Slashdot Mirror
Nvidia Talks About Next-Gen Geforce, Plus Pics
Per Hansson writes "Techspot was at Comdex in Sweden a few days ago; we have now posted a small interview with Nvidia along with some high-res pictures of the Geforce FX on this page in our new comments system." This is one of the strangest looking video cards I've ever seen (and it isn't cheap), though it may look different by the time you can buy it in a box. Which is not yet, despite all the hype.
This is "market specific?" What market? Ill tell you this, They best not think people will go for a 2 slot card for "heat management". I do agree with the passive heat sinks on the reverse though, very good idea!
Obviously this is a first crack at the FX. I'd bet serious money that within six months of its release, a version will be ready that requires only one slot. Consumers hate incoveniences like this -- what if a cap on the motherboard gets in the way of one slot? Moreover, those who wait six months are more likely to be price-conscious consumers -- which means their systems are less likely to have gobs of space open (cheaper mobos = fewer slots).
Still, I want one. Now.
Make cheese not war 8:)
What are we up to now? Three months to obsolescence? It was just last Fall that we heard about the ultra-mega-super Radeon 9700 that could render 47umptyzillion somethingorothers every picosecond (only $400 while supplies last)?
I wonder if we're ever going to get to a point where "this is the hardware. You have 10 years to do something cool with it" instead of "oh, look, your program is obsolete again! Your graphics are dated! Another 10 man-years down the drain! Place your bets... (spin)"
sigh...
LadyStar - Your Magical and Mysterious Adventure Awaits
The Inquirer has an article that takes a look at the GeForceFX. Hopefully things won't turn out as they did for 3DFX.
The dogcow says "Moof!"
Honestly, there's gotta be a smarter way to cool that thing than a huge, ugly, entire-slot-using heatpipe. Either that, or developing a new way to crunch graphics numbers other than using a single chip..... SLI on one card using two slightly slower chips? Power consumption would go up, but you could use floppy power connectors in lieu of a new bus solution that provides more voltage grunt, and it'd be easier to cool.
Why don't manufacturers start doing dual-DVI outputs? Granted, most LCD's have a second analog input, but what's the point of having one DVI output then?
I wish they'd start putting dual-DVI outputs on them. Maybe one of the other companies that makes them (MSI, PNY, Leadtek, etc) will offer one finally. AFAIK they don't even offer a hydrahead adapter for the one DVI port to split to two (doubt its possible without a proprietary output like the Radeon VE's).
THE MAGIC WORDS ARE SQUEAMISH OSSIFRAGE
I wonder if we're ever going to get to a point where "this is the hardware. You have 10 years to do something cool with it"
Only when, if ever, we can render something like the Final Fantasy movie in real-time. Something tells me Moore's "law" will have broken down before that though.
Kjella
Live today, because you never know what tomorrow brings
In my day, video cards didn't even use these new-fangled slot whatsits. We didn't even have monitors back then - the video card had to do all the drawing and thne DISPLAY it to us as well. And we didn't have RAM or ROM either, so we had to remember each byte ourselves and give it to the video card when necessary. Not that it ever TOLD you when it needed a byte, OR which byte it needed. You had to memorise the order in which bytes were required - the list was provided in invisible ink on the back of the installation manual (which we DIDN'T have) and it was written in reverse-polish ascii pseudo-hexadecimal with a Russian accent. AND it could do everything we needed! And it didn't even need a heatsink (but the horses that powered it did need a break every now and then, and you had to train them not to go potty on the computer ... that was a real CORE DUMP)
This sig intentionally left bla... dammit!
Who's got the whiteout?
I've just put together a new computer an Nvidia nforce2 ASUS A7N8X motherboard, and you know how many PCI slots I use? None. My video uses the AGP, but then sound is on board (and it's good), usb/firewire/serial-ATA RAID/regular ATA, etc are all on board PLUS two NICs. Sure, I could add SCSI (but how many home users do?), or a TV tuner (already built in to my video card), or a variety of other things, but I really have no need for these PCI slots. I'm surviving quite well without them.
http://www6.tomshardware.com/graphic/20021118/gefo rcefx-03.html
the most complex games, on the highest resolutions, get WAY too many frames
you're kidding me, right? Get UT2003 in 1600x1200 with everything maxed out and even on a 9700pro you won't see more than 30 or so fps on certain maps (alone, just looking around, in heavy firefights I'd suspect it'll drop to the teens: I don't have a system like that but I'm basing this on vidcaps I saw when UT came out).
