The Pro Market And Workstation Graphics Technology
Where do we stand technologically? Product cycles in professional cards like these move more slowly than in the mainstream segment. Thus, Nvidia has already introduced the GeForce GTX 280 to the market, which is based on the GT200 graphic chip with a manufacturing process of 65 nanometers. The top-of-the-line model introduced here, the Quadro FX 5600, is still based on the G80 at 90 nanometers. Nvidia already took two intermediate steps by developing the G84, G86 and G92 at 80 nm and 65 nm.
With regard to manufacturing processes, AMD has the advantage, as the FireGL V7700 is already produced at 55 nm. With the presentation of the Radeon HD 4000-series, AMD has already arrived with the RV770, which is employed in the HD 4850 and HD 4870.
Perhaps you can get to know more about future FireGL and Quadro products from this year’s Siggraph. We would also like to point out two interesting software initiatives. For more information on Nvidia’s CUDA platform, check out this story. The competition counters with its own Stream Computing program.
Editor’s note: It’s also important to point out that most workstation customers are still using Windows XP, as the move to Vista—especially in the professional space—is still happening very slowly.
| Workstation-Model | Chip-Basis | Fab | Mainstream-Equivalent | Graphics Memory | 3-Pin Stereo | Display Port |
| ATi FireGL V8650 | R600 | 80 nm | Radeon HD 2900 XT | 2048 MB GDDR4 | yes | no |
| ATi FireGL V8600 | R600 | 80 nm | Radeon HD 2900 XT | 1024 MB GDDR4 | yes | no |
| ATi FireGL V7700 | RV670 | 55 nm | Radeon HD 3850 | 512 MB GDDR4 | yes | yes |
| ATi FireGL V7600 | R600 | 80 nm | Radeon HD 2900 | 512 MB GDDR3 | yes | no |
| ATi FireGL V7300 | R520 | 90 nm | Radeon X1800 | 512 MB GDDR3 | yes | no |
| ATi FireGL V5600 | RV630 | 65 nm | Radeon HD 2600 XT | 512 MB GDDR4 | no | no |
| ATi FireGL V3600 | RV630 | 65 nm | Radeon HD 2600 Pro | 256 MB DDR2 | no | no |
| Nvidia Quadro FX 5600 | G80 | 90 nm | GeForce 8800 | 1536 MB GDDR3 | yes | no |
| Nvidia Quadro FX 4600 | G80 | 90 nm | GeForce 8800 | 768 MB GDDR3 | yes | no |
| Nvidia Quadro FX 4500 | G70 | 110 nm | GeForce 7800 | 512 MB GDDR3 | yes | no |
| Nvidia Quadro FX 1700 | G84 | 80 nm | GeForce 8600 | 512 MB DDR2 | yes | no |
| Nvidia Quadro FX 570 | G84 | 80 nm | GeForce 8600 | 256 MB DDR2 | no | no |
| Nvidia Quadro FX 370 | G84 | 80 nm | GeForce 8600 | 256 MB DDR2 | no | no |
| Workstation-Model | Memory Bandwidth | DirectX | OpenGL | Shader Model | Core Clock | Memory Clock | Pixel & Vertex Processing |
|---|---|---|---|---|---|---|---|
| ATi FireGL V8650 | 111 GB/s | 10 | 2.1 | 4.0 | 675 MHz | 868 MHz | 320 SPUs |
| ATi FireGL V8600 | 111 GB/s | 10 | 2.1 | 4.0 | 675 MHz | 868 MHz | 320 SPUs |
| ATi FireGL V7700 | 72,0 GB/s | 10.1 | 2.1 | 4.0 | 775 MHz | 1125 MHz | 320 SPUs |
| ATi FireGL V7600 | 51,0 GB/s | 10 | 2.1 | 4.0 | 500 MHz | 510 MHz | 320 SPUs |
| ATi FireGL V7300 | 41,6 GB/s | 9.0c | 2.0 | 3.0 | 600 MHz | 650 MHz | 16 P / 8 V |
| ATi FireGL V5600 | 35,1 GB/s | 10 | 2.1 | 4.0 | 800 MHz | 1100 MHz | 120 SPUs |
| ATi FireGL V3600 | 15,8 GB/s | 10 | 2.1 | 4.0 | 600 MHz | 500 MHz | 120 SPUs |
| Nvidia Quadro FX 5600 | 76,8 GB/s | 10 | 2.1 | 4.0 | 600 MHz | 800 MHz | 112 SPUs |
| Nvidia Quadro FX 4600 | 67,2 GB/s | 10 | 2.1 | 4.0 | 500 MHz | 700 MHz | 112 SPUs |
| Nvidia Quadro FX 4500 | 33,6 GB/s | 9.0c | 2.0 | 3.0 | 430 MHz | 525 MHz | 24 P / 8 V |
| Nvidia Quadro FX 1700 | 12,8 GB/s | 10 | 2.1 | 4.0 | 460 MHz | 400 MHz | 32 SPUs |
| Nvidia Quadro FX 570 | 12,8 GB/s | 10 | 2.1 | 4.0 | 460 MHz | 400 MHz | 16 SPUs |
| Nvidia Quadro FX 370 | 6,4 GB/s | 10 | 2.1 | 4.0 | 360 MHz | 400 MHz | 16 SPUs |
Key: SPUs = Stream Processing Units; P = Pixel Shader; V = Vertex Shader