Slashdot Mirror
Nvidia's NV20
Bilz writes "ZD Net UK has posted an article on Nvidia's upcoming NV20 video chip. According to them, they state that during complex 3D scenes the card performs up to 7 times faster than a GeForce 2 Ultra."
← Back to Stories (view on slashdot.org)
Is NVIDIA going to take display clarity and color accuracy seriously, especially at high resolutions? If they could put together a card which would rival Matrox output quality with incredible 3D performance, I would be the first in line! I returned a GeForce2MX not long ago because anything above 1024x768 started showing annoying artifacts. My Voodoo3, while not perfect, blows the GeForce2MX out of the water in terms of image quality at high resolutions. There's a site on the net dedicated to helping people fix the image quality problems of some of the NVIDIA cards .. it seems the RAMDAC speed is really a bogus figure if the manufacturer puts cheap (or just badly designed) capacitors on the video output. In the GeForce2MX example, it looks like the reference board even NVIDIA used fell victim to this design problem ..
Mark
Not all the features:
1. Graphics overlay (for playing DVD's etc..) - driver still not supporting this feature
2. Page flipping - what gives the NVidia card a real boost under Windows - is not in the driver yet.
As a person who is working extensivley with lots o f graphics cards I can testify that their drivers are damn fast compared to any driver in XFree 4.0.x - but it's not as stable as the Open Source Matrox G200/G400 driver which is found on XFree 4.0.x
Hetz (Heunique)
Then this other poster was simply wrong. The large virtual size is due to memory mapping of the framebuffer (32/64megabytes on modern cards) and mapping of the AGP space (128megabytes or more).
The various "bit planes and color depths" are called visuals and they'll occupy at most a few hundred bytes each as structures within the X11 server.
I've seen you repeat this a number of times, but I'm afraid it's completely misleading. The information on the nvidia site is not specs at the register level, and it's not even useful information for writing an open source driver. As proof of this claim, try using that information to write a driver for FreeBSD.
This URL has been floating about for months now and every now and then someone repeats on the utah-glx mailing list "hey look nvidia has full register level specs on their website". Each and every time the person is corrected immediately. So please stop spreading this misinformation.
HDTV has a resolution of 1920*1080 or 1280*720. A 350 Mhz ramdac will drive a display at 2048*1536 at 75 Hz.
Supposedly, the correct formula is (RAMDAC speed (MHz) = x * y * refresh rate * 1.32)
So, a 500 Mhz RAMDAC would be able to drive a 1536*2048 display at 120 Hz. I'm sure the calculations are slightly different for widescreen displays.
NVidia, on the other hand, uses the same codebase for both their Windows and Linux drivers.
Even for the enormous Linux kernel module that's required to use their drivers? Really?
Does their Windows driver, after less than a week of use, bloat to consume over 200MB of virtual memory? That's what their closed source XFree86 driver did with my GeForce DDR, on XFree86 4.0.1 and kernel 2.4.0-test9, even without using the 3D features at all. The open source nv.o driver that came with XFree86 isn't exactly a spartan RAM user either, but at least after it's sucked up a big chunk it stops asking for more.
Granted, they don't seem to care about keeping up with development kernels (their kernel module didn't even compile against 2.4-test for a while); I haven't exactly put much work into fixing the problem (but how can I, when I can't even recompile with debugging symbols?); and their drivers did seem to work OK with kernel 2.2.16.
Nevertheless, I don't intend to buy another NVidia card until I have an open source 3D driver to run it with. By contrast, my previous 3D acceleration in Linux came from Mesa on top of Voodoo2 glide; the frame rate may not have been as fast, but the rate of driver improvment certainly was faster.
The reason I noticed at all is that my machine was swapping like mad, even with 128MB of physical RAM, and even after turning the usual memory hog culprit (Netscape) off.
