Hi, I'm new here, I've just started converting the model I was working on to IR.
My question is: I know Intel and National Instruments have a partnership on integration of OpenVINO and NI labview.
Does that mean I can run inference on OpenVINO over the Kintex-7 70T FPGA running on NI cRIO-9040?
Even if it means I need to run code outside of labview, or even program the FPGA with a hdl file, that wouldn't be a problem.
I'm looking forward to any answers from intel support team or anyone.
Thanks in advance,
NI cRIO-9040 with Kintex-7 70T FPGA is not officially supported by OpenVino.
However I had seen someone uses OpenVino in NI Labview on their CPU/GPU, not on a controller.
In addition to that the NI cRIO-9040 does support Python which could be a good thing since OpenVino has Python modules:
I suggest that you try this workaround but there are no guarantee that it would totally work:
1. Install OpenVino prerequisite on host machine
2. Install Intel®FPGA Runtime Environment for OpenCL
3. Run the model by using aocl command & you will know ithe result (whether it works or not)
Here is guide that depict on Deploying Intel® FPGAs for Deep Learning Inferencing with OpenVINO™ Toolkit: https://www.youtube.com/watch?v=7yh1c8kJn1A
(This video might help to give overall steps that should be taken to run OpenVino in FPGA )
Hope my answer helps!
I'm closing the case since the are no reply within 5 working days.
If there are any inquiries please help to create a new thread.
Thanks & have a great day ahead.
Thank you very much for your response.
I'm searching for support for Xilinx FPGAs on OpenCL
Kintex7 is not currently supported on SDAccel, Xilinx former SKD for OpenCL, which is now Vitis.
It seems OpenCL RTE supports custom platforms:
Apparently I can start from a refernce board design and modify it
Do you think this is possible?