Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Basic Linux Boot On Open Graphics Card

timothy posted more than 4 years ago | from the bumblebee-flies-anyway dept.

GNU is Not Unix 177

David Vuorio writes "The Open Graphics Project aims to develop a fully open-source graphics card; all specs, designs, and source code are released under Free licenses. Right now, FPGAs (large-scale reprogrammable chips) are used to build a development platform called OGD1. They've just completed an alpha version of legacy VGA emulation, apparently not an easy feat. This YouTube clip shows Gentoo booting up in text mode, with OGD1 acting as the primary display. The Linux Fund is receiving donations, so that ten OGD1 boards can be bought (at cost) for developers. Also, the FSF shows their interest by asking volunteers to help with the OGP wiki."

cancel ×

177 comments

Sorry! There are no comments related to the filter you selected.

Hey (1, Funny)

Anonymous Coward | more than 4 years ago | (#27800733)

Cool story bro.

Re:Hey (4, Informative)

thsths (31372) | more than 4 years ago | (#27801001)

Cool, yes. Useful - hardly.

If you start with a clean slate, why would you bother with VGA emulation? Could you not just go for a sane solution, such as a flat frame buffer? Any other architecture does that, why does the PC architecture have to drag along legacy modes such as CGA with a number of 4 colors palettes?

A flat 8bit RGB buffer would make a lot more sense, and I am sure Linux would boot faster on it, too.

Re:Hey (1, Insightful)

Anonymous Coward | more than 4 years ago | (#27801113)

Cool, yes. Useful - hardly.

why would you bother with VGA emulation?

So you can put it in a standard x86 PC and see the BIOS?

Re:Hey (4, Insightful)

DaleGlass (1068434) | more than 4 years ago | (#27801117)

Unfortunately the BIOS and boot loader will still need VGA. Maybe Linux BIOS could remove that requirement, but you can't count on that.

They seem to have implemented it in a very cool way too. Quote from a linked OSNews article:

Aside from the logic reduction, this has other advantages. The screen resolution as seen by the host is decoupled from the physical display resolution. So while VGA thinks it's 640x400, the monitor could be at 2560x1600, without the need for a scaler. It's easily programmable, and we have complete control over how the text is processed into pixels; for instance, we could have HQ do some scaling or use a higher-res font different from what the host thinks we're using.

Re:Hey (0)

YayaY (837729) | more than 4 years ago | (#27801205)

I think they totally missed the point. They shouldn't be trying to build open hardware, they should be trying to build an open platform. They will never be able to compete with a pile of free old VGA card.

Linux don't need the BIOS to boot, so they should simply get ride of it and build new open hardware on top of a new open firmware.

Re:Hey (2)

suso (153703) | more than 4 years ago | (#27801225)

Why don't you get involved in the project then and tell them that.

Re:Hey (2, Informative)

DaleGlass (1068434) | more than 4 years ago | (#27801419)

Linux don't need the BIOS to boot, so they should simply get ride of it and build new open hardware on top of a new open firmware.

Sure it does, the BIOS boot screen, settings, etc are kind of important to be able to see sometimes. The boot loader also counts on the VGA mode too.

Now of course you could use Linux BIOS instead, but then that adds the requirement to have a supported motherboard, and wanting to risk flashing it.

Re:Hey (1)

YayaY (837729) | more than 4 years ago | (#27801479)

No, it don't.

http://www.debian.org/ports/ [debian.org]

Linux does work on other platform than the x86 and those other platforms do not have a BIOS. You could build some other computer that is not BIOS-compatible and would be open source from the bottom-up.

Re:Hey (1)

DaleGlass (1068434) | more than 4 years ago | (#27801527)

Yeah, you could.

But that non-x86 computer probably doesn't have a PCI slot where to plug that card in, so that detail doesn't seem to be very important.

Most computers where you can plug one into are going to start in text mode, and being unable to do things like changing the disk boot order in the BIOS would be quite annoying.

Re:Hey (1)

Lennie (16154) | more than 4 years ago | (#27801631)

Sparc is a pretty open platform (open processor specs if I'm not mistaken and some open source processors available as well), it has PCI-support.

Re:Hey (3, Interesting)

DaleGlass (1068434) | more than 4 years ago | (#27801709)

Ok, and how many people are going to run a desktop on it? It's server hardware.

Again, you seem to be missing my point. Yes, Linux technically doesn't need the BIOS. Yes, there exist other architectures besides x86.

But, a video card is a product for desktops, and the vast majority of desktops are x86. The vast majority of those start booting in text mode.

Pretty much all other architectures are unimportant in comparison, because they're used in embedded hardware, or are technically outdated. If anybody is going to buy this thing, I doubt they're going to put it into a modern Sun server.

It's already a project that's going to find it hard to get wide adoption, why would you make it even harder for it to find an use, by making it incompatible with the most common by far hardware it could be plugged into?