Human eye is unable to perceive extra frames beyond a certain number
bs, it also really depends on what you're doing. If you're in a driving game going straight ahead and you get 30fps, you *might* not notice the difference between your 30 and 90fps. In a shooter or other game where the screen moves around quite a bit, I'm sorry but I can see the difference between 30fps and 70fps quite easily...
The moment somebody creates a card that is able to mantain refresh-rate-synced-updates (say 85fps) in any available game at any resolution regardless of what is going on, it's the moment a new game will be announced that will take a card 4x as powerful to do the same.
It really never ends... of course if all you'd like to do is play counterstrike you can get by quite well like myself with a really old p3-450 + geforce1.
-- the cake is a lie
Its true that there's a maximum frame-rate that the human brain (not eye) can perceive. Its somewhere between 60-120 in most humans. Film is displayed [in the US] at 24 frames per second, video is 29.97. This leads to the common misconception that 30fps is the max framerate that means anything.
There is also the fact that these are "average" frame rates: if your average fps is 30, you're going to quite often be getting sub-30 fps, resulting in jerkiness. So the ideal FPS is somewhere around an average of 75-135, so as to remain in perfect smoothness. (this refers to your question about why a gamer would want a new card).
"Stumble before you crawl"
If I zoom in will I be able to see the blood pumping through it's wings?
Or a bunch of flowers.
Is each individual pollen grain to be described?
Will the water eventually splash?
There are places where the networks are not touching,and there are places where they are-Boeing's Lori Gunter
The GeForce FX is in my opinion, not going to be what the world has expected from nVidia. It is simply too little, too late - 6 months too late. It may have the performance crown for a month, but it will be short-lived.
.13u process. In case some people haven't noticed, the leaked benchmarks of the GeForce FX show it to only be marginally faster than the Radeon 9700 Pro. Not to mention that it's 500MHz vs. 325MHz. It seems that ATI is faster in terms of IPC's.
ATI will simply respond with the R350, which is likely going to be an improved R300 core, as well as DDR2 and manufactured with the
It would be unfeasible for nVidia to respond until the summer with the NV31/34, at which time ATI will announce the R400.
I will have to give nVidia one thing though, their drivers are excellent. This is perhaps the only thing they have going for them at the moment. However, ATI is pumping out a new driver set almost every month, and at this rate, they will soon reach parity with nVidia.
Oh, a quick addendum re: fps.
Part of why film [at the aformentioned 24fps] seems smooth is that motion blur is recorded on the film: when an object is moving too quickly for hte light to capture a still image on the film [due to exposure], it captures a blur. Our brain loves to use that blur to assemble motion. Since computers lack this motion blur, they need more fps.
"Stumble before you crawl"
The Inquirer has an article [theinquirer.net] that takes a look at the GeForceFX. Hopefully things won't turn out as they did for 3DFX.
Disclaimer: I have no idea about the economic status of Nvidia. But I do see them in pretty much every computer advertized, and they've generally delivered very successful products since the first Geforce chip, so I assume they got a strong finacial position. And if you can't solve it even if you got more money to throw after it than the rest, well maybe you deserve being dethroned. That's what competition is all about, isn't it?
Kjella
Live today, because you never know what tomorrow brings
People call liquid cooling dangerious, unneccesary, and extravigant, and then buy video cards that have cooling such as this one, cpu coolers that are enormious, and put half a dozen case fans in their case to try to keep the temperature down.
I do security
This sounds just like what caused the death-knell of 3DFX: company bets the bank to make a monster video card that blows everything out of the water, and holds off on a whole scheduled version release (once every 18 months) to make this monster card... and blows it big time.
3DFX used to compete with NVIDIA. When NVIDIA released a new line of cards, so did 3DFX, or when 3DFX released a new line of cards first, so did NVIDIA.
