898) Journal

    Really? I have friends who splash out $1000s on their hobbies, whether it is robots or R/C. This is a steal in comparison to some more expensive and consuming hobbies, especially considering the (underpowered but still excellent) FPGA.
    You can get similar hardware [xilinx.com] for far less or far better hardware [xilinx.com] for a bit less right now directly from Xilinx if that is your thing.

  • Re:$1500 video card! (Score:5, Informative)

    by deathy_epl+ccs ( 896747 ) on Wednesday May 21, 2008 @08:00PM (#23499088)

    Priced a Quadro FX lately?

    Yup... price of a nice GeForce and the time it takes to hack the identifier as described here [techarp.com].

  • by fpgaprogrammer ( 1086859 ) on Wednesday May 21, 2008 @08:04PM (#23499120) Homepage
    I really hope that same type of open-source economic irrationality will help fund my open-source FPGA tools startup!

    my point is that there are a dirth of FPGA boards with better cost/performance value that could be used to prototype a graphics rendering FPGA system. Physical hardware isn't the limiting factor to an open source graphics card; the open source FPGA 3-D rendering code is the real missing piece. In fact, making a board was probably a distraction for this project because by the time the firmware is ready for real graphics workloads the FPGA on-board will be obsolete.

    Here's some examples of 3-D engines for FPGA from the 6.111 lab at MIT:
    3-D Pong (using rasterization):
    http://web.mit.edu/6.111/www/s2006/PROJECT/7/main.html [mit.edu]

    Ray Tracing:
    http://web.mit.edu/6.111/www/s2007/PROJECTS/5/main.html [mit.edu]

    There are hundreds of videos and code for FPGA projects up at http://web.mit.edu/6.111 [mit.edu] (see project appendices for code).
  • Re:$1500 video card! (Score:5, Informative)

    by petermgreen ( 876956 ) <plugwash@nOSpam.p10link.net> on Wednesday May 21, 2008 @08:22PM (#23499250) Homepage
    Nah there are lots of other FPGA boards availible many of which are frankly a much better deal than this board.

    Essentilly if you don't want the card for graphics what you get is a relatively small FPGA (one of the smaller members of the spartan 3 family which is xilinx's current low end family) on a PCI-X card. This board is way overpriced for that.
  • Except it is. (Score:5, Informative)

    by pavon ( 30274 ) on Wednesday May 21, 2008 @09:01PM (#23499552)
    There are literally thousands of FPGA prototyping boards [fpga-faq.com] on the market, many of which cost much less than this one. So while you could use this for other things, I can't imagine why anyone would spend the extra money unless they wanted to use the video specific features like the dual DVI interface. Furthermore, the purpose of the project is to develop an open source video card, and this card was created as a tool for those developers to experiment with.

    So, it was created to prototype a video card, and it's only practical uses are real-time video (output) processing, thus it is a video card.
  • by OrangeTide ( 124937 ) on Wednesday May 21, 2008 @09:23PM (#23499694) Homepage Journal
    spartan-3 is good. But it's not going to be much use for high-bandwidth designs or designs that need lots of I/Os. An affordable choice for an FPGA though.
  • by Anonymous Coward on Wednesday May 21, 2008 @10:00PM (#23499956)
    No you can't. If you had the info to emulate you could write a driver, and probably a lot easier.

    This is a research & development tool for designing hardware or for use in highly specialized applications.
  • by Eric Smith ( 4379 ) * on Wednesday May 21, 2008 @10:05PM (#23500000) Homepage Journal
    It's unclear to me where you're getting your information, but the card uses a 3S4000, which is the second-largest Spartan-3 FPGA. It has over 60,000 logic elements, each of which has a 4-LUT and a FF. The part also has 96 parallel multipliers (18x18 two's complement) and 96 18-Kbit dual-port RAMs.
  • by Eric Smith ( 4379 ) * on Wednesday May 21, 2008 @10:12PM (#23500056) Homepage Journal
    The Spartan 3 is a professional FPGA. It happens to be relatively inexpensive as it is targeted at ASIC replacement. The performance is lower than a Virtex 4 or 5, but the price/performance ratio is much better. The last time I got quotes, Virtex 4 parts cost about ten times as much per logic element as Spartan 3 parts.

