GeForce3: Real-time RenderMan?
b0ris writes "This review of the NVIDIA GeForce3 at The Tech Report does a nice job explaining how the GF3 chip can create advanced graphics effects in real time. The author raises the prospect of having real-time Final Fantasy or Shrek-style animation on the desktop in a consumer graphics card. The examples from the GF3 he uses to back it up are almost convincing, even if it isn't quite there yet. Will render farms go the way of the dodo?" Well, I'm all for dreaming, but its gonna be a few years before the GeForce8 can do renderman in real time, but when we get there, Final Fantasy 21 is gonna rule.
Most of what we see with "realistic rendering" on desktop boxes is OpenGL / direct3d based. This isn't realy rendering, well... its not raytraced.
Its true that they are getting close and blurring the line between rendering and desktop 3D for all practical purposes there is a difference.
I just hope rendering never goes away... I need this job!
Another difference is that game movement is not near as complex as cinematic animation. Most game movement is pre-definded movements trigered by something. A lot of secondary animation and even some primary animation is done by a complicated set of equations. It all depends on the package, but sometimes with these solvers on, you might get 1 fps when viewing the animation. Until issues like that are fixed, you will not be able to generate stuff like that on the fly.
-I just work here... how am I supposed to know?
Achieving Pixar-level animation in real-time has been an industry dream for years. With twice the performance of the GeForce 256 and per-pixel shading technology, the GeForce2 GTS is a major step toward achieving that goal.
-Jen-Hsun Huang, President of NVIDIA Corp.
Here is what Tom Duff from Pixar thinks about that:
These guys just have no idea what goes into `Pixar-level animation.' (That's not quite fair, their engineers do, they come and visit all the time. But their managers and marketing monkeys haven't a clue, or possibly just think that you don't.)
`Pixar-level animation' runs about 8 hundred thousand times slower than real-time on our renderfarm cpus. (I'm guessing. There's about 1000 cpus in the renderfarm and I guess we could produce all the frames in TS2 in about 50 days of renderfarm time. That comes to 1.2 million cpu hours for a 1.5 hour movie. That lags real time by a factor of 800,000.)
Do you really believe that their toy is a million times faster than one of the cpus on our Ultra Sparc servers? What's the chance that we wouldn't put one of these babies on every desk in the building? They cost a couple of hundred bucks, right? Why hasn't NVIDIA tried to give us a carton of these things? -- think of the publicity milage they could get out of it!
Don't forget that the scene descriptions of TS2 frames average between 500MB and 1GB. The data rate required to read the data in real time is at least 96Gb/sec. Think your AGP port can do that? Think again. 96 Gb/sec means that if they clock data in at 250 MHz, they need a bus 384 bits wide [this is typo. 384 _bytes_ wide!]. NBL!
At Moore's Law-like rates (a factor of 10 in 5 years), even if the hardware they have today is 80 times more powerful than what we use now, it will take them 20 years before they can do the frames we do today in real time. And 20 years from now, Pixar won't be even remotely interested in TS2-level images, and I'll be retired, sitting on the front porch and picking my banjo, laughing at the same press release, recycled by NVIDIA's heirs and assigns.
Vermifax
Vermifax
Logout
"10,000 spoons when all you want is a knife", how is that ironic? It would only be ironic if later you discovered that a spoon would have done just as well for say, opening a can of paint.
A journey of a thousand miles starts with a brutal anal raping at airport security