NVIDIA Performance On Linux, Solaris, & Vista

AtomBOB suggests a Phoronix review comparing the performance of a Quadro graphics card on Windows Vista Ultimate, Solaris Express Developer, and Ubuntu Linux. The graphics card used was a NVIDIA Quadro FX 1700 mid-range workstation part. The cross-platform benchmark used was SPECViewPerf 9.0 from SPEC. Quoting Phoronix: "Using the Quadro FX1700 512MB and the latest display drivers, Windows Vista wasn't the decisive winner, but the loser... Ubuntu 8.04 Alpha 5 with the 169.12 driver had overall produced the fastest results within SPECViewPerf. In only three benchmarks had Solaris Express Developer 1/08 outpaced Ubuntu Linux, but with two of these tests the results were almost identical.""

Comments

What is the difference?

[moreati]

I've wondered this a while. What is the difference between the gaming cards and the workstation cards from Nvidia and ATI? Do they just have better DACs? Certified driver support for business apps? Or is the GPU itself somehow?

Alex

Re:What is the difference?

[Anonymous Coward]

The difference between the Quadros and the consumer cards used to come down to hardware OpenGL overlay support, if I remember right.

Re:What is the difference?

[sxeraverx]

They have different priorities. Gaming cards try to keep the framerate up by degrading image (not showing every single texture, e.g.), if need be, while cards for stuff like CAD and the like lower the framerate to show every detail requested of them.

Re:What is the difference?

[stratjakt]

Drivers that work.

I'm not joking, all the extra cost is for all the extra development and testing time for the drivers, and for much better support when things break.

Other than that, there have been plenty of bios mods over the years that turn regular video cards into their workstation counterparts, but of course, you don't get any support.

Re:What is the difference?

[alex4u2nv]

I had the very same question, and this article from Nvidia turned out to be very enlightening.
Quadro vs FX -- http://www.nvidia.com/object/quadro_geforce.html

According to the article, there are some major differences between the two architectures. Where features are programmed either at the hardware layer (quadro), or at the driver layer.

Re:What is the difference?

[xenocide2]

Of course, it doesn't help that they've started using the Quadro name for business laptops. As far as I know, chips like the Quadro NVS 110M are far closer to gaming cards than workstations.

Re:What is the difference?

[davolfman]

There at least used to be quite a few Quadro features that could on GeForces with the right tweak tool so at least some of the difference is crippleware.

Re:What is the difference?

[LoRdTAW]

Gaming cards try to keep the framerate up by degrading image (not showing every single texture, e.g.), if need be

Thats called culling and it is implemented in software, not hardware.

If I remember correctly there was a simple hack posted on Toms Hardware a while back for converting a Radeon to a FireGL. You simply solder an SMT resistor to a certain trace on the chip package and it pulls a line low. That line actually signals the BIOS to report the card as a Radeon or a FireGL. So in essence the Radeon and FireGL are the EXACT SAME CARD! The only difference is the FireGL drivers look for a Radeon reporting itself as a FireGL. This keeps production simple and even the video card BIOS versions the same.

The FireGL and Quattro cards come with optimized drivers for specific 3D programs like AutoCAD, Maya, 3DSMax, Light Wave etc. There is a drop down box that lets you select the program your using and it loads the finely tuned driver for that program.

Re:What is the difference?

[Barny]

Yes, I believe it was around the gforce 5 series or so that someone figured the resistor settings to tell a high end game card to "be a quadro", some very nice very cheap workstations were produced that year by 3rd parties.

Grandparent link is an interesting one, I can see where they would want to start implementing some of those features in standard game cards though, the "interface plane" would be a nice addition for instance to help the performance in modern games with their HUDs.

Re:What is the difference?

[Erpo]

What is the difference between the gaming cards and the workstation cards from Nvidia and ATI?

I don't know anything about ATI cards.

Other people have mentioned some features that Quadros have and GeForces don't. I'll add hardware antialiased lines to that list. However, the real difference between a GeForce Card and a Quadro card is about $1000 and a missing or extra capacitor. Really.

I suspect (and it's only a suspicion) that there are some transistors in the GPU that serve no purpose other than to implement Quadro-only features. In GeForce CPUs, those transistors may be broken or may never have been tested.

Nowadays, the difference between a high-end nvidia graphics card and a midrange nvidia graphics card from the same generation is often which pixel and vertex shader units have been disabled. The high-end card may have 32 out of 32 pixel shader units enabled, whereas the midrange graphics card may have only 24 or 16 of them enabled. Those units may be broken or they may be just fine. If you're using Windows and don't mind potentially damaging your card and voiding your warranty, there's a program called Rivatuner that can enable the masked shader units.

So it's the same deal. If you're willing to risk what you've got, you may be able to turn what you have into a whole lot more.

Re:What is the difference?

[vipz]

Actually, the NVS series seems to be strictly aimed at the business/multi-monitor crowd, competing with the likes of Matrox. They don't run games very well.

Re:What is the difference?

[xenocide2]

Mine runs Battlefield 2 etc well enough. I doubt it'll win any awards, but it suffices.

Re:What is the difference?

[pizpot]

Vid cards are not the bottleneck for CAD at all. A 10,000 part machine in CAD is not rendered with textures and the engineer doesn't want them either. CPU is the bottleneck. The programs (UG, SW, SE) output low tolerance polygons now. I can CAD just as good on a GF3 than a new quadro. Actually, a TNT2 isn't so bad believe it or not.

Surprised..

[LingNoi]

I am surprised by this as I would have thought Nvidia would have put more effort into their Vista driver with Linux drivers being mostly on the back burner. I am assuming it is because their Linux driver is old code (which we all know contains less bugs then new code) whereas the Vista driver is written from scratch?

Either way I think this shows the awesomeness of Ubuntu and Linux. ^_^

Re:Surprised..

[Alexx K]

I'm not 100% certain, but I believe Vista is constantly checking both itself and the hardware to ensure that no DRM bypassing mechanisms are being used. If so, this probably would downgrade performance.

Re:Surprised..

[bcmm]

It's been known to Linux gamers for a while that games that run on both Windows and Linux will generally perform better, often by 10-15% (by FPS), on Linux, at least on NVIDIA hardware.

Re:Surprised..

[Anonymous Coward]

That is to say, you speculate this is the case but have no proof.

Re:Surprised..

[sg_oneill]

Vistas desktop composition mode I suspect has a share of blame as well. Basically the thing puts a degree of separation between the final render buffer and the monitor to allow some of vistas special-effects to do there thing (Ie the alt tab effects, etc), and this neuters many tricks and optimisations used to squeeze fps out of the system.

I know its all gone and messed up Open GL, but heck I might just be bitter on that point, since I cant for the life of me find an accelerated GL driver for my Vista Mobile Radeon laptop.

Re:Surprised..

[Svartalf]

It has a little less to do with them putting effort into the driver and more to do with the interrupt handling model and how OpenGL
ties into the OS as a whole.

And, you'd be assuming wrong. Neither NVidia nor AMD have old or differing code, from what I understand, for EITHER OpenGL API layer.

Re:Surprised..

[Alexx K]

No. I have read it here and here, but I'm not certain whether Vista actually does this or if it's just a massive fud campaign. From what I've read, it seems to be true. But as I said, I'm not 100% sure.

Re:Surprised..

[pak9rabid]

I'd have been interested to see where WinXP would have stacked up against the others.

Re:Surprised..

[recoiledsnake]

It's mostly FUD. See here (read all three parts)

Re:Surprised..

[pak9rabid]

I'd have been interested to see where WinXP would have stacked up against the others. Whoops, clicked submit too early. I was also going to add that since the codebase for the Linux and WinXP drivers are nearly identical (according to nvidia), it seems like it would have been more of an OS-dependent benchmark.

Re:Surprised..

[Nullav]

Gutmann'd!
That is, by far, the worst thing to link in a Vista discussion. (By the way, the first link also cites the Gutmann paper as its primary source.) Vista is a horribly bloated OS, but it has much more to do with the unnecessary shiny than anything else. Aside from that stupid 'using the network while playing an MP3' problem, that paper is:

just a massive fud campaign

Re:Surprised..

[LingNoi]

According to this comment they are the same, but if you look at my comment you'll notice that the graph says XP is around 2-10% better then vista.

Re:Surprised..

[Alexx K]

Mod parent up! Very good article. Thank you.

Re:Surprised..

[Foofoobar]

That's actually an old article filled with half truths that only show one particular point of view of the DRM on Vista. It was released shortly after beta and now that Vista has been on the market for months, it has actually shown that 75% of the DRM problems were actually true (while the rest were exaggerations).

Re:Surprised..

[yanyan]

About the author, Ed Bott:

Ed Bott is a freelance technical journalist and book author. All work that Ed does is on a contractual basis.

Since 1994, Ed has written more than 25 books about Microsoft Windows and Office. Along with various co-authors, Ed is completely responsible for the content of the books he writes. As a key part of his contractual relationship with publishers, he gives them permission to print and distribute the content he writes and to pay him a royalty based on the actual sales of those books. Ed's books are currently distributed by Que Publishing (a division of Pearson Education) and by Microsoft Press.

Ed's personal website at edbott.com includes advertising. All display advertising is managed by Federated Media. Ed reserves the right to reject ads for any reason. In addition, Ed allows advertisers to purchase links in a sidebar through Text-Link-Ads. Advertisers receive no special treatment at his personal website, at ZDNet, or in books. Ed makes a small amount of money selling books (his own, primarily) through an affiliate account at Amazon.com.

On occasion, Ed accepts consulting assignments. In recent years, he has worked as an expert witness in cases where his experience and knowledge of Microsoft and Microsoft Windows have been useful. In each such case, his compensation is on an hourly basis, and he is hired as a witness, not an advocate.

Who do i trust, an independent researcher or an M$ lackey?

Re:Surprised..

[hairyfeet]

What he is talking about is protected media path which looks for the presence of DRM media and has been reported on many sites to be one of the causes of Vista slowness. While I don't know for sure if that is the cause of the slowness, there is a stripped down "gamers version" of Vista floating around the net that supposedly has all the DRM stripped. I ran a copy in a VM(after running Vista for two months on my gamer rig I wouldn't go back if you paid me) and it ran almost as fast as XP,IMHO. But that is my 02c on the subject,and I have seen folks with Dual Core 4Gb of RAM beasts that Vista ran fine on so YMMV.

Re:Surprised..

[vux984]

Its like reading one idiot correct another idiot... fta:

In this case, the unsupported assertion starts with market share numbers pulled out of thin air. Under the heading "Disabling of Functionality," Gutmann writes: ...For example many sound cards built on C-Media chipsets (which in practice is the vast majority of them) support Steinberg's ASIO (Audio Stream I/O), a digital audio interface that completely bypasses the Windows audio mixer and other audio-related driver software...

See how he slipped that little statement in there to make the problem he's discussing seem like something that will affect "the vast majority" of Windows systems? The trouble is, the vast majority of sound cards are not "built on C-Media chipsets." Don't take my word for it; that's what the company itself says. In reporting on a 2006 deal between C-Media and Asus, DigiTimes quotes a report in the Chinese-language Economic Daily News (EDN)

        C-Media anticipates that its market share in the high-end audio IC market will hit 10%, up from the current 1-3%, according to the company...

The last time I looked, 1-3% was a tiny blip, not the "vast majority."

So the first idiot says the vast majority of audio chipsets are C-media... and the 2nd idiot thinks he's counting him by quoting C-media claim they have well under 10% of the 'hign-end audio ICs'. The two assertions aren't even in conflict for crying out loud.

Consider Toyota... both the worlds largest car company and simultaneously barely represented in the exotic high end car segment. So C-Media is a Toyota of audio chips; sounds about right. This is like a bad slashdot debate, not journalism. On both sides.

Re:Surprised..

[JohnBailey]

I am surprised by this as I would have thought Nvidia would have put more effort into their Vista driver with Linux drivers being mostly on the back burner. I am assuming it is because their Linux driver is old code (which we all know contains less bugs then new code) whereas the Vista driver is written from scratch? Either way I think this shows the awesomeness of Ubuntu and Linux. ^_^ Except these are workstation graphics cards. And Windows is the one on the back burner. The CGI industry has been using Unix variants for years, and more recently many are moving to Linux for cost considerations.

