# Mitigating scalability challenges in LUT-based neural networks via pruning optimisations

Source: [Mitigating scalability challenges in LUT-based neural networks via pruning optimisations](<https://www.sota2.com/research/paper/68fa73fe1e209131cea5f16d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-17T05:00:14.085Z

Authors: Xuqi Zhu, Huaizhi Zhang, JunKyu Lee, Jiacheng Zhu, Chandrajit Pal, Sangeet Saha, Klaus D. McDonald-Maier, Xiaojun Zhai

Published: 2024-07-02T15:28:10.000Z

## Abstract

Modern deep neural networks heavily rely on a large number of multiply-accumulate operations, which constitute the predominant computational cost. To address this, Look-Up Table (LUT)-based matrix multiplications have emerged as a promising alternative for reducing the computational cost and time of the multiply-accumulate operations in a neural network. However, the LUT-based neural network still faces the scalability challenge due to the inherent limitations of LUT-based matrix multiplication. To mitigate these scalability limitations, this paper proposes a scalable and energy-efficient LUT-based approximate matrix multiplication unit (LUT-MU) constituting the basic component of the neural networks by integrating a pruning strategy on the MADDNESS algorithm, a LUT-based matrix multiplication methodology. With increasing problem size and precision demands in matrix multiplication, our proposed LUT-MU architecture effectively constrains resource expansion. The case study shows that deploying our LUT-MU in neural network architectures, including fully connected layers (MNIST) and ResNets (CIFAR-10, ImageNet)-on XCZU7EV and XCZU19EG FPGAs, produces up to $1.6 \\times$ throughput improvement and $4.2 \\times$ energy efficiency gains over mainstream CUDA-based network implementations, and $1.8\\times$ energy efficiency compared to leading quantised neural network implementations, with moderate impact on accuracy. Compared to original MADDNESS-based neural networks, our LUT-MU shows $1.3$ to $2.6\\times$ resource savings based on various resolution configuration settings of MADDNESS.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.02362>)

[PDF](<https://arxiv.org/pdf/2407.02362.pdf>)
