
CUDA 1.1 Features :
+ Standard C programming language enabled on a GPU
+ Standard numerical libraries for FFT (Fast Fourier Transform) and BLAS (Basic Linear Algebra Subroutines)
+ Support for Linux 32/64-bit and Windows XP 32/64-bit operating systems
+ Unified hardware and software solution for parallel computing on CUDA-enabled NVIDIA GPUs
+ 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
+ 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
+ Direct driver and assembly level access through CUDA for research and language development
The main reason behind such an evolution is that the GPU is specialized for compute-intensive, highly parallel computation – exactly what graphics rendering is about – and therefore is designed such that more transistors are devoted to data processing rather than data caching and flow control.
The CUDA development environment includes:
+ gdb debugger for the GPU (alpha available in March, 2008)
+ CUDA runtime driver (now also available in the standard NVIDIA GPU driver)
+ nvcc C compiler
+ CUDA FFT and BLAS libraries for the GPU
+ Profiler
+ CUDA programming manual
Requirements : Mac OS X 10.5.2 or later
License : Freeware
File size : 12.9 MB