Re:Surprised..

[recoiledsnake]

That's actually an old article filled with half truths that only show one particular point of view of the DRM on Vista. It was released shortly after beta and now that Vista has been on the market for months, it has actually shown that 75% of the DRM problems were actually true (while the rest were exaggerations). Did you even read the articles? The very first paragraph.

New Zealand researcher who wrote a paper last December that made a series of outrageous and inflammatory claims about Windows Vista. Since then, Gutmann has expanded the paper to more than four times its original size. The current version available on Gutmanns website clocks in at more than 26,000 words, making it longer than some recent works of fiction. The end of the first part:

Gutmann has added nearly 14,000 words to his report since writing the original paper but strangely hasnt updated this part. So, the article wasn't based on a 'beta' version of Vista like you claim it did. Also, Vista went RTM in Nov 2006 and the article was orginally published in December of that year.

You don't read the articles you reply to, and arbitrarily claim without any proof, reference, link or anything that 75% of the claimed DRM troubles were true. Hello? Gutmann? Is that you? :)

Re:Surprised..

[recoiledsnake]

Who do i trust, an independent researcher or an M$ lackey? FTA:

In Part 1 of this three-part series, I discussed some of the technical errors in Gutmanns paper that illustrate his lack of hands-on experience with the technology hes trying to cover and his fundamental confusion over how Windows Vista content protection features work. (Youll find more examples in Part 3.) If you think Im nitpicking over these details, you miss the point completely. Gutmann is an academic researcher, and the way scientists have worked since the end of the Dark Ages has been with a rigorous set of principles: You start with a thesis, you design experiments that test that thesis, and using those experimental results as well as those of your peers, you assemble evidence that proves or disproves your thesis. Then you publish. As I noted last month, Gutmann has completely skipped the experimental portion of this time-tested process. He has literally no firsthand evidence to support most of the outrageous claims he makes, and much of the secondhand anecdotal evidence he has assembled is either taken out of context or is of questionable relevance. As I show later in this post, some of his evidence is just plain made up. When someone who claims to be a scientist publishes a paper filled with provably wrong facts, that persons competence is called into question. When all of those errors are in one direction, that persons honesty, objectivity, and devotion to the truth are called into question as well. The point is, why do you have to trust someone? Just look up the references if you have any doubt to see if they match up or not. Alternatively, you can close your eyes and ears and chant 'la la la M$ M$ M$' while Vista plays HD content right before your very eyes. Gutmann has not even used Vista before writing a 26,0000 word diatribe. Also, if Ed Bott has a financial incentive for his spin, Gutmann has a popularity incentive. His article has become wildly popular and linked all over the internet. I am sure that counts as a incentive for his FUD mongering.

Re:Surprised..

[xenocide2]

I haven't really paid much attention to Vista DRM one way or another. But even an objective observer would at least actually try the things he Gutmann says can't be done. Rather than spend the money and try, the author cites a sales website, and a clearly photoshopped "example use" on the second page. Of course salesmen are going to say everything's possible. As the recent Vista-capable suit shows, you can't rely on such claims to be accurate.

And on the final page, we see a few interesting bits of history. People have noticed stuttering on playback, due to scheduling priorities between network and realtime playback on Vista. But more interestingly, we have a guy who's talking about how If I was trying to engineer a system with long battery life, this would be unwelcome news. And the less said about that amusing analysis of clock cycles the better.

Re:Surprised..

[recoiledsnake]

I haven't really paid much attention to Vista DRM one way or another. But even an objective observer would at least actually try the things he Gutmann says can't be done. Rather than spend the money and try, the author cites a sales website, and a clearly photoshopped "example use" on the second page. Of course salesmen are going to say everything's possible. As the recent Vista-capable suit shows, you can't rely on such claims to be accurate.

Are we even reading the same fucking articles???! I am tired of having to go back through the articles to cite them for you.

FTA:

No one has been able to identify a Windows system that will play HD content in HD quality? Countless reviews of PC hardware over the past year say otherwise. In November 2006, PC Magazine praised the Toshiba Qosmio for its exquisite playback of HD DVD discs at 1080p using an Nvidia GeForce Go 7600. (PC Pro UK offers similar praise of the fantastic 1920×1200 [1080p] picture in a more recent review of the this years Qosmio, equipped with Windows Vista Ultimate.) This CNET review published in February 2007 described outstanding Blu-ray video quality at 1080p on a Velocity Micro PC running Vista Home Premium. Laptop Magazines July review of a high-end Sony Vaio (also equipped with an Nvidia Go 7600 GPU) praises its 1080p eye candy, which the reviewers watched on a 32-inch TV over an HDMI connection. Ive been watching Blu-ray and HD DVD discs at 1080i resolution (maximum available on my set) on a Dell XPS 410 that I purchased last December. With the right hardware, you can get world-class HD performance out of a computer running Windows Vista.

Most of the reviews(NOT from the salesmen) are linked so you can check them out if you really want to. Please read the article(s) before you comment again. Or I'll have to suppose that you're just a karmawhoring troll.

People have noticed stuttering on playback, due to scheduling priorities between network and realtime playback on Vista. That was a bug in Vista that was fixed in SP1.

Re:Surprised..

[xenocide2]

I was mostly referring to the part where he links to an Austrailian vendor for proof and then provides a picture of a suggested use, with an improbably placed airport terminal monitor easily a hundred feet in the air and amazingly all in focus despite the oblique angle.

But look, you're clearly far more invested in the information than I am. Obviously a guy claiming that Vista DRM is causing global warming or that HD playback is impossible is over the top. I think I'll just continue to use Ubuntu where I don't have to worry about this or that. You win, and I guess your prize is you can keep using Vista. Enjoy.

Re:Surprised..

[recoiledsnake]

I was mostly referring to the part where he links to an Austrailian vendor for proof and then provides a picture of a suggested use, with an improbably placed airport terminal monitor easily a hundred feet in the air and amazingly all in focus despite the oblique angle. That's from Samsung's advertizing material. Looks like a obvious mockup showing the intended use of the monitor. Not a computer monitor for sure like Gutmann claimed, faked ad pic or not.

Obviously a guy claiming that Vista DRM is causing global warming or that HD playback is impossible is over the top. If you read the highly modded up FUD on here, you'd actually start believing that.

I think I'll just continue to use Ubuntu where I don't have to worry about this or that. You win, and I guess your prize is you can keep using Vista. Enjoy. I dual boot Vista x64/Ubuntu on my desktop. Used to run gentoo(after endless hours of compilation) back when I was a student and had a lot of time. Should try that on the quadcore sometime, should compile faster. Anyway, it just hurts me to see otherwise rational and smart people fall victim to groupthink and FUD.

Re:Surprised..

[recoiledsnake]

You'll note that Ed spends most of his time attacking irrelevent mistakes in details, and uses this as basis to claim the whole point is invalid. Gutmann's main point was that the DRM in Vista stops you for viewing or degrades legitimate content like home videos taken from HD camcorders. Ed proved that all of that is a crock of BS and FUD. Gutmann even claimed that it would affect medical images and videos and people started blindly believing it. MS itself had to step up because the FUD was going out of control in the media which was blindly parroting Gutmann's claims without research, and debunk it. From the wiki:

In the United States, the Federal Communications Commission approved HDCP as a "Digital Output Protection Technology" on August 4, 2004, despite its known flaws.[8] The FCC's Broadcast flag regulations, which were struck down by the United States Court of Appeals for the District of Columbia Circuit, would have required DRM technologies on all digital outputs from HDTV signal demodulators. Congress is still considering legislation that would implement something similar to the Broadcast Flag. The HDCP standard is more restrictive than the FCC's Digital Output Protection Technology requirement. HDCP bans compliant products from converting HDCP-restricted content to full-resolution analog form, presumably in an attempt to reduce the size of the analog hole. On January 19, 2005, the European Industry Association for Information Systems (EICTA) announced that HDCP is a required component of the European "HD ready" label.[9] Microsoft's new operating system, Windows Vista, utilizes this technology in the context of computer graphics cards and monitors. So you want Vista to ignore the standard and just start playing HDCP labeled content(when it comes out in a few years) in full HD on Vista on non-HDCP compliant displays? The movie studios will hit MS with a multibillion dollar DMCA lawsuit before you can say 'M$' and the judge would rule accordingly. Sorry, your anger at HDCP is directed at the wrong place. And if MS refuses to implement HDCP at all, the movie studios can tell MS to sod off, because only a miniscule number of people would want to watch HD content on laptops and computers, as opposed to big screen TVs with Bluray players. MS would have a lot to lose and Apple(a member of the BluRay association), would probably step in and implement HDCP and be the only OS for legal HD playback.

Re:Surprised..

[linzeal]

Who cares about CGI when most CAD engineering groups use Windows work stations still. CGI is kids stuff compared to some of the assemblies that they work with in the aerospace industry.

Re:Surprised..

[Foofoobar]

Article says September which as you noted, was still before RTM in November as I stated. Do your own reading.

Re:Surprised..

[recoiledsnake]

September what? The ZDNet article was written in September 2007, a full 10 months after Vista RTM in November 2006. The Gutmann article was first published in December, a month after RTM and added 14,000 words after that and was last updated in June(6 months after RTM). Cognitive dissonance?

Re:Surprised..

[Foofoobar]

Ah... ok so you are arguing semantics. Not BETA but RTM. Had I said ALPHA we would probably be having the same discussion. Point still being that VISTA was not yet released regardless which was the main point of the discussion and not whether is was ALPHA, BETA or RTM. And That fact still does not alter any point of the original discussion. The article came out prior to VISTA's GENERAL RELEASE TO OEM's and the public, and after the fact, the DRM issues have proven to mostly be true. Some minor ones have been fixed with patches but the vast majority have not and internally it has been partially blamed for the lack of uptake in Vista.

Re:Surprised..

[recoiledsnake]

after the fact, the DRM issues have proven to mostly be true. Some minor ones have been fixed with patches but the vast majority have not and internally it has been partially blamed for the lack of uptake in Vista.

Did you miss the point about the Gutmann article being updated with 14,000 words in the months following "VISTA's GENERAL RELEASE TO OEM's and the public" and also the ZDNet articles being written in September 2007? Or are you being intentionally obtuse?

What DRM issues are you talking about? Did you even read the articles? And where did you learn that "internally it has been partially blamed for the lack of uptake in Vista" ? Care to cite ANY references, experiences, even anecdotes instead of just saying it is so?

Re:Surprised..

[Foofoobar]

Sounds to me like you are the one trying to spread FUD.

Re:Surprised..

[RAMMS EIN]

``No. I have read it here and here, but I'm not certain whether Vista actually does this or if it's just a massive fud campaign. From what I've read, it seems to be true. But as I said, I'm not 100% sure.''

And since it's closed-source software, you're not allowed to go find out for yourself.

Re:Surprised..

[sloanster]

IIUC the driver code is the same across all platforms - it's not like sat down and wrote a driver for mswindows, then wrote another driver for linux, then another for solaris, then another for freebsd. At the core, it's basically all the same code, the "nvidia binary blob", the differences being in the glue logic, the "shim" that acts as an interface between the binary driver and the host OS the driver happens to be running on.

Re:Surprised..

[recoiledsnake]

Just goes to show that you were talking out of your ass all the while, and trying to karmawhore the groupthink rather than have anything concrete to contribute to the discussion. And you have no references or evidence for your claims of "75% of the DRM problems were true" and similar types of inane bs.

Re:Surprised..

[Foofoobar]

Yep... angry, bitter, swearing, demeaning to anyone who disagrees and not backing up anything you say with facts. Definitely a troll trying to spread FUD.

Re:Surprised..

[nuzak]

> Who do i trust, an independent researcher or an M$ lackey?

How about facts. Where are Guttman's?

You call yourself a nerd? Can you even think objectively?

Re:Surprised..

