Ready to start cranking out general-purpose apps for Nvidia's GeForce GTX 400-series graphics cards (and their Tesla cousins)? Nvidia has released a new version of its CUDA software development toolkit, numbered 3.0, which brings Fermi support alongside a handful of other, fairly major changes.
The new toolkit, along with a detailed list of changes and additions, are both available from this page on Nvidia's Developer Zone. Highlights of the CUDA 3.0 toolkit include:
- Support for new GPUs based on Fermi architecture - including ECC, optimized double precision, support for linear algebra libraries 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 and 11 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
We wrote at length about the Fermi architecture's new general-purpose computing functionality in our September 30 article. If everything goes according to plan, the Fermi-based GeForce GTX 480 and GeForce GTX 470 should be out by the end of the month. Fermi-based Tesla processors should follow in the second quarter.