Let's start off by looking at the major specifications of the new GeForce GT 220 and 210 graphics cards:

Because these new cards are both based on the same GT200 architecture underlying the GeForce GTX 260/275/280/285/295, we won't scrutinize the minutia too much. Rather, we'll concentrate on what makes these new cards different. For details on GT200 itself, check out our GeForce GTX 280 article here.

For a quick refresh, the GeForce GTX 285 has 10 texture-processing clusters (TPCs) with 24 individual streaming processors (SPs) or cores in each one. Each TPC also has eight texture management units (TMUs). There are eight 64-bit raster-operator partitions (ROPs), each capable of handling eight operations per clock. As a result, the GeForce GTX 285 sports a total of 240 processor cores, 80 TMUs, and eight ROPs capable of handling 64 pixels per clock, with all of the ROPs contributing to a 512-bit memory bus.

The GT216 GPU in the GeForce GT 220, on the other hand, has only two of these TPCs, each containing 24 SPs for a total of 48 processor cores. Like the GeForce GTX 280, each TPC has eight TMUs, for a total of 16 TMUs. Two 64-bit ROPs capable of handling four pixels per clock work together to give the GPU a 128-bit memory interface and the capacity to handle eight raster operations per clock. Knowing this, we can expect the GT 220 to wield about one-fifth the processing power of the GeForce GTX 285.

The GT218 GPU in the GeForce 210 is significantly smaller, with a single TPC armed with 16 processor cores and eight TMUs in total. Raster operations are handled by a single 64-bit ROP capable of handling four pixels per clock. The end result is that the GeForce 210 should be approximately one-third as powerful as the GT 220.

These new GPUs weren't designed by copying and pasting the GT200's transistors, so Nvidia's engineers added some new tricks in the process: DirectX 10.1 and Shader Model 4.1 support, an integrated audio controller supporting eight-channel LPCM audio output, and enhanced playback support for DivX, VC-1, MPEG-2, and even flash-based video streams.

Perhaps more important, these new GPUs are manufactured on TSMC's 40nm process and represent Nvidia's first 40nm commercial GPUs. This is an important milestone because, assuming good yields, this should allow Nvidia to produce more of these GPUs per die, and therefore, per dollar.