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.

Reply via email to