Master Video Card List
From WSGFWiki
Contents |
NVIDIA
GeForce 8-Series
Chipset Specs
Below are the standard (default) specifications for the NVIDIA 8-Series cards. The core and memory speeds are not universal as manufacturers can overclock the cards. What we are supplying are the numbers for the NVIDIA Reference Design. Remember, when the core and memory speed are increased so is the bandwidth.
| 8800 GTX Ultra | 8800 GTX | 8800 GTS | 8600 GTS | 8600 GT | 8500 GT | 8400 GS | |
|---|---|---|---|---|---|---|---|
| Core | G80 | G80 | G80 | G84 | G84 | G84 | G86 |
| Manufacturing Process (nm) | 90 | 90 | 90 | 80 | 80 | 80 | 80 |
| Number of Transistors (M) | 681 | 681 | 681 | 289 | 289 | 289 | 210 |
| Core Clocks (Core/Shader in MHz) | 612/1050 | 575/1350 | 500/1200 | 675/1450 | 540/1190 | 450/900 | 450/900 |
| Memory Clock (MHz / data rate) | 1080/2160 | 900/1800 | 800/1600 | 1000/2000 | 700/1400 | 400/800 | 400/800 |
| RAMDACs (MHz) | 400 | 400 | 400 | 400 | 400 | 400 | 400 |
| Stream Processors (#) | 128 | 128 | 96 | 32 | 32 | 16 | 16 |
| Memory Interface (GDDR3) | 384-bit | 384-bit | 320-bit | 128-bit | 128-bit | 128-bit | 64-bit |
| Frame Buffer Size (MB) | 768MB | 768MB | 640/320MB | 256MB | 256MB | 256MB | 256MB/128MB |
| Memory Bandwidth (GB/s) | 103.7 | 86.4 | 64 | 32 | 22.4 | 12.8 | 6.4 |
| Textures/Seconds (B/sec) | 39.2 | 36.8 | 24 | 10.8 | 8.64 | 3.6 | 3.6 |
| DirectX 10 Shader Model | 4.0 | 4.0 | 4.0 | 4.0 | 4.0 | 4.0 | 4.0 |
| Bus Technology | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e |
GeForce 7-Series
Chipset Specs
Below are the standard (default) specifications for the NVIDIA 7-Series cards. The core and memory speeds are not universal as manufacturers can overclock the cards. What we are supplying are the numbers for the NVIDIA Reference Design. Remember, when the core and memory speed are increased so is the bandwidth.
| 7950 GX2 | 7900 GTX | 7950 GT | 7900 GT | 7900 GS | 7800 GTX 512 | 7800 GTX | 7800 GT | 7800 GS | 7600 GT | 7600 GS | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Core | G71 | G71 | G71 | G71 | G71 | G70 | G70 | G70 | G70 | G73 | G73 |
| Manufacturing Process (nm) | 90 | 90 | 90 | 90 | 90 | 110 | 110 | 110 | 110 | 90 | 90 |
| Number of Transistors (M) | 556 | 278 | 278 | 278 | 278 | 302 | 302 | 302 | 302 | 177 | 177 |
| Core Clocks (Vert/Core in MHz) | 500/500 | 700/650 | 550/??? | 470/450 | 450/??? | 550/550 | 470/430 | 440/400 | 375/375 | 560/560 | 400/400 |
| Memory Clock (MHz / data rate) | 600/1200 | 800/1600 | 700/1400 | 660/1320 | 660/1320 | 850/1700 | 600/1200 | 500/1000 | 600/1200 | 700/1400 | 400/800 |
| RAMDACs (MHz) | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 |
| Vertex Shaders (#) | 16 | 8 | 8 | 8 | 8 | 7 | 8 | 8 | 6 | 5 | 5 |
| Pixel Shaders (#) | 48 | 24 | 24 | 24 | 24 | 20 | 24 | 24 | 16 | 12 | 12 |
| Memory Interface (GDDR3) | 512-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 128-bit |
| Frame Buffer Size (MB) | 1GB | 512 | 512 | 512 | 512 | 512 | 256 | 256 | 256 | 256 | 256 |
| Memory Bandwidth (GB/s) | 76.8 | 51.2 | 42.2 | 54.4 | 38.4 | 32 | 38.4 | 22.4 | 12.8 | ||
| Verticies/Seconds (million) | 2000 | 1400 | 940 | 1100 | 940 | 770 | 562.5 | 700 | 500 | ||
| DirectX 9 Shader Model | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 |
| Bus Technology | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e AGP | PCI-e | AGP |
The NVIDIA 7-Series cards all support the following features: CineFx 4.0 / Subsurface Scattering, HDR (High Dynamic Range) Lighting, Intellisample 4.0 / Transparency Supersampling, UltraShadow II, PureVideo, and CineFX 4/0 Shader Model 3.0. The following descriptions are taken from the NVIDIA website:
CineFX 4.0
The fourth-generation NVIDIA® CineFX® engine builds unimaginable speed into the NVIDIA® GeForce® graphics processing units (GPUs). Using the CineFX 4.0 engine, developers can create and display the most advanced and high-quality visual effects for emerging PC games and other cutting-edge visual applications.
