most citedLUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference

6 citations · 6 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AR2024★ 6 cited

LUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference

Yanyue Xie, Zhengang Li, Dana Diaconu +3

For FPGA-based neural network accelerators, digital signal processing (DSP) blocks have traditionally been the cornerstone for handling multiplications. This paper introduces LUTMU…