Re:Hey (2, Interesting)

farfield (1119449) | more than 5 years ago | (#27802143)

I've used Sparc desktops [sun.com] in the past. I even used one as my main home machine for a while. You could even get Sparc laptops.

In their time they beat the Intel option imo and they are still in use in some places.

Re:Hey (-1, Offtopic)

Anonymous Coward | more than 5 years ago | (#27802205)

Wow, you're special.

Re:Hey (2, Interesting)

marcansoft (727665) | more than 4 years ago | (#27801263)

For what it's worth, nVidia cards can do this just fine and have been able to for a long time. See the "full GPU scaling" option in nvidia-settings. My HTPC's nVidia card also shows the BIOS on my HDTV at 1080p link resolution (while pretending to be VGA to the software).

Re:Hey (3, Interesting)

DaleGlass (1068434) | more than 4 years ago | (#27801447)

But it probably still uses a 8x16 pixel font, which doesn't look that good on a 30" screen.

I think the idea is that the video card could pretend it's VGA, while substituting an antialiased 32x64 font in its place. Nothing earthshaking of course, but that sure would look nice.

Your text mode could look like this [omag.es]

Re:Hey (0)

Anonymous Coward | more than 4 years ago | (#27801119)

Cool whoosh bro.

Re:Hey (4, Insightful)

MBCook (132727) | more than 4 years ago | (#27801167)

Slashdot, RTFA, blah blah blah.

If you go to the Wiki, and read the link in the top article, there is a link to OS News. If you follow that and read down in the comments, you'll find this post [osnews.com] by the architect of the VGA emulation.

Apparently it really is emulation. Their MCU that they use as a PCI interface has a mode that generates the raw pixels when given VGA commands. It handles the VGA interface. The graphics processor just receives (from it's perspective) pixmaps that are constantly generated by the MCU in VGA mode.

The guy says that VGA on their card is actually resolution independent (since the MCU generates what is needed) and could actually be up-sampled to show clearer fonts without the OS having any idea it was going on.

He says it's not the cleanest way of doing things (from a methodology standpoint), but it has the least impact on the design of the hardware (compared to a "real" VGA interface).

Re:Hey (1)

TheRaven64 (641858) | more than 4 years ago | (#27801207)

Most modern graphics cards (as in, made in the last decade or so) do something similar. VGA mode has been emulated for a long time. To the grandparent wanting real framebuffers, VESA has provided this for a long time on PC hardware too, but for some things it's nice having an interface that looks like a tty, and basic firmware and OS code are two of these things.

Do we want an open source video card? (1)

Lord Byron II (671689) | more than 4 years ago | (#27800739)

I can understand open sourcing the software, but can someone explain the benefits of opening the hardware as well?

Re:Do we want an open source video card? (3, Insightful)

nurb432 (527695) | more than 4 years ago | (#27800763)

Do you want to be tied to a vendor?

If the answer is no, then you understand. if you don't mind being tied to a vendor and at their mercy, then i guess the answer for you is that there is no benefit.

Open hardware has the same value as open software.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27800855)

Tied to a vendor? Huh?

If I don't like my NVidia card, I can move to a competitor's chipset.

If I don't like the board manufacturer, I can move to any of 10 others just like them.

Pretty much ALL of these cards are interchangeable.

So far as I can tell, for now at least competition is working just fine in the graphics card market.

How on earth are a bunch of volunteers going to compete with the big boys when they don't have anything like the R&D or can cook the chips at the same scale, or have the boards made and sold by 10 cheap Asian competitors at high volume and that keep each other in check on prices.

Of course, if this is mostly an academic exercise and not really ever intended for consumers, then I understand totally.

Drivers (4, Informative)

tepples (727027) | more than 4 years ago | (#27800899)

If I don't like my NVidia card, I can move to a competitor's chipset.

Only if the competitor is friendly to the free software community. There are plenty of hardware makers that have declined the free software community's requests for low-level specifications useful for writing free drivers.

Re:Drivers (0)

Anonymous Coward | more than 5 years ago | (#27802361)

Which means that there is an incentive for those companies to be friendly to the free software community, because the competitors that are FOSS-friendly will (hopefully) do better.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27800921)

"If I don't like my NVidia card, I can move to a competitor's chipset."

So you can switch to completely different hardware, so possibly you have to throw away lots of software (like all CUDA stuff). With open hardware keeping the chipset is a possibility, you only have to find somebody willing to produce the according to the specs.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27800999)

And you also have to be willing to accept performance that's nowhere near what's available for half the price otherwise.

Yeah but FOSS is a vendor too. (2, Insightful)

tjstork (137384) | more than 4 years ago | (#27801323)

If the answer is no, then you understand. if you don't mind being tied to a vendor and at their mercy, then i guess the answer for you is that there is no benefit

Yeah, but open vendors are vendors too. That's the thing. Basically, what you are trying to do is suppress innovation for the sake of commoditization, and that's not a proposition that people want to make.

Re:Yeah but FOSS is a vendor too. (1)

nurb432 (527695) | more than 4 years ago | (#27801481)

But if you have the HDL code you can choose anyone you want to produce it, or use FPGAs

Re:Do we want an open source video card? (1)

H0p313ss (811249) | more than 5 years ago | (#27801841)

Do you want to be tied to a vendor?

If the answer is no, then you understand. if you don't mind being tied to a vendor and at their mercy, then i guess the answer for you is that there is no benefit.

Open hardware has the same value as open software.

Right... every time I run a high-end game on my propriatary 3D driver I have to stop and flagellate myself halfway though to dull the guilt... not...

Re:Do we want an open source video card? (1, Informative)

Anonymous Coward | more than 4 years ago | (#27800771)

Yes.

Reason 1: Do you really like the idea that you have no idea how your computer works. It would be trivial for your hardware manufacturer to slip in some sort of user-spying component...

Reason 2: Lot's of people can learn from it.

Reason 3: Contrary to popular belief, people do hack around with hardware and provide ways for people to improve theirs... These sort of boards make this even easier.

Reason 4: FOSS can better support it.

Re:Do we want an open source video card? (3, Interesting)

Brian Gordon (987471) | more than 4 years ago | (#27800793)

Well obviously it's of academic interest. American consumers have sunk billions into video card research and for the most part the implementations are shrouded in mystery locked up in labs. Nobody un-NDA-bound really knows how to build these things: computer graphics is a highly specialized and difficult problem for hardware engineers. The real interest is in making a hardware design that actually works well and then writing up the design in abstract, not to actually make working video cards.

Also I guess it's useful to hammer out some foundational "building blocks" and make them available freely so that entry into video card research is easier.

Re:Do we want an open source video card? (2, Insightful)

Jeff DeMaagd (2015) | more than 4 years ago | (#27800953)

Well obviously it's of academic interest. American consumers have sunk billions into video card research and for the most part the implementations are shrouded in mystery locked up in labs.

The problem with this line is that the American consumers may have sunk billions into buying video cards, they were never promised any or all the knowledge required to build one. In other words, you bought a product, not the product design process process, and your line seems to suggest confusion on that part.

Re:Do we want an open source video card? (5, Informative)

BikeHelmet (1437881) | more than 4 years ago | (#27801135)

and your line seems to suggest confusion on that part.

Doesn't seem that way to me. He's just pointing out that when compared to other electronics, we have shockingly little info available.

Even for CPUs, there are fully documented "open-source" microcontrollers available, but for GPUs there's basically nothing. It is a big mystery, how it's all done. And now we've gone so far that GPUs are doing incredible things like juggling 10,000 threads that manage all the shading when, you fire up a game.

nVidia and ATI stated GPUs are many times more complex than CPUs, and I fully believe them.

Re:Do we want an open source video card? (1)

BitZtream (692029) | more than 4 years ago | (#27801759)

Its not that big of a mystery, nor does it matter that it does in the grand scheme of things.

There are AVR microcontrollers that can output a VGA signal via bitbanging, so that part is obviously simple enough.

You don't really HAVE to continue legacy VGA support, make a new standard thats a good solid standard and will in some way benifit pc manufactures and you'll have bioses and OSes that support them shortly afterwords.

The problem isn't the technology, the problem is starting from scratch and lasting long enough to make something useful to the people who matter. If one company does it, makes it open and fails, then someone else can come along and pickup where they left off. It make not work the first try or even the first 10, but eventually it'll get good enough and someone (big) will get pissed off enough at AMD and nVidia and will want to go their own way.

nVidia and ATI are speaking about being more complex is specific ways, but they are less complex in others. They do certain things much better than a general purpose processor, and now days they do a lot of those things in parallel. They also tend to suck at complex logic control, and go to hell in a hand basket if you have to branch, which is something that is FAR more complex in an x86 processor.

Its all relative, they aren't perfect for general purpose computing or we'd be buying a $100 nVidia processor/mobo running an x86 emulator, but we aren't, are we?

Re:Do we want an open source video card? (1)

ShieldW0lf (601553) | more than 4 years ago | (#27801433)

The problem with this line is that the American consumers may have sunk billions into buying video cards, they were never promised any or all the knowledge required to build one. In other words, you bought a product, not the product design process process, and your line seems to suggest confusion on that part.

The claim to ownership is only as valid as the peoples preparedness to acknowledge it. Might be wise to keep that in mind unless you want to be tremendously unprepared for the future...

Re:Do we want an open source video card? (0, Flamebait)

The End Of Days (1243248) | more than 4 years ago | (#27801629)

Is this the magical future where people will altruistically spend billions of dollars to give free shit away to people who figure they're entitled to the work of others?

Does this amazing shift in human nature happen through concentration camps or forced eugenics or something?

Re:Do we want an open source video card? (2, Funny)

atraintocry (1183485) | more than 4 years ago | (#27801731)

This is why I love Slashdot: lazy Saturday, talking about video cards, not even 100 posts up yet...

BAM! Godwin!

Re:Do we want an open source video card? (1)

ShieldW0lf (601553) | more than 5 years ago | (#27802313)

Does this amazing shift in human nature happen through concentration camps or forced eugenics or something?

Yes. It does.

Re:Do we want an open source video card? (-1, Redundant)

Anonymous Coward | more than 4 years ago | (#27800961)

Also I guess it's useful to hammer out some foundational "building blocks" and make them available freely so that entry into video card research is easier.

Brian,

I fix cars.
I do home repairs and improvements.
I LOVE computers and video games (my fave right now is Fallout 3).
I love to read.
I know how to balance a checkbook and manage a budget.
I'm a fantastic cook (I've done that professionally before.).
I love to iron and like to clean (especially bathrooms).
I sew, mend, and quilt.
I can do pole tricks.
I'm an exhibitionist.
One of my previous psychologists diagnosed me as having "Hyposexuality Disorder", which is like a medical way of saying I'm a nympho.
I'm highly intelligent.
I give good massages.
I give great head.

Re:Do we want an open source video card? (1)

bhtooefr (649901) | more than 4 years ago | (#27801021)

Nitpick: Hyposexuality means you're the opposite of a nympho - you don't desire sex AT ALL.

I think "hypersexuality" is the word you were going for. :)

Re:Do we want an open source video card? (5, Insightful)

Animats (122034) | more than 4 years ago | (#27800993)

There's not that much mystery about the things. Making a VGA emulator in an FPGA is no big deal. If all you implemented was text mode and mode 13H, it would probably boot Linux. Getting to a card that runs OpenGL is a big job, but not out of reach. The pipeline is well understood, and there are software implementations to look at. As you get to later versions of Direct-X, it gets tougher, because Microsoft controls the documentation.

But the real problem is that you'll never get anything like the performance of current generation 3D boards with an FPGA. There aren't anywhere near enough gates. You need custom silicon.

Re:Do we want an open source video card? (1)

Brian Gordon (987471) | more than 4 years ago | (#27801121)

Just because you used a compiler-compiler toolchain to chew up your OpenGL book and spit out a hardware spec doesn't mean you have an opengl card. Implementing OpenGL efficiently isn't just a "big job" it's essentially the entire field of computer graphics hardware.

Re:Do we want an open source video card? (3, Insightful)

Animats (122034) | more than 4 years ago | (#27801187)

Implementing OpenGL efficiently isn't just a "big job" it's essentially the entire field of computer graphics hardware.

It's understood, though. And you can do it in sections. Start with an OpenGL implementation that does tessellation, geometry transforms, and fill in software. Build something that just does the fill part. (That's 1995 technology in PC graphics.) Then add the 4x4 multiplier and do the geometry on the board (that's 1998 technology on the PC, 1985 technology for SGI.). Once all that's working correctly and the read-back of the frame buffer matches the OpenGL spec for the tests, you can start to work on parallelism. (That's 2000 technology). Then comes programmable shaders and arbitrary computation on the graphics board, which gets hard.

It's a lot like Linux; a decade behind, but still useful.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 5 years ago | (#27802373)

It's a lot like Linux; a decade behind, but still useful.

Obviously the mods aren't doing their job right.

Re:Do we want an open source video card? (0)

ToasterMonkey (467067) | more than 5 years ago | (#27802555)

It's a lot like Linux; a decade behind, but still useful.

Obviously the mods aren't doing their job right.

Because there isn't a +1 True option?

Re:Do we want an open source video card? (1)

PopeRatzo (965947) | more than 4 years ago | (#27801059)

American consumers have sunk billions into video card research

American consumers have sunk billions in buying video cards on which to play games. Then, the companies that designed the components for those video cards invested in video card research.

It's not exactly the same thing.

Re:Do we want an open source video card? (1)

Brian Gordon (987471) | more than 4 years ago | (#27801183)

I was just pointing out that tons of money is being spent so the technology is advancing. Graphics hardware really is amazing; is your car superceded every 2 years by newer models with 10 times as much horsepower? Do "car textbooks" still teach carburetors while mechanics scratch their heads and wonder what happened to the thing with the air holes? Nvidia is making their own products obsolete every few years by their frenetic pace of research, but nobody really knows what they're up to.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27801639)

"Nobody un-NDA-bound really knows how to build these things: computer graphics is a highly specialized and difficult problem for hardware engineers."

The barrier isn't that people don't know how to build these things, its that it takes a lot of time and can cost a lot of money for the required tools to make a good job of it. There are a lot of programmers who know 3D graphics programming who also know electronics. Its not beyond the realms of possible that more open graphics cards will be designed.

Re:Do we want an open source video card? (1)

andr386 (703803) | more than 4 years ago | (#27801695)

Hopefully video cards companies have filled patent, meaning their 'research' paid for by the american consumers will eventually transfer to the public domain ... So everything is not lost. But really I wonder, in this area of fast paced technology, should the patent rights last so long ? How much time before this technology is released to the public ? Shouldn'it be much less ? In areas where technology is going very fast, patent's rights should be very short. Allowing the market to be more open to new innovations and new companies.