Every requirement for 3D visualization falls into one of two categories—performance or image quality—and being able to carry out more calculations in less time with the highest possible image quality.
The new NVIDIA GeForce 7 Series and GeForce Go 7 Series GPUs featuring the CineFX 4.0 engine incorporate architectural advancements that accelerate the most common operations required for 3D visualizations. This allows for more complex shader effects while maintaining the highest levels of image quality. The new design introduces innovation at every stage of the pipeline:
- A redesigned vertex shader unit reduces the time to set up and perform geometry processing.
- A new pixel shader unit design can carry out twice as many floating-point operations and greatly accelerates other mathematical operations to increase throughput.
- An advanced texture unit incorporates new hardware algorithms and better caching to speed filtering and blending operations.
The NVIDIA CineFX 4.0 engine injects breakthrough graphics technology into the core levels of the vertex shader, pixel shader, and texture engines. By accelerating triangle setup, crucial math elements of the pixel shader, and texture manipulations, the newest engine lets 3D graphics developers achieve new levels of performance and visual quality.
Source: http://www.nvidia.com/object/feature_cinefx4.0.html
Intellisample 4.0
Building on the revolutionary NVIDIA® Intellisample™ technology, the NVIDIA® GeForce™ 7 Series graphics processing units (GPUs) introduce Intellisample 4.0 technology. The fourth-generation Intellisample technology introduces two new antialiasing modes—transparency adaptive supersampling and transparency adaptive multisampling—which increase the quality and performance of antialiasing.
Transparency adaptive supersampling and multisampling take additional texel samples and antialiasing passes to enhance the quality of thin-lined objects such as chain link fences, trees, and vegetation. These types of objects are generally rendered on very simple polygon models (or even one polygon). The complexity of the final image (a group of branches or vegetation) comes from the texture that is mapped onto the polygon. Conventional antialiasing does not help this situation, because the edges of the vegetation or branches are actually inside the projected texture. Pixels inside a polygon are not touched by current antialiasing methods.
Transparency adaptive multisampling also improves antialiasing quality—with even higher levels of performance because one texel sample is used to calculate surrounding subpixel values. Although transparency adaptive multisampling is not as high quality as the supersampling method, its increased efficiency balances improved image quality and high levels of performance. The visual improvements of adaptive supersampling are obvious when compared to generic supersampling/multisampling approaches.
Source: http://www.nvidia.com/object/feature_intellisample4.0.html
UltraShadow II
Accurate shadows are critical for realistic and believable scenes in games. But the complex interactions between light sources, objects, and characters involve elaborate programming. For every frame in a game, every light source must be analyzed relative to every object, potentially bogging down the PC and affecting your gameplay. The NVIDIA® GeForce™ 6 and GeForce 7 Series of GPUs deliver the patent-pending NVIDIA® UltraShadow™ II technology, which can be applied to today’s games to build stunning visual effects and to create distinctive digital environments. With a system powered by a GeForce 6 or GeForce 7 Series GPU, anytime a game or application calculates shadows, UltraShadow II will enhance the overall performance.