[JohnBailey]

Who cares about CGI when most CAD engineering groups use Windows work stations still. CGI is kids stuff compared to some of the assemblies that they work with in the aerospace industry. Different markets, different legacy systems, different needs. Windows workstations may be the best choice for one sector, but not for another.

ws cards

[Sam00]

not sure about what I'm saying but I think the workstation cards are optimized for 2d rendering and CAD stuff.

Re:ws cards

[jawtheshark]

Nope, you buy a Quadro if you are heavily into 3D. You buy a Matrox if you want to do 2D. ;-)

Re:ws cards

[Ilgaz]

Matrox had their lesson trying to sell their excellent cards to gamers. Everyone came to forums and whined about seeing "30 fps" while their friends have "120 fps". Some sane people tried to tell the specs of human eye but it didn't matter.

I bet there are rich but non techie guys buying Quadro for gaming right now. I know a one bought ATI FireGL along with 15K RPM SCSI disk and couldn't sleep because of noise. Not just that ,his game got locked to 30 fps :)

Re:ws cards

[andersbergh]

There's definitely a different between say, 30 and 100 fps: http://100fps.com/how_many_frames_can_humans_see.htm

Re:ws cards

[enoz]

Oh god that site is golden. I knew we were onto something special when I came across the explanation:

Brightness eats darkness. but it keeps getting better after that, somehow they manage to wrangle this into the argument:

Maybe the industry didn't add enough security factor to CDs and that's why many people still feel that analog is sometimes better. I look forward to reading this guy's review of the Matrix trilogy.

Re:ws cards

[TobyWong]

30 fps is at best the bare minimum in terms of playability in a fast moving game such as an FPS. I normally cap out at 60 fps (LCD) but when I am recording game footage with Fraps I set it to 30fps to keep the disk-space consumption reasonable. Suffice to say I find it extremely painful to play at 30 fps and I have trouble making precise shots I would normally make with ease at a higher framerate. For those who haven't used Fraps before the default setting is to display the current framerate in the top corner of the screen so you always know what it is.

Whoever made the claim that ~30 fps is all the human eye can perceive obviously wasn't a gamer.

Re:ws cards

[TheLink]

You might not be able to tell the difference between 30fps and 120 fps. I can (and I'm not superhuman). I probably can't tell the difference between 85 and 100, but I've been playing games long enough to know there's a perceptible difference between 30fps and 60fps. 30fps is just "playable", >= 60fps = "good.

Just find a game, play it at a low FPS and then compare it at a high FPS. I used to play Doom and Doom 2, and believe me in many cases low res high FPS was better than high res low FPS. Plenty of other games allow you to lock the fps, and unlock the fps etc. If you can't tell the difference, well good for you and bad for you, good = you don't need to spend so much on graphics cards, bad = your eyes are probably below average in that.

33ms is a substantial amount of time for games. Even though the picture gets "smeared" in the time domain due to the way eyes work, there's a difference if you are seeing some stuff 25ms later, because it's just "not time to show the frame yet".

Re:ws cards

[Ilgaz]

If we are speaking about strict, locked at a standard like 29.997 fps or 60 fps, you will never understand the difference. You are talking about FPS going up and down to 15-20 fps levels or the graphics losing the VSync. Such things are unheard on professional video/3d market.

At TV or some movie production, there are/were hardware equipment sometimes (in analogue) to make sure the output is strictly conforming to FPS of a given output standard.

Thing is, Matrox, as a professional video/medical company was never in "100+ fps" race. For them, a strict 29.997 or 60 fps is the ideal solution. I was trying to describe the entirely different World of gaming.

Re:ws cards

[TheLink]

You're being overly dismissive. That site does present some valid info, at least at the start (not so sure about the rest :) ).

It is correct to say that it's harder to detect if your white screen suddenly went black for 1ms, than if your black screen suddenly flashed white for 1ms.

If you were in a pitch black cave and used a camera flash, you'd be seeing the inside of the cave for _seconds_ after the flash has long gone off.

"brightness eats darkness" is one way of saying it, even if it sounds silly. I'm sure the "scientific" sorts would be able to come up with the appropriate "Science Journal-ese" phrase for that using lots of fancy long words, but that'll also be silly for an article targeted at "joe average".

broken

[phrostie]

the past few drivers had been getting better and better, but this one broke about half my 3D apps.
the graphics start ok, but when i make any inputs(keyboard or mouse) what ever it is crashes.

this is on a HP Pavillion Amd turion64 running 64bit Debian at Testing

Re:broken

[Curtman]

the past few drivers had been getting better and better, but this one broke about half my 3D apps.

Same here. I can use Maya for 5 or 10 minutes, and then X goes nuts. I can move the mouse, but can't click on, or type anything. I have to ssh in and kill the X process.

I got a nVidia card to make Maya easier to work with. Time to end this experiment I think.

Re:broken

[darkjedi521]

If you're running Maya, would should be running the drivers/distro that Autodesk blesses. Last I checked, that was 2-3 year old drivers on RHEL 4/SLES 9/Fedora Core 5. I run the blessed packages for a small animation studio and only have problems when people out of memory their system (8GB RAM should be enough for anybody). http://usa.autodesk.com/adsk/servlet/item?siteID=123112&id=9683256 has the list of blessed stuff.

Re:broken

[Anonymous Coward]

8GB ram isn't enough for anyone with a 32 GB database....

Re:broken

[Curtman]

If you're running Maya, would should be running the drivers/distro that Autodesk blesses. Last I checked, that was 2-3 year old drivers on RHEL 4/SLES 9/Fedora Core 5.

That doesn't explain why it worked fine 6 months ago, but doesn't now.

Blender does the same thing (yes I got that annoyed)

OpenGL?

[LingNoi]

This is serious question, I heard a while back that Vista had done something to make OpenGL slower.

Could Vista's bad performance be due to its nerfing of OpenGL on Vista in order to get developers to pick DX?

Re:OpenGL?

[zappepcs]

While I tend to agree with you, it would be stupid on the part of MS to hobble openGL because it will only make Windows look sucky. The news for nerds crowd on the Internet (not just /.) will ensure that *ANY* Linux drivers get vicarious face time with the masses and hobbling that experience is like a huge marketing blunder on the scale of the Sony rootkit without so much of the legal problems.

One thing that I like, recently it is not a case of Linux and Solaris having to be as good as MS, but a case of hmmm lets just see which performs better without the a priori conclusion that everyone has to keep up with MS.

I think that very soon, if not now, we can start thinking of MS as an angel with a tarnished halo, if I can put it so gently?

We are slowly moving in to an era of REAL competition, where all OSs are competing for the leading edge and the masses waiting for news each quarter of who is winning rather than everyone not really caring since no other OS is as good as MS. At that point, I think you can clearly and safely declare a win for F/OSS. A battle win if not the war.

Re:OpenGL?

[glob]

http://www.opengl.org/pipeline/article/vol003_9/

"Some have suggested that OpenGL performance on Windows Vista is poor compared to Windows XP. This is not the case."

Re:OpenGL?

[Svartalf]

Considering that the workstation app crowd are, in many cases, still using immediate mode OpenGL calls...

Do you honestly think that this is going to make things work to make them change things?

It has more to do with it's interrupt handling, etc. than anything else. Vista doesn't do so hot, even with
DirectX, because it's been rewritten in a few ways that don't help them any.

Re:OpenGL?

[LingNoi]

Yet, this graph from that page shows Vista performance to be slightly worse and if you compare that graph to the data from this article then Windows XP must really suck as well.

Re:OpenGL?

[Mathness]

I think that very soon, if not now, we can start thinking of MS as an angel with a tarnished halo, if I can put it so gently? Some would probably say this have been so for many years, and probably point to one Angel in particular, the Light Bringer*, as a case in point. Whether it is true or not, it is probably best to pick a specific Angel rather than letting it be an exercise for the reader.

* More commenly known as Lucifer, and believed by some to be one aspect of Satan.

Re:OpenGL?

[Anonymous Coward]

They don't need to degrade OpenGL. OpenGL being slow (it isn't) isn't the reason most developers who pick DirectX pick DirectX. All the developers I know that use DX use it because they like the tool-kits more than what's out there for OpenGL.

Re:OpenGL?

[WK2]

it would be stupid on the part of MS to hobble openGL because it will only make Windows look sucky.

That's never stopped them before.

Re:OpenGL?

[SanityInAnarchy]

As I understand it, what Microsoft did was add an OpenGL implementation as a wrapper for DirectX. There are two things that I understand about this wrapper, though I don't really know:

First, it's overridden by any driver that chooses to implement OpenGL by itself.

And second, it's used for Aero -- the theory being that you can't have two 3D APIs controlling the hardware at once, so if you have a windowed GL app, it'll use the wrapper, whereas a fullscreen GL app will run normally. This is kind of like me running DirectX apps under Wine in a window on a Linux machine running Beryl.

Of course, I still find it obnoxious that DirectX even exists, but I don't think Microsoft were going to shoot themselves in the foot by killing all ID games, derivatives, and games which license ID engines. (If QuakeWars performance sucked on Vista, there'd be hell to pay, right?)

But I also think that all games will run faster on XP.

Disclaimer: The entire rant above is unsubstantiated. Look it up yourself.

Re:OpenGL?

[Detritus]

It may be stupid, but I read that Microsoft has deprecated OpenGL in favor of their own graphics technology. They supported it when they were trying to move people from Unix workstations to NT/2000/XP. With that accomplished, it's time to cut off OpenGL's air supply.

Why be suprised?

[EmbeddedJanitor]

It isn't just the code that impacts performance, but the driver architecture too.

Vista has a new driver architecture and it is goiing to take some time for MS to improve the graphic subsystem performance. It will also take NVidia a while to optimise their code for Vista.

Even then, the Vista architecture might just have some inherent issues that are hard to code around.

Doesn't Vista have a new driver model?

[tjstork]

I thought the whole deal with Vista is that it has a new driver model. Thus, its going to be some time before drivers can really be completely optimized for it.

Re:Doesn't Vista have a new driver model?

[figleaf]

Its an OpenGL test. The perf. difference between OpenGL and DirectX Nvidia implementations has always very large -- even in Windows XP.

Re:Doesn't Vista have a new driver model?

[Ilgaz]

It could be the same deal on OS X Leopard too. Leopard (10.5) is still yet not to Tiger (10.4) levels on OpenGL performance. Of course we have another issue, we can't bug NVidia and ATI, they tell us "Apple does drivers". These are the same guys who sells exactly same chip for 30-40% more expensive price even after Intel switch.

Of course Tiger is at .11 point release while Leopard is just .2 along with lots and lots of changes at kernel. Leopard is more like Vista 64bit while thanks to Apple, no end user has to take any action for it. Also FPS levels getting better each update.

Re:Doesn't Vista have a new driver model?

[TheNetAvenger]

Not really, OpenGL and DirectX have always been more than competitive.

Also OpenGL technically benefits MORE from the new WDDM in Vista because of the RAM allocation system and GPU scheduling as the OS handles all these details for OpenGL and OpenGL applications.

The ICD still has to be optimized to pass through and work with the new Vista WDDM model, so as Vista was first released to now, just like with DirectX - OpenGL on current drivers is considerably faster than the horrid RTM drivers from both NVidia and ATI for Vista.

Right now in MOST circumstances, even games running in an Aero Window, they are running faster under Vista than XP, no matter if they are OpenGL or DirectX.

http://www.opengl.org/pipeline/article/vol003_9/

One game a technician here plays is City of Heroes, that is a hybrid DirectX/OpenGL application (see NCSoft for more details), the tech runs the game inside a Window with Aero active, as it is 10% faster than running it full screen, which turns off Aero's composer. Why the improved performance with Aero is unknown, but measurable and a testament to the speed of how Aero is implemented with the shared device context and texture methods it uses instead of dual memory or double buffering like you find with Linux or OS X.

I personally have more regard for DirectX because of being involved with SGI and the 90s OpenGL specifications, where MS couldn't force the OpenGL participants to move to 3d Hardware gaming type constructs, even after writing a few test specifications for OpenGL. If OpenGL would have had a better view of the future, there would have NEVER been DirectX as MS wanted to be a big OpenGL proponent.

