Add to Favourites
To login click here
A recent international research project headed by Professor Marco Platzner of Paderborn University is attempting to reduce the energy consumption of AI and big data by using field programmable gate arrays (FPGAs) instead of the usual central processing units (CPUs) and graphics processing units (GPUs). FPGAs are reprogrammable hardware devices that optimise computing, memory, and interconnection networks, allowing a reduction in the number of individual calculation steps without affecting the quality of the output. The research is being supported by the Federal Ministry for the Environment, Nature Conservation, Nuclear Safety and Consumer Protection, and is aimed at making data centres more sustainable.