I never claimed it was easy! ;) It's kinda like being stuck in the middle of the ocean in a rowboat. With closed drivers, you have no paddles, and the rowboat is covered with a sealed, opaque top so you don't even know when you're near land. Open drivers is like having the top open, and a large soupspoon. Rowing yourself to shore with oars would be hard enough, and harder with a spoon. But at least it's possible.
Other benefits come for other OSes (NetBSD, FreeBSd, etc.) for which nVidia will never write drivers. Also companies don't in general last forever. What happens if nVidia goes belly up? All the people who bought their cards and are using their drivers are up shit creek without a paddle (to extend a metaphor too far). Having the code allows you to generate an extremely specific bug report, which can then be passed on to someone more knowledgable. It's very hard for core developers to fix bugs like "It crashes when I click on the menu in starcraft", which could be a hardware problem...
--Bob
1^2=1; (-1)^2=1; 1^2=(-1)^2; 1=-1; 1=0.
Try that one on a musician friend one day and see how far you get :)
Any sufficiently advanced technology is indistinguishable from a rigged demo
--Andy Finkel (J. Klass?)
Is that it apparently goes without saying that any new polygon pumpin' uberchip is only going to be used to give us Yet Another First Person Shooter.
When will this technology break out of this ghetto? Aren't there more interesting things to do?
Personally, I think 3D technology has been stuck in the "keystone cops" era long enough. In early film, the only thing people could think to show was chase scenes and other stunts. A lot of that had to do with the immaturity of the medium (no sound, poor picture quality). Eventually, I think "3D entertainment" won't by synonymous with "graphic violence."
Other benefits come for other OSes (NetBSD, FreeBSd, etc.) for which nVidia will never write drivers.
Actually, I gather from other posts in this thread that the abstraction layer between the driver core and the OS's driver interface is open (or at least published). This should make porting fairly straightforward, even with most of the driver being a black box.
There's also the option of wrapping Linux drivers in their entirity to run under *BSD, though I don't know if *BSD's Linux support has been extended *that* far.
Stick with the more open 3dfx, or Matrox. With them, if it crashes, you can track the bug down and fix it!
You'd have a lot of trouble doing that, unless it was a silly problem like a memory leak (admittedly worth fixing).
I've worked for a couple of years with a well-known software company that does third-party driver development (well-known cards, well-known platforms). Debugging a driver even *with* the standard reference texts for the card is a royal pain. Doing it blind - say, for hardware bugs or restrictions that aren't documented - is so much trouble it's not funny. This eats a vast amount of time even for us. Trying to debug a driver while having to guess at restrictions/errata in a register spec without support documentation - or worse, having to reverse-engineer the spec from code - would be at best a vast undertaking and at worst impractical.
It can be done, but not nearly as easily as you seem to think, by several orders of magnitude.
I doubt it. The tools they use to create the scenes will get more and more sophisticated. They might use fractal algorithms to generate super-fine detail in trees, landscapes, water, fog, etc. The point is, they won't be hand-placing every polygon--the same way you don't hand color-every pixel in any other form of computer art.
There will continue to be applications that push the limits of this and many subsequent 3D accelerators. Trust me.
I too have an Nvidia TNT2 card and I'm using
:0 -bpp 32
Nvidia's driver with XFree 4.
Here's what top says:
Size RSS Share
252M 252M 2024 S 0 1.7 100.4 5:18 X
Seems excessive, doesn't it? Well, I've only
got 256M on my machine, and guess what?
NO SWAP SPACE IS USED.
PS tells a different story:
VSZ RSS
276408 12704 ? S 10:00 5:21 X
VSZ is the VIRTUAL size of the process, 276M
12.7M is what it actually uses.
Another poster in another forum explained that
this apparently huge virtual size was due to
virtual-memory-mapping of various bit planes and color depths in the VRAM into virtual memory.
12.7M is still pretty high, but hardly burdensome on my 256M machine.
