Slashdot Log In
Free Software Friendly Graphics Card?
Posted by
CowboyNeal
on Thu Oct 21, 2004 09:57 PM
from the open-everything dept.
from the open-everything dept.
An anonymous reader writes "There's an interesting discussion on KernelTrap with a hardware company that is talking about developing a 'free software friendly' graphics card. The idea is to fully disclose and document all register interfaces including the BIOS, providing Linux and BSD users with a fully supported video card. The hardware engineer proposing the idea summarizes his viewpoint saying, 'the whole issue comes down to this: This is technically feasible. Should we do it?'"
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Secrets (Score:4, Insightful)
Re:Secrets (Score:5, Insightful)
Let's look at the big boys, nVidia and ATi, apart from both corporations having a lower case letter where it doesn't really belong, both companies are pretty much at the leading edge in terms of chip design/driver optimisations.
Which is pretty much why they choose to release close sourced only drivers.
This new company... well, R&D is going to be expensive if you are thinking of making the next Geforce or Radeon, so what are they planning to make?
The S3 Trios of yesterday?
If that's what they are gonna make, what about profit margins? ATi and nVidia are doing so well converting lumps of silicon into gold because their chips are fast. A graphics card by itself is not expensive at all.
Doesn't sound like they are having a very viable business plan to me
Parent
Re:Secrets (Score:5, Interesting)
Is actually an existing company with previous experience with graphics hardware and systems software. Developing a graphics card is something they are fully capable of doing. The question is whether or not they are going to make a card that targets the open source OS market.
ATi and nVidia are doing so well converting lumps of silicon into gold because their chips are fastFor people who want to run Doom3. I for one would like to give someone my money for a card with nice solid vendor supported 3D accel on Linx/Xorg without spending a hefty bundle. Or recompiling between reboots (I run multiple kernels).
Not saying that this is a viable plan, but your analysis is off
Parent
Re:Secrets (Score:4, Informative)
Parent
Re:Secrets (Score:5, Insightful)
Are Nvidia's drivers better? Yes and I will be buying Nvidia for my next card. But that doesn't excuse over dramatizing like you did.
As for Matrox, sure, they're still in the market
Sad as I feel saying it, if I were ATI or Nvidia I would be doing everything I could to keep the other party from knowing anymore about my board internals than they could. Will each eventually reverse engineer it all? Sure
I'm not dumping on Matrox
Parent
Re:Secrets (Score:4, Insightful)
Parent
Re:Secrets (Score:5, Insightful)
They realize it would be foolish to try to compete with the big 2. That and a large chunk of the people out there don't game, or just simply don't care about FPS and so forth. They just want something that is solid, works, quiet, and not space heater.
Parent
Re:Secrets (Score:5, Informative)
Parent
Re:Secrets (Score:5, Informative)
The reason they've got such tight reigns on drivers is that drivers cost a lot of programming hours to write. That is source code that I don't think the world will see. The games released for specific video cards also have some of that driver code (provided to them via NDA) from the cardmaker. their complete source code may contain very secret IP such as chip limitations, workarounds, extra settings, and other things that they may not want their competitors and customers to know about.
Parent
Re:Secrets (Score:5, Insightful)
- the person who only cares about "good enough", not "awesome" performance -
Because you're not going to equal ATI or Nvidia's offerings. The newest games will run much faster with the latest proprietary solutions. And we're headed for another revolution in gaming cards if you hadn't been following along, the return of SLI using PCI-E and multiple relatively cheap graphics cards. You can't keep up with product cycles by seeing what's out there now and expecting to bring out the same in 6 months or so.
- and who doesn't expect it to be cheaper than mainstream offerings -
You can't beat manufacturers who produce in huge volume in countries with low labor cost. It just can't be done, not even if your R&D all comes free from the community. Volume gets you discounts, sometimes spectacular discounts. It also gets you priority when parts allocations are made. Samsung (and distributors) won't really take much notice if you only want 10,000 3ns BGA memory parts but when PowerColor and Hercules ask for 10,000,000 that's another story.
