CUDA Toolkit is a C language development environment for CUDA-enabled GPUs especially designed for OS X.
In a short span of time, the programmable graphics processor unit has
progressed into an complete computing workhorse.
Thanks to high memory bandwidth and multiple cores, today's GPUs provide extraordinary resources for graphics and non-graphics processing.
The impressive evolution can be explained by the fact that the GPU is specialized for compute-intensive, highly parallel computation precisely what graphics rendering is about and as a result its designed allows for more transistors to be devoted to data processing rather than data caching and flow control.
The CUDA development environment includes:
· CUDA runtime driver
· gdb debugger for the GPU
· CUDA FFT and BLAS libraries for the GPU
· nvcc C compiler
· CUDA programming manual
Here are some key features of "CUDA Toolkit":
· Standard C programming language enabled on a GPU
· Unified hardware and software solution for parallel computing on CUDA-enabled NVIDIA GPUs
· CUDA compatible GPUs range from lower power notebook GPUs to high performance, multi-GPU systems
· CUDA-enabled GPUs support the Parallel Data Cache and Thread Execution Manager
· Standard numerical libraries for FFT (Fast Fourier Transform) and BLAS (Basic Linear Algebra Subroutines)
· Dedicated CUDA driver for computing.
· Optimized direct upload and download path from the CPU to CUDA-enabled GPU
· CUDA driver interoperates with OpenGL and DirectX graphics drivers
· Direct driver and assembly level access through CUDA for research and language development
What's New in This Release: [ read full changelog ]
· Support for MacOS 10.8 Mountain Lion