Re:Do we want an open source video card? (1)

Brian Gordon (987471) | more than 4 years ago | (#27801803)

But that hasn't traditionally been the case so our laws aren't really fit for this kind of market.

Re:Do we want an open source video card? (3, Interesting)

Daemonax (1204296) | more than 4 years ago | (#27800827)

We're geeks... So the reason is "because we can". It provides a system where we don't have another blackbox. We can actually understand down to the lowest level how things are working. This is great for people who desire to understand how things work, and also people that hope for a future of machines and hardware that are under the control of the owners.

Sorry to get a bit crazy here, but imagine a world with technology like that in Ghost in the Shell. I would not go getting such implants and additions if I did not and could not have complete control and understanding over the stuff. This type of project is a small step in maintaining individual control.

Re:Do we want an open source video card? (4, Insightful)

cduffy (652) | more than 4 years ago | (#27800841)

When a piece of music, or a play, enters the public domain, there are effects beneficial to the public:

  • Direct embodiments (sheet music, CDs, etc) become cheaper, and thus accessible to more of the public.
  • Derived works are easier (no licensing hassle) to create.

These have analogs here. Having a Free video card design means that low-end video cards can become that much cheaper (and that there's more room for new entrants into the very-low-end market), and that there's a common, available base on which new and innovative work can be done.

Re:Do we want an open source video card? (2, Insightful)

Lorien_the_first_one (1178397) | more than 4 years ago | (#27801349)

Agreed. I'm not a gamer, but I like the idea of having an open implementation of a graphics card for my use. Lower the barriers to entry to the market, and things get really interesting.

I hope this group of engineers can succeed in producing an open board that eventually provides high-end graphics capabilities.

Re:Do we want an open source video card? (1)

ypctx (1324269) | more than 4 years ago | (#27800851)

No waiting for a manufacturer to provide open source drivers. Better cooperation with other open source projects, like Xorg. Perhaps faster progress if the number of open source developers exceeds the number of developers of competing proprietary products, hourly/motivation/quality-wise.

Re:Do we want an open source video card? (1)

Jeff DeMaagd (2015) | more than 4 years ago | (#27801261)

That assumes that this open graphics card is going to be anywhere near the commercial graphics chips any time soon. If you're already content with obsolete technology by going to VGA, then open source driver support isn't going to be a problem.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27801557)

If you're already content with obsolete technology by going to VGA ...

You seem to have missed the point that the VGA handling is done by the onboard micro in order not to mess up the bulk of the graphics hardware, which is modern. VGA is acknowledgedly obsolete --- that's why it was done that way, in order to consume the least hardware resources and hence have the least possible negative impact on the project.

Re:Do we want an open source video card? (0)

Anonymous Coward | more than 4 years ago | (#27800887)

Having open hardware means faster improvements in the hardware. We don't have to find out latter that the move from a 12000xxx to 13000zxz graphics card was just an overclock.

A milestone? (3, Insightful)

Brian Gordon (987471) | more than 4 years ago | (#27800749)

Isn't VGA a very thoroughly documented and widely implemented standard?

Also, they can't possibly approach competing with NVidia or ATI and I doubt anyone's going to shell out a billion dollars to build a plant to make their cards. If they're just playing around with FGPAs then this isn't really a serious "Open Graphics Card" ... performance will be terrible .

Re:A milestone? (3, Funny)

ypctx (1324269) | more than 4 years ago | (#27800773)

Well, second step is Open Source Factories.

Re:A milestone? (5, Funny)

Kotoku (1531373) | more than 4 years ago | (#27800831)

Step 1: Open Graphics Card Step 2: Open Source Factories Step 3: ???? Step 4: Communism!

Re:A milestone? (1)

Voyager529 (1363959) | more than 4 years ago | (#27801031)

In Soviet Russia, Video Cards Render You!

Re:A milestone? (0)

Anonymous Coward | more than 4 years ago | (#27801767)

Step 5: Open Communism?

Re:A milestone? (1)

allaunjsilverfox2 (882195) | more than 4 years ago | (#27800865)

I know it's a couple of light years from this but it'd be awesome to see a combination of a solaris open cpu / fpga card. Then your computer would truly be yours.

Re:A milestone? (2, Insightful)

morcego (260031) | more than 4 years ago | (#27801045)

The best answer I've read so far regarding the "why" for this was simply: because we can.

There is a reason people pay so much for other people to make computers (sw and hw). It is so they don't need to worry about it.

I'm all for the Open Whatever project. Simply "because we can". It is like climbing a mountain.

And hey, who knows what we will see on the other side once we reach the summit.