- and who really really cares about the idealogical and hacky side of computing -
Here's your only point of differentiation - your entire value proposition, in a nutshell. It's not produced by "big, evil company X" and all the registers are open. Well sadly that's a smallish market.
In short the whole project would be a charity. A bunch of people would have to do a lot of non-trivial work which they could be financially well rewarded for were they to do it for any of a number of commercial enterprizes.
Which is fine if you can afford to do it...
Parent
Re:Secrets (Score:5, Interesting)
Parent
How about a Free Software Friendly Audio Card? (Score:4, Interesting)
I don't know about others, but I've had *way* more trouble getting audio to work on my linux boxes than I've ever had configuring video.
Re:How about a Free Software Friendly Audio Card? (Score:5, Funny)
What? Your PC speaker doesn't work now?
It's like the VGA of music!
Parent
Re:How about a Free Software Friendly Audio Card? (Score:5, Insightful)
The PC speaker is like the CGA of music. Both of which should have been left in the dust of time, but IBM cut corners on the first PC, and the PC speaker is still with us.
Parent
Heh (Score:5, Insightful)
Neat idea (Score:5, Informative)
Can this company create a card that's competitive? And if they can, will they get pushed out of business through patent litigation?
Nvidia/ATI (Score:5, Interesting)
Re:Nvidia/ATI (Score:5, Insightful)
Parent
Re:Nvidia/ATI (Score:4, Informative)
Parent
#3 might be an option (Score:4, Interesting)
What are Matrox and VIA doing these days?
Parent
I'll never buy Matrox again (Score:5, Informative)
"Worst?", I hear you say, "How can that be? My ATI doesn't work great either!". Well, consider this; It's been almost a year [matrox.com] since their last driver was released. It doesn't support Linux 2.6 [matrox.com] yet. People are trying to patch [matrox.com] things [matrox.com] up [matrox.com], but it's a losing battle. It doesn't support SMP [matrox.com] either, which means that any P4/HT users are out of luck. And I'm not just talking about not actively enhancing the drivers for SMP, no, it will outright crash and bring the the whole computer down with it if you som much as think of starting an OpenGL application. Oh, and while we're at it, there is of course no support at all [matrox.com] for AMD64.
Quite frankly, Matrox has remained so apathetic to the Linux crowd that I'm now convinced that they tricked us all just to get our money, and deep down inside they just hate us.
Parent
Is this... (Score:4, Interesting)
(Age old...) (Score:4, Interesting)
Yes.
WILL they do it?
No.
~~~~~~
It's a "trade secret thing. nVidia doesn't want ATI to know what they are planing / doing so they can make their buck...
Free graphics cards? (Score:4, Funny)
I think this would be a great thing, (Score:4, Interesting)
It would also be fantastic for the linux community because the existence of such a card-- and the preferential treatment the card would receive-- would put pressure on all the other cardmakers to follow suit, or at least tighten up their linux support.
Unlikely (Score:4, Insightful)
" Should we do it?" - Why not? (Score:5, Insightful)
why not just lobby nvidia? (Score:5, Insightful)
Re:why not just lobby nvidia? (Score:5, Insightful)
As it stands, they aren't making enough money off of F/OSS users to pay for a buyout of the IP in question, pay for the lawsuit if they broke the license agreement, or clean room re-write the code. If any of those 3 conditions are met, they should be able to turn a profit on selling cards to Linux/*BSD users.
Parent
Re:why not just lobby nvidia? (Score:4, Insightful)
Parent
Re:why not just lobby nvidia? (Score:5, Insightful)
Parent
Re:why not just lobby nvidia? (Score:5, Insightful)
Parent
Re:why not just lobby nvidia? (Score:4, Insightful)
Remember that leak of Windows 2000 source? Something like 16% of it was application specific kludges. Many of the apps weren't even MS'. This isn't the sort of developer stability we need.
Also, many applications require more than technical excellence. They require trust. I don't trust the provider of a binary only driver to support my equipment 5 years down the road.
