NVIDIA Makes First 4GB Graphics Card

Frogger writes to tell us NVIDIA has released what they are calling the most powerful graphics card in history. With 4GB of graphics memory and 240 CUDA-programmable parallel cores, this monster sure packs a punch, although, with a $3,500 price tag, it certainly should. Big-spenders can rejoice at a new shiny, and the rest of us can be happy with the inevitable price shift in the more reasonable models.

Comments

Power != memory

[unity100]

excuse me but this is total bullshit. oldest trick in the book. if you are behind in technology, pop out a card with huge ram and try to get some sales.

lets face it. nvidia has fallen behind ati in the chip race. you can place any number of 4870s in a setup as much as you like to equate the power of any monolithic nvidia card and they always kick the living daylights out of that nvidia card in terms of cost/performance per unit of processing power.

Re:Power != memory

[jgtg32a]

Does ATI have some sort of CUDA functionality?
This isn't a gaming card

Re:Power != memory

[Neon Spiral Injector]

Yes, AMD's Stream technology. I don't think it is used as much as CUDA in practice.

Re:Power != memory

[rogermcdodger]

Or maybe there are companies that need high end cards with 4GB of RAM. This isn't some trick to get consumers to pay more for a low end card. This is now Nvidia's highest end workstation card.

Re:Power != memory

[Anonymous Coward]

This is not a gaming card, this is CAD/CPU card. what I mean to say is, this card in is basically a super computer that fits in a slot and you can put more than 1 on a machine. The idea, being that you can use these GPU's to do more than just graphics. This card's shader is horrible and would not play any graphics intensive game well. it would be a waste of money for a gamer.

Re:Power != memory

[Ephemeriis]

excuse me but this is total bullshit. oldest trick in the book. if you are behind in technology, pop out a card with huge ram and try to get some sales.

lets face it. nvidia has fallen behind ati in the chip race. you can place any number of 4870s in a setup as much as you like to equate the power of any monolithic nvidia card and they always kick the living daylights out of that nvidia card in terms of cost/performance per unit of processing power.

In case the $3,500 price tag didn't tip you off, this isn't a gaming/enthusiast card. This is a Quadro - a professional card for high-end 3D rendering. Stuff like generating film-grade 3D or insane CAD stuff. Actually, due to the design of the card, it'd be pretty horrible at playing games.

This thing is aimed at high-end scientific calculation and professional-grade rendering.

ATI may, or may not, have something comparable. ATI may even have something better. I don't know, I don't follow the GPU industry very closely. But claiming that they're just slapping a bunch of RAM on a card to drum up sales is just plain wrong. Hell, the blurb here on Slashdot even mentions the fact that it has 240 cores.

Re:Power != memory

[GNUPublicLicense]

Moreover ATI/AMD specs are opened... meaning you can code directly the hardware. That's times more powerfull and flexible than CUDA. And there are frameworks in the works in order to have easy access to GPU lowlevel interfaces (see Intel/AMD GEM work in the mesa project).
Basically, nvidia behavior is generating a lot of hate in coders community...

Re:Power != memory

[Anonymous Coward]

It is not used anything like as much. ATI hasn't decided what they want to do. For a while they were touting Brook++. The problem there may have been that one of Nvidia's employees wrote Brook as his PhD thesis :)

Re:Power != memory

[Grey_14]

Coder Hate like that brought by the shitty, bug filled drivers that ATI has a long history with?

I think ATI/AMD is on the right path, but they have a long history of being on the wrong path, while NVIDIA has always been more towards the middle (Not completely right, but not too badly wrong). It'll take some time before I jump to the ATI Bandwagon as completely as you obviously have.

Re:Power != memory

[pak9rabid]

excuse me but this is total bullshit. oldest trick in the book. if you are behind in technology, pop out a card with huge ram and try to get some sales.

Are you some kind of idiot?

With 4GB of graphics memory and 240 CUDA-programmable parallel cores

That alone should be a plain indicator that this ISN'T a consumer-level card, nor is it even remotely close to being targeted as such by nvidia.

Re:Power != memory

[KasperMeerts]

Man, I would love it if you were right but face it, nVidia still controls the largest part of the market. The reason nVidia isn't opening up their specs is because they don't have to. That's the big problem with a monopoly, you don't have to give a shit. And that's exactly the same we've been getting from Microsoft.
However, there is hope. The Vista failure is biting Microsoft in the ass so hopefully this will also happen in a way for nVidia and give us some OSS drivers. If everything else fails, there is still Nouveau.

Re:Power != memory

[Hatta]

lets face it. nvidia has fallen behind ati in the chip race. you can place any number of 4870s in a setup as much as you like to equate the power of any monolithic nvidia card

But can you get decent drivers for it?

Re:Power != memory

[LearnToSpell]

That's times more powerfull and flexible than CUDA.

I like how statistics are so meaningless we're not even putting the numbers in anymore.

Re:Power != memory

[mikael]

There is no upper limit on the amount of memory required for tasks like volume visualisation, where you have a nice big 3D cube of data in 16-bit format. A cube 1024 voxels in each dimension with a single channel of 16-bit data (2 bytes) is going to be 2 Gigabytes. You will need at least two such cubes to do any sort of image processing work.

Even a digital movie can be considered to be a cube if you consider time as the 3rd dimension.

Rather than having cards with a fixed amount of VRAM, which can't manufacturers just put a bunch of memory card sockets on the card and allow users to add memory when they want?

Re:Power != memory

[doti]

In case the $3,500 price tag didn't tip you off, this isn't a gaming/enthusiast card. This is a Quadro - a professional card for high-end 3D rendering. Stuff like generating film-grade 3D or insane CAD stuff.

Cm'on, we are all grown ups here. You can say it clearly:

It's for high-detailed 3D virtual porn.

Re:Power != memory

[ccool]

You're absolutly right, but it would be amazing with any CUDA-apps right now. Hell, you could probably use that to encode your H.264 movies more than 18x faster!!! see http://www.nvidia.com/object/cuda_home.html

Re:Power != memory

[icedcool]

Yea. This card is made for Cad functioning and not shading or any kind of gaming. The card is more for workshops.

Re:Power != memory

[ardor]

meaning you can code directly the hardware

Guess what CUDA and Stream have been designed for? Yes: for programming the hardware. What you suggest is pure insanity. NEVER EVER touch hardware directly from an userland app. And once you start writing a kernel module, you end up with something like CUDA/Stream anyway.

I am a coder, and quite frankly I couldn't care less about nvidia drivers being closed source. They are MUCH better than the ATI ones, especially in the OpenGL department. nvidia whipped up a beta GL 3.0 driver in less than a month since GL3 specs were released. ATI? Nope. New standardized feature X is added to the registry. nvidia adds it pretty quickly; ATI adds it months, even years later. nvidia drivers are also pretty robust; I can bombard them with faulty OpenGL code, and they remain standing. With ATI's fglrx, even CORRECT code can cause malfunctioning.

THESE are the things I care about. Not the license.

Re:Power != memory

[GleeBot]

But claiming that they're just slapping a bunch of RAM on a card to drum up sales is just plain wrong. Hell, the blurb here on Slashdot even mentions the fact that it has 240 cores.

Umm, the GeForce GTX 280, a gamer card released last summer, also has 240 "cores" (as Nvidia counts them; actually stream processors).

This workstation card, as you might expect, is essentially the same thing as the consumer card, just tweaked towards the professional market (more RAM, different drivers). It's nothing especially innovative.

Re:Power != memory

[vadim_t]

They used to do that. You can find sockets on ancient cards, like a S3 ViRGE.

The problem in my understanding is that current cards push memory as far as it will go, and a socket would impose a limit on it. Besides, it's hard to put a heatsink on the RAM then.

Re:Power != memory

[Mister Whirly]

You don't want to see most of those "actors" in that great of detail.

Re:Power != memory

[GleeBot]

Rather than having cards with a fixed amount of VRAM, which can't manufacturers just put a bunch of memory card sockets on the card and allow users to add memory when they want?

They used to, at least on some of the better ones (way back when "Windows accelerators" that drew rectangles faster were hot stuff).

You need to realize, though, that graphics cards are on the absolute bleeding edge of memory technology. It's not electrically feasible to pump the sort of bandwidth and latency a modern GPU requires (which is literally orders of magnitude faster than what your CPU gets), while at the same time enabling expandability (especially if you want to make it a standard socket).

Video card design takes a systems approach to integration a GPU with the right RAM and other components. It's one of the main reasons why GPU technology can advance much more quickly than CPUs do. How much benefit are you really going to get when your blazingly-fast GDDR3 RAM gets replaced the very next year with the latest hot new GDDR4 RAM technology? (This is at least one of the reasons why VRAM upgrades never really took off.)

And really, the cost of RAM is a pretty minor portion of the total; compare the price differential between otherwise comparable, say, 256 MB and 512 MB cards.

Re:Power != memory

[Gewalt]

I ACCIDENTALLY THE WHOLE COMMENT!!!

*insert lowercase letters here to defeat lameness filter that doesn't know how to take a joke.

Re:Power != memory

[nschubach]

This is a new age of statistics. Instead of putting numbers up there that could be misinterpreted, the author has chosen to take the politically correct route and allow the user the decision that best pleases them.

This way you get your message out, and the person on the other side is happy with their decision. It's a win-win!

Re:Power != memory

[Gewalt]

You don't want to see most of those "actors" in that great of detail.

No, not real human actors. Close up, a human actor's ugly bits are actually... well... ugly. That's why it's necessary to create virtual pron stars, they have ugly bits that are aesthetically pleasing.

Re:Power != memory

[Sycraft-fu]

Two reasons:

One is simply that the cards use memory that isn't available normally. They don't use normal DDR RAM, they use special RAM for graphics cards, called GDDR. It is similar but not the same as memory in systems. Thus you can't just go out and buy sticks of RAM for it. So they'd have to be made special for the cards (and each gen of card uses different RAM), and thus would be expensive.

The bigger one is that the RAM is really pushed to the limit. You start to run in to all sorts of shit you never thought about. The electrical properties of the connection are highly important and there is a difference between what you get soldered on to traces and in a socket.

It's a nice thought, but not practical these days. Graphics cards are heavily dependent on high RAM bandwidth and you get that by really pushing the envelope. That means new RAM technologies all the time and the chips being pushed to the max.