PeterM
This new card may be nice but I still will not support nvidia till they open their drivers. Their drivers are among the most unstable drivers around for linux. Yeah it is nice they are fast but not at the cost of stability. I also don't like binary only kernel mods. I have no idea what might be in that driver and what it might do in the kernel. Also when updating kernels that driver break a lot since it is binary only. If it were open it would probably work a lot better.
Look at the sblive for an example of this. In the beginning it was closed and a pain in the ass to get working under linux. There were kernel version mismatches etc. When they opnened the driver it progressed much faster and it got incorporated into the kernel. Now the sblive is one of the best cards to get for linux since it is supported by every major dist out of the box. In some dists they even use the alsa driver instead of the oss one which is even more capable.
I am not going to get locked into nvidias way of doing things again. When I bought the card they had announcements about how they were going to open their drivers. This did not happen. My next card is going to be an ATI, Matrox, or 3DFX. I am waiting a bit on the radeon till I see the open drivers for them. However the matrox cards and 3dfx cards do have open drivers. I do like 3d but I like stability more and the box with the g200 here has never crashed in x. The nvidia geforce box crashes a lot more often then that.
So please even if you like their hardware don't support them till they open the drivers. In the long run it will help us a lot more. Teaching companies that drivers alone are not enough.
Computer modeling for biotech drug manufacturing is HARD!
Actually, right now, modellers first create the model they want, and then do their best to reduce the polygon count.
And you can kill a lot of polygons just modelling a realistic telephone. Which you can then reuse everywhere you need a telephone.
A RAMDAC has nothing to do in reality with 3d acelleration. Instead, the RAMDAC relates to converting from graphic's card's display memory to Analog signals on the monitor. Hence where RAMDAC comes from: Random Access Memory Digital to Analog Converter. A fast RAMDAC can support very high refresh rates. Now a 500Mhz RAMDAC will probably become necessary with high definition TV's which have a resolution a bit higher than 1600x1200, at a decent refresh rate. But as an above poster pointed out, it is likely a mistake in the article.
------ 24.5% slashdot pure
NVidia might have good video cards, but their way of handling themselves really sucks. Check here.
I quote from the article...
"Pioneer of the first ever GPU (Graphics Processing Unit), Nvidia is now introducing a programmable GPU, seven times faster than the previous Geforce 2 Ultra, the NV20."
Now, there are two possibilities here - either the article's author has a shocking grasp of the English language (wouldn't THAT be bad, considering he writes for ZDNet UK, the home of "The Queen's English"), or he hasn't done his research properly, and thinks that NV20 refers to the GeForce2 Ultra.
The GeForce2 Ultra is the NV15 if I'm not mistaken - simply a GeForce2 GTS with faster RAM. GeForce2 MX is the NV10.
The NV20 is the new GPU ZDNet's supposed "leaked documents" claim will be 7 times faster in complex scenes (ie TreeMark). You've gotta love it when the speed at which a product performs is judged by how it performs in a program designed to make it shine.
Bad journalism all round I think - not that we should be surprised....
Most consumers and compulsive upgraders don't realize how underutilized video cards are. We go through two or three generations of cards during the development of a single game, and more than anything we're just trying to keep up with it all. The bottom line, and I mean this sincerely, is that the kind of performance people are seeing from cards based on chips like the GeForce 2 could be coaxed out of cards from two years ago. It's not that the card is crap, but that the bottleneck is almost always on the code side of things. People don't want to hear that, though. Or maybe they do, because it validates their reasons for upgrading to new CPUs and video cards.
If you look at the PlayStation 1 hardware from five years ago, it doesn't even have bilinear filtering or zbuffering. It's also a total dog. And yet there are PS1 games that look as good or better than many current PC titles that require a TNT2 or better (maybe 15x faster than the PS1 hardware). So theoretically an "old" card like the Voodoo2, which is still 10x faster than a PS1, could do amazing, amazing things--much better than what people expect to see from a GeForce. But we don't bother, because things keep changing at a crazy rate and we're simply trying to get things out the door.
