Compare any two graphics cards:
GeForce 8800 GS vs Radeon HD 4670 1GB
IntroThe GeForce 8800 GS features a GPU core speed of 550 MHz, and the 384 MB of GDDR3 RAM is set to run at 800 MHz through a 192-bit bus. It also is comprised of 96 SPUs, 48 Texture Address Units, and 12 Raster Operation Units.
Compare all of that to the Radeon HD 4670 1GB, which features GPU core speed of 750 MHz, and 1024 MB of GDDR4/GDDR3/DDR3/DDR2 RAM running at 1100 MHz through a 128-bit bus. It also is made up of 320(64x5) Stream Processors, 32 Texture Address Units, and 8 Raster Operation Units.
Power Usage and Theoretical Benchmarks
Power Consumption (Max TDP)
Theoretically speaking, the GeForce 8800 GS will be 9% faster than the Radeon HD 4670 1GB in general, due to its greater bandwidth. (explain)
Texel RateThe GeForce 8800 GS is a little bit (about 10%) better at AF than the Radeon HD 4670 1GB. (explain)
Pixel RateIf running with high levels of AA is important to you, then the GeForce 8800 GS is the winner, but not by far. (explain)
Please note that the above 'benchmarks' are all just theoretical - the results were calculated based on the card's specifications, and real-world performance may (and probably will) vary at least a bit.
Memory Bandwidth: Bandwidth is the maximum amount of data (in units of MB per second) that can be transferred past the external memory interface in a second. The number is worked out by multiplying the interface width by its memory clock speed. In the case of DDR type RAM, the result should be multiplied by 2 once again. If it uses DDR5, multiply by 4 instead. The higher the memory bandwidth, the faster the card will be in general. It especially helps with anti-aliasing, HDR and higher screen resolutions.
Texel Rate: Texel rate is the maximum amount of texture map elements (texels) that can be processed per second. This number is calculated by multiplying the total amount of texture units by the core speed of the chip. The better the texel rate, the better the graphics card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels processed in one second.
Pixel Rate: Pixel rate is the most pixels the video card could possibly record to its local memory in a second - measured in millions of pixels per second. The figure is worked out by multiplying the number of ROPs by the the core clock speed. ROPs (Raster Operations Pipelines - also sometimes called Render Output Units) are responsible for drawing the pixels (image) on the screen. The actual pixel rate also depends on many other factors, especially the memory bandwidth of the card - the lower the memory bandwidth is, the lower the potential to get to the max fill rate.