Re:Power != memory

[Anonymous Coward]

This would've been modded funny a week ago...

Re:Power != memory

[MBGMorden]

As opposed to the detail of the real thing a few inches away?

Trust me, if ultra detailed closeups of a woman's naughty bits was that much of a turn off, real world sex wouldn't be as popular as it is. Apparently, people are managing to cope . . .

Re:Power != memory

[Mister Whirly]

Really? When you have sex, do you do it with thousands of watts of spotlights illuminating every tiny detail? Or do you do it like the rest of the population in less than "broad daylight in the dessert" conditions?

Re:Power != memory

[Anonymous Coward]

Or running the next version of Vista

Re:Power != memory

[Anonymous Coward]

Actually, due to the design of the card, it'd be pretty horrible at playing games.

The card is exactly the same as the Geforce GTX 280 except with quadruple the VRAM. Like all of the Quadros, they're the same as the normal lineup with more RAM and different drivers.

Re:Power != memory

[Anonymous Coward]

Too bad ATI card still suffer from their utterly, utterly shit drivers. ;_;

ATI may have double the power nVidia does, and it doesn't help a bit if I have to struggle nonstop to get their cards working - especially on a dualboot system.

Re:Power != memory

[billcopc]

Yes and no.

It is a Quadro, and the extra memory is indeed handy for "professional" rendering, but don't get too far ahead of yourself. The rest of the card is nearly identical to the gaming versions. I suspect this is a GTX 260 with minor changes... mostly in the firmware.

Re:Power != memory

[Anonymous Coward]

Thank god for porn is all I say.

Re:Power != memory

[Jeremy Erwin]

Yea. This card is made for Cad functioning and not shading or any kind of gaming. The card is more for workshops.

Excuse me? Nvidia says

The reference standard for Shader Model 4.0 and next generation operating systems
Enabling breakthrough ultra-realistic, real-time visualization applications.
Available only on the Quadro FX 3700

Flip through the OpenGL specifications sometime. Ask yourself whether there are any features of OpenGL which are not useful for games.

Examples that have been used to sell Quadro cards in the past include:
wireframe antialiasing (as opposed to full screen antialiasing)
multiple clip planes
two sided lighting.

Come on! Do you play games in wireframe mode?

Yes, you might be able to fool the computer into thinking your GeForce is a Quadro, but, iirc, the quadro devotes a bit more silicon to these features, so the performance hit isn't quite as severe.

On the other hand, the Quadro is designed for precision over speed. If a frame is a bit more complex than usual, your framerate will drop. Not good for games.

Re:Power != memory

[White Flame]

Maybe they meant power consumption! :-D

Re:Power != memory

[Drakkenmensch]

Truth. I was having lunch a few weeks ago and overheard someone who said was working in the porn industry and she lamented that HD cameras are awful to their business. The slightest blemish, the smallest skin imperfection, every tiny bit of hair stubble shows up on the screen with crystal clarity. HD cameras are not the adult industry's friend.

Re:Power != memory

[LingNoi]

In that case I decide the number to be 0.0001

Re:Power != memory

[otomoton]

Now I hope you do realize that this is not a gaming card. This is a card for a high end engineering and or a CAD/3D modeling system. You can't compare those type of cards to enthusiast level cards like the 4870. It's like comparing a rice-burner civic to a top fuel drag car.

Re:Power != memory

[PitaBred]

Because the memory commonly available isn't usually as fast as the memory that's on those cards, and is often in a different "flavor" to allow faster graphics-style access over standard memory?

There's a reason there's GDDR3 and DDR3 as different specs, not to mention that there's GDDR5 out on ATI 4870 cards right now, and you can still barely buy standard DDR3 DIMM's.

Re:Power != memory

[EvilIdler]

Spotlights and mirrors - the best way to have sex!

Re:Power != memory

[hierophanta]

see, system works as designed

Re:Power != memory

[Anonymous Coward]

Thank you!

I am sick of these idiots telling everyone to buy ATI because of the license.

The drivers are shit, they've always been shit and quite frankly they're always going to be shit unless ATI fixes the problem (like that's ever going to happen).

Re:Power != memory

[TheLink]

Uh what monopoly does nvidia have?

The only reason why nvidia has better market share is because ATI was crappier than nvidia.

They only recently got somewhere with their 4xxx series. However I _still_ see more complaints about their drivers - even the recent ones, compared to nvidia's.

Re:Power != memory

[Fumus]

That, and the fact that the ATI drivers for windows insist on installing java and god knows what else on my PC is pissing me of. If I want java. I'd download it myself. What the hell does java have to do with graphics drivers?

Re:Power != memory

[Anonymous Coward]

Also hardware limits, what you are basically describing is a motherboard, with a cpu that is only doing graphics and vector calculations.

If you start adding 'flexible' memory you will certainly run into certain design constraints, for example, access speed, if you know the exact amount of memory you have you can often optimize for it. There is no such thing as a free lunch, for every little neat feature you are loosing something somewhere.

Re:Power != memory

[MBGMorden]

Standard room lighting normally (unless she wants the lights off), but even under normal lighting you're still going to see plenty of "detail". I'm perfectly capable of accepting that right close up every girl doesn't have utterly perfect skin or might have some razor burn.

Re:Power != memory

[fuzzyfuzzyfungus]

No longer quite true. With the advent of Nvidia's "Turbocache" and ATI's "Hypermemory" the ultimate in dubiously ethical spec pumping is to puke out a card with relatively little RAM(extra credit if you use slow RAM on a narrow bus); but print a huge number on the box(corresponding to card RAM+huge amount of stolen system RAM).

Re:Power != memory

[TheLink]

But doesn't that give them more realism?

Look at the video games, they keep trying to add flaws and blemishes everywhere to make it look real.

In X years they won't be able to compete with perfect skin from virtual actors. So why bother?

Given the porn market has people going for strange stuff, I'm sure there would be a fair number who would actually prefer their porn stars to have a tiny bit of hair stubble, slight blemishes etc.

For the "perfect" stuff, they'll probably still have jobs providing original motion capture stuff.

You can have a virtual actor sit still and look pretty, but I think it'll be a while before a computer can figure out how to make it "move sexy" even "move humanly" seems hard - they often just use motion capture.

I believe humans have age old instincts in rapidly distinguishing from "moving healthily" to "moving not so healthily", and so on. Maybe in a decade or so the research will be done, and a product actually made. Even then I think they might have jobs just for voice overs - and voices are important.

And not least Brand names are important.

Looking at Hollywood movies and you can see some actors who just look pretty and are good candidates for replacement by virtual actors...

Upcoming actors of that sort who aren't already established Brandnames are the ones who should worry.

Re:Power != memory

[Penguin Follower]

I keep seeing people bash ATI for bad drivers, and it was VERY true in the past... but I've had a couple ATI cards over the last year or so that really have broken the track record for me personally. I've even got one of them overclocked and not had any trouble out of it other than when I push the clocks too far. At stock speed the thing has absolutely never hiccuped and I've yet to have any lockups/blue screens. Maybe some of you people haven't tried an ATI card in a few years?

Re:Power != memory

[unity100]

in case you still dont know, the price tag for 'gaming' stops at no limit.

Re:Power != memory

[thtrgremlin]

I can not see myself ever buying an ATI card. I realize that my prejudice is VERY old, but with so many problems with ATI cards 12+ years ago, and not having any significant issues since "switching"m I am a die hard nVidia fan. Same with and corsair, and AMD... but people have been saying things more along the lines of ATI having more of a good cost/performance ratio, where as I have always been more of an... anemic gamer.

Re:Power != memory

[Anonymous Coward]

It is a shame you are capped at +5 sir.

Re:Power != memory

[thtrgremlin]

working hard + hiring best talent + large market share != monopoly. Microsoft is a monopoly because it uses illegal/manipulative tactics with OEMs and retailers. There are some really important differences.

If the fetus you save is gay, will you still fight for its rights?

Yes, but only as much as any other child: till its born.

Re:Power != memory

[Hatta]

I haven't. Good to hear you're having success. Are you using the open source drivers or the binary drivers?

Re:Power != memory

[thtrgremlin]

Just because a joke isn't funny or is a failed attempt at satire doesn't make it flamebait. Good thing for meta-moderation.

Re:Power != memory

[thtrgremlin]

I was under the impression this is a card for broadcasting. The 4GB allows for many streams to be buffered simultaneously for smooth real-time mixing / crossovers. The biggest thing driving these cards is sports broadcasting due to the demand for a large number of layers.

Re:Power != memory

[FuckTheModerators]

Yes, yes, and yes.

I thought I was the only one who remembered those drivers.

Re:Power != memory

[Mister Whirly]

I know. Too bad there isn't a "-1 Bitter Grapes" mod - at least that would be more accurate.

Re:Power != memory

[Ecuador]

Do you realize that for computers 12+ years is several GENERATIONS?
I had always been using ATI for Windows boxes and laptops, since my main concern was almost always video performance and TV-Out capability and I could not even get a video overlay work over TV-out with nVidia cards for years.
Of course, when I had problems with linux drivers I built nVidia (I admit, even intel) linux boxes. But that is a thing of the past, I am back to ATI for linux, they are good and even getting better with each release.
Anyway, long term loyalties is pretty silly. I bought my K6 233 at the same price my friend bought his MMX 166, in retrospect we all know how those two compare. I kept on buying Athlons when others were paying more for their crap P4's (they weren't called crap back when it was the best intel had to offer). But, hey, I am now buying Core 2 for non-low end systems, until AMD can come up with something better.
Fanboyism gets you bad deals at least half of the time. You buy hardware, you don't marry it. Ok, I know this is slashdot and the last statement might generate some debate, but anyway you get the point.

Re:Power != memory

[sexconker]

Keep that shit on 4chan.

Re:Power != memory

[sexconker]

Still a .01% increase over the competition.

Re:Power != memory

[khellendros1984]

NVidia drivers are better...but it wasn't *that* much work to get the ATI drivers running. I run dual screens, each running at different resolutions and refresh rates (in Linux). It took about half an hour to set up, and now it "just works".

Re:Power != memory

[Jabbrwokk]

I'm with you, I've had too many ATI annoyances to jump back anytime soon. I've never had drivers bork my system as much as theirs (didn't uninstall the old ones first, then reboot and run as generic VGA first? ERROR... New drivers prevent Source engine games from launching... texture flickering... shadows look like ass... I could go on.) And I find it interesting how perceptions have changed from nVidia being the plucky little guy, taking on big, bad Voodoo, to now being the big, bad guy monopoly company.

