GPU computing with NVIDIA CUDA for data-intensive processing that inter-operates with the OpenGL API
GPU computing with NVIDIA’s new CUDA (compute unified device architecture) technology uses ‘C’ programs called threads that are similar to multi-threading programs on traditional CPUs. In contrast to multi-core CPUs, where only a few threads execute at the same time, NVIDIA GPUs featuring CUDA technology process thousands of threads simultaneously enabling a higher capacity of information flow. Threads cab also communicate with eachother. The CUDA SDK includes standard FFT and BLAS libraries, a C-compiler for the NVIDIA GPU and a standalone runtime driver that inter-operates with OpenGL drivers from NVIDIA. Available for Windows and Linux.
Nov 09, 2006 | Category: Developers •