DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivity

2026-09-08

AI Summary

DiffLUT-Net通过可微训练FPGA LUT网络及其连接，从零开始训练以实现高效神经网络推理，最终在五个基准测试中达到良好的准确性和资源平衡。

Abstract

Field-programmable gate arrays (FPGAs) enable efficient neural-network inference, but most deployment flows either accelerate multiply-accumulate operations or convert pretrained quantized models into lookup tables (LUTs). We present DiffLUT-Net, an FPGA-native network connected by six-input LUTs that are trained from scratch. We jointly learn the 64 truth-table entries of a LUT and the source to each of its six input ports using a differentiable LUT function relaxation and hardware source selection. After training, the truth tables and connections are discretized, unused logic can be pruned, and the network is exported directly as synthesizable Verilog. Across five benchmarks, DiffLUT-Net achieves favorable accuracy-resource trade-offs. These results demonstrate the effectiveness of jointly learning LUT functions and sparse connectivity for compact FPGA-native inference. The code is available at https://github.com/TUDa-HWAI/DiffLUT-Network.

Problem

• FPGA
• neural-network inference
• lookup tables (LUTs)
• differentiable training
• connectivity

Innovation

• Differentiable LUT Function Relaxation
• Learnable Connectivity
• FPGA-Native Network
• Sparse Connectivity