I think OpenGL shot themselves and a lot of users in the head with their closed minded moves, and if it hadn't been for the gaming movement of Linux when 3D acceleration was becoming a normal aspect of computing, OpenGL to this day might have disappeared or remained a 'high brow' 3D specification that didn't want to dirty their hands with more direct 3D hardware support or features condusive to gaming.

Anyway, check out the link, there are several posted about OpenGL performance on Vista in the past few months comparing both it and DirectX to various situations and XP, showing that the rewriting and optimizataion of the Vista drivers fro NVidia and ATI for the past few months are finally as mature as the XP drivers. (Which isn't too bad considering they were written from scratch late 2006, with no real world performance or game profiling optimizations that the XP drivers had built on for years.)

Here is another thread a tech here has been following and forwarded to me this morning, since I was reading it right before I flipped to SlashDot, I thought I might as well include it as well, not a concrete study or test, but more of what users are experiencing to their surprise after all the negative Vista vs XP press:

http://futuremark.yougamers.com/forum/showthread.php?t=72298

Re:Doesn't Vista have a new driver model?

[Billly Gates]

I think the test is unfair. OpenGL under Vista is emulated through the directX layer which is slow as hell.

Nvidia has had terrible drivers for Vista for awhile too.

Re:Doesn't Vista have a new driver model?

[Nicolay77]

Reading the links you provided it seems that games and indeed all programs load faster in Vista than in XP.

But for actual gaming (measured in fps) XP is still faster by about 2%-5% in most cases, losing in just 2 of about 15 tests.

I don't see how can you reach the conclusion that Vista is faster for actual gaming, based in those links.

However the real test should be this: I game in XP. I have an optical USB mouse that can be plugged to the PS/2 port, and there's a huge difference between playing with the USB interface and the PS/2 one. There's no input lag with the PS/2 connection.

However this is not enough to score a frag with some of the people I game with. I had to disable all performance counters in XP, to be able to reach the same framerates in multiplayer that I had in offline play. Now the network performance is amazing. The difference between getting a frag or being killed is just a small fraction of a second, and the fact that there's no lag in any part of my system helps me a lot.

So my test would be using a heavily tuned Vista system, and see if I can feel the same responsiveness in competitive playing as I feel it in XP.

So far my only test has been a default Vista in a friend's laptop, and the damn thing would lag by almost 15 seconds just to show some text I have typed!!!

More tests are needed, but your links don't really paint Vista as superior to XP at all. Well they do, but only for loading times, not running performance.

Re:Doesn't Vista have a new driver model?

[TheNetAvenger]

I don't see how can you reach the conclusion that Vista is faster for actual gaming, based in those links.


Well those links weren't to showcase FPS advantages of Vista, there are tests out there on hardware and gaming review sites that show some games like Oblivion for example to push 20% faster than XP in most test senarios. This is dramatic and opens the box of 'what is' possible with some WDDM/Vista optimization.

Tests are hard to reign in, as you will find some sites use canned tools, some use canned portions of a game to be more real world, yet none are entirely accurate in the scope of user experience, or variance in the product to product marriage that is consistent in the PC world of 1,000,000 hardware variations. Take a new ATI card and put it in 10 different mainboards, on 4 of them, it will beat NVidia, and 6 of them it will lose and sometimes lose horribly in most games and tests.

So it comes down to what you say as a gamer and 'your' experience is what counts. Well you are reading online tests only, you don't know what 'your' experience is or will be. Take an hour, make a dual boot setup for XP and Vista and see what you can get out of both based on your personal knowledge of the games and testing.

With regard to this suggested challenge, our internal techs 9 to 10 prefer Vista for gaming, espeically after the performance growths in the Vista drivers from both ATI and NVidia from June-Sept 07 timeframe when MS went to both companies and worked to get optimizations more in line with how WDDM works instead of thinking like XPDM or even single application GPU usage performance profiling.

I also notice you are disregarding a major aspect of the gaming tests from even the links I provided.

As for Vista being faster at gaming, there is more to gaming than just FPS. Losing even 5% FPS is losing less than two (2) FPS when a game is stuck at a 'low' 30fps. This is OUTSIDE the human ability to fully notice a 5% FPS difference. And when you take this to modern gaming where 60-100fps is normal, 2-5FPS at these rates is virtually non-existent.

So lets take 'only' the tests from the links I posted, you are losing 5 or lets even say 10% FPS on average. Yet your game runs smoother because there is less HD bottleneck, you can run massively higher quality textures with Vista's WDDM VRAM virtualization system, and also push higher levels of AA without any FPS loss beyond the base 5-10% range.

Would you give up 2-5 fps in a game so that you could run with 4x AA and Ultra High Textures vs XP with 2x AA and Medium or High Textures? Most games would without question, and this is just ONE area the WDDM in Vista outshines XP in terms of what resources it makes available to games and the GPU.

This is also contextually talking about ANY 3D application not just DirectX10, as the WDDM in Vista works across all OpenGL and DirectX equally, meaning that GPU RAM Virtualization and GPU scheduling are handled at the OS level even for a very old 3D game from 10 years ago, so even OLD games get a performance, or quality boost in Vista because of the WDDM, and it is not dependant on just new games.

There is also the 'multi-tasking' aspect of the WDDM and the way Vista can handle multi and multi-core GPUs, as well as schedule single GPUs across several 3D applications. Vista WDDM essentially gives the OS pre-emptive scheduling control of the GPU as well as managing RAM assets.

For people playing single games this will not always add benefit, but if you are running the game in a Window under the 3D Aero composer (as the example of my Tech playing CoX) it does matter as both Aero and the game assume they have 100% control of the GPU 3D operations and assets and technically neither do, Vista does. This is why the game's FPS doesn't drop to horrible numbers. In fact, you run multiple instances of several games at the same time inside Windows on Vista, you will lose surprising few FPS in each game because of Vista multi-tasking the GPU between the applications with

Re:Why does it fucking matter anyways?

[JoeCommodore]

I... Am... utterly amazed - by your brilliance!

I can tell we are conversing with the elite of computer wisdom here. AC, if you read your replies, what sort of experience do you have in um.. education, or the job market?

Vista Slow?

[Anonymous Coward]

That is only because it has to check the signature of each polygon to make sure that it is properly licensed to be rendered in the current user's context on the active display.

Other OS's

[__aamisb9940]

...I wonder how XP stacks up

Re:Other OS's

[Ilgaz]

I would add Windows 2000 to list too. As long as Nvidia/ATI provides professional driver support (DirectX is irrelevant for pros), TV studios, Engineering offices will stay in what is working. Security issues etc. generally doesn't matter since the machines are not connected to Internet or only connected to LAN with a very strict firewall.

I don't think professionals are on latest Linux kernel (major version) either.

Also even on Apple, at least the AVID people are sticking with OS X Tiger 10.4.10 (not 11) with older Quicktime. I am betting CAD people stay with whatever Autodesk tells them.

How is this a comparison of OS's

[arse maker]

This is a comparison of drivers, if there were consistent performance difference between the os's, you could claim one OS is faster than the other. This isn't the case at all, the scores are all over the place. Sure, some difference is OS based, but when the results are such a small sample with not much of a clear trend, its only useful to compare which OS is better for this particular hardware / driver combo.

No XP?

[sleeponthemic]

If you're a quattro user, your OS choice would surely be on software available for whatever particular professional application you are using the card for. As a sound designer, that would be for me, XP. I don't think many professionals are ready to jump to vista quite yet so I'm surprised that they have not included it. We are, after all, looking for stability.

Re:Why does it fucking matter anyways?

[robzon]

Communist linsux doesn't have any real software to take advantage of the hardware. Where are the fucking games? Aww, go to your mommy tell on those bad, bad, nasty Linux developers that they don't want to play with you. She'll find you new friends. Maybe even soothe your wail with a nice mug of coco and a hug. Grow up.

Ah for a bit of Suntools

[Anonymous Coward]

So why not? If Linux or Solaris adopted a direct to hardware model like Sun used to have with Suntools and Windows has with its DirectX APIs I expect they would both handily push Vista right out of contention.

this is a surprise

[rice_burners_suck]

What?! Windows did not have the best NVIDIA performance?!

This is a new one. No, really. Usually NVIDIA makes their Windows drivers their best drivers, and Linux is supported as an afterthought because they can make a few percentage points more in sales this way, and because it discourages reverse engineering their hardware, since those who would take the time and effort to do so won't on account of there being a working solution.

In other words, I am surprised that although Windows Vista has been such a mess in terms of compatibility and speed, that even the NVIDIA benchmarks put it last.

Re:this is a surprise

[pak9rabid]

Usually NVIDIA makes their Windows drivers their best drivers, and Linux is supported as an afterthought because they can make a few percentage points more in sales this way... Not really. Nvidia's drivers are designed incredibly well. Their drivers were designed ground-up to abstract all of the rendering code such that porting it to different platforms is a simple process of designing a shim to connect the driver engine to a specific OS's API. So, with the exception of the driver shim, the codebase is almost identical.

Re:this is a surprise

[Anonymous Coward]

This is a new one. No, really.

Actually, you're talking complete rubbish. Linux has a large proportion of the market for engineering/scientific and other 3D (e.g. movies) workstations (taking over from SGI Irix and Sun). And Nvidia's high end cards are in many of those boxes. So nvidia has, for years, produced high-performance high-quality linux drivers, especially for their high-end cards.

Now, I'd rather they were open source, but mostly as a matter of principle in Nvidia's case (and, mildly, so that they could integrate faster with the rapidly-developing x.org X server's new tricks). This is in marked contrast to ATi/AMD, which has always had terribly buggy linux drivers.

But ATi finally released specs. This is good news, but it's being done primarily as a last-ditch attempt to claw back some of the high-end linux-based workstation market where nvidia rules (since 3DLabs and Matrox basically gave up).

Re:this is a surprise

[xenocide2]

I wouldn't be surprised if Nvidia pays developers to make Quadro cards run fast on Unix and Linux in particular. Many purchasers of that hardware want it.

Re:this is a surprise

[linzeal]

Why, name a CAD solution that does not run on windows that the industry uses. Now name the ones that are not supported on Linux and it is over half.

Re:this is a surprise

[howlingmadhowie]

90% of hollywood runs maya under red hat for special effect work

Re:this is a surprise

[linzeal]

CGI != CAD .

Re:this is a surprise

[RAMMS EIN]

Wasn't there an issue with nVIDIA drivers not working with Vista at all?

Re:this is a surprise

[howlingmadhowie]

my point being why did you choose cad, where linux has traditionally been weak, and did not regard a market where linux dominates and powerful 3d graphics are a must? my post was designed to answer the question as to why nvidia would invest a lot of time and money in linux drivers by pointing out, that asking for cad software that only runs on linux is besides the point.

Re:Headline is misleading!

[Anonymous Coward]

Man, don't you PCLinux spammers even read the fucking article?

Re:Headline is misleading!

[Ilgaz]

If I was to benchmark a thing like OpenGL, I would go for bare bones Linux like Slackware or Debian., Vista Business edition and Solaris (non developer). If there was OS X opportunity, I would choose clean installed OS X without developer tools, especially "CHUD" tools.

They were completely wrong on OS choices not just Ubuntu.

Re:Headline is misleading!

[Cal Paterson]

I would be surprised if PCLinuxOS was more popular than Ubuntu. It probably just gets more traffic on distrowatch. Either way, I'm sure Debian, RHEL/CentOS, FreeBSD and SuSE make up the vast vast majority of distro installs.

Either way, this is totally irrelevant to the article. Ubuntu is a big desktop orientated distro. It's appropriate for the testing, and I doubt there is much difference for the purposes of this test between Ubuntu and PCLinuxOS.

Video on Linux

[Doc Ruby]

I thought the nVidia Linux drivers don't get enough performance out of the cards to do good video framerates on Linux, or good alpha blending for compositing "picture in picture" or GUI overlays on top of the images.

Maybe that's on the latest (higher) models of cards, which actually have the performance to do TV. How come those frequently-complained driver limits don't appear in these benchmarks?