Technology Advances
With UltraShadow II hardware, the more passes that are required for the lighting and shadow calculations in a scene, the more significant the performance improvement, with the most complex scenes achieving the most noticeable results. Thus, emerging next-generation games, that employ multiple light sources with many visible objects in each scene—such as DOOM 3™ from id Software—will see dramatic improvements in execution speeds. The technology advancements in UltraShadow II also deliver a 4× performance increase (compared to the previous generation) for passes involving shadow volumes.
Additionally, NVIDIA UltraShadow II gives developers the ability to calculate shadows much more quickly by eliminating unnecessary areas from consideration. By defining a bounded portion of a scene (called "depth bounds"), and focusing calculations only on the area most affected by the light source, developers can greatly accelerate the shadow generation process. With the ability to fine-tune shadows within critical regions, developers create incredible visualizations that mimic reality, and still achieve awesome performance for fast-action games. UltraShadow II also works perfectly with NVIDIA® Intellisample™ technology to ensure that shadow edges are properly antialiased.
The Result
Ultimately, the innovative techniques combined in NVIDIA’s UltraShadow II technology will empower developers with more programming flexibility and the hardware muscle they need to create unprecedented effects in their games and 3D applications. Complicated lighting and shadow effects become practical and next-generation games rise to the next level in cinematic realism. The results are more photorealistic scenes and environments in your games, without compromising PC performance.
Source: http://www.nvidia.com/object/feature_ultrashadow2.html
PureVideo
Watch videos on your desktop PC, notebook PC, or HDTV without the annoying artifacts and imperfections of traditional PC-based video solutions. NVIDIA PureVideo technology is the combination of a dedicated video processing core and software that delivers ultra-smooth, high-definition H.264, WMV, and MPEG-2 movies with minimal CPU utilization and low power consumption. And the high-precision subpixel processing enables videos to be scaled to any size, so that even small videos look like they were recorded in high-resolution.
Ultra-smooth Video
- Dedicated video processing core provides astonishingly fluid high-definition video on your PC without stutter or skips.
- Programmable video processor accelerates H.264, WMV, and MPEG-2 high-definition movies.
- Discrete video processing core offloads the CPU and 3D engine of complex video tasks, freeing the PC to run multiple applications simultaneously, while consuming less power.
Superb Picture Clarity
- NVIDIA PureVideo delivers crisp pictures by eliminating double images, blurring, and distortions.
- Jagged edges are smoothed with spatial temporal de-interlacing, inverse telecine, and advanced scaling technologies.
Precise, vivid colors on any display
- Gamma, brightness, saturation, color temperature correction, and LCD sharpening provide lifelike pictures and vivid colors on any display.
- Native HDTV support drives high-definition televisions at resolutions up to 1920x1080p through Component, DVI and HDMI interfaces.
Source: http://www.nvidia.com/page/purevideo.html
ATI
X1000 Series
Chipset Specs
Below are the standard (default) specifications for the ATI X1000-Series cards. The core and memory speeds are not universal as manufacturers can overclock the cards. What we are supplying are the numbers for the ATI Reference Design. Remember, when the core and memory speed are increased so is the bandwidth.
