Compare any two graphics cards:
GeForce 8600 GT 256MB DDR2 vs Radeon HD 5550
IntroThe GeForce 8600 GT 256MB DDR2 features core speeds of 540 MHz on the GPU, and 400 MHz on the 256 MB of DDR2 memory. It features 32 SPUs along with 16 TAUs and 8 Rasterization Operator Units.
Compare those specs to the Radeon HD 5550, which has core speeds of 550 MHz on the GPU, and 400 MHz on the 512 MB of DDR2 RAM. It features 320(64x5) SPUs as well as 16 TAUs and 8 ROPs.
Power Usage and Theoretical Benchmarks
Both cards have the exact same bandwidth, so in theory they should perform the same. (explain)
Texel RateThe Radeon HD 5550 will be a bit (about 2%) more effective at AF than the GeForce 8600 GT 256MB DDR2. (explain)
Pixel RateIf using lots of anti-aliasing is important to you, then the Radeon HD 5550 is the winner, but it probably won't make a huge difference. (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: Memory bandwidth is the maximum amount of information (measured in megabytes per second) that can be transported across the external memory interface in one second. It is worked out by multiplying the bus width by its memory clock speed. If it uses DDR RAM, the result should be multiplied by 2 again. If it uses DDR5, multiply by ANOTHER 2x. The higher the bandwidth is, the better the card will be in general. It especially helps with AA, HDR and higher screen resolutions.
Texel Rate: Texel rate is the maximum amount of texture map elements (texels) that are processed per second. This figure is worked out by multiplying the total amount of texture units of the card by the core speed of the chip. The higher this number, the better the video card will be at handling texture filtering (anisotropic filtering - AF). It is measured in millions of texels per second.
Pixel Rate: Pixel rate is the maximum number of pixels that the graphics chip could possibly record to its local memory per second - measured in millions of pixels per second. The figure is calculated by multiplying the number of colour ROPs by the the core speed of the card. ROPs (Raster Operations Pipelines - aka Render Output Units) are responsible for filling the screen with pixels (the image). The actual pixel output rate also depends on quite a few other factors, most notably the memory bandwidth - the lower the bandwidth is, the lower the ability to reach the maximum fill rate.