    What most people seem to have overlooked is that this isn't an expensive video card. It's a midrange FPGA development card, that happens to be suitable for prototyping video card functionality. It is NOT intended that average users or even power users would buy this to use it as a video card.

    The plan is that this card will be used for development of the logic for a video card, which will then be realized in an ASIC in order to produce actual video cards.

  • by Eric Smith ( 4379 ) * on Wednesday May 21, 2008 @10:16PM (#23500082) Homepage Journal
    I've seen Spartan 3 parts used in designs with lots of bandwidth and lots of I/Os. "Lots" is a relative term. Yes, you can get more bandwidth and more I/Os with a Virtex 4 or 5, but for many applications the Spartan 3 (or 3E, or 3A) are perfectly satisfactory.
  • by Eric Smith ( 4379 ) * on Wednesday May 21, 2008 @10:27PM (#23500128) Homepage Journal
    The Xilinx tools run fine on Linux, either on 32-bit or 64-bit x86 boxes. Even the no-charge edition (ISE WebPACK) comes with 32-bit Linux binaries, and can be run on 64-bit Linux systems. The main drawback of WebPACK is that it doesn't the largest FPGAs, including the XC3S4000 on this board. Unfortunately you do need the paid version of the tools for that.

    If you can find an FPGA for which there are open-source development tools, by all means please let us know about it. Meanwhile those of us that want to get actual work done with FPGAs will make do with the closed-source tools.

    People routinely appear in comp.arch.fpga saying that they will write open-source FPGA development software, but none have succeeded at that yet. Perhaps the underestimate the magnitude of the problem. Xilinx has literally thousands of man years invested into developing their tools; it's not something for which one person or a small team can knock out a functional replacement in a year or two.

    I try to use open-source software as much as possible, and I release much of the software I write in my spare time under the GPL, but for certain problems, open-source software just isn't going to be practical in the near term.

  • Re:PCI-X (Score:3, Informative)

    by SpacePunk ( 17960 ) on Wednesday May 21, 2008 @10:48PM (#23500298) Homepage
    This product needs to be realized on PCI-E, other wise it'll just be a hobbyist item that will never become anyting more.
  • by Runefox ( 905204 ) on Wednesday May 21, 2008 @11:49PM (#23500730)
    While Project VGA does look very interesting (and much more practical than this particular project), I have to point out that PCI-X is almost always inherently compatible with PCI, and vice-versa. In this case, the manufacturer specifically states that it will work in a PCI slot. If you're having trouble finding a PCI motherboard, then maybe you're doing it wrong.
  • Re:I think not (Score:3, Informative)

    by Hells Ranger ( 305981 ) on Thursday May 22, 2008 @12:16AM (#23500906)
    The FPGA performance with the basic GPU would be enough to have a glitch free experience when using a 3Ddesktop in linux using the card acceleration or playing some old game. The thing is,the FPGA is probably going to run near 100MHz with 1 or 2 fixed pipeline so the performance will be ok for a desktop and stuff. For the latest game the framerate isn't going to be acceptable.

    Once the design is finalized it's going to be ported as a chip. The initial production cost for fabbing a chip is near 1 or 2 million for about 100k unit. Once the chip is fabbed the unit cost drop dramatically. Using that final chip you can save a lot because you need a simpler board and less component than the development board.