Re:Video on Linux

[Chandon Seldon]

For any normal use - including accelerated video - the NVidia Linux drivers are solid and have been for years.

There may be edge cases where they have worse performance than other drivers, but not in any area that I've personally seen using the drivers.

Re:Video on Linux

[Abcd1234]

You're almost certainly thinking of ATI, who's drivers for Linux have historically been of very poor quality (though I understand they're working to fix these issues, and in fact may already have done so). This would be why Nvidia cards have generally been the 3D accelerator of choice for Linux users for many years, now.

Re:Video on Linux

[Abcd1234]

Sorry, I should say, not just 3D accelerator, but also accelerated video and MPEG2 decoding card of choice. For example, the Geforce FX5200 (or newer) has been the recommended card for MythTV for years.

Re:Video on Linux

[batkiwi]

This is an openGL test. Nvidia's linux drivers for openGL have been really fast for a long time now. In fact they've confirmed that they use the same driver code for windows and linux, just with a different API exposed.

What you're talking about is that the video acceleration APIs are not exposed for linux (purevideo). This is still the case, and annoying.

Re:Video on Linux

[dbIII]

There has been hardware rescaling to TV modes on their cards for a few years so you'll find the cheapest models with TV-out do a good job. Other features have improved a lot in the linux and other drivers - look at the README on the nvidia download site for the long list and how to turn some on or off.

Re:Video on Linux

[ratboy666]

What is a "good video framerate"? Video is 30 fps. No faster, no slower.

The 5200 FX is able to display SD (standard definition) video with no problems. Of course, cards of this class do not have HD encoders.

The 6000 and up series is able to do HD (high definition) video with no problems. I am using a 7300 (AGP 4x bus interface) to do 1080i display (the machine I am typing on, which happens to be my PVR). I am not sure if the card will drive 1080p, but that isn't a "mode" that my TV will do.

The card/driver does have XV support, which means that "video overlays" and yuv conversion is handled in the card/driver (and is most likely accelerated). MCxV is also supported (but I tend not to use that).

No problems (stability or performance) -- except for software that doesn't understand the concept of overscan, and wants to place things too close to the display edge. Window managers that don't understand 30 fps interlaced, and try to draw large horizontal single pixel lines (resulting in flicker). But these aren't nVidia's issues. As a system integrator, I deal with these problems (my value add when building MythTV boxes).

I try to support AMD (ATI) but nVidia has had an enormous advantage in the Linux sphere for years (things tend to "just work").

Re:Video on Linux

[pushing-robot]

Video is 30 fps. No faster, no slower.

Really?

Re:Video on Linux

[SanityInAnarchy]

What is a "good video framerate"?

No dropped or mangled frames, playing at the appropriate speed, keeping up with the audio.

Video is 30 fps. No faster, no slower.

You could not be more wrong if you tried.

It depends entirely on the video source, and the framerate for that standard of video, and whether interlacing is used. Even where it's about 30 frames per second, if it's traditional video, it isn't -- it's 29 point something.

And then there are digital video sources, which can be pretty much anything, especially when the source is computer graphics.

Of course, cards of this class do not have HD encoders.

You probably mean HD decoders, which would be pretty useless until nVidia provides any kind of support for them on Linux.

The card/driver does have XV support, which means that "video overlays" and yuv conversion is handled in the card/driver (and is most likely accelerated).

That is nice. It's something I've come to expect from any machine I put Linux on. The only time I was really made aware of it was when this was not working with the binary ATI drivers -- thus, I could run the open drivers and get XV, or the closed ones and get accelerated OpenGL. It sucked.

Since then, I haven't touched an ATI machine with Linux, so it's hard for me to imagine a card without XV support.

MCxV is also supported (but I tend not to use that).

Do you mean XvMC?

Yeah, you didn't mention why you don't use that. I don't, because it tends to cause problems, especially when doing ARGB and such (Compiz) -- but also, in general, it seemed less flexible and less responsive. Plus, the computers I use nowdays can pretty much do HD video, even with the decoding in software, so hardware-accelerated mpeg2 is kind of pointless.

However, hardware-accelerated h.264 would be nice, especially at HD resolutions.

except for software that doesn't understand the concept of overscan, and wants to place things too close to the display edge.

I don't understand the concept of overscan. They are chopping off a part of your display, and you don't consider that broken?

I try to support AMD (ATI) but nVidia has had an enormous advantage in the Linux sphere for years (things tend to "just work").

Wish I could still say the same.

Lately, I haven't been able to really pin it down (though I suspect hibernate/resume), but my X will occasionally start leaking memory. It's not an X app (so xrestop says), so I'm pretty much at a loss. Inevitably, it crashes weirdly, especially on my laptop -- and until then, it just sucks down more and more RAM.

And this pretty much only happens on my nVidia machines. And it's on Kubuntu, so it's not as if it's some tweaked-out Gentoo system that is somehow My fault for picking the wrong combination of compile settings and libraries.

Now, Intel machines are rock solid, but that's to be expected -- they actually have mature open drivers. Unfortunately, nVidia has an advantage in actually being able to play most games at an acceptable framerate. This is the main reason I cheer Intel on in the debates about raytracing.

Re:Video on Linux

[ratboy666]

29.97 to be specific.

The framerate we are concerned with (this is a video card), is the framerate used to drive the output device. Therefore HD encoder is correct (we are not interested in decoding a stream here, we are encoding the frame buffer to the TV). TV sets follow specific standards, and my original comment holds.

Computer Monitors, on the other hand, are driven in a whole bunch of (wacky) modes -- some VESA defined, some TV spec, others... well, with the advent of "autosyncing", the sky is the limit. Some TV sets (with VGA, DVI, or HDMI inputs) can accept some of these wacky modes as well...

To the issue of tearing/dropping -- dropping can only happen if source material cannot be fed to the video card at the needed rate. Not a problem with modern video cards (may be an issue with HD source material, and some busses). Tearing? Haven't seen it in YEARS. Indicates that there is a memory controller issue.

XvMC? Yes, I did get the letters discombobulated. Sorry. Its driver/hardware assist for motion vector compensation. Not terribly useful these days, and, I will agree that the nVidia driver displayed some anomolies with it, using a 5200 FX, when I last tried it (2 years ago).

As to overscan. Broken? Maybe. TVs do it. If I am trying to display to a TV set, overscan should be accomodated. Most of the MythTV themes DO NOT.

Re:Video on Linux

[SanityInAnarchy]

The framerate we are concerned with (this is a video card), is the framerate used to drive the output device. Therefore HD encoder is correct (we are not interested in decoding a stream here, we are encoding the frame buffer to the TV).

I suspect that the actual problems I've experienced are more on the side of decoding and/or scaling, and of trying to keep up with the framerate in the actual video. That is, it's still possible for h.264 to require more CPU than you have to decode realtime, no matter how fast your video card is. And that's why we want a hardware decoder.

the nVidia driver displayed some anomolies with it, using a 5200 FX, when I last tried it

To be fair, it was awhile for me, too, but it wasn't "some anomalies". It was more like crashing and/or making the rest of your desktop unusable, sometimes an inability to go fullscreen, etc.

If I am trying to display to a TV set, overscan should be accomodated. Most of the MythTV themes DO NOT.

Fair enough.

I still think that you should not be allowed to call it a "1080i" set if it's really more like 1000i, due to overscan. It's probably offtopic here, but I still consider it to be a defect.

the difference does not matter.

[gnutoo]

Gaming cards traditionally follow workstation cards in time.

What's significant here is that Windows has lost it's graphics crown. DRM and bloat or industry defection for the same reasons, we all know the root cause. Free software is simply cleaner and works better. If the ability to run DirectX 9 under Wine was not enough to move gamers to Linux, this is. Things can only go downhill for Microsoft now. Free drivers will be even cleaner and the performance gap will widen.

Re:the difference does not matter.

[Anonymous Coward]

Wow, you sound a lot like twitter, except if I recall, twitter knew how to use the apostrophe correctly. "...Windows has lost it is graphics crown." Makes about as much sense as the rest of your post.

Re:the difference does not matter.

[The Analog Kid]

Things can only go downhill for Microsoft now. Free drivers will be even cleaner and the performance gap will widen.

History has shown that the higher quality product does not always win. I bet if I randomly took 100 people off the street, put them in a room and asked what Linux was, maybe 5 at the most would have an idea, if I asked what Windows was, at the very least they could tell me it was made by Microsoft and came with their computer. Linux distros do not have the marketing capabilities that Microsoft does, and in a world where people think things should get easier to use overtime, Linux will not take even 10% of the desktop marketshare.

Re:the difference does not matter.

[recoiledsnake]

What's significant here is that Windows has lost it's graphics crown. DRM and bloat or industry defection for the same reasons, we all know the root cause. Free software is simply cleaner and works better. If the ability to run DirectX 9 under Wine was not enough to move gamers to Linux, this is. Things can only go downhill for Microsoft now. Free drivers will be even cleaner and the performance gap will widen. From TFA:

Then in September, we had looked at NVIDIA's multi-GPU performance under Linux and Windows when running two GeForce 8600GT 256MB graphics cards in SLI (Scalable Link Interface). Windows XP and the ForceWare driver had outpaced Linux in every gaming test we conducted. The drivers have a lot more influence than you give it credit for.

Re:the difference does not matter.

[onefriedrice]

If the ability to run DirectX 9 under Wine was not enough to move gamers to Linux, this is. Things can only go downhill for Microsoft now.

Not to rain on your parade, but a single benchmark showing Ubuntu besting Windows in nvidia driver performance is not likely to move any gamers to Linux, let alone mark any downward slide for Microsoft which already isn't taking place. Seeing as how this isn't even a graphics card for gamers (it would run games very poorly indeed), it will take a lot more than this to move either casual or hardcore gamers to Linux.

Re:the difference does not matter.

[blantonl]

Then "open source marketing" will fix that.. and don't think that marketing can't be open sourced - someone will innovate and figure that problem out.

Re:the difference does not matter.

[LiquidCoooled]

Would they care if a linux kernel and display driver opened up when they clicked the exe?
an actra few seconds onto a load won't bother anyone and then that game can have super quick graphics?

Is that even possible?

Re:the difference does not matter.

[bigpicture]

You think? I remember and have followed a similar kind of scenario, it started over 30 years ago when I was younger. It went something like this: GM was the Biggest of the Big. Had a market share greater than all other automobile manufactures combined. Had revenues higher than the GNP of 90% of the worlds nations. etc. etc. etc. They developed this Business Model called "Planned Product Obsolescence". (Your vehicle was planned to be scrap in about 10 years or before.)

There was also another little automobile manufacturer called Toyota with a very small market share, they made crappy little vehicles, used to be called "piss pots". They had a Business Model called "Continuous Improvement". There was a historic event in 2007 that went quietly unnoticed, Toyota surpassed GM in world market share and revenues.

Re:the difference does not matter.

[Anonymous Coward]

You argument is flawed. You're arguing because windows is better known it will always
have the largest market share. The same could have been said about IBM pcs, or lotus 1-2-3,
Borland's compiler suite, or wordstar word processor.

The fact of the matter that next winner has to start out small because it gets to grab
marketshare. Google is an excellent counterexample to your argument. They were just 2-3 people
in 1998 working on a master's thesis project when Yahoo and AOL were the big thing. And where
is AOL now? How much marketshare does Yahoo have for search engines?

Personally I think that Dell selling preinstalled Linux boxes in the U.S. was the first toll
of the death bell for Microsoft. Then walmart selling out the green PCs was the next tolling of
the bell, and now that Asus is selling Eepc laptops I think is the first nail in the coffin for Microsoft.

Will Microsoft die overnight? No. Will they go out with a bang? No. I think they will go out with
a whimper within the next 5 years unless they somehow manage to reverse their course like they
did in 1995 and embrace the fact that GPL software is here to stay and start using it.

Re:the difference does not matter.

[Anonymous Coward]

Mod the fucking parent up. Why the hell is this modded down, it has a good point.

