Compare any two graphics cards:
Radeon HD 3870 X2 1GB vs Radeon HD 5870
IntroThe Radeon HD 3870 X2 1GB uses a 55 nm design. AMD has set the core speed at 825 MHz. The GDDR4 RAM is set to run at a speed of 1126 MHz on this model. It features 320(64x5) SPUs along with 16 TAUs and 16 Rasterization Operator Units.
Compare those specs to the Radeon HD 5870, which features GPU clock speed of 850 MHz, and 1024 MB of GDDR5 RAM set to run at 1200 MHz through a 256-bit bus. It also is made up of 1600(320x5) SPUs, 80 TAUs, and 32 Raster Operation Units.
Power Usage and Theoretical Benchmarks
As far as performance goes, the Radeon HD 5870 should theoretically be a bit better than the Radeon HD 3870 X2 1GB in general. (explain)
Texel RateThe Radeon HD 5870 should be a lot (about 158%) better at texture filtering than the Radeon HD 3870 X2 1GB. (explain)
Pixel RateThe Radeon HD 5870 should be just a bit (approximately 3%) faster with regards to anti-aliasing than the Radeon HD 3870 X2 1GB, and will be able to handle higher screen resolutions without slowing down too much. (explain)
One or more cards in this comparison are multi-core. This means that their bandwidth, texel and pixel rates are theoretically doubled - this does not mean the card will actually perform twice as fast, but only that it should in theory be able to. Actual game benchmarks will give a more accurate idea of what it's capable of.
Memory Bandwidth: Bandwidth is the maximum amount of data (measured in megabytes per second) that can be transferred past the external memory interface in one second. It is calculated by multiplying the card's bus width by its memory speed. If it uses DDR RAM, it should be multiplied by 2 again. If it uses DDR5, multiply by ANOTHER 2x. The better the card's memory bandwidth, the faster the card will be in general. It especially helps with anti-aliasing, High Dynamic Range and higher screen resolutions.
Texel Rate: Texel rate is the maximum number of texture map elements (texels) that can be applied per second. This is worked out by multiplying the total amount of texture units of the card by the core clock speed of the chip. The higher the texel rate, the better the video card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels processed per second.
Pixel Rate: Pixel rate is the maximum number of pixels the video card could possibly record to the local memory per second - measured in millions of pixels per second. Pixel rate is calculated by multiplying the amount of Render Output Units 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 fill rate also depends on quite a few other factors, especially the memory bandwidth - the lower the bandwidth is, the lower the potential to get to the maximum fill rate.