    Also once fabbed the chip is going to have more pixel pipeline and will be running a lot faster.Why more pixel pipeline and faster? A fabbed chip is more efficient than a FPGA both in term of surface usage and performance because of the way the circuit is made. So it allow the developer to use a maximum of surface. Since rendering graphics is a highly parallel task the graphics pipeline is easy to duplicate. Also usually in most design today the chip size is more dictated by the IO density than the core so there always space to add more pipeline.
  • by Danny Rathjens ( 8471 ) <slashdot2.rathjens@org> on Thursday May 22, 2008 @12:25AM (#23500970)
    The Tachikomas [wikipedia.org] in Ghost in the Shell were all rendered with a software shader that makes them look hand-drawn. That type of specialized shader certainly seems like a great application for this.
  • by DMUTPeregrine ( 612791 ) on Thursday May 22, 2008 @03:15AM (#23501828) Journal
    Fixed That For You, Hope That Helps, Have A Nice Day.

    YHBT. YHL. FOAD.~
  • by PSargent ( 188923 ) on Thursday May 22, 2008 @04:17AM (#23502120)

    Now that they are ready to offer the hardware, I find myself seriously considering purchasing one.

    Don't! and I'd say that to anyone. What they are offering is a FPGA dev kit, with nothing to put on the FPGA. Yes, they've done a board design, but that's really one of the easiest bits, especially as most firms that sell the chips give you sample designs that you can stitch together.

    The HDL is the key to this project, and as far as I can see they haven't produced anything beyond very basic PCI and Memory Controllers (which I'd expect to be very low performance). I looked at the same code about 2 years ago (maybe more) and it's in exactly the same state now as it was then. I say this as someone who writes VHDL / Verilog for a living and was wondering if I should contribute, but I'm not interested in carrying the whole thing myself.

    If this projects manages to get a framebuffer device up and running within 5 years I'll be impressed. I think the whole project is incredibly naive, and doesn't understand the scale of the project they're trying to do

  • by petermgreen ( 876956 ) <plugwash@nOSpam.p10link.net> on Thursday May 22, 2008 @05:11AM (#23502380) Homepage
    sorry my mistake, I read the 3S400 entry rather than the 3S4000 entry by mistake.
  • Re:$1500 video card! (Score:4, Informative)

    by petermgreen ( 876956 ) <plugwash@nOSpam.p10link.net> on Thursday May 22, 2008 @05:27AM (#23502448) Homepage
    sorry I misread the comparision table (mixed up the 400 and the 4000).
  • Re:$1500 video card! (Score:3, Informative)

    by Yetihehe ( 971185 ) on Thursday May 22, 2008 @05:56AM (#23502584)
    Yes, it MAY become graphics card, for example when they finally develop framebuffer logic (to act as card without acceleration). Then they plan to make vga emulation, so you could boot your computer with this card. You can read more in their FAQ [traversaltech.com]
  • Re:$1500 video card! (Score:3, Informative)

    by mustafap ( 452510 ) on Thursday May 22, 2008 @07:15AM (#23502966) Homepage
    The original post was misleading. This is not a video card, but an FPGA development platform that has some video output capability.

    The developers must be cursing slashdot at the moment :o)
  • OT: "dirth" (Score:3, Informative)

    by Tim C ( 15259 ) on Thursday May 22, 2008 @07:51AM (#23503168)
    Just to let you know (and because I'm a pedant ;) ) it's spelled "dearth", and it means "lack of" or "not large enough supply of".

    Basically, you said exactly the opposite of what you were trying to say :)
  • by Eric Smith ( 4379 ) * on Thursday May 22, 2008 @02:19PM (#23508796) Homepage Journal
    SGI originally made fully-functional OpenGL rendering hardware with far less than 125 million transistors. Maybe that was the minimum for a competitive graphics card at the time of the first GeForce card, but it's definitely possible to render OpenGL with a lot less than that.

    The FPGA card is NOT intended to compete with ATI and Nvidia. My understanding is that even the eventual ASIC version isn't intended to compete with the high-end cards.

Thus spake the master programmer: "After three days without programming, life becomes meaningless." -- Geoffrey James, "The Tao of Programming"

Working...