In a way, I'm starting to see new video cards as a way of getting suckers to part with their money.
I second that 'Moron'.
Son, I was wondering, you're playing that new hyper realistic game. How can you tell the difference between that and reality?
Er, we bought it at the store Dad. You were there, remember?
Yes, but when you've been playing it all day, don't the lines blur between games and reality?
Er, no? I load up the game, sit motionless for 10 hours. People shoot me and I feel no pain. I can carry a bazooka and 20 rockets without getting winded. My game guy picks up stuff with his hands, not mine. IT'S a GAME Dad.
I think you need protection from games. I'm going to start a group against realistic games. Uh, can you show me how to use this new 'HyperNet' to make a web page?
Dad, you don't make web pages anymore. You have to make fully interactive 3-D enviroments. Since everything went analog they haven't used IPv6 in YEARS.
Don't take that tone with me! I was a Unix guru back in the day!
Later
ErikZ
Democrats or Republicans. They are both taking us to the same place and they are not afraid of us anymore.
Damn, I thought I'd had it ;)
A deep unwavering belief is a sure sign you're missing something...
No, I mean that a lot of PC game makers ignore gameplay in favor of graphics. Example of those that don't, Epic with UT. Examples of those who do, ID with Quake3.
A deep unwavering belief is a sure sign you're missing something...
The point is that Ring0 gives access to hardware that you'd otherwise not have. And yes, ASM will ALWAYS be needed. Think about it, the hardware platform won't change for several years. (upgrades have proved to be complete and utter failures on consoles. Nintendo couldn't sell the $40 RAM upgrade, and MS sure as hell won't be able to seel a new GPU.) In order to keep each generation of game looking better, you have to bypass standard APis and write to the metal. The first games will use OS features, but I can bet you that by the second or third generation games come out, people will have built up custom ASM libraries and will use as little of the OS as possible. Look at the Saturn, for example. The first few games used DirectX, then all games afterwords used custom routines and the to-the-metal Sega OS. Windows 2K doesn't work EXACTLY like the underlying hardware. Given that the hardware is constant, why bother to write to the OS when you can get a nice 10-15% speedup by writing to the hardware. DirectX doesn't work like the NVIDIA chip does, so why bother with an API? Its not that much harder to code, so why not do it? PSX developers still use a large amount of ASM, and only recently has there been a trend towards C-only games. However, even those access hardware directly. Unless DirectX8 is a hell of a lot thinner than it was when I was using it (yesterday) I can guarentee you that most of the good games will be XBox-only. Also remember than console and PC gamers are totally different demographics, and there is little incentive for many console manufaturers to jump the fence.
A deep unwavering belief is a sure sign you're missing something...
Not necessarily. When you don't have an OS in the way and you get to run in ring0, you do everything you can to show up your competitors and tweek the system. The reason ASM and direct access have little use these days is because of all the diversity in PC hardware. Given a stable platform, game developers ALWAYS find a way to tweek games beyond what would be possible by going through the standard APIs. Saying that people will use DirectX8 all the time is like saying PS developers will use OpenGL all the time. It just won't happen.
A deep unwavering belief is a sure sign you're missing something...
Graphics are graphics, physics are something else. Physics engines are incredibly diverse in what they do. A one-size fits API handicaps physicas designers MUCH more than it does graphics designers. Gameplay and story don't really take any processing power. If you can offload graphics and audio processing to dedicated processesors (a much more practical design) then the remaining 1000MHz of your CPU can be dedicated to physics and AI. Gameplay and story is totally unlimited by hardware, and just dependant on what the designers do. The Final Fantasy series has great graphics, sound and gameplay. A lot of PC game makers just aren't that skilled.
A deep unwavering belief is a sure sign you're missing something...