Re:A milestone? (1)

prefec2 (875483) | more than 4 years ago | (#27801169)

Right now engineers develop so called smart fabs, which are able to produce different types of products based on similar concepts. They are very popular in the automobile industry. So you can build on the same process line a VW Golf and a Audi A8 at the same time.

I guess something similar will happen to the chip factories. This would be a step in the right direction for many companies selling gadgets like smartphones, netbooks, navigation systems etc.

This would allow them to integrate all functions on one chip.

Re:A milestone? (1)

TheRaven64 (641858) | more than 4 years ago | (#27801235)

Not exactly the same thing, but there are a few IC manufacturers who specialise in low-yield jobs. Often they are a generation behind in terms of process technology (130nm stuff is really cheap now), but they are relatively cheap for lots as small as a few thousand, and a few of them will do lots as small as ten, in the corner of another customer's wafer (much more expensive per-unit). While not everyone can make an open source CPU or GPU in their home, anyone can contribute to the design, and with enough people interested in getting one you can produce them quite cheaply. Manufacturing will cost more than manufacturing an Intel chip which expects to sell millions, but the R&D costs are lower, so the final price difference may not be as much as you'd expect.

Re:A milestone? (1)

maxume (22995) | more than 4 years ago | (#27801577)

When the nanoassembler dream comes true, Open Graphics Card will be there.

Or something. This stuff doesn't really spin my gears, but there are people doing a far better job completely wasting time than these guys.

(I really don't see how these guys are ever going to be competitive with old Nvidia or Intel hardware and also cost less than said hardware, the old Nvidia and Intel stuff is mad cheap)

Re:A milestone? (4, Informative)

DavidR1991 (1047748) | more than 4 years ago | (#27800797)

The /. post gives the wrong impression about the VGA implementation - it was difficult because they wanted to implement it in a extremely simple fashion, not because VGA itself is complex

Re:A milestone? (1, Interesting)

Anonymous Coward | more than 4 years ago | (#27800807)

There are custom fabs all over the world. This might also be a real boon to folks who make embedded devices; a low-cost video core that you can customize for your application or load on your cpu/fpga combo could be a "big deal"

John

Re:A milestone? (4, Interesting)

iamacat (583406) | more than 4 years ago | (#27800825)

Also, they can't possibly approach competing with NVidia or ATI

If you are running Windows on an x86 box, this may be true. Move to FreeBSD on an ARM embedded display and getting the drivers becomes dicey. Want to optimize medical imaging requiring 48 bit color rather than a typical game? Bet you will have better luck with an FPGA than an off the shelf card.

Re:A milestone? (1)

noidentity (188756) | more than 4 years ago | (#27801249)

I think the FPGAs are part of their development environment, not the final hardware, sort of the equivalent of putting files together on a hard drive, and in the end using that as the master for DVD pressing.

if you want 48-bit color... (1)

YesIAmAScript (886271) | more than 4 years ago | (#27801335)

You're gonna need 16-bit D/A. And you don't do that with FPGAs. What you really need is a 48-bit RAMDAC. The rest is easy, you don't even need any GPU acceleration if it would be too difficult to work it out, just use the CPU.

I have written display drivers for several ARM embedded devices. I find it pretty easy, because when you make a system like that, you can get the entire spec for the display from the display controller vendor, something you can't get from NVidia or ATI.

Re:if you want 48-bit color... (0)

Anonymous Coward | more than 5 years ago | (#27801851)

I find it pretty easy, because when you make a system like that, you can get the entire spec for the display from the display controller vendor, something you can't get from NVidia or ATI.

So, perhaps Intels Larrabee will not be about performance but openness..

Re:A milestone? (1)

hpa (7948) | more than 4 years ago | (#27800863)

VGA is reasonably well documented, although a lot of the quirks aren't. It is, however, a horrible and painful design which had a zillion rarely-used features.

Re:A milestone? (1)

taniwha (70410) | more than 4 years ago | (#27800971)

well yes and no - chunks of VGA are well documented - but it's a register spec that doesn't say what happens when you deviate from the documented register values - over the years various programmers have stepped outside the spec and gone their own way (doom, microsoft, ....) enough people have done it that unless your design does the right thing in all these architectural black holes you're not 'compatible'

Re:A milestone? (4, Informative)

Jeff DeMaagd (2015) | more than 4 years ago | (#27800891)

A lot of times, FPGAs are used for development. Once the design is proven, then you can go to etching into silicon. Almost nobody builds a fab for one chip, the good news is that chip fabs can make numerous different kinds of chips. There are many fabs that are willing to take any design that comes their way, as long as the money is there.

Re:A milestone? (1)

zlogic (892404) | more than 4 years ago | (#27800923)

Both ATI and Nvidia are fabless companies. They only design chips and then send the specs to a plant in China.

