Yannick Grenzinger's notes

http://www.silicon.fr/fr/news/2008/12/22/comment_le_gpgpu_va_revolutionner_le_calcul_parallele

I have already talked about CUDA after the GPU barcamp. Now it's time for OpenCL which specifications have been "officialy" launched a few days ago. Like they say : "OpenCL (Open Computing Language) is the first open, royalty-free standard for general-purpose parallel programming of heterogeneous systems. OpenCL provides a uniform programming environment for software developers to write efficient, portable code for high-performance compute servers, desktop computer systems and handheld devices using a diverse mix of multi-core CPUs, GPUs, Cell-type architectures and other parallel processors such as DSPs." An article in french : http://www.hardware.fr/articles/744-1/opencl-gpu-computing-enfin-democratise.html Another article in english : http://arstechnica.com/news.ars/post/20081209-gpgpu-opens-up-with-opencl-1-0-spec-release.html

To launch this blog, I will talk about my saturday at La Cantine with a GPU barcamp . I have seen many interesting and passionate people thanks to the planners : François Lagunas and Eric Mahé. I have seen some of the presentation after a small intro. Comprehensive Sensing first, which is a fascinating new way to capturate our world (from classic picture to spectral). More information on nuit-blanche.blogspot.com . CUDA , the "general" programming language for Nvidia GPU (waiting for OpenCL to have a common language for all hardware). It seems powerfull. However the language is a bit hard due to specifical programming of architecture, optimizations and parallelism. Like you see in diagram below, the architecture of CUDA is based on multiple grid running one kernel (program). Grids contain blocs which contain thread. One thread apply kernel on one data (for example a float). Warning : there is only one if else prediction by kernel. A very interesting note is that code run in...