| X1950 CF | X1950 XTX | X1950 PRO | X1900CF | X1900 XTX | X1900XT | X1900GT | X1800XT | X1800XL | X1800GTO | X1600XT | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Core | R580 | R580 | R570 | R580 | R580 | R580 | R580 | R520 | R520 | R520 | R530 | |
| Manufacturing Process (nm) | 90 | 90 | 80 | 90 | 90 | 90 | 90 | 90 | 90 | 90 | 90 | |
| Number of Transistors (M) | 384 | 384 | 330 | 384 | 384 | 384 | 384 | 321 | 321 | 321 | 157 | |
| Core Clocks (Vert/Core in MHz) | 650/1040 | 650/1040 | 575/690 | 650/1040 | 650/1040 | 625/1000 | 575/690 | 625/1000 | 500/800 | 500/600 | 590/230 | |
| Memory Clock (MHz / data rate) | 1000/2000 | 1000/2000 | 690/1380 | 725/1450 | 775/1550 | 725/1450 | 575/1150 | 750/1500 | 500/1000 | 500/1000 | 700/1400 | |
| RAMDACs (MHz) | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 400 | |
| Vertex Shaders (#) | 8 | 8 | 16 | 8 | 8 | 8 | 8 | 8 | 8 | 8 | 5 | |
| Pixel Shaders (#) | 16 | 16 | 48 | 16 | 16 | 16 | 12 | 16 | 16 | 12 | 4 | |
| Memory Interface (GDDR3)* | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 256-bit | 128-bit | |
| Frame Buffer Size (MB) | 512 | 512 | 256 | 512 | 512 | 512 | 256 | 512 | 256 | 256 | 256 | |
| Memory Bandwidth (GB/s) | 64.0 | 64.0 | 49.6 | 49.6 | 46.4 | 38.4 | 48.0 | 32.0 | 32.0 | 22.4 | ||
| Verticies/Seconds (million) | 1300 | 1300 | 1250 | 1300 | 1250 | 1150 | 1250 | 1000 | 1000 | 737.5 | ||
| DirectX 9 Shader Model | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | 3.0 | |
| Bus Technology | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e | PCI-e/AGP | |
| *The X1950 uses GDDR4 RAM. | ||||||||||||
The ATI X1000-Series cards all support the following features: Avivo™, HDR (High Dynamic Range) + FSAA, Adaptive Antialiasing, and can take advantage of ATI's new Trade-Up Program. The following descriptions are taken from the ATI website:
Avivo™
Integrated into ATI's latest generation of graphics and TV tuner products, ATI Avivo delivers PVR, HDTV and next-generation HD disc capabilities with vibrant, sharp images, and the smoothest video playback ever offered by ATI. ATI Avivo also enables universal, professional-quality connectivity for TVs and displays, ensuring the ultimate entertainment experience on your PC.
Source: http://www.ati.com/technology/avivo/index.html
HDR + FSAA
"HDR" is the widely used abbreviation for "High Dynamic Range" calculations. This technology can be found in an increasing number of modern computer games to make lighting effects with very high contrasts look as realistic as possible. The concept builds on the fact that even in environments where the human eye is partly exposed to a very bright light source that creates a glare, it can still make out less brightly lit objects in the surrounding area. In virtual 3D worlds, however, such a high dynamic range of light requires very complex calculations.
All graphics cards belonging to the new Radeon X1000 series support modern HDR calculations. While conventional graphics cards may also offer HDR support, they are unable to combine it with the benefits of FSAA. All Radeon X1300, X1600 and X1800 models allow the use of all available FSAA modes - even in conjunction with HDR calculations. This results in an extremely realistic image quality offered only by ATI.
Source: http://www.ati.com/products/radeonx1k/imagequality.html
Adaptive Antialiasing
n modern games, many objects are not realized as 3D objects because this would unnecessarily increase the strain on the graphics card. An example of this is fences or leaves on trees and plants, since their complex structures would require too many polygons to depict accurately. Instead, game designers often take an alternate route and use a special texture (bitmap) to depict these complex structures. Certain areas within the textures are then declared transparent, ensuring a realistic appearance within the game.
Conventional FSAA methods break down when applied to these kinds of objects, since the edges aren't actual object edges but only appear within the larger texture (bitmap). The new adaptive FSAA of the Radeon X1000 models automatically recognize this type of object, ensuring optimal anti-aliasing quality.
Source: http://www.ati.com/products/radeonx1k/imagequality.html
Trade-Up Program
ATI's trade-up program allows you to upgrade your existing graphic card, no matter who made it.
- Buy a new ATI graphics card
- Send ATI your old graphics card
- Get US$50 for your old graphics card.
For more info: http://shop.ati.com/tradeup.asp