When the GeForce2 cards came out, everyone waited for 3DFX to release their competitive line. About 4 months later, 3DFX released a couple Voodoo4 cards, but not much in the way of competition, and nothing spectacularly advanced above the Voodoo3's. However, they also let out news of plans to make a market breaker card, the Voodoo 5-6000, which would take up fall case length (and bump harddrives), have 5 fans on it, and require an external wallwart-style DC adaptor for power supply. It was a $600 card meant for the mega-gamers and graphic designers out there. This was a huge card... and their biggest flop, for once it came out, NVIDIA was already releasing the GeForce3's which had better specs and lower prices overall.
Now, Nvidia does something just like that. This card is double-height (the second slot worth is ducting for external air intake and exhaust) and is full case length. It's got monster specs, and has thrown off their regular 18-month cycle of new cards. This new one is $600 as well.
Sounds to me like some of the execs of 3DFX have gotten on the board of NVIDIA via the buyout, and are trying to make another Voodoo5-6000. I hope it doesn't end the same way, with this company going down the tubes as well.
Building in a cooling solution like that which is totally unrepairable by the end user is a great way to build in forced-obsolescence.
I think I'll stick with my radeon. If the fan quits, I'll just replenish the oil.
Kudos to Nvidia, though, for finding a way to force their users to buy new cards in the future! This'll certainly be the wave of the future, like fibreglass bodies on cars!
If you could be told what you can see or read, then it follows that you could be told what to say or think - BoC
I wonder if they are coming out with a laptop model also... =P
Check out some of the equipment from Sun Microsystems, SGI, IBM, and Stereographics.
A bunch of their equipment is designed for a 10 year obsoletion-cycle. Cost's a hefty penny, though. Designed for business and major research universities.
At the University, we were using Creator3D graphics cards from Sun Microsystems. That was in 1999, and the general consumer market still hasn't caught up with that tech. Me, I'm still looking around for auto-stereoscopic monitors. Sharp is coming out with a consumer model next year, I hear.
it's called silicon real-estate.
it's also called packaging cost.
it's called data routing on the board (FR4 is very, very slow unless you use a LOT of traces, which is very, very diffcult).
I think it may also be called lower MTBF.
and how about "debugging is a pain?"
either way, though - don't expect "multi-processing" on but the most high-end incarnations - when they have squeezed out of every bit of performance per-chip.
My life in the land of the rising sun.
While all of the modern 3D chipsets have impressive frame rates for running 3D games they tend to suck badly for much of anything else.
The chips are very slow to switch from text to graphics and vice versa.
I had a board with a slightly older Nvidia chip set. I wasn't very satisfied with the stability of the Xfree drivers for it so I tried the Nvidia Linux drivers. Their driver took five minutes to switch between text and graphics modes.
Older chipsets were much more practical for day to day use; the super speed models remind me of trying to drive a AA fuel dragster to the office every day.
Actually, this goes out to all the video card manufacturers..
Why hasn't anyone put the GPU on the OPPOSITE side of the card yet? Every AGP card I see, the GPU is ALWAYS facing towards the PCI slots in the system where it.
A. Blocks out other PCI cards
B. The fan causes noise and instability if it is running too close
C. It exhaust the heat onto those other cards.
Instead of trying to put the carridge before the horse, why not just mount the GPU on the opposite side? There's no PCI slots to get in the way, and you could fit a HUGE cooling solution there.
Hey Nvidia if you want to hire someone with more common sense design tips like this i'm availiable. I'll slap your engineers with a cluestick for ya.
Once again, we're seeing a very elaborate (and ungainly) design for the next ultra high power graphics chip. As technology progresses, we're accustomed (as it should be) to the new products to be the same physical dimension (or smaller) as the older products. This is how we have such concepts as the PDA, the microATX form factor, just to name a few.
The graphics card arena has been a major exception to this for the last few years. It's one of the few industries that I can think of where the product is actually GROWING in size and becoming more combersome as the technology becomes increasingly faster and more complex. I believe this is a sign that, not unlike how we discovered in the Pentium II/III era, that card/based processor packages are poor product design that are a) larger than necessary b)gum up the works, and c) only enhance the problem of cooling, thus needing continuingly more complex cooling systems.
The current AGP(or PCI or whatever) bus expansion card methodology for video cards can be seen as going through the same problem, especially in the case of the GeForceFX. We've seen these problems previously in the designs for the GeForce3,4, made much fun of them in the case of the 3dfx Voodoo5 6000 cards, and even the latest ATI cards are requiring more power than the AGP bus can provide. Doesn't this show that there is an inherent flaw in the packaging design for this technology?
