Better Looking Linux: Tungsten Graphics

Several folks have e-mailed about the formation of Tungsten Graphics, which is composed of quite a number of ex-Precision Insighters. Linuxgames is carrying a bit of a conversation with Frank LaMonica, the CEO of the new company. They've got a contract with Red Hat already in place. Frank's statement summarizes what they are doing well: "The work we are doing involves Mesa ^? and XFree86, including both 2D and 3D multi-screen technology, and we are working very closely with the OpenGL ^? ARB to maintain the integrity of the OpenGL API. We believe that OpenGL 2.0 needs more industry support, so we are working to help generate that support. DRI ^? technology is still in its infancy, and TG plans to help bring it to full fruition. Our first step in that goal is to significantly improve the existing open source DRI driver for the Radeon chipset. That driver is tentatively scheduled for release in late spring or early summer of 2002. "

Comments

Graphics expertise and their website

[awgy]

Its not that their website doesn't serve its purpose, but the Tungsten Graphics site doesn't quite instill any security in my mind of their graphics experience. Granted, hardware and DRI-related issues generally don't require good graphical design, but someone should at least offer them a logo.

Re:Graphics expertise and their website

[randumb_surfer]

After looking at your site I don't think they'll be coming to you for site design assistance.

Re:Graphics expertise and their website

[Quizme2000]

Maybe they changed their website to a more slashdotting compatabile design. They are also dealing with alot of different browsers hitting their site. Hey its simple, fast, and IMHO suited very well for its purpose. Hell I bet its valid html code. If you want bloat, fancy graphics, and bandwidth hogging webpages please go here.

Re:Graphics expertise and their website

[ptrourke]

You lose that bet. It's (probably hand-encoded) HTML3.2, but with empty alt attributes, and a number of other validity problems (a lot of them merely typos). Not well formed, either. Looks to me like it's a placeholder written by someone who has the skills but lacks the time. Expect something better to pop up eventually. See for yourself: http://validator.w3.org/check?uri=http://www.tungs tengraphics.com/

Re:Graphics expertise and their website

[Quizme2000]

I too went a checked it out on the HTML validy tool. But then I went and checked my own webpage too. Ouch. Anywahy, working for a startup that hasn't been funding with millions of dollars, the website is a very low priority for non-internet related technologies.

Re:Graphics expertise and their website

[Jobe_br]

Contrary to what others are writing, I agree with this poster. Regardless of if you're intending to be working with graphics or not, if you intend to be taken seriously, a design is essential. A simple 2-3 page site (which is what it looks like they currently have) plus maybe a released template that they can use to add their own pages later doesn't have to cost $20K.

Creating sites that load quickly (for the target audience), are most compatible across browsers (including text console apps such as Lynx, if desired) and are low-load for the server (to sustain a slashdot effect) are what professional interactive agencies are called on to do. My company (shameless plug) answers that call and answers it well (say what you will about our own site, which doesn't get nearly as much time invested in it as our client's sites do).

For something like Tungsten, I'd say that having a page that loads in Lynx isn't nearly as important as having a page that looks professional and inspires trust in this brand new company. And while many, many slashdotters will be going to their site from Linux workstations using Mozilla, Galeon, Konqueror, or Opera, the visits that probably matter most to the executives at the moment are those coming in on IE, from other executives sitting in plush offices with money to invest!

Isn't the abbreviation wrong?

[kawlyn]

On the web page it's TG, but shouldn't it be WG?

Re:Isn't the abbreviation wrong?

[rlowe69]

>> On the web page it's TG, but shouldn't it be WG?

>wang grabbing?
>wookie grease?
>womanly grunts?

*sigh* ... W is the chemical symbol for the element Tungsten - incidentally, the W stands for wolfram. Don't they teach basic chemistry in high school these days? Maybe I'm just biting a troll ...

Re:Isn't the abbreviation wrong?

[Webmoth]

wanting goatse?

(sorry... it had to be said)

Here is to wishing..

[Erasei]

We believe that OpenGL 2.0 needs more industry support

I would +love+ to see this happen, especially in the gaming area. I know we (the /. readers and karma whores like myself) all talk about how great Linux is, and for the most part, I agree. I would not replace my Slackware server for any version of Windows, ever. But I still run a Windows desktop, purely for gaming. That is really all I do on my home desktop, is play games. I would love to be able to play those same games on a *nix machine.

Then maybe I wouldn't feel slightly guilty for pirating windows.. naaah.. I don't feel guilty.