Re:Power != memory

[sexconker]

Too bad there isn't a "-1 Mixed References" mod - at least you might learn it's "Bitter Tears" and "Sour Grapes".

Re:Power != memory

[thtrgremlin]

Personally, I think those are some of the best conditions, because relatively whatever is going on, you are having more fun than the people watching. Not to mention brighter lights keep your partner warm while you are trying to see what you are doing. If you are going to be doing something, do it with enthusiasm. But I will agree that too many desserts really puts a damper on stamina; anyone can be different.

Re:Power != memory

[sexconker]

Yet PORN was the first industry to truly support HD.
PORN always supports new tech.

Re:Power != memory

[Ecuador]

What kind of Troll are you? Catalyst drivers require the .Net framework for their control center and that's it. And even that, YOU have to install it yourself before running the control center. They don't install anything else, and certainly not Java.

Re:Power != memory

[Anonymous Coward]

Any 5 year old card can handle Maya in a production environment. The rendering part is done in pure software either using PRMan or Mental Ray. The proprietary and undocumented NVidia hardware doesn't thelp there.

240 cores my ass. It can execute 240 graphics instructions in parallel which is not the same. It does hardware multithreading but it's extremely limited. The Cell is way more advanced than NVidia's tired glorified DSPs.

Glass

Re:Power != memory

[sexconker]

Yes, it's actually close to scamola.

They add buttloads of ram and give you different drivers, but the hardware is the same.
What you're really paying for is the toolset (which is always half-implemented) and support (which is less than supportive).

Re:Power != memory

[sexconker]

Kinda like dividing by 0.

Re:Power != memory

[Anonymous Coward]

Well I guess if you haven't personally heard an expression, it can't exist.
Do you realize that there are such things as grapes that aren't sweet, sometimes even called "bitter"?
Do you realize that eating such grapes would leave an unpleasant taste in your mouth?
Do you realize what "leaving an unpleasant taste in your mouth" isn't always meant to be taken literally?

I have heard the term "bitter grapes" used in that very context before. Strange.

Re:Power != memory

[LingNoi]

Yes, after posting I instantly realised I forgot the minus sign, if only I had a time machine, or used the preview button..

Re:Power != memory

[LordKazan]

ATI has their own solution similiar to CUDA, but 3rd parties have also gotten CUDA running on ATI cards.

Re:Power != memory

[Mister Whirly]

I know both of those expressions. And apparently I know at least one more than you also. I have heard others use the expression before, so I can't take any credit for coining it. But thanks for offering.

Re:Power != memory

[mdm-adph]

Well, it's not exactly a monopoly, but they do have a huge majority share -- most stats I see have their share of discrete graphics market somewhere in the 70% range.

Re:Power != memory

[Chandon Seldon]

working hard + hiring best talent + large market share != monopoly.

An actor that has significantly more market power than anyone else is a monopoly. Microsoft is an abusive monopoly, which should have specific legal ramifications, but even the nicest possible single provider of a product or service is still a monopoly.

Re:Power != memory

[0xygen]

I have switched sides twice during that time, have had bad cards from both manufacturers during the last 5 years and will continue to now buy based on individual product reviews.

The landscape for most hi-tech products seems to change so quickly now, and suppliers / manufacturers change at such short notice that it is no longer possible to rely upon a vendor's name as a sign of quality.

In the worst cases, even the same product with the same part number is a different product with different performance characteristics a few months down the line. This happens a LOT in the USB flash drive market.

Re:Power != memory

[PlasticArmyMan]

Literal or figurative shit? There's lots of literal on there...

Re:Power != memory

[JonShado]

Umm...You missed the word "programmable". I'd like to see you do that with the GTX280. They're not SUPPOSED to be the same card.

Re:Power != memory

[Penguin Follower]

I mostly use ATI under Windows & Mac. I try to go Intel integrated for Linux. That said, I've use ATI's binary driver under Linux with a degree of succecss.

One of my ATI cards is an x1900xt 512MB PCIe. It came as a build to order option in my Mac Pro Quad that I bought in April 2007. Under bootcamp in Windows XP it has been near flawless. And I'm not using Apple's supplied driver. I downloaded the driver from AMD's website that includes the ATI Control Center (mainly so I could overclock it). I've not had any lockups other than one time I pushed the clock rates pretty high. So long as I stay at stock or a reasonable overclock the card behaves itself. I play Call of Duty 4 mostly. I have popped in the Ubuntu Live CD a couple times on my Mac Pro and it drives the ATI card OK, but the resolution comes up at 1280x1024. That looks ugly on a 22" Widescreen whose native resolution is 1680x1050. That's the open source driver.

My other ATI card (x1600Pro) is in a PC that runs Gentoo. Once I got the Xorg config right, it didn't give me very many problems. I was using the binary driver, as it was able to get the resolution correct (unlike above). I rarely do any 3D under Linux, so can't really comment on 3D stability of the binary drivers of late. So far 2D is stable. This PC actually had an eVGA Nvidia card in it prior to the ATI card, but the Nvidia card crapped out right after the warranty expired(oh of course!). So I tried ATI because of the good luck with the one in the Mac.

I'd like to put an HD 4850 in my Mac, but ATI doesn't make one for Mac yet. The HD 3870 is the highest I can go, and even then it's priced at $215 @ OWC (higher than the PC only equivalents).

Re:Power != memory

[HeronBlademaster]

If you're willing to include integrated graphics in the graphics chipset market, Intel has the majority by far.

Re:Power != memory

[TheLink]

Huge majority share does not mean monopoly.

Nvidia has a monopoly only in the sense that people would rather pay more $$$ per performance for Nvidia rather than put up with ATI.

But that's not a monopoly, that's just ATI being crap - if ATI was much better or Nvidia started becoming worse, Nvidia would rapidly lose market share.

Games and apps in theory can run on both ATI cards and Nvidia cards. In practice you might have driver problems, but that's not a "market stranglehold" problem.

At most it is closer to an oligopoly of ATI and Nvidia for discrete cards.

Re:Power != memory

[Fumus]

I wasn't trolling. Just this summer I set up a clean windows install with new hardware and after installing the drivers provided by ATI and rebooting, Java popped up too. Maybe that was just the CD version or whatnot, but it certainly DID install Java.

Re:Power != memory

[eltaco]

same here. nvidia all the way. what do I care about 5fps more and 10 bucks less? I care about spiffy drivers that do their job and do it well. especially under linux.
having said that, I don't claim to be fully up to date on the ati-linux-driver-front. have things changed or is it still a major hassle to even get basic things (3d acceleration, videos, etc) working?

Re:Power != memory

[Ecuador]

"the drivers provided by ATI" are available on their website and contain no third party software. ATI has not made graphics cards for a few years now, so there is no "CD Version". The CD you have is provided by your card manufacturer and should have the official ATI distribution plus extra software the card manufacturer is offering. Generally, a manufacturer would not "stealth" install Java when it is not needed for the driver, unless you selected some sort of "express install" that adds bundled software and some of it might have required java.
In any case, saying "I installed drivers provided by ATI and Java popped up" is indeed trolling ;)

Re:Power != memory

[randyest]

I reckon you don't really know what you're talking about. Do you know what the "mono" in "monopoly" means? I think not, so shut up, sit down, and prepare for a schoolin'

Main Entry: monopoly
Pronunciation: \m-nä-p(-)l\
Function: noun
Inflected Form(s): plural monopolies
Etymology: Latin monopolium, from Greek monoplion, from mon- + plein to sell
Date: 1534

1 : exclusive ownership through legal privilege, command of supply, or concerted action
2 : exclusive possession or control
3 : a commodity controlled by one party 4 : one that has a monopoly
Also:

Monopoly, n.:
1. (economics) a market in which there are many buyers but only one seller; "a monopoly on silver"; "when you have a monopoly you can ask any price
2. exclusive control or possession of something

Moreover, you seem to contradict yourself: "An actor that has significantly more market power than anyone else is a monopoly" != "the nicest possible single provider of a product or service is still a monopoly." So which is it -- must one have "significantly more market power than anyone else" or be a "single provider?" (Hint: it's the latter.)

Re:Power != memory

[randyest]

Just because you've heard some idiot say something (wrong) doesn't make it right. Look up Aesop and prevent future embarassment.

Re:Power != memory

[Anonymous Coward]

All Nvidia cards since the 8000 series have CUDA programmable cores. This card looks exactly like a GTX 280, only with 4 times the memory.

For people who want a Quadro but don't need 4GB of VRAM you can just get a GTX 280 and softmod it to a Quadro. Save yourself about $3,000 in the process too.

Re:Power != memory

[randyest]

So? ATI's "solution" isn't comparable in ease or performance, and CUDA on an ATI card is like quake3 on a nintendo DS -- yeah, it's neat that you could do it, but it's useless.

Re:Power != memory

[Fumus]

Bah. A confused troll then. ..it did come out of nowhere..

Re:Power != memory

[Anonymous Coward]

Admit you failed.

Re:Power != memory

[Mister Whirly]

Admit your identity.

Re:Power != memory

[Chandon Seldon]

You are technically correct.

Now, the next question is this: Is the class of problems caused by the existance of a monopoly restricted to situations where a market actor meets the strict definition of a monopoly that you gave?

The answer is no, and anti-trust law in the United States recognizes that. Therefore, you can be convicted of "abusing monopoly power" without technically being a monopoly. Since strict monopolies basically never occur in nature without government interference (and even then you could argue about black market suppliers), it is convenient to use the term imprecisely to refer to any market participant that has significantly more market power in relation to a single product or service than any other participant.

The general (economic and social) problem is market power, not the number of suppliers. Any oligopoly will warp the market in their favor and cause the same type of problem that a theoretical abusive monopolist would.

Re:Power != memory

[Penguinoflight]

eVGA offers lifetime warranties on all their graphics cards, it's really the only reason to choose their products considering the poor quality and high prices.

As for the 4850, don't hold your breath. Hardly any of the current integrated coolers can handle the heat, and apple doesn't design cases with high-heat graphics cards in mind.

Re:Power != memory

[Anonymous Coward]

I will take your advice and ignore what you have said. Thank you sir.

