Compare any two graphics cards:
GeForce GTX 650 vs Radeon HD 4890 2GB
IntroThe GeForce GTX 650 features a core clock speed of 1058 MHz and a GDDR5 memory frequency of 1250 MHz. It also features a 128-bit bus, and uses a 28 nm design. It features 384 SPUs, 32 Texture Address Units, and 16 Raster Operation Units.
Compare all that to the Radeon HD 4890 2GB, which has clock speeds of 1000 MHz on the GPU, and 975 MHz on the 2048 MB of GDDR5 RAM. It features 800(160x5) SPUs as well as 40 TAUs and 16 ROPs.
Power Usage and Theoretical Benchmarks
Power Consumption (Max TDP)
Performance-wise, the Radeon HD 4890 2GB should in theory be quite a bit superior to the GeForce GTX 650 overall. (explain)
Texel RateThe Radeon HD 4890 2GB is a bit (more or less 18%) faster with regards to texture filtering than the GeForce GTX 650. (explain)
Pixel RateThe GeForce GTX 650 is just a bit (more or less 6%) better at AA than the Radeon HD 4890 2GB, and also should be able to handle higher screen resolutions while still performing well. (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.
Please note that the price comparisons are based on search keywords - sometimes it might show cards with very similar names that are not exactly the same as the one chosen in the comparison. We do try to filter out the wrong results as best we can, though.
Memory Bandwidth: Bandwidth is the maximum amount of information (measured in megabytes per second) that can be transported past the external memory interface in one second. It's worked out by multiplying the card's bus width by its memory speed. In the case of DDR type RAM, it should be multiplied by 2 again. If DDR5, multiply by 4 instead. The higher the memory bandwidth, the better the card will be in general. It especially helps with AA, HDR and high resolutions.
Texel Rate: Texel rate is the maximum number of texture map elements (texels) that are processed in one second. This is worked out by multiplying the total amount of texture units by the core speed of the chip. The better this number, the better the card will be at handling texture filtering (anisotropic filtering - AF). It is measured in millions of texels processed in one second.
Pixel Rate: Pixel rate is the maximum amount of pixels that the graphics chip can possibly record to the local memory per second - measured in millions of pixels per second. Pixel rate is calculated by multiplying the number of Render Output Units by the the core clock speed. ROPs (Raster Operations Pipelines - aka Render Output Units) are responsible for outputting the pixels (image) to the screen. The actual pixel fill rate is also dependant on quite a few other factors, most notably the memory bandwidth - the lower the bandwidth is, the lower the ability to get to the max fill rate.