Add `pynq-zu` board to `VivadoAccelerator` backend

fastmachinelearning / hls4ml

Machine learning on FPGAs using HLS

https://fastmachinelearning.org/hls4ml

Apache License 2.0

1.19k stars 390 forks source link

Add `pynq-zu` board to `VivadoAccelerator` backend #755

Open jmduarte opened 1 year ago

jmduarte commented 1 year ago

Add support for pynq-zu.

Type of change

[x] New feature (non-breaking change which adds functionality)

Tests

https://gist.github.com/jmduarte/41a6afcd412dbd7c39cdbd0e2a1a01a3

Checklist

[x] I have read the guidelines for contributing.
[x] I have commented my code, particularly in hard-to-understand areas.
[ ] I have made corresponding changes to the documentation.
[ ] My changes generate no new warnings.
[x] I have installed and run pre-commit on the files I edited or added.
[x] I have added tests that prove my fix is effective or that my feature works.

vloncar commented 1 year ago

I'm wondering if we should also have an extension API handle adding support for new hardware or new drivers because now one has to make manual changes to the codebase to add new boards/drivers.

jmduarte commented 1 year ago

@vloncar yes, i think that's a good idea.

Regarding this PR in particular, I'm having an issue in Vivado 2020.1 where it says:

WARNING: [Board 49-26] cannot add Board Part tul.com.tw:pynqzu:part0:1.1 available at /home/users/woodson/XilinxBoardStore/boards/TUL/pynqzu/1.1/board.xml as part xczu5eg-sfvc784-1-e specified in board_part file is either invalid or not available

even after installing the board files / pointing Vivado to the right place (and the same procedure works for pynq-z2).

Could this mean this FPGA part is only supported in >= 2020.2 ?

jmitrevs commented 1 year ago

Release 2020.1.1 added some support, though I am not sure it includes this:

https://support.xilinx.com/s/article/75475?language=en_US