Updated verisons of the CUDA C Programming Guide (v3.1.1) and the Fermi Tuning Guide (v1.2) are now available. You can download them from http://developer.nvidia.com/object/gpucomputing.html.
Notable changes to these guides from the previous versions:
[*]Removed sections about loading 32-bit device code from 64-bit host code using the driver API, as this capability will no longer be supported in the next CUDA toolkit release.
[*]Removed the reference to the canMapHostMemory property and mentioned that all devices of compute capability greater than 1.0 now support mapped page-locked host memory.
[*]Mentioned that host device memory copies of a memory block of 64 KB or less are asynchronous.
[*]Fixed the maximum size of a 3D texture reference for devices of compute capability 2.0 (2048 instead of 4096).
[*]Updated the paragraph about __fdividef(x,y) to clarify behavior depending on compute capability and compilation flag.