Re:Power != memory

[RobertM1968]

Lets add to the above...

Is this card "64bit OS" only? Or is it "Windows in PAE mode only"?

If not, I am not sure exactly how it is advantageous to anyone... on a 32bit Windows machine in non-PAE mode, wouldn't the card's required address space mean that the machine, even if maxed out to 4GB, would have negative available memory?

For instance: (in Windows 32bit non-PAE) 4GB addressable (minus) other add-on cards and the busses (minus) 4GB+ for the graphics card (is equal to) a negative amount of available memory.

Or is there some driver trick involved to page the memory thus allowing it to use a smaller address space mapping?

Just curious... anyone know how this will work?

Re:Power != memory

[Penguin Follower]

eVGA offers lifetime warranties on all their graphics cards, it's really the only reason to choose their products considering the poor quality and high prices.

Damn, I wish I had paid attention to that... oh well too late. I tossed it.

As for the 4850, don't hold your breath. Hardly any of the current integrated coolers can handle the heat, and apple doesn't design cases with high-heat graphics cards in mind.

SMC Fan Control FTW! My Mac runs quite cool, and I've still managed to keep it near-silent. The fans only needed small bump. Only time I hear anything is when I'm playing CoD4... then the fan on the x1900xt spins up. :/

Re:Power != memory

[Chandon Seldon]

This is probably worth looking at for anyone who's interested in the topic of monopoly: Wikipedia: Concentration ratio

Re:Power != memory

[Anonymous Coward]

I've found that the linux drivers for ATi have got a lot better, with 3D acceleration, videos etc. working perfectly out of the box (a Radeon7000 under openSuse 11.0), whereas I had to download and run a binary from nVidia to get the same. (GeForce8400GS under Gentoo).
I almost want to cry when I see that openSuse box with the relatively low spec card in it handling 3D better than my gentoo box. Ah well, ATi next time... such is life.

Re:Power != memory

[mdm-adph]

Oh, I'm not -- that's why I said "discrete." ;)

Re:Power != memory

[Raziel-chan]

New standardized feature X is added to the registry. nvidia adds it pretty quickly; ATI adds it months, even years later

So you're saying that nVidia drivers fully support Xrandr and no Ati drivers support it? Yay, that means that I was doing something wrong and THAT'S why I can't have sensible dual screen with different resolution monitors and direct rendering to both screens! Now I can fix it! ... Oh, wait...

cya
Raziel-chan

Re:Power != memory

[Anonymous Coward]

don't be so full of shit

Re:Power != memory

[Iamthecheese]

I have a lovedoll you insensitive clod!

Re:Power != memory

[Anonymous Coward]

Isn't the price tag more about support? How much support is nvidia going to give you when something doesn't work on your softmod setup?

Re:Power != memory

[ogl_codemonkey]

Does this mean that for all that time we spent winging about video cards not running under linux; the real solution was to run linux on the video card?

Re:Power != memory

[ogl_codemonkey]

You are technically correct.

The best kind of correct.

Re:Power != memory

[tyrione]

Yes, AMD's Stream technology. I don't think it is used as much as CUDA in practice.

Soon to be supplanted by OpenCL as being OpenCL compliant.

Re:Power != memory

[dogmatixpsych]

Exactly! I do neuroimaging research and I'd love to have something like this to help with our renderings of brain structures. It would make some of my work much easier.

Re:Power != memory

[mikael]

I like the phrase 'ancient graphics cards' - I had a Hercules Graphics Station Card, a full-size graphics card with the innards of a GPU splattered all over the circuit board. The VRAM chips were a problem - they stuck out so much that they would make contact with the adjacent cards.

I guess, if RAM chips were installed in sockets, they would have be slid in between the heatsink and the circuit board like a memory stick.

From this article, GPU memory clock speeds are coming close to 990 Megahertz, while regular CPU memory is running at 1333 Megahertz, but that GDDR3 memory is optimised for longer length block read and writes.

Re:Power != memory

[tyrione]

meaning you can code directly the hardware

Guess what CUDA and Stream have been designed for? Yes: for programming the hardware. What you suggest is pure insanity. NEVER EVER touch hardware directly from an userland app. And once you start writing a kernel module, you end up with something like CUDA/Stream anyway.

I am a coder, and quite frankly I couldn't care less about nvidia drivers being closed source. They are MUCH better than the ATI ones, especially in the OpenGL department. nvidia whipped up a beta GL 3.0 driver in less than a month since GL3 specs were released. ATI? Nope. New standardized feature X is added to the registry. nvidia adds it pretty quickly; ATI adds it months, even years later. nvidia drivers are also pretty robust; I can bombard them with faulty OpenGL code, and they remain standing. With ATI's fglrx, even CORRECT code can cause malfunctioning.

THESE are the things I care about. Not the license.

No offense, but ATi is working on being first to be OpenCL and OpenGL 3.0 compliant. Good luck on nvidia getting off it's ass which is evident by their desperate CUDA push.

Re:Power != memory

[Anonymous Coward]

Not really. Try being correct while being insightful, instead of slavish.

Re:Power != memory

[raftpeople]

The GTX280 is programmable with CUDA also? There are differences between he cards, but you seem to be implying you can't use CUDA with the GTX280.

Re:Power != memory

[catch23]

wow 12 years ago? so... 1996? In 1996 there was a little known company called 3dfx that was announcing the release of a graphics accelerator card called the Voodoo 1... it was kind of funny since you had to do this weird video card passthru thing.

I don't think Nvidia even existed back then. Around late 1998 they would release the Riva card though. They're first foray into 3d gaming. And until late 1999, the riva drivers sucked badly.

Re:Power != memory

[randyest]

I'm trying to be like you, but I keep falling short!

Re:Power != memory

[badkarmadayaccount]

Mod parent up. Please!

Re:Power != memory

[badkarmadayaccount]

$20 worth of DSP's can't do that?

Re:Power != memory

[ardor]

Their CUDA push has zero to do with GL3. As I mentioned before, nvidia ALREADY supports OpenGL3 in a beta driver. So they beat ATI once again. I really hope AMD forces ATI to beef up its driver development...

In addition, one just has to look at the OpenGL extension registry, and note the authors. MANY extensions (and most cutting-edge ones) came from nvidia.

Re:Power != memory

[ardor]

First, this is about OpenGL.

Second, I have twinview with direct rendering on both screens. While it is not Randr, it works reasonably well. Nvidia itself states in their driver FAQ that they are waiting until Randr is fully freezed before development starts.

Re:Power != memory

[Raziel-chan]

Twinview works reasonably well ONLY for monitors with the same resolutions. If the resolutions differ - it works like pure shit.

I have a 1680x1050 and a 1024x768 screens. This leaves part of the 'big desktop' unused and also compiz is no longer able to break the big screen apart for effects liken the desktop cube.
Also, it often causes problems with fullscreen games. In other words - Twinview is ANYTHING but good.

Also, about the 'this is about OpenGL' part. Let me quote.

[quote]They are MUCH better than the ATI ones, especially in the OpenGL department.[/quote]

You never limited your statement to OpenGL. You also said that it was GENERALLY much better. I don't see why my comment is besides the point, especially, that:

[quote]New standardized feature X is added to the registry.[/quote]

And I've just proven that untrue. Xrandr 1.2 is included in the newest X.org. Therefore, it's pretty much a standard. And Ati drivers support it pretty much perfectly, while nvidia ones trail behind.

cya
Raziel-chan

Re:Power != memory

[GNUPublicLicense]

Right. But the main issue is to remotely pilot through PCI express the complexity of a modern GPU from the Linux kernel on the host system. Currently a lot of work is done in designing a set of layers: - lowest GPU specific interface. - GEM. - Gallium3D. I hardly can wait for 3D engines based on those interfaces, bypassing opengl 3...

Re:Power != memory

[ardor]

Twinview works reasonably well ONLY for monitors with the same resolutions. If the resolutions differ - it works like pure shit.

I am running one monitor at 1680x1050 and another one at 1280x1024. I have yet to experience any of these problems you mention. And I do run games. I even coded myself a X11-OpenGL-library because SDL, GLFW etc. do not support multiple contexts and multiple monitors; for example, I can have two contexts, one for each monitor, both at fullscreen, and render to both with direct rendering. Compiz also works for me.

You never limited your statement to OpenGL. You also said that it was GENERALLY much better.

Okay, my error. I meant it is *mostly* about OpenGL. For a non-OpenGL example, when I switch to a text console and then back to X11, fglrx freezes the kernel on my laptop with a 9600 radeon. This is an ancient card, and one might think that bugs as major as this one have been ironed out by now, but no. I have never experienced something similar with nvidia. With nvidia drivers, it "just worked". Always. Complete with DRI and all. With fglrx, I am lucky to get it to work at all. Then, I have to spend more time trying to get DRI to work. I thought this is just true for the old 9600 , but imagine my surprise when very similar issues appeared with the HD 2600 I use at work.

And I've just proven that untrue. Xrandr 1.2 is included in the newest X.org.

Xrandr is not part of the OpenGL registry. Read again what I said:

New standardized feature X is added to the registry .

Re:Power != memory

[Raziel-chan]

You didn't specify that you meant the OpenGL registry up until your last post, thus reading that again won't change a thing.

Also, are you using Xinerama, Twinview or separate X servers? Problems I mentioned are well documented.

Twinview stretches a single large desktop over multiple screens. Thus, if the vertical size differs, there will be unused gaps. You can make the smaller screen scroll over that space, but it doesn't really help much, does it?
In my case it's 1050 vs 768 - that's quite a difference. In your - 1050 vs 1024. That's 26 pixels of difference. You may not even notice the unused space.

In Xinerama, on the other hand, you can only render directly to one screen at a time. That's been documented too.

Also, I have had various problems with nvidia drivers. Maybe I'm just unlucky, then.

cya
Raziel-chan

Re:Power != memory

[thtrgremlin]

I like nVidia. It has worked reasonably well for me. At the same time, I do not have a lot of money, but spoil myself every few years with a top of a line card when I can.

I would bet if I got an Ati card, if would work just fine. I am sure there are many other card makers that would work really well too. It is just that I got burned once a long tine ago, and nVidia has never done me wrong. Maybe more than loyalty is caution. Why switch away from what worked? I stopped using Mac cause it didn't work for me. Stopped using Windows cause it didn't work for me. I am happy with Linux, but it took several distributions to find the one I was most comfortable with. Going through that again isn't something I would wish for.