Re:A milestone? (1)

JDub87 (1391689) | more than 4 years ago | (#27800967)

They don't need to shell out billions to build their own plant, just funding to have a 3rd party foundry build thier chips. Most manufacturers (intel, nvidia etc) sell off their old fabs when after a few generations for RAM production etc. Hell AMD recently spun off its fabrication division due to lack of funds. Now they just contract to (globalfoundries?) for their chips. http://arstechnica.com/hardware/news/2008/10/and-then-there-was-one-amd-spins-off-foundry.ars [arstechnica.com] Wish I knew what kind of price penalty you take by having another company handle that stuff for you in several quantities of say 10,000 - 100,000 and 1,000,000 chips. I'll bet if you make bulk orders it isnt bad, fabs are probably just happy to keep the machines running before they're obsolete.

Re:A milestone? (1)

prefec2 (875483) | more than 4 years ago | (#27801089)

I guess it is a little bit like FOSS. First it is developed by a group of geeks who have fun doing such things. Even though they cannot compete with anybody on any term. Then after a while, it becomes good enough for other geeks, so they use it. And even if it is only to show their independence from EVIL companies. And after two decades they provide a VGA chip, which is good enough for the average user. Yes the gamers will use then still really expensive hardware from EVIL companies, but other organisation will use cheap hardware designed by the open hardware community. IBM, Intel, AMD will support them and will have founded the Open Hardware Development Labs.

Perhaps... (1)

Lorien_the_first_one (1178397) | more than 4 years ago | (#27801443)

...you underestimate the capacity of volunteers, or even companies that allow their engineers to work on such products. As an example, it's been well documented that the cost to build Linux [developerfusion.com] exceeds at least a billion dollars. And few took Linux seriously in the beginning except the volunteers who believed in the project.

So if companies and individuals worldwide are willing to free themselves from proprietary graphics card designs so that their software will work better, then they're probably willing to invest a billion dollars or more, for it.

You seem to think that the performance would be so terrible for an open graphics card. Don't forget that the companies that have invested in Linux now have a world class operating system for things like supercomputing, transaction processing (think NYSE) and similar pursuits. This comes complete with the GCC which is highly regarded among programmers, some might even regard it as the best compiler available. Free.

If large corporations who use Linux weren't happy with the performance there, then they might have gone back to the proprietary software they were using before. But they didn't. I'm inclined to think that a similar line of progression can be anticipated with graphics cards.

Wouldn't you agree?

Re:Perhaps... (1)

Brian Gordon (987471) | more than 4 years ago | (#27801763)

So if companies and individuals worldwide are willing to free themselves from proprietary graphics card designs so that their software will work better, then they're probably willing to invest a billion dollars or more, for it.

I think you're making an unwarranted connection between how much it would have cost to build Linux commercially and how much Linux is actually worth. Though it may have taken a billion dollars of work, if it only carves out 500 million of wealth in its lifetime then investors certainly wouldn't be kicking themselves wishing they'd invested a billion. Doing a billion dollars of work doesn't guarantee you profit: a thousand people sitting around prime factorizing The Largest Number Ever Discovered for 50k/yr * 20yr certainly isn't worth at least a billion dollars. And even if you're doing something promising like open-sourcing your hardware, it's a lot to risk.

Could be... (1)

Lorien_the_first_one (1178397) | more than 5 years ago | (#27801935)

How do you estimate 500 million? Linux has become a utility platform for computing for ventures large and small. And for a growing number, desktop computing. It could be that the value of Linux to many people is intangible. You know, freedom, transparency, that sort of thing. But that can translate into saved man-hours, which is money.

As far as risk is concerned, most companies and individuals have taken many calculated risks since there is no guarantee of profits. This is true for any venture (otherwise it's not capitalism).

I believe that the value of an open source graphics card will be worth the investment to the companies that do invest in it, in the long run.

Re:Could be... (1)

Brian Gordon (987471) | more than 5 years ago | (#27802101)

I do think Linux is worth a billion dollars, but "how much it would have cost" doesn't have anything to do with it.

What's the purpose of a "new" legacy card? (0)

Anonymous Coward | more than 4 years ago | (#27800829)

Why not build a card that has the simplest digital output modes and focus on the frame buffer interface and rendering?

Can legacy BIOS booting (VGA, text mode) be handled through software emulation?

Re:What's the purpose of a "new" legacy card? (2, Informative)

sxpert (139117) | more than 4 years ago | (#27800903)

If you had RTFA you would have noticed that that's exactly what they have done !!

Nice to see (1)

R.Morton (1540993) | more than 4 years ago | (#27800849)

the project is not dead after all I remember reading about this a few years ago.

Just hope that can get enough Interest together soon so we can have a nice open Graphics Platform to work with other than boring and slow but at well supported Intel Integrated Chipsets.