Parent
Put your money where your mouth is... (Score:5, Interesting)
I'd be willing to pre-order a graphics card that fully documented it's specs and cooperated with the Linux community for my desktop. The problem is that many companies aren't prepared for such a thing, and don't have a way to take your money. So, helps us out... Where do we pre-buy one?
Sean
Yes (Score:5, Insightful)
So please do it. I know some Linux users take pride in their amazing ability to get some piece of not-really-supported hardware to function, and in fact there are whole companies which provide installation of Linux on unsupported laptops as their business, but this is not fun and is a waste of time.
When can I buy it?
Missing the point (Score:5, Insightful)
This is a 2D only card. He would not try to compete with BigBadVideoCardVendor. He knows that development of a competitive 3D card is out of the question for now. But you have to start somewhere.
Unlike an opensource software project, an "opensource" hardware project can't "show me the code" in order to gain legitimacy and gather developer attention. He's looking to see if there is real interest so that he can make a case to his boss. He seems to understand the risks involved, and I hope he can make it work.
Re:Missing the point (Score:4, Interesting)
I don't do games, and I have no use for 3D. A nice 2D card that was endorsed by the kernel and X gurus (something like ``this company is doing everything we ask to make sure we can use their hardware'') would be an easy sale to me, as long as it didn't cost much more than the low-end NVidia.
If it would do dual-head, and drive a couple of 21 inch monitors at 1600 x 1200 with 32bit color, it could cost way more than the low-end Nvidia and be a great deal.
I'll be in the market for some new hardware about the time they could get this out, too. I'll be keeping my eyes open.
Parent
Hell ya. I want G-DOS. (Score:5, Interesting)
That would rock the house considurably.
GRAPHIC MANUFACTURERS SELL GRAPHICS CARDS, NOT DRIVERS.
Open source drivers are a great inducement to purchase a card.
Even if the card is slower then others and slightly more expensive, I would still buy it. If it's very much slower and very much more expensive then it would be a issue.
Ok what I am about to say will only make sense is you understand what ISA's are.
Get out of your mind the ISA slot and the x86 ISA is teh suck. PowerPC has a ISA, for example.
It's a standard way on which software is ment to interact with hardware in your computer.
For example you first created the 386. Most of what the software ran on was raw hardware. However the modern pentium4's and Althons are VERY much DRASTICLY different from the original 386 cpu.
Lots more REAL registers. Lots of extensions, SSE, MMX, so on and so forth.
Why then are they able to run programs and even DOS OSes designed from the i386?
BECAUSE THE ABSTRACTION NEEDED TO FIT INTO THE ISA STANDARDS IS BUILT INTO THE HARDWARE.
So what we need for video cards is a ISA for them. Like the VESA standards, but for hardware 3d acceleration.
Something built around OpenGL, because it's open standards and universally accepted, unlike DirectX which is NOT just for 3-d but for input, sound and all sorts of other stuff and is only specific to one vendor operating on only one platform.
Think about it.
Video cards are mini miniture computers.
They have a micro proccessor.
They have RAM.
They have a BIOS.
So on and so forth.
So why not build the drivers for the video cards like you build a OS?
And why not build a opensource OS for it built around a Open ISA standard for OpenGL capable video cards?
Maybe a GDOS? Graphical Driver OS?
That way you have a choice. You have a generic OpenGL capable drivers that will run only any compatable video card irregardless of make or model. The GDOS would be something exceedingly simple. It only has one purpose, take care of OpenGL instructions from software running on it's Parent OS and transform it into instructions to be ran on the hardware itself.
Then people like Nvidia and ATI could take that Free G-DOS and add extensions to it for their own private optimized rendering stuff that sits outside the normal OpenGL standards. Propriatory ways of rendering Anti-Aliased text for example.
If they don't want to release their secrets to propriatory bits of software they dont' have to.
But if you don't want to run the propriatory software you still have full standards-compliant OpenGL drivers. If they are a bit slower, then so what? I'd rather have slightly slower Open source, open standards, drivers then slightly faster closed source drivers anyday.