I realize that this article was covering far more than just games.. but I know games are what we are all thinking when we hear the terms 'OpenGL' and '3D'.

Re:Here is to wishing..

[Comrade Pikachu]

Gaming? Naah...not I.

Some of us actually use this stuff for work. I speak of animators, modelers, chemists and mathematicians. The entertainment industry (3D animation for film, television, and those games you enjoy) is extremely competitive. Thanks to the legacy of IRIX, there is a solid Unix culture there. This is the one area where Linux on the desktop has a serious competitive advantage!

Re:Here is to wishing..

[PotatoHead]

Oh yeah. Someone rumored that some big SGI names are involved. This can only be a good thing. Graphics on an IRIX box are great compared to the other UNIXes.

Re:Here is to wishing..

[BitwizeGHC]

The problem is, Direct3D has the game market about sewn up. Except for those holdouts over at id, the PC game industry has pretty much standardized on Direct3d version X.Y (whatever it is this week). We may have bought OpenGL some time but in a few years I see Fahrenheit repeating itself where OpenGL is subsumed entirely as a "legacy" layer on top of Direct3D, especially as the game market pulls more clout in the overall 3D scene.

OSS Radeon Drivers.

[reaper20]

Thanks guys, we all know we can't rely on ATI for decent drivers - for anything. Heh.

Will graphics be getting closer kernel ties?

[Flarners]

I've gotten the impression that the reason many cards (including my Matrox G400) underperform in Linux compared to Windows is due to the fact that the majority of the 3D talk is done in userspace, outside of the kernel. NVidia has chosen to completely bypass DRI and throw their entire driver into the kernel, which produces equal or better performance in Linux compared to Windows, at the expense of numerous stability problems (especially on multiprocessor boxes).

So, what I'd like to know is, is there a happy medium between userspace code in the X server and driver code in the kernel than can provide adequate performance without sacrificing stability? Right now, Linux 3D support is at either one end of the spectrum or the other: Stable yet slow DRI, or unstable yet blazingly fast kernel drivers. I would love to dump Windows for all my Unreal Tournament and Tribes 2 gaming needs, and am a loyal Loki customer, but I hate having to put up with either regular crashes or a large drop in performance. Hopefully, these Tungsten folk will find the best compromise.

Re:Will graphics be getting closer kernel ties?

[BlueGecko]

IIRC, BeOS's video drivers were in user space, and seeing as that was a media OS, I'm assuming that there's some merit to keeping such drivers out of the kernel. The trick more likely has to do with the fact that Linux lacks real-time scheduling and the extremely low-cost context switches that were absolutely essential on an OS so pervasively threaded as Be, so I honestly do not know if such a solution would be practical in Linux without a major rewrite of the scheduler, etc.

Re:Will graphics be getting closer kernel ties?

[cpeterso]

A major rewrite of the scheduler is planned for every new Linux kernel. Plus a rewrite of the VM, NFS, SCSI, VFS layer. Linux is getting greater all the time. That's why they have to keep rewriting it.

The NT kernel has not changed much since NT 3.51 in the earlier 90s, yet Linux is still losing benchmarks against NT.

Re:Will graphics be getting closer kernel ties?

[BillWhite]

FWIW, both the 3Dfx and ATI OpenGL Windows drivers were in user space in Windows. The way it works there is that the driver asks the 2D display driver for a memory buffer, the driver fills the memory buffer in with commands, most of which have the form "draw a triangle", and then the driver submits the buffer of commands to the hardware through a kernel interface. This is the way the ATI Rage128 drivers worked, and the 3Dfx V3 and V5 drivers worked. In fact, for OpenGL, you could use the Visual C++ debugger to debug the driver. DirectX is under the Win32 mutex, so debugging it is a big PITA, and required SoftICE.

My guess would be that they are exactly the same now. The problem with Linux performance is not that the driver is in user space, but that the driver, Mesa, is not very efficient.

Re:Will graphics be getting closer kernel ties?

[be-fan]

*Very* off-base. NVIDIA's drivers are regular GLX modules loaded by the X server in userspace. They simply use a different (but functionally equivilant in terms of protection) scheme than DRI to bang registers and interrupts on the card. The stability issues are due to other problems (to be fair, though, I have been using them for a long time and Galeon and AbiWord have crashed numerous times while the NVIDIA drivers have never frozen the kernel or even X).

Re:Will graphics be getting closer kernel ties?