Microsoft is on its way to irrelevancy. Its losing market share in all its markets. Its losing desktop operating systems to the likes of Mac and Linux and even smaller contenders like *BSD and Solaris. (Some may argue BSD isn't so small, what I mean by it is *BSD isn't really what it used to be and is basically getting squashed by Linux and its own descendant: Mac OS X.

Its because Windows is aging, and not gracefully. Hell, by the time Windows became a little more independent from DOS back in the day it was already pathetically aged. But by that point Microsoft was bursting out as a horribly anti-competitive company. I remember one post elsewhere on this site stating that "UNIX has matured, Windows has aged." They were correct.

Then there are a shitload of markets Microsoft is in they never secured simply because those experienced with products in the market knew a crappy thing when they saw it: I think one of the best examples of this was the WebTV debacle. Another example is X-Box. Sure, the damn thing is popular, but its losing Microsoft money. Wii is beating out the 360. Though the 360 is beating out the PS3 by a wide margin. though I doubt its on the account of quality of the 360 as a lack of quality and real marketing for the PS3. I never liked Playstation anyway, only got popular because Sony managed to hype it way too fucking much. Note that the PSP and PS3 are flopping like stranded fish because gamers have finally caught on to what pieces of crap the consoles are.

The 360 is worse. I can't go to many gaming news sites or even a few articles here on /. without hearing about the horrible DRM, or the incredibly common and fatal Red Ring of Death (How the fuck could Microsoft let such a flaw slide? Answer: Microsoft doesn't give a shit about the console working. Once you buy the console, they got their sale, who gives a shit if it works. Fish oil, my friends. They have the money and the market share, that's the only metric for product success.)

What gives me a fucking orgasm is when I see their existing killer apps like IE, Windows, and Office start to diminish not only in quality, (Going from bad to worse.) but also popularity and install base. Like, as I said earlier, Windows losing its share, and the reality that the whole reason we're seeing IE7 and IE8 is because the likes of Safari, Firefox, and Opera are starting to beat the shit out of IE. (6 years between IE6 and IE7 should have made this obvious. They got cocky knowing that crushed Netscape and so they felt they didn't have to do anything with the browser, and then enter Firefox. Note now how IE7 acts like an FF wannabe, and now IE8 will be acting like a Safari wannabe.) And With Office 2007 ruining everything people are going off to Google Apps and OOo which deserve more applause than the piece of trash that is Office.

What does Internet Explorer, Windows, and Office have in common? They're unoriginal, pieces of garbage, and they landed their commercial success thanks to lock-in, embrace, extend, extinguish, anti-competitive practice, partner backstabbing, and FUD. It sure as *hell* wasn't thanks to standards-compliance or making a GOOD product of all things.

Go ahead and mod me a fucking troll, but we all know that Microsoft is evil and deserves to burn for what its done to companies that actually deserved to shine. Netscape, Spyglass, Be. Down with Microsoft and its cock-sucking lapdogs.

Re:the difference does not matter.

[Anonymous Coward]

Well, he has been bragging up a new sockpuppet since the Twitter and Erris IDs have been buried deep in a karma hole...

Personally, I've been hoping that he's been kdawson all along. Those two Zealots deserve each other.

Re:the difference does not matter.

[glitch23]

I bet if I randomly took 100 people off the street, put them in a room and asked what Linux was, maybe 5 at the most would have an idea, if I asked what Windows was, at the very least they could tell me it was made by Microsoft and came with their computer. Linux distros do not have the marketing capabilities that Microsoft does, and in a world where people think things should get easier to use overtime, Linux will not take even 10% of the desktop marketshare.

These are the same people who when asked what kind of computer they have answer with "black". Also, not many people can associate the maker of the softare they use with the actual software application. You ask them which browser they use and they will say "I don't know. I just click on the blue 'e'." despite the fact that the title bar says "Internet Explorer" 100% of the time the application is open. So I hope you don't expect them to know Microsoft created it if they don't even know its name.

As far as marketing capabilities, I hardly ever see a Microsoft commercial. When I do they don't ever specify any particular product in the commercial. How does that really sell Windows or Office? All the marketing seems to happen behind the scenes from the point of view of the end consumer using deals that happen between OEMs and Microsoft salespeople.

Re:the difference does not matter.

[manekineko2]

I'm as much for open source as the next guy, but for the love of all that is holy, what are you talking about? If marketing can be open sourced, how will it work? "Someone will innovate and figure that problem out"?

Square pegs don't fit every type of hole. No matter how much we sit around and think about it, no "innovation" will make it fit. We can make some sort of hack and call it a square peg fitting in a round hole, but it isn't really.

The difference between programming and marketing is that marketing isn't about standing on the shoulders of others. Giving away your previous work isn't going to help your successor market to any significant effect.

They have invented "open-source" marketing in the sense of hacks, like viral marketing, that aren't really open source but sort of a vague gesture in that direction, but don't expect traditional marketing to be going anywhere.

Re:the difference does not matter.

[pizzach]

History has shown that the higher quality product does not always win. But that is why Linux is destined for greatness. We have both the higher quality product and the lower quality product, GNOME and KDE! There is no way we can lose with this monopoly or great-suckiness.

*I think I just hemorrhage about 5 mod points indirectly with this post at a poor attempt at humor

Re:the difference does not matter.

[linzeal]

Than why can't I use my CAD of choice Pro Engineer in Linux anymore ? They tried to support Linux and found it wasn't worth it.

Re:the difference does not matter.

[westlake]

Free software is simply cleaner and works better. If the ability to run DirectX 9 under Wine was not enough to move gamers to Linux, this is.

Operating System Market Share for February, 2008

Linux with a 0.65% market share.
In the W3Schools OS Platform Stats Linux has seen 1% growth in four years, Vista 7% growth in one year.

The test suite is at best a snapshot of performance at a particular moment in time. It is rarely as objective a measure of the user's experience as its proponents claim.

Re:the difference does not matter.

[Stephen Samuel]

It's the tip of the wedge.... One of the arguments of why to go to Windows was the superior performance of Windows drivers written (and tweaked) by the chip manufacturers vs drivers for the same chips shipping 6-12 monthsl later on Linux and designed by reverse-engineering the chips over a coal fire.

Nowadays, however, it's looking like the fastest solution (or, at least, a reasonably fast solution) might be to put your game on a Ubuntu live-CD and/or encourage the average gamer to move from Windows to Linux.

Given that gaming and photoshop are two of the big apps holding many people back from Linux, this is a big deal.

Re:the difference does not matter.

[Bert64]

Vista has seen growth because it's not a new OS, it's an incremental upgrade to an existing one...
It's comparable to linux users moving from ubuntu 6 to 7, or OSX users from 10.4 to 10.5.
For the share of "linux" as a whole to increase, there needs to be more people using linux who weren't using any version of it before.

Re:the difference does not matter.

[ozmanjusri]

If marketing can be open sourced, how will it work?

Lugs, installfests and similar events, and even GNU and FSF are all partial steps toward open-source marketing. I have no doubt clever people will be able to harness enthusiasm and intelligence towards getting the word out if we decide it's needed.

Re:the difference does not matter.

[c0p0n]

http://spreadfirefox.com

Re:the difference does not matter.

[apoc.famine]

You ask them which browser they use and they will say "I don't know. I just click on the blue 'e'." despite the fact that the title bar says "Internet Explorer" 100% of the time the application is open.

To be fair, for those people, IE probably doesn't say Internet Explorer at the top while they have it open. And if it does due to some strange quirk of the several varieties of spyware/rebranding crashing, it's probably covered with a toolbar, dancing snake, or some other shit.

The people you are referring to probably don't get the same browser twice, so just knowing what the icon looks like is probably the best you can hope for.

Re:the difference does not matter.

[Simon Brooke]

As far as marketing capabilities, I hardly ever see a Microsoft commercial. When I do they don't ever specify any particular product in the commercial. How does that really sell Windows or Office? All the marketing seems to happen behind the scenes from the point of view of the end consumer using deals that happen between OEMs and Microsoft salespeople.

We clearly don't read the same media. I would guess that 50% of all adverts I ever see are directly from Microsoft, and another 20% from companies selling Microsoft's products. That's a gobsmackingly huge advertising spend.

Re:the difference does not matter.

[Airline_Sickness_Bag]

There was also another little automobile manufacturer called Toyota with a very small market share, they made crappy little vehicles, used to be called "piss pots". They had a Business Model called "Continuous Improvement"

Actually, it goes back further than that, with the Volkswagen Beetle.

The Japanese cars that were imported into the US back in the 60's and 70's tended to rust even faster than the US cars. This may have been due to Japanese laws that discouraged ownership of cars older than 4 or 5 years old.

Re:the difference does not matter.

[thegux]

Where's my "+1 Car Analogy" mod?

Re:the difference does not matter.

[the_B0fh]

...Office 2007 ruining everything people are going off to Google Apps and OOo which deserve more applause than the piece of trash that is Office

Uh... How is OOo not a piece of crap? It has improved quite a bit since StarOffice 5.x, which was _REALLY_ crappy, but that's just like moving from an old Yugo to a newer Yugo. For what it does (for the end user), the office suite is actually pretty damn usable, if you don't need advanced features, such as tables within tables. Once you start going beyond what 80% of the population needs, it sucks pretty hard. Unfortunately, OOo sucks pretty hard right out of the box.

Not saying OOo is not improving, but it still has a long way to go.

Re:the difference does not matter.

[glitch23]

I don't consider commercials to be part of reading material. Ads in magazines and commercials on TV are both categorized as advertisements to me though. Yes, I do see lots of ads in magazines for Microsoft products but as far as TV is concerned I probably see 1 new MS commercial (i.e. advertisement for TV as opposed to print) once every few months if not less often. I don't read the Wall Street Journal so I can't speak for it but all the printed ads for MS that I see appear in technical magazines which a regular user would't see in the first place. Even in the WSJ, the readership is specialized. Only a commercial on TV would reach a mass general audience and I'm surprised MS isn't doing more of that. They used to advertise on TV when a new version of Windows was released (IIRC) but I never recall seeing one for Vista. Did anyone else?

Re:the difference does not matter.

[nuzak]

The 360 is worse. I can't go to many gaming news sites or even a few articles here on /. without hearing about the horrible DRM, or the incredibly common and fatal Red Ring of Death

Perhaps you should step away from the screaming animal cages that are the typical gaming forums. No one who actually buys one of these things for games cares about the DRM, and they've fixed the RROD problem, completely.

You're not a troll, just another representative type of idiot that gives slashdot its loudest shrillest voice.

No one cares about your amateur analysis: their sales are growing in double digits. During a recession.

Re:the difference does not matter.

[bigpicture]

Business is business, nothing special or unique about software, just the "before and after" time curve. The term "sunset industry" was used frequently for the auto industry. But I suppose when they make hardware "quasi live" and "self programing" then software will be a "sunset industry" too!

Give him/her a couple of mod points for the aggravation here!

Re:Headline is misleading!

[kklein]

I read Slashdot every day, and until this moment I had never even heard of PCLinuxOS. I had to look it up.

Ubuntu, however... Ubuntu, my parents have heard of.

Don't know what metric Distrowatch uses, but it seems to be flawed.

Granted, I don't use Linux as a day-to-day OS, but I have some Linux apps I like which I run via Ubuntu in VMware Fusion. As a casual user, of the distros I've tried, Ubuntu wins hands-down. It's still too hard to set up for my parents, say, but not so hard that I don't just say "fsck it" and delete the partition, as I have done with all the others.

Re:Headline is misleading!

[Svartalf]

Uh... Dude? Did you even RTFA? (No, that'd presume too much- it is Slashdot, after all...)

Ubuntu PASTED Vista, and fared really good against Solaris, even when it was beaten by it.

Reality is, this largely has nothing to do with whatever Distro you care to favor- it's that an out
of the box Linux distribution pretty much pasted an out of the box Vista install.

Nothing more. Nothing less.

One more step...

[mebrahim]

One more step towards Desktop Linux. But we need some real games to use these 3D capabilities!

Re:One more step...