I care more about the stability of my system then anything else.
Then when the OpenGL standards are upgraded, or you need a new generation of ISA to get rid of the cruft it would be simple, since you only dealing with a single-tasking, single-purpose, specialized peice of hardware. Backware compatability would be taken care of by allowing older cards to render in Software (Mesa) the bits that they can't render in hardware due to their oldness.
The OS would be kept independant of it. The kernel would be kept out of it. The G-DOS could be in it's own memory space or even in userspace (since with displays your only dealing with one user at a time)
G-DOS 1.0 cards
G-DOS 2.0 cards
So on and so forth. With in this framework their would be very much room for performance growth. It would reduce User's suffering, increase stability, and increase ease of debugging and testing.
And if some companies don't want to join in with the standards, along with everybody else. Then dinosaurs realy do go instinct, you know. But I don't see that happening. After all companies like ATI and Nvidia already do belong to open standards groups like OpenGL.
RTFA! please (Score:5, Informative)
How about (Score:4, Insightful)
Feasability... (Score:5, Insightful)
Expecting geeks to pony up a few hundred bucks for an open-source video card that has little if any chance of competing with ATI/Nvidia on speed seems pretty unlikely.
I wouldn't buy it (Score:5, Insightful)
From a ROI perspective, you have to convince me there's some improvement over the status quo. I couldn't care less about the source. I know that 3d graphics are among the most alien software topics to developers. Its difficult, especially when you're mixing it with low level programming in a performance sensative environment. Not providing 3d means I'll look for a second card. More likely, I'll be looking at a different card that offers more functionality, even on Linux, at 50 dollars, than this can offer at 100.
Simply put, an free-software friendly board lacks a community to push it forward, and I don't see it treading water among the highly competitive graphics card market. If you want this to sell, you need to identify and explicitly cater to your niche market. Promote it as a learning tool, and grease the community wheels. Just putting it out there and expecting the world to recognize its value won't net you much.
Market, Workload, and _Patents_. (Score:5, Interesting)
You won't compete performance-wise with high-end consumer 3D cards. You won't compete budget-wise with low-end consumer 3D cards. You're going to have crappy Windows drivers unless you wave money in front of your developers to work on that uninteresting part and _maintain_ it, _and_ shell out for the Microsoft developer packages for this sort of thing.
Your revenue? Linux geeks who are patriotic enough to pay for a product with less bang for the buck than a standard commercial card, and who will take the promise of eventually-less-buggy drivers some time in the future as being more valuable than a buggy but adequate and fast 3D driver now.
The thread makes mention of hardware cost control, though they're having serious trouble making that competitive (hard to beat quantity-millions for bulk rates). However, Alan Cox's message highlights a serious problem - you have a lack of programmers for cards that specs are already known for.
The only realistic solution I can think of is to pay coders to produce a minimum adequate driver implementation for the new card (or heck, even one of the old ones). Making a decent accelerated 2D driverfor an experimental card is a few person-months of work, if memory serves. Making a decent accelerated 3D driver is a few person-years of work. The budget for this is within reason, but still has to come from somewhere. As there isn't a deeply pressing need for this being felt by most people (see previous point), the pace of volunteer development will be slow (as is shown by Alan Cox's comments about current driver projects).
I'm not suggesting taking this outside the open source community. I'm suggesting paying open source people enough that they can do this as their day job, and have _incentive_ to do this as opposed to some other interesting project.
This is the Big Problem. I can't stress it enough. Any easy way of implementing _anything_ to do with 2D graphics cards was patented a decade ago or more. Any easy way of implementing any basic 3D was patented more recently, but is still patented. Even crawling through the patent database to look for implementations that were missed will take a lot of time, and cost a significant amount of money (you need experts on graphics algorithms and VLSI design to do this, and patent lawyers to back them up; see previous point about volunteer time vs. needed schedule).
