Compare any two graphics cards:
GeForce 8800 GTS (G80) 320MB vs GeForce GTS 450 1GB
IntroThe GeForce 8800 GTS (G80) 320MB comes with a core clock speed of 513 MHz and a GDDR3 memory speed of 792 MHz. It also features a 320-bit bus, and makes use of a 90 nm design. It features 96 SPUs, 48 TAUs, and 20 Raster Operation Units.
Compare that to the GeForce GTS 450 1GB, which comes with GPU core speed of 783 MHz, and 1024 MB of GDDR5 memory running at 902 MHz through a 128-bit bus. It also features 192 Stream Processors, 32 Texture Address Units, and 16 Raster Operation Units.
Power Usage and Theoretical Benchmarks
Power Consumption (Max TDP)
The GeForce 8800 GTS (G80) 320MB, in theory, should be a small bit faster than the GeForce GTS 450 1GB overall. (explain)
Texel RateThe GeForce GTS 450 1GB will be a little bit (more or less 2%) more effective at texture filtering than the GeForce 8800 GTS (G80) 320MB. (explain)
Pixel RateIf using lots of anti-aliasing is important to you, then the GeForce GTS 450 1GB is a better choice, and very much so. (explain)
Memory Bandwidth: Memory bandwidth is the max amount of data (in units of megabytes per second) that can be transported over the external memory interface within a second. The number is worked out by multiplying the bus width by the speed of its memory. If the card has DDR type memory, it should be multiplied by 2 again. If DDR5, multiply by 4 instead. The better the card's memory bandwidth, the better the card will be in general. It especially helps with AA, High Dynamic Range 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 worked out by multiplying the total texture units of the card by the core speed of the chip. The better this number, the better the video card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels in one second.
Pixel Rate: Pixel rate is the maximum number of pixels that the graphics card can possibly write to the local memory per second - measured in millions of pixels per second. The figure is calculated by multiplying the amount of ROPs by the the card's clock speed. ROPs (Raster Operations Pipelines - aka Render Output Units) are responsible for drawing the pixels (image) on the screen. The actual pixel rate is also dependant on many other factors, especially the memory bandwidth - the lower the bandwidth is, the lower the ability to get to the maximum fill rate.