The shining point of GeForce3 at present
tnaw_xtennis 2001.03.02

With the feature of full DirectX 8.0 compliant, GeForce3 will be undoubtedly a great video card for tomorrow. The core/memory speeds of GeForce3 (200MHz/230MHz) are no any faster than those of GeForce2 Ultra (250MHz/230MHz), still GeForce3 that ties to its innovation antialiasing and memory architecture brings end user nowadays a praiseworthy performance boost over GeForc2 Ultra.

The antialiasing performance is the most shining point of GeForce3. Benefit by both of the Quincunx AA mode and the high profitability memory bandwidth interface (Table 1.), GeForce3 run today games with Quincunx antialiasing enabled almost twice as fast as the GeForce2 Ultra with 4xFSAA(Supersampling) under the same situation (Table 2.). It is interesting to note that the new memory bandwidth interface to be extremely in favor of antialiasing fulfillment of GeForce3. The known benchmarking results (Table 2.) show that there is about +10% performance boost of GeForce3 over GeForce2 Ultra under the normal conditions, while we get a performance boost as high as over +50% with antialiasing enabled.

Count the number of pins on the chip showed in Table3, you should find that there are 208 extra pins on the GeForce3 chip (700 pins) comparing with GeForce2 chip (492 pin). Will there be a 256bit DDR memory interface version of GeForce3 in a few months?
 

Table 1. Advanced Memory Interface of GeForce3

GeForce3 Lightspeed Memory Architecture Illustration GeForce3 / GeForce2
Memory Bandwidth Efficiency
Crossbar Memory Controller
( Memory controller that is optimized for accessing data with a fine granularity access pattern, ensuring that less fractions of the memory bandwidth is wasted when accessing small datasets. )
1 : 1
4 : 1

Lossless Z Compression
( 4:1 lossless data compresses and decompresses by video chip hardware in real time, thus the memory bandwidth consumed by Z-buffer traffic is reduced by a factor of four. )

4 : 1
Z-Occlusion Culling
( A hidden surface removal (HSR) rendering mechanism that reduces memory bandwidth requirements by avoiding having to access pixels that would not be visible. )
it can demonstrate as much as four times the performance of traditional rendering mechanism, while in practice the typical benefit of it averages a 50%-100% improvement. ( 2 ~ 4 ) : 1

 

Table 2. Quake3 (color depth:32bit) Benchmarking Results of GeForce3

Source Video Card 1024x768 1024x768 2xFSAA 1024x768 Quincunx AA 1024x768 4xFSAA 1600x1200
NVIDIA GeForce2 Ultra / / / 34 /
GeForce3 / 85 71 51 /
Tomshardware GeForce3 159 85 72 51 /
Digit-life GeForce2 Ultra 117 52 / 33 /
GeForce3 128 85 71 51 /
PC Professionale GeForce2 Ultra 108 / / / 55
GeForce3 118 / / / 61

 

Table 3. Pins on Chip of GeForce3 and GeForce2

GeForce3
GeForce3

GeForce2
GeForce2

 

Turning your GeForce/GeForce2 into a Quadro/Quadro2

Pentium 4 1.5GHz or Athlon Thunderbird 1.2GHz (DDR) ( 2000/11/28 )

Calculating the Potentiality of Your GeForce2 ( 2000/12/26 )

Sidelights of Voodoo5 6000 ( 2001-02-08 )

Video Core and Memory Speed of GeForce3 ( 2001-02-21 )