Big graphics companies solve this by doing the requisite grunt work, and aggressively patenting everything they can think of as a defensive measure. The standard way of solving patent conflicts is bitter litigation followed by cross-licensing relevant patent portfolios from each other (we've seen this in other parts of the hardware world often enough too). A low-budget open source card project won't be able to afford either of these, and both will eventually become necesary (someone will claim you're infringing no matter how clear it is you aren't, because it's in their best interests to make the claim).
In summary, the only way that I can see an open source graphics architecture being developed is if the community and donors scrape together several hundred thousand to a few million in startup capital to fund hardware and software development, and to deploy lawyers. A side benefit is that you might even be able to afford chip spins if you're on the high side of the funding scale, though it'd probably be more wise to divert the funds to multi-platform driver support and patent portfolio instead.
Variant options that come to mind:
The catch is th
What crappy comments... (Score:4, Insightful)
Yes, you'd have working drivers, which is valuable, but barely worth noting. The big deal will be the more advanced features.
HDTV is developing pretty well, and even if you can't get HDTV broadcasts, there's plenty of HD material on the internet. Unfortunately, most computers aren't fast enough to play 1080 material in any format, and I'd bet there's a few that can't handle 720 video encoded with MPEG-4, WMV, etc. The real answer is to have hardware decoding... MPEG-1/2 are all that we see now, and even that is pretty rare under Linux. I happen to be lucky on that front, but xvmc doesn't allow you to deinterlace before it's displayed, so it's fairly useless at this point.
When you have all the specs for the FPGA, you can just download the latest upgrade, and have full-fledged MPEG4/Theora/WMV decoding on the same videocard, meaning a 100MHz PC could playback HD-DVDs perfectly. No doubt Tivo would be equally as interested in the features of this card.
Even if you don't have a videocard powerful enough to decode your favorite codec, you'll still get serious gains from it being open. If you check-out mplayer's vidix drivers, you'll see that you can get serious performance improvements if the developers have the docs for the card. It's hard to explain what a HUGE performance boost you would get from having a fully-open card.
Plus, FPGA programming is getting a bit of attention lately. It wouldn't be hard to imagine companies setting up clusters of computers, and filling every available PCI slot with this graphics card, and using the cards to do most of the calculations. Remember the PS2 cluster? Imagine the processing power of that, but on steroids.
In addition, think of all the groups trying to setup display-walls, with multiple monitors. Being able to do that much easier with this card could make it a big seller, if nothing else...
As someone who has setup several Unix machines for multimedia, I think there would be a big market for this, even if it costs, say, $60, and has no 3D support. If you think you need 3D support everywhere, you're probably mistaken. If you're running anything other than x86 (or maybe MacOS on PPC) you've got practically no options for hardware-accelerated 3D anyhow. So, putting a 2D card in there, instead of wasting money on a new Radeon, makes everything work better, and you loose nothing.
Personally, I have only 2 suggestions.
1. Make it as cheap as possible, while still being fully functional. If it sells for $30 (maybe after a few months) I'll buy dozens of them myself!
2. Include as many output options as you can. I use S-Video a lot, but very few have interlaced TV-output support. DVI is important for those with LCDs. Composite looks like the next standard for HDTV output, and that could turn into lots of sales (especially if your card costs less than ATI's Radeon/HDTV adapter!). I've heard lots of cards don't work with HDTV well because they can't output an interlaced signal at HDTV resolutions.
Dual-head support would be very nice, at least if you can include dual overlay support with it. Then you only need 2 cards for a 4-head Linux system.
The other killer app (Score:5, Insightful)
A path that could be very fruitful is to design a video card to be used in a TiVo-like device. In particular, in addition to the good suggestions involving the Render and Damage extensions, a 2D-only card should do some hardware accelerating of IDCT and motion compensation, so that i.e. DVD's and MPEG-4 files can be played with a very minimal CPU. Work with systems integrators that are willing to put MythTV on a silent fanless system with a pcHDTV card and your video card/chip. This could be a good way to go for smaller but demonstrated market, where the part is easier to design than a 3D-nvidia-ati competing beast. Actually doing the video and TV on the same part is a good idea, if it can be done, since these machines are usually space and PCI-slot constrained.
