GeForce 9800 GTX vs GeForce GT 640 DDR3

Intro

Compare those specs to the GeForce GT 640 DDR3, which has core speeds of 900 MHz on the GPU, and 1782 MHz on the 2048 MB of DDR3 RAM. It features 384 SPUs as well as 32 Texture Address Units and 16 ROPs.

Display Graphs

Hide Graphs

Power Usage and Theoretical Benchmarks

Power Consumption (Max TDP)

GeForce GT 640 DDR3		65 Watts
GeForce 9800 GTX		140 Watts
	Difference: 75 Watts (115%)

Memory Bandwidth

In theory, the GeForce 9800 GTX is 23% quicker than the GeForce GT 640 DDR3 in general, because of its higher bandwidth. (explain)

GeForce 9800 GTX		70400 MB/sec
GeForce GT 640 DDR3		57024 MB/sec
	Difference: 13376 (23%)

Texel Rate

The GeForce 9800 GTX is a lot (approximately 50%) better at texture filtering than the GeForce GT 640 DDR3. (explain)

GeForce 9800 GTX		43200 Mtexels/sec
GeForce GT 640 DDR3		28800 Mtexels/sec
	Difference: 14400 (50%)

Pixel Rate

The GeForce GT 640 DDR3 will be quite a bit (about 33%) better at AA than the GeForce 9800 GTX, and also should be able to handle higher resolutions while still performing well. (explain)

GeForce GT 640 DDR3		14400 Mpixels/sec
GeForce 9800 GTX		10800 Mpixels/sec
	Difference: 3600 (33%)

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 maximum amount of information (counted in MB per second) that can be transported across the external memory interface in a second. It is calculated by multiplying the card's bus width by its memory speed. In the case of DDR RAM, it must be multiplied by 2 once again. If it uses DDR5, multiply by ANOTHER 2x. The better the bandwidth is, 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 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 this number, the better the card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels applied in a second.

Pixel Rate: Pixel rate is the maximum number of pixels the graphics card can possibly record to the local memory in one second - measured in millions of pixels per second. The figure is calculated by multiplying the number of 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, especially the memory bandwidth of the card - the lower the bandwidth is, the lower the ability to get to the max fill rate.