Compare any two graphics cards:
GeForce 8800 GTS (G80) 320MB vs GeForce GTS 450 1GB
IntroThe GeForce 8800 GTS (G80) 320MB has a GPU clock speed of 513 MHz, and the 320 MB of GDDR3 memory runs at 792 MHz through a 320-bit bus. It also is made up of 96 Stream Processors, 48 TAUs, and 20 ROPs.
Compare that to the GeForce GTS 450 1GB, which uses a 40 nm design. nVidia has clocked the core speed at 783 MHz. The GDDR5 memory works at a speed of 902 MHz on this model. It features 192 SPUs along with 32 TAUs and 16 Rasterization Operator Units.
Power Usage and Theoretical Benchmarks
Power Consumption (Max TDP)
As far as performance goes, the GeForce 8800 GTS (G80) 320MB should theoretically be a little bit better than the GeForce GTS 450 1GB in general. (explain)
Texel RateThe GeForce GTS 450 1GB will be a small bit (more or less 2%) more effective at anisotropic filtering than the GeForce 8800 GTS (G80) 320MB. (explain)
Pixel RateThe GeForce GTS 450 1GB will be a lot (more or less 22%) faster with regards to FSAA than the GeForce 8800 GTS (G80) 320MB, and capable of handling higher screen resolutions without slowing down too much. (explain)
Memory Bandwidth: Memory bandwidth is the maximum amount of information (counted in megabytes per second) that can be moved across the external memory interface in one second. It's calculated by multiplying the interface width by the speed of its memory. If the card has DDR memory, it must be multiplied by 2 again. If it uses DDR5, multiply by ANOTHER 2x. The higher the card's memory bandwidth, the better the card will be in general. It especially helps with anti-aliasing, HDR and higher screen resolutions.
Texel Rate: Texel rate is the maximum texture map elements (texels) that are processed in one second. This figure is worked out by multiplying the total texture units by the core speed of the chip. The higher the texel rate, the better the video card will be at handling texture filtering (anisotropic filtering - AF). It is measured in millions of texels in one second.
Pixel Rate: Pixel rate is the most pixels that the graphics chip can possibly write to its local memory per second - measured in millions of pixels per second. The figure is worked out by multiplying the amount of colour ROPs by the clock speed of the card. ROPs (Raster Operations Pipelines - also called 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 of the card - the lower the bandwidth is, the lower the ability to reach the max fill rate.