I do not think, out of the gate on a small budget is reasonable or feasable to get a 3D part. It would be better to start small, and plan some features for the second generation. For funding, take pre-orders. Oh and hype the shit out of it, on slashdot.
Secondly, how feasable is it to put a cheap off-the-shelf CPU on the part to handle the 3D workload. Certainly that's faster and cheaper than a FPGA. CPU's with MMX or Altivec instructions can be had in the 1-2 GHz range for < $50.
-- Bob
Bad idea. Will be obsolete on day one. (Score:4, Insightful)
It might be more worthwhile to work on better relationships between Linux developers and Via. Via sells a large fraction of the motherboard chipsets (if it's not Intel, it's probably Via) and, as a commodity part manufacturer, doesn't have a strong business interest in a proprietary interface.
If Via can be brought on board (assuming it isn't already) that provides more leverage for dealing with other vendors, like nVidia.
Sounds good to me (Score:5, Insightful)
Support multi-head operation with robust Xinerama support, good colour calibration etc. and provide hardware acceleration for compositing, video4linux overlays, SDL hardware blitting, X primitives, Freetype font renderers, DirectFB acceleration - this card could form the heart of every low-cost or embedded linux system sold in existing or emerging markets round the world, and provide significantly better 2D desktop acceleration than ATI or NVidia, who seem to put 100% of their efforts into appeasing the Doom3 players.
Even if its not a match 3D-wise to a Geforce FX6800, it wouldn't be hard to do a better job of supporting Linux APIs than 90% of the manufacturers out there.
I disagree (Score:4, Informative)
Just a reminder, drivers are a cost for video card manufacturers. They sell a card and have to bury the cost of driver development and maintenance into the cost of the card. Open sourcing driver development lets a card manufacturer profit from the hardware while the community develops drivers for them and they get good karma to boot. This would be a fairly inexpensive/low risk way for a low-end (PCI only it appears at the moment) card manufacturer to get their "foot in the door".
Only the "big boys" (Nvidia and ATI) have anything to lose by open sourcing their cards. People would actually see to what extent they fudge their cards and drivers for benchmarks.
Parent
Re:I'll second that. (Score:4, Interesting)
I would be THRILLED if there was a card out there for $150, where I could compile the drivers from source and run OpenGL-based games at a decent speed on this computer.
Like some others have said though, while I don't expect them to be competitive with nVidia and ATi's higher end products, I WOULD like them to provide moderate performance, perhaps on par with a lower end radeon cards. The lower end ATi Radeon 9200 provided excellent performace per dollar, and I would be willing to purchase a similar open-source'd card for well over the amount I paid for that card ($89). I realize that this would require quite of bit of investment though, since the company would probably need to use top-of-line or nearly top-of-line device process flows to achieve this type of chip.
My only fear is that if this becomes a reality and catches on, we will see ATi/nVidia step up their support for Linux JUST enough to pull away any consumer base this company might gain.
Regardless, I agree that to get from concept -> implementation requires $$$, so I would recommend that this company come to some kind of decision and allow the consumer to "prepurchase" or otherwise finance such a card.
Parent
Re:I'll second that. (Score:4, Interesting)
As soon as you start talking Linux, the performance advantage of the Radeon 9x00 vs it's GeforceFX equivalents vanishes.
As soon as you start talking Radeon X800 vs Geforce 6800, the Geforce is clearly ahead on windows. And there are no X800 Linux drivers yet AFAIK, so that's clearly a wash. But even assuming they were availeable we can extrapolate from both companies' track record and assume the 6800 drivers will still be better.
In summary:
9x00 > a similarly priced GeforceFX *ON WINDOWS*
GeforceFX > a similarly priced 9x00 *ON LINUX*
6800 > X800 *PERIOD*
Now, it is possible to find a benchmark on Windows where the X800 outperformes the 6800, but they are few and far between. And since we're mostly interested in FOSS OS's, who the hell cares anyway?
Parent