neeyik.info | ||||||||
![]() |
||||||||
The charts are categorised by the highest DirectX support the model offers - please use the links below to find the appropriate model. For information about what the specification terms mean, please click here. | ||||||||
DX6 or earlier | DX7 (TnL) | DX8 (SM1.1) | DX9 (SM2.0) | DX9 (SM3.0) | DX10 (SM4.0) | DX11 (SM5.0) | ||
Model | ATI | Matrox | ||||||
Radeon '256' SDR |
Radeon '256' DDR |
Radeon '256' LE |
Radeon 7200 |
Radeon 7500 |
All-in-Wonder | G550 | ||
Core | ||||||||
Codename | R100 | R100 | R100 | R100 | RV200 | R100 | ? | |
Process scale (nm) | 180 | 180 | 180 | 180 | 150 | 180 | 180 | |
Transistor count (millions) | 30 | 30 | 30 | 30 | 30 | 30 | ~ 30? | |
Core clock speed (MHz) | 166 | 183 | 148 | 166 | 290 | up to 183 | 126 | |
Vertex processing pipelines | 1 | 1 | 1 | 1 | 1 | 1 | 1 | |
Vertex shader version (best) 1 | TnL | TnL | TnL | TnL | TnL | TnL | TnL | |
Pixel processing pipelines | 2 | 2 | 2 | 2 | 2 | 2 | 2 | |
Total effective no. of texture units | 6 | 6 | 6 | 6 | 6 | 6 | 2 | |
Max pixels output per clock (colour/depth) | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | |
Pixel shader version (best) | - | - | - | - | - | - | - | |
Overall DirectX level | 7 | 7 | 7 | 7 | 7 | 7 | 7 | |
Memory | ||||||||
Interface width (bits) | 128 | 128 | 128 | 128 | 128 | 128 | 64 | |
Interface type | SDR | GDDR | GDDR | SDR | GDDR | SDR / GDDR | GDDR | |
Clock speed (MHz) | 166 | 183 | 148 | 166 | 230 | up to 183 | 166 | |
Theoretical Peak Performance | ||||||||
Vertex processing rate (Mtis/sec) | 27 | 30 | 24 | 30 | 45 | up to 30 | ~ 20? | |
Pixel processing rate (Mpixels/sec) | 333 | 366 | 296 | 333 | 580 | up to 366 | 252 | |
Texel applied rate (Mtexels/sec) | 999 | 2199 | 888 | 999 | 1740 | up to 2199 | 504 | |
Pixel output rate (Mpixels/sec) | 333 | 366 | 296 | 333 | 580 | up to 366 | 252 | |
Memory bandwidth (GB/sec) | 2.66 | 5.86 | 4.74 | 2.66 | 7.36 | up to 5.86 | 2.66 | |
Model | NVIDIA | |||||||
GeForce '256' SDR |
GeForce '256' DDR |
GeForce2 GTS |
GeForce2 Pro |
GeForce2 Ultra |
GeForce2 Ti |
GeForce2 MX |
GeForce2 MX200 |
|
Core | ||||||||
Codename | NV10 | NV10 | NV15 | NV15 | NV16 | NV15 | NV11 | NV11 |
Process scale (nm) | 220 | 220 | 180 | 180 | 180 | 150 | 180 | 180 |
Transistor count (millions) | 23 | 23 | 25 | 25 | 25 | 25 | ~20 | ~20 |
Core clock speed (MHz) | 120 | 120 | 200 | 200 | 250 | 250 | 175 | 175 |
Vertex processing pipelines | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
Vertex shader version (best) 1 | TnL | TnL | TnL | TnL | TnL | TnL | TnL | TnL |
Pixel processing pipelines | 4 | 4 | 4 | 4 | 4 | 4 | 2 | 2 |
Total effective no. of texture units | 4 | 4 | 8 | 8 | 8 | 8 | 4 | 4 |
Max pixels output per clock (colour/depth) | 4 / 4 | 4 / 4 | 4 / 4 | 4 / 4 | 4 / 4 | 4 / 4 | 2 / 2 | 2 / 2 |
Pixel shader version (best) | - | - | - | - | - | - | - | - |
Overall DirectX level | 7 | 7 | 7 | 7 | 7 | 7 | 7 | 7 |
Memory | ||||||||
Interface width (bits) | 128 | 128 | 128 | 128 | 128 | 128 | 128 | 64 |
Interface type | SDR | GDDR | GDDR | GDDR | GDDR | GDDR | SDR | SDR |
Clock speed (MHz) | 166 | 150 | 166 | 200 | 230 | 200 | 166 | 166 |
