DailyTech heard NVIDIA didn't have any luck shrinking its GT200 GPU to the 40nm node, the site says these attempts were disastrous at best:
One solution was to begin manufacturing on the 40nm bulk process like ATI has done. According to our sources, NVIDIA's attempts to produce a die-shrunk 40nm GT200 chip were "disastrous at best". Design problems became evident, since the GT200 was originally designed for the 65nm node. Two shrinks in a row without a major redesign was just too much for NVIDIA, and our most recent information from Taiwan is that the first 40nm chips from NVIDIA will be in the GeForce 300 series.
Without a power efficient GT200 based GPU solution for the mobile or mainstream value markets, NVIDIA is rebranding the 55nm G92b chip yet again to meet these critical segments. The original 65nm G92 chip was used in the GeForce 8800 GT, but you can only do so much with an older design. The chip was respun as the G92b with a 55nm die shrink, and is currently used in the 9800 GTX+. All G92 chips are only DirectX 10 capable, and will not support the full feature set of DirectX 10.1 or DirectX 11 that will come with Windows 7.