[LoonieMiami]

Considering TFA is about the Quadro family, games are irrelevant. There are a few people out there running Maya, XSI and such that will be very happy to hear the news.....Oh, and just for kicks, desktop linux is already here! It's been here for years. I mean, my screen looks like linux, my other computer too....I've switched quite a few people to desktop linux and they cringe at the idea of going back to windows. So, desktop linux is already here, now it's time to make it "popular"... Just my 2c

Re:One more step...

[plasticsquirrel]

Desktop Linux distros like Ubuntu have worked well for a long time now. They aren't something always on the horizon. You're not going to wake up one morning and realize that this year is the year of Linux on the desktop, and see mass conversions.

And FWIW, the best Quadro performance isn't going to make a difference unless you're doing high-performance rendering or some similar task (and you actually have a Quadro card).

Re:One more step...

[SanityInAnarchy]

Well, for the systems actually intended to run games (that is, NOT Quadro cards), there are a few Linux ports -- I consider Id games to be "real games" -- and Wine will run quite a lot of Windows games, some of them better than on Windows.

But I don't care about "The Year of Desktop Linux" anymore. All I care about now is developing open standards. For the most part, the Web works on Linux. You may need a Firefox derivative, maybe a binary Flash plugin, but it works. And that's a start, and probably a much smarter direction to be taking things.

Re:One more step...

[RAMMS EIN]

I have been working on a list of games that will run on non-Windows platforms. If anyone has games they would like to be added, please contact me. If you could include both a link to a website about the game and a short description of the game, that would be grand.

Re:Headline is misleading!

[Svartalf]

Heh... It IS Slashdot we're posting this on, after all... >:-)

NOBODY reads the effin' article, don't you know... :-D

Not only that

[recoiledsnake]

Not only that, the benchmark runs on OpenGL and not DirectX. A DirectX might be significantly faster on Windows. Reason being that Nvidia optimizes drivers for DirectX for windows and OpenGL for other platforms, because of usage patterns to get the best ROI.

Just wait - windows graphic will reclain the crown

[skeptictank]

I have it on good authority that the next Windows Driver Model will run Crysis on 3 SLI 8800GTs and render it in 8-bit color at 640x480 resolution at over 50 FPS! So take that you Linux/Unix hippy beatnik freaks!

Re:Headline is misleading! Not it is not.

[PineGreen]

Dude,
different distributions mean just different packaging systems, artwork, support, etc. Underlying kernel and drivers are the same. The performance is essentially the same, especially for things like graphics subsystem!

Re:Headline is misleading!

[kc8apf]

That's interesting. Considering that I am a developer for the CHUD Tool (no quotes) and I do performance analysis and benchmarking for a living, I don't think they did anything wrong. Things that aren't running on a system rarely affect run-time performance. Going from a distribution like Ubuntu to Debian just removes a bunch of things from disk, but those things have zero impact on the metric being measured. For Vista, it might make a difference if the version used was shown to have less idle activity, but in practice, you want to compare what a typical user would be running. So, since the OSs chosen reflect typical users, the data is perfectly valid for a comparison between them. If you want absolute performance numbers, then you need to start tuning the OSs before you run the tests. Things like disabling daemons or services and unplugging network cables can cause measurable differences in some benchmarks.

As for the CHUD Tools, they are completely inert unless you happen to be running one of the tools and even then, it isn't likely to cause any significant difference. The kernel extensions used by the CHUD Tools are designed to do absolutely nothing until they are asked to. If you are running a Time Profile in Shark, it will have some impact, but it will be limited to 1-2%.

Why surprised?

[DesScorp]

"I am surprised by this as I would have thought Nvidia would have put more effort into their Vista driver with Linux drivers being mostly on the back burner."

Nvidia is putting a lot of effort into their Vista drivers. The problem is that Windows Vista just plain sucks ass, and there's nothing Nvidia can do about that. They're probably thinking what most other people (including Microsoft, more than likely) are thinking... write Vista off as another WinME-type loser, and wait for the next Windows OS, which promises to be must more responsive with the MiniWin kernel.

Re:True, but...

[ozmanjusri]

This just gave me a bunch of confusing text:

No, you've just accidentally switched to Firefox on Slashdot.

Wait a few moments, the cognitive dissonance will pass and you'll be up and trolling like a champ again.

Re:Headline is misleading!

[glwtta]

Is "pasted" the new "pwned" or something?

Damn kids, can never understand what they are trying to say.

linux vs xp/2000/98

[yanyan]

I've known this for quite some time. Back when i regularly played Quake 3 i used to do benchmarks on linux and windows boxen. The benchmarks involved nothing more than a timedemo with the same settings. The linux version always came out faster by 5-10 FPS.

Re:True, but...

[tapehands]

If you really want to blow your mind, try typing in:

man woman

back on topic...nvidia pdf from september of 2003 explaining the differences. Yeah, old, but it's the only document on nvidia's website that I could find that would explain the differences.

Re:Headline is misleading!

[X.25]

One could say that it's very popular but at my last check, PCLinuxOS was more popular. http://www.distrowatch.com/ agrees. There is a lot I do not agree with when it comes to Ubuntu and I am not surprised that it's not performing that well.

You should probably read an article first, before making an idiot out of yourself (too late for that now, though).

I'm going to have to call BS

[Tsaot]

Free software is simply cleaner and works better.

I have to call BS on that. If I have to choose between the latest versions of Open Office and Microsoft Office, I will take M$'s closed solution hands down. The interface on 2007 is vastly improved over other office offerings out there. Making something free and open source does not make it good. I can think of many free applications that don't make the grade in cleanness and usability when compared to commercial offerings.

Re:I'm going to have to call BS

[Anonymous Coward]

The interface on 2007 is vastly improved over other office offerings out there. I know a lot of people who will disagree with you there. As I recall, a lot of people complained about the new interfaces in Office 2007. Honestly, it boils down to what you need. For basic documentation needs (which is 90+% of people), OpenOffice or Abiword is plenty sufficient. Some people with slightly more need will require Office. Then there are those who require serious document layout but are still using Office, because they have never been enlightened by real software designed for serious documents, like the tools available from Adobe.

So to break it down: 90% of people could probably survive on OOo or Abiword with nothing else. About 9% need Office and any extended features it has available. The remaining 1% really need to ditch office for better true design programs. Make sense?

Re:I'm going to have to call BS

[Electrawn]

Concurrently,

We had a use for Visio in the Office. Before we ordered Visio, I checked out OpenOffice Draw based on sites that recommended it as a Visio clone. I made one doc in Draw, a half hour later I ordered Visio.

The interface was fine, the underlying libraries are not there/not easy to install.

Re:I'm going to have to call BS

[LuisAnaya]

No... LaTex is a bloated archaic software, full of cryptic commands and cryptic options. Give me groff with memorandum macros any time...

... ok, I'm bitter... I never learned the darned thing... they taught us troff in College.

:)

Hmmm...curious

[mzeb]

Well ok, let's be careful here. Ubuntu as a whole performs better than Vista according to the article. But it leaves out a little too much "why" for me. I don't want to say "the driver is faster" because there is a lot more in the underlying OS for all three OSs. Also, I want to see Fedora, Suse and Debian. If you do the search for "Mainstream, Intel Compatible" Linux OSs on linux.org (the first hit in google) Ubuntu doesn't even show up. How can you expect a standard gamer to even find the OS except by knowing a Linux geek. Ubuntu is still to niche to run a "real live" scenario test on. Use debian or fedora and you'll be more likely to hit what a normal user would use.

Re:Hmmm...curious

[SanityInAnarchy]

I don't want to say "the driver is faster" because there is a lot more in the underlying OS for all three OSs.

True, but Windows makes it difficult to test "just the driver", or close to it.

That is, on Linux, I can actually go as far as custom-compiling a kernel to not include things unrelated to the game at hand -- or, at the very least, turn off services until I pretty much just have X.org and the game running. With just X and the game, I think it'd be a fair test of the kernel/driver combo.

Windows... nLite it all you want, but is it really feasible for a benchmarker to disable enough of it (including the default shell, taskbar, etc) so that you're just testing the kernel/driver?

That, and no "standard gamer" is going to go that far. Even if it turns out that it's the rest of Vista slowing it down, that's still good to know.

Ubuntu is still to niche

You've got to be kidding.

Ubuntu is pretty much the mainstream Linux OS now. It comes on Dells! I know there are other distros, but I'm still going to say that any "standard gamer" who switches is much more likely to use Ubuntu than pretty much anything else.

I don't know about you, but in a lot of places, we talk about distros without qualifying them as "Linux". That is, if you asked me what OS I was running, I would probably say "Ubuntu" or "Kubuntu". So that might be skewing the Google results a bit.

Why is my Linux desktop so slow then?

[jkells]

Latest NVIDIA drivers 7800GTX card and the new KDE and gnome with there transparent windows are jerky and slow. This is 2008 ppl.

Re:Why is my Linux desktop so slow then?

[arevos]

I have the same setup, but Compiz has always been as smooth as silk for me. What distro are you using?

Re:True, but...

[JohnBailey]

If you really want to blow your mind, try typing in:

        man woman Story of my life :-(

But Microsoft is not GM

[westlake]

It went something like this: GM was the Biggest of the Big. Had a market share greater than all other automobile manufactures combined.

60% of Microsoft's revenues now come from outside the U.S.

Microsoft has been reporting 15% growth in revenues the U.S., 20 to 30% growth abroad each quarter. This isn't the picture of a company on the way down, it is the picture of a company on the way up.

Microsoft's strength in Europe is astonishing given the entrenched resistance, the take-no-prisoners mood of the EU bureaucracy.

Re:But Microsoft is not GM

[AJWM]

Microsoft has been reporting 15% growth in revenues the U.S., 20 to 30% growth abroad each quarter. [emphasis added]

Amazingly enough, Microsoft has been known to lie about some things. I suggest you review the fine print on those "reports", and then ponder why, if Microsoft's growth is really as reported, their stock hasn't been doing as well as it historically used to. Their cash reserves are also shrinking. Then there are the legal battles they're fighting.

That is the picture of a company on the way down.

Re:But Microsoft is not GM

[dabraun]

Their cash reserves are also shrinking.

Their cash reserves are shinking because they decided to start paying dividends with a timetable for explicitly draining a significant chunk of the bankroll - believing it to be better to pay back their investors than to hold on to gobs of cash that they were not using (other than for investing purposes, which basically meant that at some level they were acting as a fund, and that is not the business they want to be in.)

Re:But Microsoft is not GM

[MrMr]

The fact that Microsoft offered 44 Billion, half of it in its own shares and the rest in cash, for a 12 Billion company (1.3B shares*9$) gives you an idea how much they really think their own stocks are worth...

(IANE btw)

Re:But Microsoft is not GM

[westlake]

Amazingly enough, Microsoft has been known to lie about some things.

Microsoft's numbers are given microscopic examination by the financial press and countless others. The Geek who pretends otherwise is just kidding himself.

Re:But Microsoft is not GM

[bigpicture]

When you get to the top, the only way left is down. That is always inevitable, world domination empires only last for so long and then they are gone. Just some archaeologists digging through the ruins.

Did you know that Bill is not the richest man any more? He has sunk to number 3 because of the Yahoo deal, and corresponding MS share price drop. Buyers/Sellers in the stock market set stock prices, maybe because they are not naive enough to believe what MS reports.

Comment removed

[account_deleted]

Comment removed based on user account deletion

Re:True, but...

[yoyhed]

If you really want to blow your mind, try typing in: man woman/blockquote 1994 called... nevermind.

FPS. - - What about 'CPS'?

[Anonymous Coward]

It's been known to Linux gamers for a while that games that run on both Windows and Linux will generally perform better, often by 10-15% (by FPS), on Linux, at least on NVIDIA hardware. Yeah, but how many cumtissues-per-second does it take you propellerhead bastards to get the game properly running under Lunix in the first place?

My guess is 'a lot.'

Re:FPS. - - What about 'CPS'?

[RiotingPacifist]

your guess is wrong!
1)install wine (apt-get install wine)
2)download a platinum game(e.g steam) or use a platinum game CD
3)click install
4) profit, erm i mean play.

sure not all games are platinum rated but there are a lot.

besides i think he was talking about native games which is even easier
1) find somewhere that sells UT
2) buy UT
3) play UT

also saves time as you dont have to wonder which game to buy

Re:FPS. - - What about 'CPS'?