GPUs need to take the same road that CPUs have taken (and now restored since we now use socket based motherboard solutions again) and be sold soley as the graphics processor, with the memory substructures and soforth built onto the motherboard. This increases the efficiency and ease that the GPU can communicate with the central bus and the rest of the system. In addition, you will no longer need to build an elaborate cooling strucutre to make up for the lack of ventilation provided by the typical AGP/PCI card slot design.
Nvidia is part way there with the NForce already, building the graphics subsystem as a central part of the motherboard chipset and PC bus, but the flaw here remains (as in most integrated motherboard systems) that you are stuck with the technology. Of course, you can upgrade an NForce system with a full GeForce4 FX or Radeon if that is your choosing, but that just brings back the card problem. What needs to be done is to create a NForce type chipset with an FCPGA type socket for the GPU as well as the CPU, that way both systems are imminently upgradable (not to mention the potential benefits in creating a more efficient in-line cooling solution for the interior of the system) and thus our size problems begin to be alleviated.
-Julius X
remove "-whatkindofspamdoyoutakemefor-" from email to send
I thought I'd take a
picture and make a rebuttal to your statement. Gotta love digital.
In this pic there are 5 mobo's.
Intel 850GB
Some asus socket370 thing
Some soyo socket370 thing
Iwill BD100 slot1
Some intel socket370 thing
You will notice on the asus board I put a tape measure across as a reference.
Now out of the 5 boards sampled, only 1 has no space for heatsinks on the right
side. Also to note this board is a slot1, which is no longer in production.
On the other hand, every single semi modern board in this picture has more
than adequate room for heatsinks on the right side.
So unless these newer cards are going into an outdated system, putting the
fans/heatsinks on the right side shouldn't be a problem right? Simple enough
solution without having to resort to heat pipes/water cooling or peizo electric
cooling.
"How cool, a video card with what looks like a trojan stretched over it for safe gaming."
How apt!
- - - - - - - -
Don't worry, being eaten by a crocodile is just like going to sleep in a giant blender.
bs, it also really depends on what you're doing. If you're in a driving game going straight ahead and you get 30fps, you *might* not notice the difference between your 30 and 90fps. In a shooter or other game where the screen moves around quite a bit, I'm sorry but I can see the difference between 30fps and 70fps quite easily...
It's interesting to note that the US military has done extensive testing in this area, specifically so that they can build simulators as absolutely 'real' as possible, and not produce any extra frames (and the increased cost involved in delivering them). According to a few engineers from Evans and Sutherland, who at least used to build the image generators for them, the vast majority of fighter pilots were unable to distinguish between framerates above 60fps.
Of course, then there's the whole 'aliasing' you get whenever you actually have a 'frame-based' video, compared with 'real life'. Case in point: Ever notice how helicopter blades, propellors, wheels, etc. seem to spin 'backwards' on TV? It's sample aliasing. Even your own eyes see this whenever your light source 'blinks', which is the case in nearly all artificial light. Take a bicycle tire, put it between your eyes and a flourescent light, and spin it; you'll see the aliasing artifacts with no problems. Take the same bicycle tire outside (in sunlight), and do the same thing-- no more aliasing!
To realistically remove all aliasing, we'd have to have much higher framerates than 60fps; however, it's generally considered a 'normal' thing, since we grew up seeing it, and nobody fusses about it.
-- Sometimes you have to turn the lights off in order to see.
I remember reading that John C is going to cap the FPS on Doom3 to like 30 or 40 FPS per seconds. I'm hoping so, I bet he is tired of people grading video cards by how many FPS they can get Quake 3 running.
The best thing about the FX isn't the overall FPS per second. It is the pixel shaders and such. The number of instructions it can excute per shader, and the rate at which it processes these is the real evolution of this card. The more complex the shader and the faster they run the more life like graphics will look.
We have been stuck in the same basic quake engine for a while now. Unreal II and Doom 3 ( doom3 more ) will be the first real change in graphics we've had. Now the GPU's can handle movie style rendering, without a ton of little tricks.