[be-fan]

Actually, BeOS splits up the video drivers. The low level work that *has* to be done in the kernel (like handling interrupts) is done in kernel space. The high level work (everything else, including drawing) is done by the X server (from userspace) directly manipulating the registers on the card. This is actually faster than putting the driver in the kernel because you don't have to make a slow system call to do drawing. The major bottleneck in the system is that you have to communicate between the X server and the application.
Ideally, processors would implement protection mechanisms similar to the x86 segmentation method. That method let you define 4 protection rings, and allowed code to access certain segments based on the privelege level of the segment containing the code. That way, everything could be done in the application. The app code would have a privlege level of 3, so it couldn't trash kernel or windowing system data. The window system would have a privelege level of 1 or 2, so it could access its data and the applications, but couldn't trash kernel data. The kernel would have a privelege of 0, so it could access anything and be safe from other code. Using such a mechanism, it would be possible to make everything (including windowing operations and system calls) require no more time than a simple function call.

Re:Will graphics be getting closer kernel ties?

[be-fan]

First, it does have an X server port. Second, it has the app_server, which does essentially the same thing.

Re:advertisement?

[cduffy]

The formation of a new company specializing in some aspect of open source that affects people (like video device support!) is news. Further, since those of us who've been around a while know the people involved (like Brian Paul), it's interesting to know that our friends (acquaintances, whatever) have found New And Interesting work.

Not very supportive of Open source

[A Commentor]

We believe that some code MUST be open source, other code can go either way, and some, especially at the lowest levels of hardware and the code within applications, can be completely closed with no loss of benefit to the industry or its customers.

Didn't we have to face this problem before with some of the video card (S3?) manufactures that refused to give out programming information... Code to control hardware should be open just like any of the other code.

Re:Not very supportive of Open source

[MrHat]

Nice find - they have this completely reversed.

People should *demand* that code closest to the hardware is open source. Look at it this way: a company collapses and takes with it a base of code. Would you rather it be a driver at the core of your display subsystem, or your text editor? One product has alternatives that don't render your existing hardware useless.

Did you buy into the Circuit City Divx thing? No? Then you shouldn't go for this kind of crap either. Companies that get my money are the ones that aren't afraid of full disclosure.

IIRC, a similar issue with print drivers was the driving force in the establishment of the GNU project.

Re:Not very supportive of Open source

[MadAhab]

There is one way, and only one way, to completely close code with no loss to the customers, and that is to put that code in hardware and have open specs for interacting with it.

Anything else means that you can be stranded by the vendor.

Re:Not very supportive of Open source

[4of12]

...code in hardware and have open specs for interacting with it.

Yessir.

I've often said the same:

• open up and describe fully the interface.
• go ahead, tweak and tune your proprietary black box implementation

Re:Not very supportive of Open source

[ClosedSource]

"open up and describe fully the interface.

go ahead, tweak and tune your proprietary black box implementation"

I agree, but I think this argument can also apply to APIs and other higher-level SW interfaces. I'd rather a fully described API without source code then a poorly documented API with source code. You can learn a lot looking at source but it's not always the most efficient method of getting your work done.

Re:Not very supportive of Open source

[Ogerman]

It'd be nice, but we don't need "Free Hardware" as a prerequisite for open source drivers. It's more a problem of misunderstanding of braindead management who don't realize that the only thing of possible value to their competitors is in the silicon itself. Open Source or not, driver software is pretty easy to reverse engineer.

If these people are going to write closed source ATI drivers, I'm not interested. They want me to stick untrusted binaries into the kernel? Forget it! Sounds like another bunch of traitors who weren't innovative enough to devise an Open Source business model. Oh well, we can always reverse engineer their drivers can't we?

Re:Not very supportive of Open source

[4of12]

Yes, I, too, would rather have a fully-described API w/o src than a poorly-documented API w/ src.

But your point got me to thinking about how 98% of the APIs are insufficiently documented, to the point where the ugly necessity of looking at someone else's source is often the only recourse.

And the standard for "fully-described" is high.

Frequently the exposed API will intimate that X is how you do some particular task, but the implementation is so sucky that doing W, Y, and Z turns out to be practically better from the standpoint of performance, memory, complexity, etc.

Imporving the Radeon driver...

[wbattestilli]

Would be great!!!

I would really love to buy a radeon for my Linux workstation, but nVidia provides superior dirvers. I would like to philosophically take a stand and reject nVidia for their refusal to release specs but I need complete and efficient drivers. The radeon currently cannot compete with nVidia on linux (or windows) even though the radeon is likely better hardware.

Expect impressive products

[KnightStalker]

... whatever they might be. You can't complain about a development team that includes the guy in charge of XFree86 *and* the developer of Mesa. This could definitely lead to some cool software :-)

Radeon?