Umm, with 3DFx down until Rampage comes out god knows when (Q2 next year), and Matrox sitting this round out, GPL fanatics have no choice but to sit on their G400MAX's and hope that ATI takes pity on them and decides to GPL the T&L part of their drivers. (The Radeon drivers are not completly OSS, just the rasterization parts are) Lastly, GPL fanatics will most likely ONLY get low quality drivers. Besides the legal reasons why NVIDIA cannot OSS their drivers, there is the fact that the drivers kick serious ass. They are the fastest, most stable implementation of OpenGL (what did you think an OpenGL driver was? This isn't an ethernet card!) on the face of consumer hardware. Now why in god's name would NVIDIA just give away an entire OpenGL pipeline to competitors who could take advantage of it (eg, ATI) to make their cards competitive with NVIDIA's?
A deep unwavering belief is a sure sign you're missing something...
They won't be compatible. Games written for XBox will be assuming Ring0 operation on a stripped down Win2K kernel. It's going to take some work to port, though probably not as much as it normally would. Of course, if the developers take advantage of the console nature, they'll start using custom ASM routines and bypassing the OS, in which case a port might be much harder.
A deep unwavering belief is a sure sign you're missing something...
Umm, complex scenes can be done just by setting MAX to not reduce the polygons so much. Trust me, people are FAR, FAR away from the day when the scene becomes too simple for the hardware.
A deep unwavering belief is a sure sign you're missing something...
Another implication of 3D games is the annihilation of imagination. Why try to think of your own universes, when they are provided them on a plate?
>>>>>>>>>>>>>>>>>>>>>>>
Actually, the columnist from MaximumPC (can't remember his name, forgieve me, he's the one with the beard) poited out that games are much closer to books than movies in that movies give you a prepackaged world on a plate, while games give a tool for you own mind to imagine things more vividly. I am inclined to agree. Well-done games take a lot of imagination to play, and can often stimulate the mind like a book does. (I'm not talking Quake, I'm talking Final Fantasy or Zelda.)
A deep unwavering belief is a sure sign you're missing something...
-----------------------
Nicotine free Amish .sig.
Sure - several good 21 inch screens support 2048x1536 @ 75 Hz. At about $1000, they aren't too expensive - I'd rather spend more on the monitor and less on the system.
The Radeon has a version of this implemented, but (to be honest), the Radeon isn't really too powerful. Imagine a powerful NVIDIA chip loaded up with HSR, and you'd get up to 7x faster in complex scenes, while simple scenes would only be a bit faster (less hidden surfaces to begin with).
They're the same boards, with the same chips. The only difference is the position of two chip resistors which identify the product type. In some models, the "high end" board was a part selection; the faster chips went to the high end. But with the latest round, the GeForce 2 Ultra, the low end is faster. So the reason for the distinction has vanished.
nVidia finally bought ELSA, the last maker of high-end boards that used nVidia chips. At this point, ELSA basically is a sales and tech support operation. It's not clear yet whether nVidia is going to bother with the high end/low end distinction much longer. I hope they get rid of it; its time has passed.
Did you see the claimed numerical performance for the new NVidia chip? 100 gigaflops. I can hardly wait until we have that kind of performance in the main CPU(s).
Don't believe everything you see, especially on ZDnet. They're not exactly the most reliable source around. Plus, different places have all claimed to have had leaked specs, and they all conflict with each other. I've yet to find two sites that have "leaked specs" that agree. Check The Register for instance for a different set of specs.
This isn't to say that these aren't right, but be sure to take with a grain of salt.
You think your problem with the NVidia driver would be fixed if it were open source?
No, I think a driver would exist for my OSes of choice if NVidia opened the driver sources. It's not all about Linux. On FreeBSD, OpenBSD, and NetBSD, recent NVidia hardware is as useless as an HP or Lexmark WinPrinter. Feh.
The maximum complexity for worlds will be a limit that won't be hit for a very long time. Look at the difference in world complexity between what is done for the highest quality 3d movies ( think Final Fantasy ), and compare with the most complexe real-time worlds.
