GeForce GTX 660 vs Radeon HD 4870 1GB

Intro

Compare all of that to the Radeon HD 4870 1GB, which comes with GPU core speed of 750 MHz, and 1024 MB of GDDR5 RAM set to run at 900 MHz through a 256-bit bus. It also is comprised of 800(160x5) Stream Processors, 40 TAUs, and 16 Raster Operation Units.

Display Graphs

Hide Graphs

Power Usage and Theoretical Benchmarks

Power Consumption (Max TDP)

GeForce GTX 660		140 Watts
Radeon HD 4870 1GB		150 Watts
	Difference: 10 Watts (7%)

Memory Bandwidth

The GeForce GTX 660, in theory, should perform a lot faster than the Radeon HD 4870 1GB overall. (explain)

GeForce GTX 660		144192 MB/sec
Radeon HD 4870 1GB		115200 MB/sec
	Difference: 28992 (25%)

Texel Rate

The GeForce GTX 660 will be quite a bit (approximately 161%) more effective at AF than the Radeon HD 4870 1GB. (explain)

GeForce GTX 660		78400 Mtexels/sec
Radeon HD 4870 1GB		30000 Mtexels/sec
	Difference: 48400 (161%)

Pixel Rate

If using lots of anti-aliasing is important to you, then the GeForce GTX 660 is a better choice, and very much so. (explain)

GeForce GTX 660		23520 Mpixels/sec
Radeon HD 4870 1GB		12000 Mpixels/sec
	Difference: 11520 (96%)

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.

Price Comparison

Specifications

Memory Bandwidth: Bandwidth is the max amount of information (measured in MB per second) that can be transferred over the external memory interface within a second. It is worked out by multiplying the interface width by its memory clock speed. If the card has DDR type RAM, the result should be multiplied by 2 again. If DDR5, multiply by ANOTHER 2x. The higher the 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 are applied in one second. This number is calculated by multiplying the total texture units of the card by the core speed of the chip. The better this number, the better the graphics 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 can possibly write to the local memory in a second - measured in millions of pixels per second. The figure is worked out by multiplying the amount of ROPs by the the core clock speed. 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 many other factors, most notably the memory bandwidth of the card - the lower the memory bandwidth is, the lower the ability to reach the maximum fill rate.