[tempest303]

I wonder what they mean by the "Radeon chipset"? Is this just for the "classic" Radeons, or for the new 7500/8500 series? While I've got a legacy Radeon, I really hope the support is for the new series - I'd love to see cutting edge cards like the Radeon 8500 get the support it deserves in Linux, and I'd pay for the privilege. (You listening, ATI? :)

Look out nvidia.

[Penguinoflight]

With the Radeon 7500 (the one with the technical stuff to smash a geforce 3), nvidia will likely see a loss in it's sales to linux users. The Radeon 7500 is actually a radeon 64mb ddr that goes a lot faster. The radeon 8500 on the other hand is another generation, too bad it's not supported yet.

To be frank, if it weren't for the heat that nvidia cards produce, I'd probably get one. I just can't afford to have my server go down because a GPU overheated and pumped the case tempurature to 120 degrees. I don't want a video card that has a fan for something other than cosmetics.

This technology has been around for years!

[Carrion]

Tungsten graphics is usually low resolution, about 0.25 DPI. It's also got high power consumption and therefore heat dissipation, around 25-90W/pixel. If you want colour, triple those numbers. You wouldn't want one of these displays on your workstation, believe me!
Still, it's often used due to it's scaleability; I've seen dozens of companies use them in the major cities, ever since I was a kid.
Slashdot is behind it's times, posting articles of old technologies, well-known in the advertising business!

For those more interested in the technology, each pixel is made out of a usually pear shaped glass bubble. A tungsten spool is inserted, and the air is removed from the bubble causing a vacuum. When electricity is sent through the spool it starts glowing brightly so that light is emitted. The absence of oxygen from the vacuum keeps the tungsten from oxidating, making it last much longer. By variating the current through the spool, you can increase or decrease the brightness of the pixel.

Re:This technology has been around for years!

[JabberWokky]

Subtle, tongue in cheek, overdrawn humor is lost on you then. The funniest aspect of this post is not the post itself, but that it got moderated up as "Interesting", meaning that some idiot out there with moderation points bought it.

--
Evan

Re:This technology has been around for years!

[spitzak]

Static displays of arbitrary shape and complexity can be created using off-the-shelf components. These are very popular for Christmas decorations on the exteriors of houses.

2D performance of current Radeon drivers is awful

[Thagg]

The current DRI Radeon drivers are fine for 3D, providing pretty much the full power of the machine to the Linux world -- but the 2D performance is awful. Why, you might ask? Because when ATI contracted with VA Linux to create the drivers, they only funded development of 3D, and didn't specify that the 2D performance should be accelerated.

This turns out to be a real problem in the visual effects community -- a lot of our work depends on having good, fast 2D. Film frames, after all, are still just 2D images.

I hope that this new driver they speak of, and future drivers, recognize this. We'll see. At this point, we have to by nVidia boards, even while the drivers are closed-source, they provide pretty good 2D support.

thad

Precision Insight

[4of12]

Am I correct in my impression that Precision Insight included some of the more famous names from SGI and that some of these same people would be part of Tungsten Graphics?

Re:Precision Insight

[4of12]

no..
thats nvidia

My mistake. My apologies.

Maybe that talent pool has something to do with nvidia's successes in the market, although I would not discount the importance of intelligent management, either.

Re:And they do what again????

[technomancerX]

And designing a website has what to do with writing drivers for video cards???

Re:Is either one that bad for you?

[cduffy]

why would someone buy a nice card and then waste it's features in linux? It's not like you can play any games properly in it!

Beg pardon -- playing Tribes 2 at 1600x1200 with a perceptibly perfect framerate is somehow improper?

What the hell is he talking about?

[waldoj]

The work we are doing involves Mesa? and XFree86, including both 2D and 3D multi-screen technology, and we are working very closely with the OpenGL? ARB to maintain the integrity of the OpenGL API. We believe that OpenGL 2.0 needs more industry support, so we are working to help generate that support. DRI? technology is still in its infancy, and TG plans to help bring it to full fruition. Our first step in that goal is to significantly improve the existing open source DRI driver for the Radeon chipset. That driver is tentatively scheduled for release in late spring or early summer of 2002.

I'm no moron. I own a handful of computers, Mac and Linux, I've built a few dozen machines in my time, and I managed to configure X on them when necessary. That said, what the hell does this mean?

Really. I'm asking.

-Waldo Jaquith

Re:What the hell is he talking about?