Obviously the developers of 3d worlds in film have not yet maxed out their imaginations in terms of what to build, and how detailed to make it - and the gap between their work and the realtime 3d scene is a very big gulf indeed.
So I really don't think we'll be coming up to any significant blockages in terms of human imagination anytime soon. I suppose one might argue that as soon as we hit the point when 3d world complexity is visually indistiguishable from reality we may have hit the max. needed realism. But then of course there's always the visual effects of cosmic-zoom where you might want to soar through the microscopic cracks in someone's skin, etc. So there's plenty of room to keep plugging away.
There are a thousand forms of subversion, but few can equal the convenience and immediacy of a cream pie -Noel Godin
Thats one helluva secret document Nvidia surely wouldn't mind to reveal...
The fact is, these "secret" documents are released as a form of cheap marketing. In fact, a large portion of todays "journalism" is written directly from the company spin doctors. PR twats wastly outnumber journalists and the trends are extending this.
Always look for hyperbole (like the zdnet headline) and emotive adjectives in phrases like "screaming chipset design". They mention that it will only double performance when large polygons are used. Well I haven't seen many games that are written only for the GeForce. Given the price of development these days, games companies are reluctant to alienate potiential customers by asking for huge specs (unless your name is Geoff Crammond). I think it is safe to assume that the new cards will follow the trend of Nvidia's chipsets since the riva128, at least until benchmarks are out. The next generation is about twice as quick as the plain vanilla flavour of their current best chipset although they can probably manufacture benchmarks to make it look better.
Corporate hype is not newsworthy (as much as they like you to believe it is), but I will be interested when someone reputable publishes benchmarks (and no, not Toms).
Me, I'm happy to run quake3 on my riva128/amd233. Sure it looks like crap and is choppy as hell but ..... man, I really gotta upgrade. Where was that link again ..
We've already seen that in the game industry. Teams of 20 to 100 people cranking out stuff for 2 or 3 or 4 (Daik... nevermind) years.
Sure, movies do it, we get some beautiful movies that kill anything gaming hardware will be able to do. But movies are, what, 2 hours long? A proper game has to have 30 hours of gameplay at the very least (I'm thinking Diablo II at about 25-30 hours to take one character through), I'd rather have 75-100 hours. And with a movie, you might visit a model/texture once, where with a game it might be something that you can look at from all angles, as long as you like.
So we'll have a couple of guys working on an engine to pass geometry and texture, another 5 or 10 working out AI and extensibility and 200 artists and modelers creating the world.
Bleh!
My argument is simply that there's nothing more frustrating than having a bug that you can't fix. I'm the type that at least gives a hack at it if I find a bug. Open source is not about open source developers fixing bugs for you. It's about coherent, concise bug reports that come from an examination of the code. It's also about (as you mention) fixing simple things that I could find and fix like memory leaks. Clearly I could not write or reverse engineer a driver in any reasonable period of time. Clearly nVidia are the best people to write the driver. Open source is most useful in the last 10% of the development process, fixing bugs and refining the code. If a company expects a magic cavalry of developers to appear to write their driver for them, they are sadly mistaken. But they can expect people to do a little hacking to get an existing driver to work with their hardware combination.
Open Source is not the panacea of magic software creation that some people (3dfx, apparently) think it is. But when I buy a product with closed source drivers and those drivers suck, I'm fucked. If those drivers are open, at least there is hope. I find that in general, if I depend on other people to fix my problems, they will never be fixed. I hack "open source" to fix my problems. nVidia can't own every possible combination of motherboard/processor/OS, and therefore can't fix every possible problem. Open source is simply the only way to go, and I won't ever again bother with companies that aren't open with their drivers.
--Bob
Egad, who modded my original post down as "Troll"? Do your worst, metamoderators.
1^2=1; (-1)^2=1; 1^2=(-1)^2; 1=-1; 1=0.