There would just need to be a motivating factor to go away from what has worked so well.

Re:Power != memory

[thtrgremlin]

The way monopoly is used today, though imprecisely as you mention, is in violation of anti-trust. Small companies have been convicted of anti-trust for doing illegal things to drive out competitors. By contrast, Cisco Systems has near complete world market domination on routers and such. They were brought to court to see if there was any illegal reason for their success. The court concluded that they were just really good at what they do, and that their products were just better and everyone knows it, without any indiscretion.

By contrast, Microsoft is in the business of bribes and brutally destroying the competition. They buy competitive products that are any threat and frequently just lock them away doing nothing with them. They pay off regulators at every opportunity, all around the world. They produce an inferior product and threaten OEM's, retailers, and other businesses that try to be more than an exclusive Microsoft supplier / seller. They price gouge, and near constantly lie in their ads, and manipulate benchmarks, reviews, and any other statistic.

They did this to get large market shares, and continue to do it with the power of the market share that they have. That is the kind of monopoly that they have, and exactly the kind that anti-trust attempts to punish.

With respect to the context, that wasn't just 'technically' correct, it was absolutely correct. The definition is very clear, but anti-trust law in the United States didn't come from Silver; see the Sherman and Clayton Anti-trust Acts. A monopoly exists when a company violates its trust with consumers and investors through its power of being a dominant market force player. Normally, this is a civil matter when trust is broken, but when it is with consumers or investors as a whole, then it is a matter of class action / anti-trust law.

Microsoft is also the ONLY company that has violated an anti-trust judgment order of the European High Court. This is a special kind of evil.

Re:Power != memory

[Chandon Seldon]

By contrast, Cisco Systems has near complete world market domination on routers and such. They were brought to court to see if there was any illegal reason for their success. The court concluded that they were just really good at what they do, and that their products were just better and everyone knows it, without any indiscretion.

Just because they weren't found to be abusing their monopoly doesn't magically make the router market healthy and competitive.

Microsoft's monopolistic certainly put them into a special class, but that doesn't mean that oligopolies in general are suddenly a good thing just because Microsoft is especially bad. *Every* oligopoly create a warped market, and Monopoly a good (if imprecise) term to use for a uniquely dominant Ologiopolist.

Re:Power != memory

[Anonymous Coward]

you are kidding right? The quadro line is basically the the way to do what sgi was doing but,with intel architecture. again the ignorant pontificate about subjects with which they have no knowledge.

Just what I always wanted!

[Jaysyn]

A video card I can't use on XP32 since it can't properly allocate that much VRAM & system RAM at the same time.

Re:Just what I always wanted!

[TheSovereign]

you mean you aren't on x64 yet? pfft get with it gramps!

Re:Just what I always wanted!

[Anonymous Coward]

Um the card in question is in the Graphics workstation Quadro line, not for gaming, for making money doing CGI animations, 4D modeling, etc. Would not have 32bit drivers for XP, only drivers 64bit Microsoft and Linux O/S's.

Re:Just what I always wanted!

[altloser]

nobody uses xp64

Re:Just what I always wanted!

[IanCal]

If you're doing scientific computing requiring about 4 gigs of ram, and need the processing power of current-gen graphics cards then you should be able to figure out how to migrate from XP32 to 64 bit.

That you are using an old operating system incapable of dealing with this new hardware is not the fault of nVidia.

Re:Just what I always wanted!

[TheSovereign]

believe it or not on my home pc, I DO

Re:Just what I always wanted!

[Lord Ender]

The sort of person still running a 32 bit OS is not from the same set as those who might spend $3k on the latest and greatest hardware. You don't matter to them.

Re:Just what I always wanted!

[Anonymous Coward]

You don't understand memory management on Windows XP.

The OS doesn't allocate video RAM into the OS; DirectX hands those features off to the video card to do its own memory management with DirectX objects. The OS pumps DirectX data to the video card driver, which passes it off to the video card, without mapping that memory into system memory space.

Re:Just what I always wanted!

[Anonymous Coward]

You don't understand PCI addressing or graphic apertures.

Re:Just what I always wanted!

[smussman]

I do as well. And *both* of us can't be nobody.

Re:Just what I always wanted!

[Hal_Porter]

A video card I can't use on XP32 since it can't properly allocate that much VRAM & system RAM at the same time.

That's not necessarily a problem. VRAM doesn't have to be mapped into system RAM, it could be banked like it was back in the Dos/ISA days. It's not really clear whether they do but I did find this

http://lists.opensuse.org/opensuse-multimedia-de/2006-04/msg00012.html

The graphics component of XFree86-DGA is not supported because it
requires a CPU mapping of framebuffer memory. As graphics boards
ship with increasing quantities of video memory, the NVIDIA X
driver has had to switch to a more dynamic memory mapping scheme
that is incompatible with DGA. Furthermore, DGA does not cooperate
with other graphics rendering libraries such as Xlib and OpenGL
because it accesses GPU resources directly.

Which sounds like graphics memory is banked into CPU address space on an NVidia card. It doesn't make any difference in the common case because normal the hardware on the card does the drawing, not the CPU. Using a card like this as a dumb framebuffer for the CPU to draw into is kind of a waste.

Re:Just what I always wanted!

[petermgreen]

The days of the graphics card mapping all it's memory into PCI address space at once are over and have been for some time. IIRC modern cards use a movable window of 256MB or so for access to graphics card ram from the rest of the system.

Re:Just what I always wanted!

[Anonymous Coward]

As do I. It is the greatest thing since Windows 2000.

Re:Just what I always wanted!

[Jackie_Chan_Fan]

32-bit is dead. It should have been dead 4 years ago...

Any serious computer enthusiast or professional running a 32bit os on today's hardware should be ashamed. They're holding the industry back.

Re:Just what I always wanted!

[Poltras]

I do as well. And *both* of us can't be nobody.

you both ain't somebody either.

Re:Just what I always wanted!

[flape]

get real ... reaaly good choice for desktop os ;) more stable and faster than xp32 as the xp64 is based on windows server 2003 core ;)

Re:Just what I always wanted!

[pak9rabid]

A video card I can't use on XP32 since it can't properly allocate that much VRAM & system RAM at the same time.

A few things things wrong with this statement:

1. The GPU (which is far beyond 32 bits) is accessing the VRAM, not the CPU
2. Video rendering/CAD powerhouses are the target audience for this card (not consumer-level gamers/enthusiasts), whom are probably NOT going to be running this card on a 32 bit version of XP

Re:Just what I always wanted!

[PRMan]

Actually, it's all the applications (such as Adobe Flash) that don't work on 64-bit that are holding the industry back.

It's much easier for them to recompile than it is for us to work without certain software...

Re:Just what I always wanted!

[Jaysyn]

Yeah, it was a joke, I'm not using modern hardware. Hell, I don't even have a computer with a PCIe bus in it other than my laptop.

Re:Just what I always wanted!

[saudadelinux]

That you are using an old operating system incapable of dealing with this new hardware is not the fault of nVidia.

There's

a FUCKLOAD

of problems that are I'll never buy anything with an Nvidia card in it again.

Re:Just what I always wanted!

[Anonymous Coward]

Yup. Parent is right, and GP is wrong.

Re:Just what I always wanted!

[Anonymous Coward]

Thank you Anonymous Coward for putting that right. I know I can trust your statement on the matter.

Re:Just what I always wanted!

[Anonymous Coward]

FUD.

Plus, "linux"? Either you're an Intel fanboy or you're astroturfing.

Re:Just what I always wanted!

[Cowmonaut]

Agreed. I personally love it. 5 months after it came out the driver issues went away and its more stable than XP in my experience. Faster too. Benefit of using the server kernel I suppose.

Re:Just what I always wanted!

[EvilIdler]

64-bit Vista, 64-bit Kubuntu on the gaming computer. Theoretically, all the Macs should also be 64-bit. 32-bit is dead to me :)

Re:Just what I always wanted!

[Anonymous Coward]

IIRC

You don't.

Re:Just what I always wanted!

[TheThiefMaster]

32-bit apps work fine on 64-bit Windows unless the application specifically checks for it and doesn't work on purpose.
The most common problem I have is my Windows XP x64 being misidentified as Server 2003 because it shares the same kernel version (NT 5.2), and even though the "I am a server OS" flag is OFF the software still refuses to run because you apparently have a server OS. Vista x64 is obviously not affected by this, as it has the same kernel version as 32-bit Vista, so an app that works on 32-bit Vista should also work on Vista x64.

Re:Just what I always wanted!

[Anonymous Coward]

Not really, 32 bit is adequate for the masses. Surfing the web, forwarding chain emails and loading up your iPod does not require > 4 GB of RAM and 64 bit platform.

32 bits out to be enough for anyone...

Re:Just what I always wanted!

[Chandon Seldon]

32-bit apps work fine on 64-bit Windows unless the application specifically checks for it and doesn't work on purpose.

Unless it's a binary plugin to a binary application (like Flash), in which case either being 32-bit forces the other to be 32-bit. Hope no-one planned on having more than 2gb of browser windows open...

Re:Just what I always wanted!

[Anonymous Coward]

I think it would be more fair to say that a lack of 64 bit drivers is holding the industry back, not people who are unwilling to buy new hardware just because.

Re:Just what I always wanted!

[Penguin Follower]

FUD? I had an eVGA 8800GTS that for some reason always detected as a mobile chipset when I'd use Nvidia's driver chooser on their website. I always thought that was weird... then one day the card burned up. The same day I read about the mobile chipset failures. Coincidence? Maybe... All I know is I'm a happy owner of an ATI card right now that has given me zero problems so far. Granted I don't use it under Linux. It's been flawless under XP though.

Re:Just what I always wanted!

[serviscope_minor]

There's a FUCKLOAD of problems that are I'll never buy anything with an Nvidia card in it again.

And there's a load of problems with ATi drivers (presumably it's the drivers). There's a load of problems with Intel (performance). So, what are you going to buy. I hear that IBM have fully debugged their "Video Graphics Array" and drivers now.

Re:Just what I always wanted!

[Mashiki]

Three nobody's? Damn it...

Re:Just what I always wanted!