[talonyx]

The work we are doing involves Mesa? and XFree86, including both 2D and 3D multi-screen technology, and we are working very closely with the OpenGL? ARB to maintain the integrity of the OpenGL API.

-- Mesa is an OpenGL compatible 3D API. Xfree86 is a free version of the X Windowing System.
Multi-screen technology is when two video cards (or one, with DualHead) and two screens are tied together on the same desktop.
The statements about OpenGL simply mean Tungsten is going to make sure their products remain compatible with OpenGL.

We believe that OpenGL 2.0 needs more industry support, so we are working to help generate that support.

---This is pretty clear; the almost-industry-standard OpenGL is being updated to version 2.0 very slowly, and Tungsten is going to try to get this in gear.

DRI? technology is still in its infancy, and TG plans to help bring it to full fruition.

--DRI = Direct Rendering Infrastructure, Xfree86 4.0+'s method of allowing programs to render directly to hardware acceleration, with fewer API layers and bagges.

Our first step in that goal is to significantly improve the existing open source DRI driver for the Radeon chipset. That driver is tentatively scheduled for release in late spring or early summer of 2002.

-- They want to fix the drivers. :D

Re:What the hell is he talking about?

[Chris Pimlott]

You're missing the point. They use a bunch of graphics buzzwords and technologies but they don't actually say what they are doing. I don't think the original poster was confused about the technologies themselves.

Who these guys are

[kingdon]

I'll agree that the website or the other linked material don't really go beyond the fluff, so let me try to explain why this matters. Frank and most of the other people involved in this have been going to the Linux shows and writing XFree86 drivers for Red Hat and stuff like that since at least, well, 1996 or so (probably longer). Then the Linux Hype Effect sucked them into VA Linux and spat them out the other side (hopefully it had its rewards, although I don't know how much stock they got or when/whether they sold it). Now they are going back to their roots - a small technically oriented company. I expect to see more of this - lots of good companies went through much upheaval in the days of the Linux Hype Effect and so now we should see things realigning in a more stable, sustainable configuration.

Re:Here is to wishing.. (amen!)

[PotatoHead]

OpenGL is not just about games, though I play them along with everyone else :)

Mcad, Scientific Vis. , Simulation are some applications that depend on OpenGL right now. There is a *lot* of pressure to move some of these to the win32 graphics API to gain the economics of scale that surround the Intel platform.

In the MCAD area, OpenGL is widely used because the big players are still cross platform. Over the last few years, there has been little real Linux interest, and little UNIX interest. Almost every one starting new with MCAD was starting on win32.

This year has been different. People are asking about MCAD on Linux and UNIX. Seems that some of the backlash we all have postulated about here is beginning to happen. (about goddam time!)

One interesting approach has been to put in win32 MCAD because it is cheaper than UNIX, maybe use a UNIX backend and hope to migrate to Linux when things come together in the near future. Hearing this stuff is huge and indicates to me that Tungsten is in the right place at the right time.

Good quality X servers can at least take advantage of back-end UNIX compute servers. Enough people do this and realize the administrative and support advantages and Linux native ports will follow.

So here's to hoping for next year. OpenOffice will continue to get capable, Linux graphics will get strong and compare more favorably to highend implementations like IRIX, and some ancillary applications will appear to make technical computing on Linux a reality outside the developer and adademic communities.

Looks pretty familiar.

[booch]

Compare these 2 web pages:

Precision Insight Team
Tungsten Graphics Team

What about people who just want a nice GUI?

[HanzoSan]

Besides specialized uses like that, the linux gui can really use some help. It cant even do transparency properly, and you can forget about genie effects.

Re:What about people who just want a nice GUI?

[vandan]

You should check out Enlightenment - both 0.16.5 and 0.17.

Re:Unoriginal name...

[Junks Jerzey]

It is very difficult to tell if this person is (A) trying to be funny, or (B) really, really uptight.

Old news

[mallan]

The NVIDIA stability problems are old news. Yes, for the first 6 months they were available, they had some stability issues. Just because they stated in their README that they were having stability issues on multiprocessor boxes 18 months ago does not mean the stability issues exist today.

I only use dual processor boxes. I have a dual processor box at home, and we've got 11 dual processor Linux boxes at work. All use NVIDIA hardware, and all of them are very, very stable. Our lab does flight simulators and scientific visualization, so the machines get heavy 3D use on a daily basis. I havn't had any NVIDIA Linux box lock up in about a year.

Most of the people I've talked to who are having stability problems with the NVIDIA cards under Linux have either a cheap motherboard or an inadequate power supply. No driver in the world can compensate for either of these.