Wow, a real non-gamer crowd! Doesn't anybody remember the PowerVR Series chips? The reason NV20 will be 7x faster for complex models and only 2x faster for simple ones is that it will use tiling (my hypothesis only.) In a tiling-based architecture, the 3D renderer first sorts all the geometry, and then splits it up into small tiles. The tiles are then loaded into small on chip buffers and rendered. This has several advantages:
A) It doesn't over-render. If geometry isn't going to be seen, it doesn't get rendered. Normally, cards have to render the pixel, and then discard it if the Zbuffer test fails. With tiling, there is no Zbuffer and pixels get discarded before they're rendered.
B) The sorting allows transparency to be handled very easily since geometry doesn't have to be presorted by the game engine.
C) It allows a hideous number of texture layers. The Kyro (PowerVR Series 3 chip-based) can apply up to 8 without taking a noticible speed hit. Also, it lower the bandwidth requirement significantly since the card doesn't have to access the framebuffer repeatedly.
D) It allows incredibly complex geometry. Even though the Kyro is a 120MHz chip, it can beat a GF2Ultra by nearly double the fps in games that have high overdraw (such as Deus Ex.)
The main problem with tiling is that standard APIs like OpenGL and D3D are designed for standard triangle accelerators. As such, the internal jiggering tiling cards have to do often outweight their performance benifets. Also, up until now, only 2bit companies have made tiling accelerators, so they haven't caught on.
If you want to read the Kyro preview, head over to Sharky Extreme.
A deep unwavering belief is a sure sign you're missing something...
The increase in speed doesn't just go to framerate. Newer game engines will have their framerate locked (at a user-specified value) and will vary visual quality based on how fast the hardware is.
How can that extra speed be used? More polygons, gloss maps, dot product bump mapping, elevation maps, detail maps, better transparency/opacity, motion blur, cartoon rendering, shadow maps/volumes, dynamic lighting, environment mapping, reflections, full screen anti-aliasing, motion blur, etc. I could go on forever. All this will be in my game engine, of course. :)
------
The problem isn't creating of complex scenes or worlds but rendering complex worlds. It has been estimated that one needs about 80M polygons in scene to render realistic looking image. Say you want 25 fps for your game - that equals to 2000M polygons/s - Even if NV20 is 7 times faster than current chips it's still far too slow to render images like this in real time. And the problem is you need those 80M polygons for just one frame. It's like you sit in a virtual room and it takes 80M polygons to present it to computer. Now imagine whole house with similar accuracy: if you had 10 "rooms" you would need roughly 800M polygons for it. Now imagine a city! The problem is how to decide 25 times per second which 80M polygons to render because you cannot even calculate whole geometry fast enough.
_________________________
_________________________
Spelling and grammar mistakes left as an exercise for the reader.
I know they have carefully thought out arguments as to why their non-open source, crappy drivers are better than open source ones. But folks, it just ain't worth it. I don't care how fast their cards are, I'll never make the mistake of buying nVidia again. Stick with the more open 3dfx, or Matrox. With them, if it crashes, you can track the bug down and fix it! Or someone else can. The number of open source hackers that might fix a bug are much, much larger than the number of employees at nVivia working on drivers.
--Bob
1^2=1; (-1)^2=1; 1^2=(-1)^2; 1=-1; 1=0.
I think that with all this new 3D hardware that has come out in the last 6 months, and then the addition of the rumor of this chip, developers are going to have a hard time actually creating worlds complex enough for gamers to actually tell the difference in what card they are using.
For example, this chipset is 7 times faster in rendering complex scenes, but only 2 times faster for rendering simple 3D scenes. I know that things like shadowing and lighting effects can be built into the gaming engine, but, still, isn't there a lot left to the developer's imagination (such as actually modeling and skinning characters and the objects in the world)? I can see this bumping up the development time for games slightly more every 6 months...
Friends don't let friends use multiple inheritance.