[Phil Urich]

I would amend the set of steps.

1) Go "oh yeah, UT3 was supposed to run on Linux"
2) Be disappointed that it's been held up for vague legal reasons
3) Go buy Quake Wars from nearly any retail store instead.
4) Become obsessed.

Not that UT isn't a brilliant game, and countless hours of my life have been spent on it (and even on UT2004). But IMHO the best new FPS multiplayer game out there is ET:QW, and it runs marvelously on Linux (entirely native, no need for Wine).

Using the chessboard, the retarded monkey ...

[aeschenkarnos]

"Using the chessboard, the retarded monkey wasn't the decisive winner, but the loser ... The college-level physics student overall produced the best results."

Who's actually surprised by this? Bueller? Bueller?

toppest notch

[Anonymous Coward]

you fucktarded shitdot sheeple all live in your parent's basements, unable to get fucking laid because of your shrinking dicks, thick glasses, and/or speaking through your noses. why don't you go and commit suicide immediately by defeating the safety on your parent's microwave, setting it on high, and starting it with the fucking door open while your fucking head is in it. best post in slashdot history. excellent, let the linfaggots have it.

Stereo 3D Support Is One

[maz2331]

The Quadro boards allow OpenGL stereoscopic images to be displayed in a window, and the non-Quadro boards do not. If you want really good 3D, you need a Quadro.

I use them for my stereoscopic video stuff with either a pair of shutter glasses or 3D HMD goggles, and can do a live, 3D viewfinder to compose the scene, align cameras, etc.

Re:Stereo 3D Support Is One

[Kyojin]

My old Asus GeForce 1 card came with shutter glasses. They were cool. They required additional drivers from Asus. I don't see what would stop another card manufacturer from doing the same with a more modern card, except there doesn't seem to be much of a market for them.

Re:Stereo 3D Support Is One

[TheThiefMaster]

I've used stereo shutter glasses as recently as the geforce 6000 series. Nvidia have the drive listed on their website as "consumer 3d stereo" and it is a plugin for the normal geforce driver.

Unfortunately it hasn't been updated since.

Are there any stereo solutions that work with a dvi-connected tft?

"Not showing every texture"??

[Joce640k]

What sort of rubbish is that? Even if it would speed things up (which it wouldn't, not really) there's no way a card could figure out which textures to "hide".

The difference is partly in the capabilities, eg. Pro cards can do two-sided lighting, and partly in the drivers. Drivers for "pro" cards are more conservative (not always the very latest release), do more validation of input data, and are therefore a little bit slower.

PS: The difference in features is completely artificial, I've "added" two sided lighting to a consumer card by moving a resistor on top of the GPU.

Re:Why does it fucking matter anyways?

[SanityInAnarchy]

The only fucking games on communist linsux are lamr puzzles and a yahtzee clone thatcan't fucking randomize properly.

Maybe you've heard of a little game studio called Id Software? Or Epic Games? I'm not even going to mention what works on Wine.

Whie we're at it, where are the professional 3D applications?

Oh, I don't know, Maya? That's off the top of my head -- I don't do 3D professionally.

But while we're at it, why did you bring up games in what is clearly an article about professional graphic design hardware? Or do you actually buy Quadro cards and wonder why your games run like shit?

I am not talkin about the gpl3 shit

Like what? Closest I can think of is blender, which is under the GPLv2. Is that what you're not talking about?

BTW, great initals, Richard stallman=RMS Titanic

Yeah, because that was totally unique to the Titanic. Except it wasn't -- it actually stands for "Royal Mail Ship".

Then you wonder why you can't get a fucking job

I'm doing nicely, thank you.

Never suspected it was the Windows fanbois living in their mother's basements all along, though. Thanks for that, you just made my day.

Network effects and open standards

[Lonewolf666]

With Windows and Office, Microsoft enjoys the advantage of strong network effects (http://en.wikipedia.org/wiki/Network_effect) that make their technically mediocre products more attractive.

To some extent such network effects exist with cars too (a repair shop that knows GM cars in every village), but they are arguably weaker and could be overcome by Toyota with significantly better quality.

Right now, Microsoft's network effects are in danger because governments increasingly insist on open standards that can be implemented by everyone. Microsoft tries to obstruct this as long as possible, see
-the attempt to push OOXML (poorly defined pseudo-standard that mostly describes Microsoft Office with all its faults) through ISO instead of supporting PDF.
-their delay in publishing the server interface documentation, until the EU hit them with a large fine.
But this time I think they will lose, because the EU commission is not as docile as the Bush government was in the US antitrust suit against Microsoft (I still think the judgment in the first instance, braking up Microsoft, would have been appropriate).
Also, they have pretty strong opposition in IBM concerning the OOXML-as-ISO-standard business.

Unreal tournament 2004/3, Quakes, Doom ...

[GNUPublicLicense]

Cool, moreover the GNU/Linux graphic stack is being remade to give developers even more control and ultimate horse power. We are still waiting for the UT3 64bits linux native client thought. But that's fine, since it will rock like Quakes, Dooms etc etc... If you want to get more games on GNU/Linux (32 bits and 64 bits), buy the games from those who make the effort to make a native version and let everybody know you play with it using GNU/Linux (don't forget 64 bits systems plz!).

Re:Headline is misleading!

[GreatBunzinni]

One could say that it's very popular but at my last check, pclinuxos was more popular. http://www.distrowatch.com/ agrees.

So you presented distrowatch as the basis of your allegation that the obscure PClinuxOS distribution is somehow more popular than Ubuntu. Do you happen to know that what distrowatch measures isn't the install base of the individual linux distributions but in fact the number of hits on a certain distrowatch page that covers a certain distro? That means that, if you have an happy idiot who likes to spend it's day refreshing some obscure distrowatch's distro page then that distro is bound to get hugely popular. Heck, the fact that distrowatch lists something named Sabayon as more popular than Mandriva, Slackware, Gentoo and even Debian should be a clear sign that Distrowatch is a joke at measuring the popularity of linux distributions.

You don't have to go much further to get other sources of statistics that show that Ubuntu is the second most popular distro behind Debian and that pclinuxos doesn't even appear in the chart.

Re:True, but...

[Dunkirk]

I lol'ed the first time I need to check my security log, and typed `less secure'.

That was then, this is now.

[gnutoo]

XP is over. Sooner than you would like, new graphics cards are going to come with nothing but Vista drivers or Vista and Linux drivers.

Re:That was then, this is now.

[walt-sjc]

Considering that Corporate America is not embracing Vista, and neither are savvy gamers (due to lower performance), I predict that your prediction will not become reality.

Re:That was then, this is now.

[recoiledsnake]

I think you missed my point totally. Linux drivers sucked back then, but now they've been optimized. Vista has a completely new driver model. The drivers may mature over time to back to XP/Linux levels as the nvidia driver writers learn about Vista kernel nuances.

Re:That was then, this is now.

[gnutoo]

Then Linux or Windows7 will emerge as the winner. If Vista can't do PC gaming, something else will but it won't be XP. With ATI, Nvidia and Intel on the Linux bandwagon, the likely winner is Linux.

Re:Headline is misleading!

[Svartalf]

Nooo... It's an OLD saying.

Re:Headline is misleading!

[betterunixthanunix]

FreeBSD is not Linux. (I had to do it).

Re:Headline is misleading!

[Cal Paterson]

Well, the original poster was using "linux" as a synonym for FOSS Unix. Either way, Free Unix is a much better catch-all for what I was talking about. This is pretty tangential.

Re:True, but...

[SpydeZ]

That is why I use most.

Re:Headline is misleading!

[Fri13]

PCLinuxOS is great distribution. It can really wipe floor by using Ubuntu on it. http://www.tuxmachines.org/gallery/v/pclos2007/desktop.jpg.html Most users just need to understand that it's not about different OS's but it's about different Distributions. Ubuntu can be as good as any other distribution or any other distribution could be as good as Ubuntu. Only thing what really makes difference is default settings and Ubuntu had those bretty well (Mandriva was having better much earlier) but now there is PCLinuxOS. And now all "big" distributions are doing same, making things simple. And after few years, i think that there is no difference what distribution you choose, because almost all are samekind, like now, but with different themes, like now ;-)

Re:Why does it fucking matter anyways?

[Anonymous Coward]

I am a CAD/CAM administrator in aircraft design and aerospace engineering. I use Siemens PLM (formerly UGS) Unigraphics NX on Linux workstations using QuadroFX video cards. You wanted a professional 3D application? NX is used for design on the F-22 Raptor, all GM cars, and several aircraft. The Linux version is an evolution of the UNIX versions released for Solaris, HPUX, and AIX. The Linux version is more reliable and performs better than the Windows version in my experience, and the engineers who use it are happy with it.

I'm sorry you would rather spew invective than learn and actually know what you're talking about.

Re:Why does it fucking matter anyways?

[robzon]

Again - grow up.

Mod parent up! It's FUNNY?!

[pyrr]

I trust any rabid, foaming-at-the-mouth 14 year old ad-hominem mongering and shoot-the-messenger troll who lives in his parent's basement and calls Microsoft M$.

I was about to say, "Said the pot to the kettle," but that's way too obvious with this post. I mean, in the best case scenario, this assumes that "M$ lackey" is an ad-hominem on some level. The OP quoted Ed's own profile, his description of himself fits the definition of "M$ lackey". But then to spew a half-dozen real ad-hominem attacks, that's more comic irony than anything. Well, that would assume that the AC who posted it was actually trying to be funny and wasn't just a M$ lackey who's taken offense.

Speaking of ad-hominem attacks, though, the M$ lackey who was originally being discussed, Ed Bott, launched into a bunch of what could be considered indirect ad-hominems as he babbled about just how BAD Gutmann's paper is (as he implies that Gutmann is ignorant, inexperienced, a liar, a sloppy & disorganized writer, and he distorts the truth, etc.). When I first read Bott's article around the time it came out, I was struck by how it seemed to be more of a rambling tirade directed at someone who gave M$ a bit of a black eye than a rebuttal that offered any appreciable substance. That's a personal tone that I don't feel is all that appropriate in tech journalism.

That said, I don't think that "lackey" characterizes Bott correctly. The description of "M$ sycophant" is far more apropos for him.

Re:Headline is misleading!

[kklein]

I was just thinking about this last night as I was trying to set up Cinelerra on my Ubuntu virtual machine. It was a stupid hassle, because the instructions were different for each distro, and even for each version! I'm pretty awful at Linux, and only know very basic CLI commands, but even that is far, far beyond what most people can handle. Throw distro differences into the mix, and you have a nightmare for most people.

Then there was the other problem stymieing me last night: Terribly-written documentation. And by "documentation," I mean "forum postings and pages cobbled together by people on the project." They typically are written by and for people who are very familiar with the fundamentals of *NIX, and leave important details out. Just little things, to be sure, and obvious to people who are already used to using it, but which can cost hours for newbies. The trouble yesterday and the day before with Cinelerra was that I was supposed to look for the package directly in Synaptic, instead of in the Ubuntu Add/Remove Software tool, which I thought was Synaptic. Well, it wasn't. I had to go to a totally different part of the system to do it. Once I figured that out, it was easy-peasy, but the only reason I did figure that out is through tons of googling until I found someone's step-by-step on how to do it in Ubuntu 7.10. It's clear in hindsight, but it certainly wasn't for the last 2 days. I didn't even know you could install from there. Most people just stop when the official instructions are wrong.

Anyway, the point of the story is that the distro model is not very good for Linux uptake, as it muddies the waters of an already very opaque sea of confusion for most people.

Re:Headline is misleading!

[ezeze5000]

It took me 2 years to talk my dad into letting me build him a PC. I built it and loaded it with Ubuntu, and he just loves it. I love it for it's stability and lack of virus. He has been using it for about two and a half years, with no problems. My kids like SuSe better, they have been using it for 5 years now with no problems. If you want a small and fast OS try Puppy Linux. Well that's my 2 cents worth.