[TheThiefMaster]

I figure he was either talking about the flash development software (but presumably that would work on x64) or he's referring to the flash firefox plugin on linux, but it works fine in the 32->64-bit plugin wrapper in 64-bit firefox or with 32-bit firefox. No-one uses a 64-bit browser on Windows yet. And more to the point, the op (and therefore the thread) was about XP / Windows, so linux would be off-topic.

Re:Just what I always wanted!

[Anonymous Coward]

Windows XP x64 comes with IE 64-bit and I would imagine Vista x64 does too. People DO use 64-bit browsers.

I have IE x64, Firefox x64 (x64 Minefield build actually) and Opera x64 on my PC. And no, I don't use Flash. In my opinion Adobe is doing the world a service. Hopefully Flash will die off as more people move to modern operating systems.

Re:Just what I always wanted!

[Artuir]

Most systems can use what is called "Physical Address Extension" now which will allow 32 bit Windows XP systems to access up to 64GB of RAM. So the 4GB limit is a non-issue now - just patch up XP.

Re:Just what I always wanted!

[Anonymous Coward]

That's not the OS who will manage that memory, but the video driver by talking directly to the video card. It can work at its full potential, even on XP.

Re:Just what I always wanted!

[IanCal]

I have no idea why you have replied to me, since we're not talking about even remotely the same point.

His argument was against a card with 4GB ram, due to the fact that a 32 bit OS is incapable of referencing so much ram. This argument doesn't even have anything to do with nVidia apart from the fact that they are releasing a 4 gig card.

Re:Just what I always wanted!

[Jackie_Chan_Fan]

Yes, but we need to drag the masses kicking and screaming into the 64-bit world. It is in OUR interest...

32-bit is dead. Grandma doesnt need 8GB's of ram, but the industry as a whole needs to stop taking the easy route and catering only to the dumb myspace masses. It holds technology back.

32-bit has no future.

Re:Just what I always wanted!

[Jackie_Chan_Fan]

You're correct, but it also takes user statistics to change the minds of software devs. If more people are using 64-bit, and less people using 32-bit... they will make flash in 64-bit.

There is no future in 32-bit. Adobe is simply lazy and needs to be dragged kicking and screaming into 64-bit. Photoshop users were begging Adobe for a 64-bit photoshop and Adobe actually said something to the effect of "going to 64-bit wont improve performance"... Which is ridiculous. That was around the release of CS3. Everyone was disappointed. Adobe has recently released Photoshop CS4... and it now has 64-bit support.

these companies need to be dragged kicking and screaming because its not in their interest to spend more money converting their old code.

Re:Just what I always wanted!

[toddestan]

But for what benefit? The only benefit most people see from 64bit is the ability to natively address more than 4GB of ram. It's kind of telling that 64bit has been around for years, but really didn't gain any traction until desktop computers started bumping into that 4GB barrior. And like AC said, you don't need 4GB+ of ram to forward chain emails and load up an iPod.

Re:Just what I always wanted!

[Jaysyn]

This explains what I was referring to earlier better than I can.

http://en.allexperts.com/q/PC-hardware-CPU-1023/Windows-XP-memory-limit.htm

I'm only bringing it up having run into it earlier this year while building a PC for a friend.

Re:Just what I always wanted!

[TimothyDavis]

Oooh Oooh! I can answer this one (as I actually have one of these cards).

The memory on the card is being accessed by the GPU, not the CPU! So it doesn't matter if you are running on a 32 bit system - the graphics card itself can use >4 GB on onboard memory.

Re:Just what I always wanted!

[badkarmadayaccount]

Can't you run a ramdisk in the higher address range and swap to it? /plan9user

Benchmarks

[toxygen01]

Any numbers how does it compare to the rest of cards? except number of cores and amount of memory...

History repeats...

[B5_geek]

I am reminded of old 3DFx advertisments just before they went belly-up.

Re:History repeats...

[CaptainPatent]

Hey, I loved my Voodoo 5 6000 until the day it was never shipped to me.

what a revolution

[jollyreaper]

Does this mean we can finally run Crysis now?

Re:what a revolution

[dreamchaser]

Oh come on, you can run Crysis with half that number of cores and only 2 gig of video RAM. This card is obviously being built because of the impending release of Duke Nukem Forever.

Re:what a revolution

[Albanach]

Nope, but you can run Vista.

Re:what a revolution

[SimonTheSoundMan]

Almost.

Re:what a revolution

[Anonymous Coward]

Geesh, spreading wild rumors... 4GB video RAM isn't enough to even load the intro for Duke Nukem Forever, let alone play it.

Re:what a revolution

[BForrester]

Not only can you run it, you can crank your graphical settings to medium!

Re:what a revolution

[BarneyL]

I heard that if anyone ever possessed both Duke Nuem Forever and a graphics card powerful enough to run it then the game would cease to exist and be replaced with something more complicated.
Others say that the developers have in fact already done this several times.

Re:what a revolution

[Anonymous Coward]

Posting anonymous because I'm embarrassed....

Is that from the matrix or something?

Re:what a revolution

[Anonymous Coward]

But will it run solitaire!

Re:what a revolution

[collinstocks]

No, it's from The Hitchhiker's Guide to the Galaxy.

It goes something like this:

Some people speculate that if both the ultimate question and the ultimate answer were known in the same universe, the universe would cease to exist and be replaced with something more complicated.
Others say that this has in fact already happened several times.

Re:what a revolution

[Anonymous Coward]

Damit that was my third guess...I knew I recognized it. Thanks.

Re:what a revolution

[lavaface]

it's from the preface of douglas adams' Restaurant at the End of the Universe:

"There is a theory which states that if ever anyone discovers exactly what the Universe is for and why it is here, it will instantly disappear and be replaced by something even more bizarre and inexplicable. There is another theory which states that this has already happened."

Re:what a revolution

[dreamchaser]

Only if you turn Aero off.

Any wagers?

[Duradin]

Anyone want to put odds on the next Crysis requiring at least two of these?

All things considered, I'm glad I gave up the pc gaming habit. Consoles may not have the newest-super-duper-double-1337-hyper-lens-flair effect but they do tend to play any game made for the system without feeding it new hardware every six months.

Re:Any wagers?

[jgtg32a]

Technically Crysis runs on a ATI 9800, personally I run it on a 1950pro (med setting) and it looks better than most games.

Re:Any wagers?

[BrennanM3]

You don't have to upgrade your machine with the latest expensive stuff every 6 months to play games. I'm still running a machine from 2005 and have played crysis, fallout 3, etc without any problems.

Re:Any wagers?

[Arboris Clover]

Unfortunatly, bad design in games can still create slowdowns on consoles. Especially with multiplatform titles.

Re:Any wagers?

[bigstrat2003]

PCs do that too. It's not the fault of PC game makers that you're too damned cynical to realize even very modern games run on relatively old hardware. Including Crysis.

Re:Any wagers?

[gallwapa]

Have you played No More Heros for Wii? It suffers frame rate slowdown issues...

Imagine...

[Anonymous Coward]

a beowulf cluster of beowulf clusters of these

Preemptive strike

[MaxwellEdison]

Yes. It runs Crysis. Please stop asking. You have mistaken a short lived snide remark as an actual joke. It is not funny.

Now if anyone with an actual understanding of the architectures present here which would like to describe the actual improvement created, go ahead. But if you want to play the Crysis card, please crawl in a drainage pipe and die.

Re:Preemptive strike

[badkarmadayaccount]

Don't feed the trolls, I know, but I must.

..., please crawl in a drainage pipe and die.

I'm dumb, show me how.

Sorry, needed that.

Correction...

[Anonymous Coward]

That should be 'in history SO FAR'..

In other news, new things better than old.

Coming up later - this graphics card but only cheaper.

cool

[circletimessquare]

i've always wanted to watch wall-e as it is being rendered in real-time

Re:cool

[loufoque]

Not gonna happen, RenderMan is CPU-only.

no it's not

[hcdejong]

... "the most powerful video card in history", it's "the most powerful videocard yet".

[/pet peeve]

Re:no it's not

[Anonymous Coward]

Looks at his history books and current events... Yep, most powerful card in history (so far)

Re:no it's not

[Anonymous Coward]

I dunno, those Germans made quite a powerful video card back in the 1940s.

It certainly had more power than those steam-powered video cards the French made in WWI.

Re:no it's not

[L4t3r4lu5]

Wrong closing tag.
 
You mean [/pedant].

Re:no it's not

[lysergic.acid]

maybe you should call Guinness Book of World Records and tell them that all their records are incorrect. or you could, you know, stop being such a pedant.

Re:no it's not

[Swanktastic]

"the most powerful video card in history", it's "the most powerful videocard yet".

FACT: The Rebel Alliance used significantly more powerful videocards to render the Death Star in Star Wars Episode IV: A New Hope.

FACT: This event occured a long time ago in a galaxy far far away.

[/pet peeve]

Re:no it's not

[Anonymous Coward]

Well history is the summation of previously recorded events, right? So if it's the most powerful yet, then it is by default the most powerful in history.

Re:no it's not

[nedlohs]

Everyone else takes the definition of "history" in this context as:

* the aggregate of past events

You seem to be taking it as:

* the continuum of events occurring in succession leading from the past to the present and even into the future

Both of which are valid, the first is far more common though.

Claiming that the statement is wrong, when it is correct according to the more common definition of the word is a bit of a stretch.

Re:no it's not

[nedlohs]

But given the far far away bit, is it in the Earth's past light cone?

Re:no it's not

[Spatial]

Most powerful single GPU. But there are more powerful dual-GPU cards available (AMD's HD4870 X2, for example), although they have less RAM.

Re:no it's not

[Sentry21]

Well if we include 'history' as 'before right now' I'd argue that it's accurate. Maybe it won't be in a few years, but right now it is.

Not a card for gamers.

[BoredAtWorkWhatElse]

It's a Quadro, not the kind of card you buy to play Crysis on. It's meant for workstations or server farms.

A GTX280 with VRAM thrown at it...

[Anonymous Coward]

Same number of cores as the GTX 280. Sure, it's got 4x the memory (at 10x the cost), but the extra memory is only useful for some applications.

And what about their chip bonding problems?

[Enleth]

Are we going to shell out $3,500 for a card that will fail after half a year, or did they correct the problem already?

Re:And what about their chip bonding problems?