R.Morton

some kind of useful background (5, Informative)

Anonymous Coward | more than 4 years ago | (#27800925)

from http://www.osnews.com/permalink?360100 [osnews.com] As the original architect of the way VGA is done on this board, perhaps I can offer an explanation. There is perhaps a more straightforward way of implementing VGA than the way we did it. The direct route would require two components. One piece is the host interface that interprets I/O and memory accesses from PCI and manipulates graphics memory appropriate. The other piece is a specialized video controller that is able to translate text (which is encoded in two bytes as an ASCII value and color indices) in real-time into pixels as they're scanned out to the monitor. This is actually how others still do it. To us, VGA is legacy. It should be low-priority and have minimal impact on our design. We didn't want to hack up our video controller in nasty ways (or include alternate logic) for such a purpose, and we didn't want to dedicate a lot of logic to it. Doing it the usual way was going to be too invasive and wasteful. Also, we want eventually to do PCI bus-mastering, which requires some high-level control logic, typically implemented in a simple microcontroller. So we thought, if we're going to have a microcontroller anyhow, why not give it dual purpose. When in VGA mode, the uC we designed (which we call HQ) intercepts and services all PCI traffic to OGD1. Microcode we wrote interprets the accesses and stores text appropriately in graphics memory. Then, to avoid hacking up the video controller, we actually have HQ perform a translation from the text buffer to a pixel buffer over and over in the background. Its input is VGA text. Its output is pixels suitable for our video controller. Aside from the logic reduction, this has other advantages. The screen resolution as seen by the host is decoupled from the physical display resolution. So while VGA thinks it's 640x400, the monitor could be at 2560x1600, without the need for a scaler. It's easily programmable, and we have complete control over how the text is processed into pixels; for instance, we could have HQ do some scaling or use a higher-res font different from what the host thinks we're using. We call it emulation because, in a way, our VGA is implemented entirely in software, albeit microcode that's loaded into or own microcontroller.

Re:some kind of useful background (1)

MostAwesomeDude (980382) | more than 4 years ago | (#27801239)

I approve.

Re:some kind of useful background (2, Interesting)

mako1138 (837520) | more than 4 years ago | (#27801487)

So does the host interface part reside in the Lattice FPGA, in 10K LUTs?

Full open-source stack (1)

BrainInAJar (584756) | more than 4 years ago | (#27801073)

This, running on a T1 or T2 [opensparc.net] machine, running ${FREEOSOFCHOICE}. yum.

Re:Full open-source stack (1)

api (112263) | more than 4 years ago | (#27801369)

Getting there, getting there. Just wait until you can run gEDA/PCB [linuxfund.org] on open hardware designed with gEDA/PCB.

Linux on a graphics card?! (1)

Maexxus (970160) | more than 4 years ago | (#27801097)

I'm definitely the only one that read this as a Graphics card that was able to boot Linux XD

Hippie Hardware (0, Troll)

Jamie's Nightmare (1410247) | more than 4 years ago | (#27801101)

A great post about this ridiculous project was made to the Linux Hater's Blog [blogspot.com] back in 2008. Worth a read if you want to know why it's a piece of crap.

Summary of Link (-1)

Anonymous Coward | more than 4 years ago | (#27801465)

Summary of parent's link:
Open hardware is useless because no one wants it. They want Intel graphics cards instead. Besides, it's not completely open source yet. It costs too much.

Imagine the above being said in the most sarcastic and preachy tone humanly possible.

Not really worthwhile (1)

Orion Blastar (457579) | more than 4 years ago | (#27801129)

unless the chips and expansion card circuit boards can be made in masses to make them more affordable. You have to make them in mass quantities in order to drive the cost of them down.

Nobody wants to buy a $300 Open Source graphic card, when a closed source graphic card costs $100 and has better graphics.

Still this is a good idea, instead of Chinese companies stealing closed source ideas and violating IP laws, they can make open source graphic cards using the open source license and be legal. I would like to see open sourced computer systems complete with monitors, keyboards, wireless network adapters, etc. That way the Asian cloners can copy an open source standard instead of pirating the IP needed to make cheap knockoff clones.

I say we ban imports from asia. (0, Troll)

tjstork (137384) | more than 4 years ago | (#27801309)

I don't support asian cloners at all. They are just a bunch of thieves with protectionist laws and a disdain for IP on their end exploiting our own free trade and respect for IP on ours. We shouldn't be trading with these people. If we are to take up a collection for anything, it should be for u-boats to sink containerships as they sail towards America.

Re:I say we ban imports from asia. (1)

maxume (22995) | more than 4 years ago | (#27801633)

Yo dotter marry Chinese man?

better FPGA (0)

Anonymous Coward | more than 4 years ago | (#27801699)

What's really needed is a Virtex 5 FX100T, FX130T or FX200T. It'd be dang pricey, but with two power PC's to handle things like the basic VGA modes, you could dedicate most of the logic to the shaders / 3d portion. I don't think a Spartan 3 has a snowball's chance in heck. You need the faster clocking ability of the V5 and a much more vast gate count.

Re:better FPGA (0)

Anonymous Coward | more than 4 years ago | (#27801749)

oh, and 256MB ram? come on.

fu3ker (-1, Troll)

Anonymous Coward | more than 5 years ago | (#27802117)

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>