We really do need the horse power. The FX could probably render toy story in real time, that is pretty amazing. I can't wait till I can watch a movie and pause it and change the angle. The ability to have true 3-d movie projection is becoming more realistic with this type of hardware ( of course we need the 3d projector )
$400 dollars for this is nothing. You don't seem to realize that just 10 years ago a 486 DX system could cost over $4000 grand. With 16 megs of ram and 1/2 gig of harddrive. The price is rather low considering what it takes to create such wonders, stop bitchin.
Open source will help out in this arena as well. You got to think that the pros that did the work on Golem for LOTR are fans of open source, it won't be long until those kinds of shaders and techniques will be available for game programmers.
To me saying "why do we need all this power" is kind of sacreligous. Remember that increasing speed and creating a market for new hardware is what keeps most of us employeed. Never say more speed is a bad thing. And don't blame sluggish performance on the developers, as software becomes more complex you have to give up some performance for stability and expandability.
That's Quake IV or DOOM III.
:)
Personally, the day Quake III comes out is the day I upgrade my video card.
Well, you're a couple years late, better hurry!
Oh for christs sake, the damn thing is priced at ATI 9700 Pro prices. I have no idea why the prices are so high for Europe (sorry), maybe the original post is way out of date.
Best Buy preorder
[RIAA] says its concern is artists. That's true, in just the sense that a cattle rancher is concerned about its cattle.
nvidia has lost this and probably the next generation of 3D to ATI. ATI's Radeon 9{5|7}00 is a very good card. Superior to the GeForce4. By the time the GeForceFX is released, ATI will have their next-generation chipset prepared. nvidia will be a generation behind. ATI cards are already close in price to their nvidia bretheren. nvidia needs a new product to get the performance crown back, or ATI will dominate.
Slashdot is a waste of time. I enjoy wasting time.
These shots were done with this card
autopr0n is like, down and stuff.
"Huh? That's how I get my dual monitor setup; geforce in the agp, old pci gfx card in the 1st pci slot (some cards still complain if they're not in the first slot). Losing my first pci slot is NOT worth it, as I need my second monitor for photoshopping and 3dsmax."
Starting at $150 you can get NVidia Geforce cards that natively support dual monitor, even if they have the DVI output on the back. You just need an adapter to go from DVI to Analog.
I am running a Geforce 4 TI 4600 right now with dual monitors at 1600 by 1200, works great. Before I was using an Xtasy Geforce 4 MX that had two analog ports, it worked great as well. Get one of those cards, plug both your monitors into them, and you won't regret it. As a bonus, keep your PCI card and you can plug a 3rd monitor in. I have a friend that's doing that today. He seriously has 3 monitors hooked up that way.
Speaking of motion blur brings to mind other practical uses for an accumulation buffer...
I wonder why today's uber-fast video cards don't offer temporal anti-aliasing to use with older, slower flat panels (that are in the 20 to 30 Hz max refresh region). Three to five consecutive frames blended together, then the result output at the slow refresh, and it wouldn't feel so slow at all. No jerkiness, no tails on screen, just steady going, smooth looking display.
I'd like to be offered that option. And plenty of those kind of panels around! (As to video cards, AFAIK, accumulation buffer has been part of the DX spec for some time. In OGL a very long time.)
But I wasn't talking about motion blur. I'm talking about TAA
I thought TAA and motion blur were the same thing, as this page seems to imply. Is there a difference?
I meant that it should be offered as a choice in the video card drivers. Much like Nvidia etc. offer enforced spatial anti-aliasing (FSAA)
The OpenGL rendering model introduces a big difference between spatial effects and temporal effects. The coordinates passed to OpenGL are three-dimensional (x, y, z), not four-dimensional (x, y, z, t)[1]. In OpenGL's coordinate space, coordinates of individual polygons within a rendered scene can be considered continuous. Only the rasterizer breaks this continuity, and a video card can choose traditional rasterization or FSAA rasterization because it has access to the (x, y) coordinates for interpolation within a pixel. On the other hand, OpenGL time is discrete, and each frame is considered a separate scene. There's no way to automatically map which polygons in one scene correspond to which polygons in another scene, so there's no way to interpolate an edge's coordinates along the fourth dimension.
[1] 't' (the time dimension) has nothing to do with 'w' (the homogenizing factor in homogeneous coordinates).
Will I retire or break 10K?