[Anonymous Coward]

I dunno how that's a troll, aren't a lot of the major integrated device retailers (HP, Dell, Apple) experiencing 15%+ failure rate with certain NVIDIA chips?

Modding that post as troll is kind of implying that assessment is false. I'm inclined to think it's true based on the number of these reports, and the sites they are reported on...

Whoever modded this as a troll should be modded as a troll.

Re:And what about their chip bonding problems?

[LingNoi]

Because the die problems are with notebooks of the previous generation cards so how is it in anyway related?

Also it's lame to post a AC pretending to be someone else because you were modded troll. Real lame.

Re:And what about their chip bonding problems?

[Anonymous Coward]

The troll mod is warranted simply for quoting the Inquirer.

Re:And what about their chip bonding problems?

[Enleth]

No, it wasn't me. Don't believe? Well, that's your problem.

And it was mentioned once or twice here (I don't remember, if it was TFA, or the comments) that some desktop cards are affected, too, and the guys at Nvidia aren't actually completely sure that they fixed the problem. Maybe it was false, maybe not, but it's hard to confirm anything when there's an equal amount of bullshit and actual information floating in the tubes and they look pretty alike. And starting a discussion about an uncertain topic isn't somethin you mod down for.

Re:And what about their chip bonding problems?

[Anonymous Coward]

when there's an equal amount of bullshit and actual information floating in the tubes and they look pretty alike.

So why fucking spread the bullshit.. *facepalm*

Not for home users

[Bieeanda]

If the price tag didn't tip you off, this is one of Nvidia's Quadro line. They're not enthusiast boards, they're for intensive rendering work-- film-grade CG or simulations. Now, while the technology may come down to consumer-level hardware, especially if Carmack's supposition that real-time raytracing is the next big step, but this is like comparing a webcam to a real-time frame grabber.

Re:Not for home users

[Microlith]

And if it's anything like their Quadro line to date, the difference between it and a standard gaming card is a couple BIOS settings and the driver setup.

Re:Not for home users

[Anonymous Coward]

And the ability for them to guarantee accurate rendering in cad/cam applications they support. We've had a few nvidia engineers on site working with us on projects to fix minor issues in rendering. For those who need it, the price of the card is in the support.

Re:Not for home users

[Anonymous Coward]

Carmack should get busy on games that don't suck *looks at doom3 and quake4* before he worries about the next big trend in GPU technology.

Re:Not for home users

[ZachPruckowski]

They're also generally top-binned cards. Even if you make the pencil lines and change the BIOS and play with the drivers, your card might break because it doesn't pass the more rigorous testing required. Same thing as with CPUs.

Re:misread the subject

[Bromskloss]

I read that as 4*MB* video card.

I fucking hate the beginning of work weeks.

Working hard, I see.

you're all confused

[DragonTHC]

I don't believe anyone claimed this was a gaming card.

This is a scientific number cruncher. Its use is in visual computer modeling for anything from weather models to physics models.

How about folding@home? this does it faster than any computer on the block.

All of you kids making jokes about crysis are missing the point. This might run games, but it's a science processor first.

Re:you're all confused

[Anonymous Coward]

You should know by now that even when explained in simple terms, most of slashdot still won't understand. Just look back to the government CTO threads to see the number of people who STILL think that it's someone who will dictate what technology everyone in America can and can't use. When simpletons choose not to understand something, it's better to leave them be.

Re:you're all confused

[Anonymous Coward]

Actually, the Tesla is for scientific computing. The Quadro line is for graphics.

Re:you're all confused

[644bd346996]

And the difference between a Tesla card and a Quadro card is a DVI port...

Re:you're all confused

[sa1lnr]

folding@home.

My 3GHz C2D gives me 1920 points every 30/33 hours. My Geforce 8800GT gives me 480 points every 2.5 hours.

Re:you're all confused

[prefect42]

No it's not, it's a graphics card. Most people buying them will be doing it for realtime rendering. Something like volume rendering can use boatloads of memory. Certainly we were using 1Gbyte of texture memory in 2000 on SGI machines.

If you want a 'science processor' you should be thinking about a Tesla http://www.nvidia.co.uk/object/tesla_c1060_uk.html.

Re:you're all confused

[cheier]

And about $1,800.

Tesla C1060 = $1,700
QuadroFX 5800 = $3,500

You're right about the difference pretty much being the DVI port, but it is a pretty expensive DVI port. Compute professionals didn't want the GeForce series because of lack of support, and they didn't want Quadro because it was too expensive, so the Tesla was NVIDIAs middle ground.

Re:you're all confused

[644bd346996]

When you stop to think about that extra $1,800, it doesn't sound that unreasonable. Most of that premium goes to cover the software costs - particularly all the QA needed to make sure that all the $20k+ software packages still work.

Re:you're all confused

[Anonymous Coward]

So... can it do my homework?

HA! At last!

[rarel]

Sony batteries worldwide now shake with fear at the perspective of meeting a most worthy opponent!

Programming specs? Where are they?

[GNUPublicLicense]

NVIDIA still lagging behind Intel/AMD/Via... where are the programming specs? Keeping such specs hidden is an hate generator...

Re: history \notin future

[Anonymous Coward]

FYI: history does not include the future.

Your argument is invalid.

That's Awesome.

[Petersko]

In two years I'll be able to pick it up for $149.

That's the great thing about video cards. Even a card that's two generations old is a terrific card, and they're fantastically cheap.

Re:That's Awesome.

[rogermcdodger]

The Quadro FX 5500 is two and a half years old and still goes for $2000+ new so I wouldn't count on it.

Games must be optimized

[Starturtle]

Doesn't matter how much RAM they pump into these things, the game ultimately has to be optimized to leverage the new memory. If you check most benchmarks in Tom's Hardware, you'll see no significant gains and potentially a loss if the game or driver's aren't optimized to take advantage of the new memory.

Re:Games must be optimized

[Eddy Luten]

Doesn't matter how much RAM they pump into these things, the game ultimately has to be optimized to leverage the new memory. If you check most benchmarks in Tom's Hardware, you'll see no significant gains and potentially a loss if the game or driver's aren't optimized to take advantage of the new memory.

That's because most games these days are made for last generation SM 3.0 hardware and severe memory limitations.

More RAM means larger framebuffer (higher resolutions) and higher quality or more textures per frame. It also allows for the caching of shader programs, etc. etc. All in all, higher clockspeeds, more RAM and more processing units are never bad, IMO.

Also, a Quadro is targeted towards professional applications (Maya, Max, Cinema4D, Scientific, etc.), not for games. But it will probably take a short while before GeForce cards will carry 4GB of RAM on-board.

Re:Games must be optimized

[_Shad0w_]

If someone is playing games with one of those cards in their system, it's because they're killing time in their lunch break before going back to do some seriously complex computational work. That's not a gaming card.

Comment removed

[account_deleted]

Comment removed based on user account deletion

Headlines

[Nom du Keyboard]

It's all about the headlines, that's all.

Old news

[freddy_dreddy]

These were being sold in the first half of August for 10500$ - containing 2 of those cards. Only 3 months late.

Re:Old news

[AppyPappy]

Four gig?????? My first mainframe had 4 meg of RAM.

Re:Old news

[swabaharjar]

This card is basically a Tesla c1060 with video output, which was first announced in June. So arguably this news is 5 months late.

How did this retarded comment get upmodded?

[Nimey]

Really, people. If you're going to buy such an expensive professional card, you're going to go with a professional-grade operating system, which will of course be 64-bit.

TFLOPS?

[wjh31]

as people have pointed out, lots of ram isnt really relevant, not compared to its TFLOPS rating, especailly considereing its intended use. a quick google finds this: http://fxvideocards.com/PNY-Nvidia-Quadro-FX-5800-4GB-PCI-E-VCQFX5800-PCIE-PB-p-16430.html which seems to suggest it comes in at about 1TFLOP, which compared to the ATI HD4870x2 2GB capable of 2.4TFLOPS at only £350 ~US$550 makes for apparently quite poor value

Re:TFLOPS?

[Ash-Fox]

What about the nVidia Tesla?

The ultimate power

[Anonymous Coward]

... for cracking WPA keys using GPU assisted decryption.

Its the concept car of video cards.

[Kaptain Kruton]

Car manufacturers occasionally make concept cars that look neat but have no real purpose other than drawing public attention and possibly testing ideas. They are not practical and do not serve any real purpose for the general public. This card is simply the concept car of video cards. It draws public attention to the company (being on slashdot definitely draw attention) and it tests the idea of putting a large potential for processing capabilities used by movie makers and CAD users (and it tests the market for that field). However, for the general public and most companies, it is pointless and has no real value. My $0.02

Our incremental history

[Captain Spam]

[...] NVIDIA has released what they are calling the most powerful graphics card in history.

...until three months from now when the "GeForce".(++$ver_num) is released. Just like three months ago. And before that, and before that, and...

Especially since

[Sycraft-fu]

You can still run all your 32-bit programs with no problems. Windows has an extremely good virtualization layer that allows 32-bit software to run in the 64-bit OS with no problems. We've done extensive testing and use of it at work. So even supposing you did need a big card and a 32-bit app, well that'd work.

Of course if you are doing anything that would need 4GB of video RAM, good chance you need a good deal more than 4GB of system RAM. After all, you probably aren't keeping the data only on the card, never to touch main memory. So there's a real good chance once you take the OS + background tasks + your app + your data you get a required amount of RAM over 4GB.

If you are getting a video card with 4GB of RAM, I'd be surprised if you didn't have 8GB or more of system RAM.

Does it run Linux?

[argent]

No, really, could it?

Re:Does it run Linux?

[Cowmonaut]

Now THAT would be interesting! Run a virtual machine off of a separate hardware device powered by the host's motherboard(e.g., the video card in this case).

I think I just got an idea for a better and potentially higher scalable terminal setup. I suppose I should be running to the patent office before I get sued to oblivion for discussing it.

Re:Does it run Linux?

[argent]

That's more or less how the Sonnet G3 processor upgrade for the Powermac 7200 worked. They used the motherbord as an I/O coprocessor and did all the heavy lifting on what's basically a complete G3 on a PCI card.

Re:Does it run Linux?

[Anonymous Coward]

No.

