The NVIDIA® CUDA® Toolkit provides a comprehensive development environment for implementing GPU-accelerated applications. The CUDA Toolkit includes a compiler for NVIDIA GPUs, math libraries, and tools for debugging and optimizing the performance of your applications and has been downloaded more than million times.
In the latest version, CUDA 6.0 has partially integrated KBLAS into its GPU-accelerated math library (cuBLAS) to enhance the performance of the symmetric matrix-vector multiplication kernel (SYMV/HEMV) on NVIDIA GPUs. This kernel is critical for efficiently solving dense symmetric eigenvalue problems, which can be found in many scientific applications (e.g, computational chemestry).
The official NVIDIA announcement can be found here: