*One does not have to wait for the K! (6th generation if Nvidea processors) gen 4 and 4i are here, now! For $199 you can have 72 GPUs in an Android tablet from ~newegg.*
*It **is **also, eg, programmed with AOHD (Always on High Definition). Presumably they are fast enough that one can do ~Frankencamera_lite sorts of things with them:-)* *---~* *http://www.newegg.com/Product/Product.aspx?Item=34-099-001&SortField=1&SummaryType=0&Pagesize=100&PurchaseMark=&SelectedRating=-1&VideoOnlyMark=False&VendorMark=&IsFeedbackTab=true&Keywords=%28keywords%29#scrollFullInfo <http://www.newegg.com/Product/Product.aspx?Item=34-099-001&SortField=1&SummaryType=0&Pagesize=100&PurchaseMark=&SelectedRating=-1&VideoOnlyMark=False&VendorMark=&IsFeedbackTab=true&Keywords=%28keywords%29#scrollFullInfo>* *http://u.tgu.ca/Frankencamera_lite <http://u.tgu.ca/Frankencamera_lite>* *greg* *~krsnadas.org <http://krsnadas.org>* *-- * *from: Devon McCormick [email protected] <[email protected]>* *to: Chat forum <[email protected] <[email protected]>>* *date: 28 February 2014 07:36* *subject: Re: [Jchat] Parallel Processing for J* *Skip -* *>you're right that GPUs offer tantalizing possibilities for J. I made sure to have an nVidia processor in the last PC I bought - the (C++-based) demos are very impressive. However, I have yet to grapple with learning enough about the CUDA libraries to think about how to integrate them into J.* *I'll take a look at those videos.* *Regards,* *Devon* *--* *from: Skip Cave [email protected] <[email protected]>* *to: Chat forum <[email protected] <[email protected]>>* *date: 28 February 2014 00:34* *subject: [Jchat] Parallel Processing for J* *>I participated in an ACM webinar today presented by nVidia, where they covered their latest multiprocessor "accelerator" GPU chip, the Tegra K1<http://bit.ly/1mJYL5O <http://bit.ly/1mJYL5O>>. The K1 has 192 CUDA parallel cores as well as four ARM-15 cores. It is designed to be used in cellphones, so it uses very low power. The webinar link is at: http://bit.ly/1cq6E6E <http://bit.ly/1cq6E6E> I would recommend taking a look at the presentation, as it shows just how far we have come in putting serious multiprocessing power in the hands of the masses* *>nVidia claims the architecture is being used in various "green" supercomputers, running models of Molecular Dynamics, Quantum Chemistry, Material Science, Weather & Climate, Lattice QCD, Plasma Physics, Structural Mechanics, and Fluid Dynamics. They claim that they have built compilers and interpreters for their multiprocessing architecture in Fortran, C, C++, Pyton, and F#, which will make it easy for programmers to distribute processing load across the array of CUDA cores in the K1, as well as the four ARM processors.* *>I always felt that the primitives in J define a powerful and general set of array operations that could benefit from a parallel processing architecture. The nVidia processors will be showing up in cellphones in the near future. It would be interesting to see if J could take advantage of the amazing parallel processing power of these chips - a supercomputer in your pocket.* *Skip.* ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
