On Wed, Oct 16, 2019 at 1:57 AM jonnymo <[email protected]> wrote: > Isn't the purpose of OpenCL is to handle the parallel processing between CPU, > GPU, and other related devices? Disabling the GPU seems counter intuative. > Where are you getting your data that a GPU is not needed for Machine > Learning? This again seems counter intuative.
The TI Deep Learning SDK uses OpenCL interface to the DSP cores and the EVE (embedded vision engine). Here is an overview: http://downloads.ti.com/mctools/esd/docs/tidl-api/intro.html Regards, Drew -- For more options, visit http://beagleboard.org/discuss --- You received this message because you are subscribed to the Google Groups "BeagleBoard" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/beagleboard/CAEf4M_CX0mJXuOvGyZ%2BCDimQaMMGSrSnjGeCkt_X%3DMwBTV4%3Dmw%40mail.gmail.com.