Forgetting Nvidia Tesla

[Anonymous Coward]

The Nvidia Tesla little more powerful, http://www.nvidia.com/object/tesla_c870.html

Actually not mainly a science processor

[Sycraft-fu]

It's mostly a professional visualization card. nVidia has three different brands for the same basic hardware:

GeForce: This is the consumer line of cards. They are intended for desktop and gaming use. They generally feature the least RAM, and no special outputs (just dual DVI and the like).

Quadro: Professional visualization cards. Same core as the GeForce, just a different market. The primary difference is they are certified with pro apps, and you pay extra for that. Along those lines, they have drivers optimized for pro work. They are also often available with more RAM (though they usually have lesser RAM options too) than GeForces, and are available with pro features like genlock and HD-SDI output.

Tesla: Stream computation boards. These are based on the Quadros, but do not have any video outputs. They are for computation only, not for video. They also tend to have tons of RAM and there usually aren't lesser RAM options.

So in this market the consumer card is the GeForce GTX 280. 1GB of RAM, 512-bit memory bus, 240 stream processors. The professional card is the Quadro FX 5800. Same 240 SP, same 512-bit bus, but 4GB of RAM. The computation card is the Tesla C1060. Same 240 SP and 4GB as the Quadro, but with no display outputs.

Same deal with the last generation. They developed a heavy hitting GPU on the high end gaming market and used it in pro cards for other purposes.

Re:misread the subject

[Anonymous Coward]

Just maintaining an even strain good buddy, just maintaining an even strain...

Oblig

[Anonymous Coward]

But will it run Vista?

Stupid.

[DarthVain]

All this amounts to is a proof of concept for technology. To quote Simon from Mad TV "LOOK WHAT I CAN DO"!

To those that think that this has any application what so ever let me say a few things.

#1) Can you just think of what the driver for this think might be? Ludicrous.

#2) It would likely require specialized programing even to function, none of which would be supported anywhere, and all of which would likely have to be custom.

#3) For those think this has scientific applications guess again. You should get together with the "but can you make a beowulf cluster of these" group and slam foreheads together. It would likely be more efficient and cheep just to network together a whole pile of lesser cards and systems to achieve the same results.

#4) As an addendum to the last, and against those thing this has applications in the movie or film industry for doing animation and effects, again for years it has used server farms. Again it would be probably cheaper and more efficient to use cheaper, more mature technology.

They may be able to leverage this technology to create more reasonable cards into the future, which is probably what they are trying to prove likely to gain capitol or to reassure stock holders in trying times. This is not a product, this is a PR stunt.

Re:Stupid.

[collywally]

Actually we do use cards like this. Think of the film "The Dark Night" This was shot on I-max resolution film. That's 70mm size film which they scanned in at 8k. Now you want to color correct that film. There is no way your going to want to do that in less then real time. The guys doing it get paid way to much and the equipment that they use rents for way to much to just have them waiting around for a render even if its from the renderfarm. With 4GB of ram you would have one hell of a frame buffer and with the ability to calculate some of the more complicated things in the hardware in real time you can get way more done.

Here are some systems that already use Nvidia 2GB quadro cards:
Inferno
Luster
Toxic

Re:Stupid.

[DarthVain]

I think what I mean is that this is too bleeding edge.

I also use quattro cards every day in my work station, and have for many years now. I do GIS work. Bottom line is IT departments are not going to invest or support product that new. I am talking a lot of systems large scale.

If you are an independent, with a few workstations, you can ad hoc it all you like. That however is an ultra-unique niche group. Not one to which nVidia or anyone else is going to market to. They would not be able to sell enough, be it 3500$ or 10000$ to make it financially viable.

If you look at the Quattro line up, it is pretty old and mature technology (relatively speaking).

Though I had a bit of a chuckle about guys getting paid too much. An example of this came up our last computer upgrade. I recommended a card upgrade, and the bean counters recommended a card downgrade. I then tried to explain to the managers that the reduced cost of the cards is peanuts compared to what it will cost in salary time and work projects. However I am sure they get a bonus for saving a few bucks short term, and they probably figure they will be on to the next executive job before the long term results are in. So yeah I am now running a worse card now than I was 2 years ago. Lame.

Let me guess...

[Anonymous Coward]

Yet another non-programmer FOSS fanboi idiot?
Have you ever programmed CUDA?
Have you ever programmed anything?
Take your English major degree and get out of my lawn.

Powerful?

[Terrorwrist]

Most powerful....until next week and the next model comes out.

Re:Powerful?

[thedistrict]

Won't be a few years until this is actually at a point where people can actually buy it though...by that time there'll be another bleeding edge processor on the next big GFX card.

Re:misread the subject

[Anonymous Coward]

Sounds like someone's got a case of the Mondays!

with that shitty drivers im banging in games

[unity100]

including crysis. full detail (with dx10 hack in xp even).

and i dont even have a 4870. i still use 3870.

Re:with that shitty drivers im banging in games

[sexconker]

Hint: This discussion isn't (shouldn't be) about games. It's (should be) focused on WORKSTATION cards.

Re:with that shitty drivers im banging in games

[coolsnowmen]

The fact that they [the ati drivers] can be made to work, says nothing about how nice the interface and implementation is to the coders who have to work with it.

no, but you might be

[unity100]

either an idiot, or a fool. to quote other users :

The card is exactly the same as the Geforce GTX 280 except with quadruple the VRAM. Like all of the Quadros, they're the same as the normal lineup with more RAM and different drivers.

Yes and no. It is a Quadro, and the extra memory is indeed handy for "professional" rendering, but don't get too far ahead of yourself. The rest of the card is nearly identical to the gaming versions. I suspect this is a GTX 260 with minor changes... mostly in the firmware.

my regards to the fool that modded you insightful.

Re:no, but you might be

[pak9rabid]

The card is exactly the same as the Geforce GTX 280 except with quadruple the VRAM. Like all of the Quadros, they're the same as the normal lineup with more RAM and different drivers.

Well no shit Sherlock. This has always been the case of GeForce vs Quadro cards, where the difference comes in the firmware controlling the card. In fact, you can even soft-mod a GeForce card such that the OS thinks it's its Quadro 'equivalent' (it's not of course because it lacks the firmware that makes it a Quadro, thus the perforamnce won't be anywhere the same in professional applications). So yea, nothing new here..nvidia has always taken advantage of this synergy to branch out into the professional market with minimal changes (thus cost) to an existing lineup.

PLEASE

[unity100]

refer to comment http://slashdot.org/comments.pl?sid=1023961&cid=25708385

I want 2 in SLI

[deadcellplus]

(n/t)

and you

[unity100]

grow some balls to speak harshly with your OWN username and then come back.

Most powerful?

[Anonymous Coward]

http://www.gwn.com/news/story.php/id/10042/Nvidia_Reveal_18000_PC_Graphics_Card.html

"According to Nvidia, a node can achieve up to 64x full scene anti-aliasing (FSAA), deliver a performance of up to 148 megapixels on 16 synchronized digital-output channels and eight HD SDI channels. The firm says that the fill rate reaches 80 billion pixels/s while the geometry performance is rated at seven billion vertices/s."

From more than two years ago.

eaaaah

[unity100]

shitty drivers does not bring coder hate. it brings user hate. surprisingly, even shitty drivers and that shitty control panel that STILL requires bloaty net framework to run on xp couldnt bring much user hate. to the contrary, they have quite a fan base.

Re:eaaaah

[HeronBlademaster]

Funny. At my workplace we (the programmers) hate ATI because of their crappy drivers. Some of their default values for OpenGL settings are wrong (according to the OpenGL documentation)! Things like that make our graphics buggy on ATI cards; switching to an nVidia card makes the issues vanish.

So saying it doesn't bring coder hate is wrong; but saying it brings both coder hate and user hate would be correct.

Re:eaaaah

[unity100]

the number of programmers to users are unfortunately not significant. ati does those drivers for users, not programmers who may be doing 3rd party apps. they are not the driving force behind the market.

Re:eaaaah

[HeronBlademaster]

That may be true, but if you piss off developers they won't target your card, and they'll recommend nVidia to their users... I'm sure you can extrapolate from there.

Reality Check

[Anonymous Coward]

Given the porn market has people going for strange stuff, I'm sure there would be a fair number who would actually prefer their porn stars to have a tiny bit of hair stubble, slight blemishes etc.

Hair stubble and slight blemishes are perfectly normal. (Actually, hair is more normal than hair stubble). It's the "idealised" surgically-enhanced cosmetic-plastered participants in porn that aren't normal.

What this card is REALLY meant for

[Anonymous Coward]

It's for cracking crypto: http://www.elcomsoft.com/edpr.html?r1=pr&r2=wpa

4G...

[mebrahim]

4G should be enough for everybody!

Concept Car? Far from it

[raftpeople]

While your statement that this is not geared towards the general public is correct, it is far from a concept car like item. There is a tremendous amount of scientific processing sitting out there waiting to happen but it's too costly on supercomputers. For my own project, a neural network artificial life simulation, even this card won't get me the speeds I want/need. I'm testing with GTX280's right now and when I'm satisfied my code makes use of the card properly, then I will move on to the card in the article or continue adding GTX280's.

4G WTF?!

[woolio]

I used to play Duke Nukem on a 60MHz Pentium with a 2MB video card and 8MB RAM... What is the world coming to!?!?

4GB?

[V!NCENT]

Oh I think I have to get a second $647 Radeon 4870 X2 card (2+2=4GB).

Yes I have a dual core 2GB RAM graphics card...

Okay, I'll bite.

[rts008]

As for myself, I have been an ATI fanboy since nVidia's TnT 2 64 (mine was a 32 MB AGP card).
My ATI card 'just worked' with Win 98se, and then Win XP Pro.

I will admit to some problems however:
Battlefield 1942 sometimes required hacking some config. files to get a working desktop/game environment, instead of a black screen.(It's not just a *nix thing!)

AMD/ATI have improved their *nix support lately to the degree that I feel I have no other choice but to reward/support good behavior. (Use *nix/ati)

Opposite poles, and different perspectives as I see it.

I will agree with you that nVidia's Windows drivers seem to be better than ATI's Windows drivers....but my perspective is warped by not having had to deal with that directly for some time.

*note* I am still my family's 'computer geek', so I try to keep up with Windows as time allows.

Re:misread the subject

[badkarmadayaccount]

C'mon, that was good.

Radioxid

[Radioxid]

This Nvidia card looks like the Tesla one with much more video entries... Tesla is for HPC computing !