Forum Discussion

Björne2's avatar
Björne2
Icon for New Contributor rankNew Contributor
1 year ago

Advice on CNN inference on Agilex 7 using oneAPI

Greetings everyone, I'm tasked with porting an CNN trained with PyTorch to an Agilex 7 FPGA using HLS. I think the right tool for the job is oneAPI. Since this is not a completely novel task, I wond...
High-level Design Tools
whitepau_altera's avatar
whitepau_altera
Icon for Contributor rankContributor
1 year ago

Do you have a board in mind? Keep in mind that if you wish to use oneAPI FPGA Acceleration, you should choose an acceleration card with a supported BSP. We have a list of vendor cards on our homepage:

https://cdrdv2.intel.com/v1/dl/getContent/824530

Instead of building a full oneAPI BSP, you can also use the oneAPI DPC++/C++ compiler to create IP that you can integrate using a platform designer system. We demonstrate this in the Platform Designer code sample, and the Nios V reference design. You can learn more about IP interface customization by studying the HLS Flow Interfaces code samples as well.

Manually integrating your IP with Platform Designer (or SystemVerilog/VHDL if you are so inclined) gives you the ability to accelerate the embedded HPS, so you are not tied to an x86-64 host CPU.