Français
1. From CPU to GPGPU
This section looks at the developments in CPUs and GPUs that are driving the current interest in graphics card computing. The CPU has evolved towards parallelism and the GPU has become programmable and massively parallel. This has prompted developers to take a renewed interest in parallel programming after the 1990s of the Connection Machine and the Transputer .
The Ultimate Scientific and Technical Reference
This article is included in
Signal processing and its applications
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
From CPU to GPGPU
Current NVIDIA and ATI/AMD architecture for general-purpose computing
Bibliography
(books, articles, symposium proceedings, theses and dissertations, referred to in the text as – and therefore numbered – or not)
Websites
(portals, personal pages, forums, discussion lists)
HARRIS Mark General-Purpose Computation on Graphics Hardware http://gpgpu.org/ (page accessed September 20, 2015). The most important site on the subject with news, forums and tutorials.
NVIDIA Corporation CUDA Zone – The resource for CUDA developers...
Events
(conferences, trade shows, symposia, study days)
Conference and exhibition: The International Conference for High Performance Computing, Networking, Storage, and Analysis (SuperComputing) http://www.sc-conference.org takes place every year, presenting trends and innovations in high-performance computing.
...
The Ultimate Scientific and Technical Reference
