#1 Use Support Vector machine with GPU

[Richard Ulrich]

At the moment we use a SVM implementation from dclib which has a nice C++ interface, but runs only on one Core.
OpenCL seems to have a SVM implementation that can also run on the GPU:
Although, I don't know if it supports regression yet...
http://www.cmsoft.com.br/index.php?option=com_content&view=category&layout=blog&id=117&Itemid=173
http://developer.amd.com/documentation/articles/pages/OpenCLOptimizationCaseStudySupportVectorMachineTraining.aspx