The CUDA Toolkit 3.0 production release is now available at www.nvidia.com/getcuda

Key features in this release include:

• Support for new GPUs based on Fermi architecture - including ECC, optimized double precision, libraries of linear algebra operation routines (such as BLAS and LAPACK), the CUDA-GDB debugger and Visual Profiler
• C++ support – delivering improved productivity with class and template inheritance
• GPGPU/Graphics interoperability – delivering Direct3D 9,10 and11 and OpenGL for both CUDA and OpenCL
• Improved developer tools for Linux –  including the new CUDA Memory Checker that reports misalignment and out-of-bounds errors
• Tesla Compute Cluster (TCC) – improving performance and cluster management

Sign up for our GPU Computing Registered Developer Program!

Registered developers get early access to upcoming releases, direct access to our bug database, and more.

http://nvdeveloper.nvidia.com/content/GPUComputingDeveloperApplication/frmDeveloperRegistration.asp