We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

Posts: 8
Registered: ‎05-06-2018

machine learning process in Xilinx FPGA

    I want to do machine learning in Xilinx FPGA, how to transfer the code written in Python or C++ to FPGA.

Should I write the code directly with HDL language, or is there any other convenient method? what is the specific process?

Posts: 1,859
Registered: ‎03-22-2016

Re: machine learning process in Xilinx FPGA

@zxyglx_ That is not a productive approach - simply attempting to move the code.

You could go two ways: 

- Use SDSOC and let Vivado identify what can be accelerated for you

- Use HLS (my preferred method)

The most effective way is to identify modules in your code that could have streaming inputs/outputs and then recode them from scratch in HLS, perhaps with a bit of copy/paste from existing sources. 

No HDL (Verilog/VHDL) is strictly necessary.

vitorian.com --- We do this for fun. Always give kudos. Accept as solution if your question was answered.
I will not answer to personal messages - use the forums instead.