Today NVIDIA introduced its next-gen CUDA GPU architecture (GT300) at the GPU Technology Conference in San Jose, California which it calls "Fermi", named after the Italian physicist Enrico Fermi who invented the nuclear reactor.

Key information about the next-gen chip comprises the following :-

• Transistor count of over 3 billion
• Built on the 40 nm TSMC process
• 512 shader processors (which NVIDIA may refer to as "CUDA cores")
• 32 cores per core cluster
• 384-bit GDDR5 memory interface
• 1 MB L1 cache memory, 768 KB L2 unified cache memory
• Up to 6 GB of total memory, 1.5 GB can be expected for the consumer graphics variant
• Half Speed IEEE 754 Double Precision floating point
• Native support for execution of C (CUDA), C++, Fortran, support for DirectCompute 11, DirectX 11, OpenGL 3.1, and OpenCL

NVIDIA's press release on Fermi can be found here. There's also a bunch of info and presentation slides shared out over at Legit Reviews.