Theoretical Peak Performance | ||||||||
Vertex processing rate (Mverts/sec) | 15 | 15 | 25 | 25 | 31 | 31 | 20 | 20 |
Pixel processing rate (Mpixels/sec) | 480 | 480 | 800 | 800 | 1000 | 1000 | 350 | 350 |
Texel applied rate (Mtexels/sec) | 480 | 480 | 1600 | 1600 | 2000 | 2000 | 700 | 700 |
Pixel output rate (Mpixels/sec) | 480 | 480 | 800 | 800 | 800 | 1000 | 350 | 350 |
Memory bandwidth (GB/sec) | 2.66 | 4.80 | 5.31 | 6.40 | 7.36 | 6.40 | 2.66 | 1.33 |
GeForce2 MX400 |
GeForce4 MX420 |
GeForce4 MX440 |
GeForce4 MX460 |
GeForce4 MX4000 |
GeForce PCX 4300 |
|||
Core | ||||||||
Codename | NV11 | NV17 | NV17 | NV17 | NV18 | NV18 | ||
Process scale (nm) | 350 | 150 | 150 | 150 | 150 | 150 | ||
Transistor count (millions) | ~20 | 29 | 29 | 29 | 29 | 29 | ||
Core clock speed (MHz) | 200 | 250 | 270 | 300 | 250 | 250? | ||
Vertex processing pipelines | 1 | 1 | 1 | 1 | 1 | 1 | ||
Vertex shader version (best) 1 | TnL | TnL | TnL | TnL | TnL | TnL | ||
Pixel processing pipelines | 2 | 2 | 2 | 2 | 2 | 2 | ||
Total effective no. of texture units | 4 | 4 | 4 | 4 | 4 | 4 | ||
Max pixels output per clock (colour/depth) | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | 2 / 2 | ||
Pixel shader version (best) | - | - | - | - | - | - | ||
Overall DirectX level | 7 | 7 | 7 | 7 | 7 | 7 | ||
Memory | ||||||||
Interface width (bits) | 128 | 128 | 128 | 128 | 64 | 128 | ||
Interface type | SDR | SDR | GDDR | GDDR | GDDR | GDDR | ||
Clock speed (MHz) | 166 | 166 | 200 | 275 | 200 | 200? | ||
Theoretical Peak Performance | ||||||||
Vertex processing rate (Mverts/sec) | 25 | 31 | 34 | 38 | 31 | 31? | ||
Pixel processing rate (Mpixels/sec) | 400 | 500 | 540 | 600 | 500 | 500? | ||
Texel applied rate (Mtexels/sec) | 800 | 1000 | 1080 | 1200 | 1000 | 1000? | ||
Pixel output rate (Mpixels/sec) | 400 | 500 | 540 | 600 | 500 | 500? | ||
Memory bandwidth (GB/sec) | 2.66 | 2.66 | 6.40 | 8.80 | 3.20 | 3.20? | ||
Model | S3 Graphics | SiS | |||||||
Savage XP | 315 | ||||||||
Core | |||||||||
Process scale (nm) | 180? | 150 | |||||||
Transistor count (millions) | 12~15? | 10~15? | |||||||
Core clock speed (MHz) | 166 | 166 | |||||||
Vertex processing pipelines | 1 | 1 | |||||||
Vertex shader version (best) 1 | TnL | TnL | |||||||
Pixel processing pipelines | 2 | 2 | |||||||
Total effective no. of texture units | 4 | 2 | |||||||
Max pixels output per clock (colour/depth) | 2 / 2 | 2 / 2 | |||||||
Pixel shader version (best) | - | - | |||||||
Overall DirectX level | 7 | 7 | |||||||
Memory | |||||||||
Interface width (bits) | 128 | 128 | |||||||
Interface type | GDDR | SDR | |||||||
Clock speed (MHz) | 166 | 1666 | |||||||
Theoretical Peak Performance | |||||||||
Vertex processing rate (Mverts/sec) | > 16 | > 15 | |||||||
Pixel processing rate (Mpixels/sec) | 333 | 333 | |||||||
Texel applied rate (Mtexels/sec) | 666 | 333 | |||||||
Pixel output rate (Mpixels/sec) | 333 | 333 | |||||||
Memory bandwidth (GB/sec) | 5.31 | 2.66 | |||||||
Notes |
1 - DirectX 7 compliant GPUs have dedicated hardware to
performing the transforming and lighting (hence, TnL) of vertices;
non-DX7 GPUs use the CPU to do this. |
3D Graphics Card Specifications - Copyright © - N D Evanson |