cs.LGNov 8, 2026

ConvLUT: Rethinking Convolutional Architectures for Ultra-Low-Latency LUT-Based Inference

Authors: Marta Andronic, Olivia Weng, Danial Zuberi, Ryan Kastner, George A. Constantinides

Organizations: Imperial College London London, UK · University of California San Diego San Diego, CA, USA

Abstract

Lookup-table (LUT)-based neural networks (NNs) offer a compelling path to ultra-low-latency inference on FPGAs. However, existing LUT-based neural networks have largely been restricted to MLP-style topologies, leaving structured vision and audio tasks underexplored. We present ConvLUT, a family of fully unrolled LUT-mappable convolutional architectures targeting the MLPerf Tiny benchmarks. It is comprised of a standard convolutional model built around a hierarchical tree of LUTs and a depthwise separable model following the MobileNet design philosophy. These architectures are enabled by four key contributions: a unified LUT-based convolutional framework supporting standard, depthwise, and pointwise convolutions under explicit fan-in constraints; a LUT-tree that addresses the k2ck^2c receptive field dimensionality bottleneck; a channel-partitioned LUT pooling layer that replaces conventional spatial pooling; and a hardware-aware iterative pruning strategy for stable convergence at scale. Evaluated on CIFAR-10, Visual Wake Words, and Keyword Spotting, ConvLUT achieves competitive accuracy with fully unrolled inference latencies below ∼50\sim 50 ns. On CIFAR-10 it reaches at least a 8844×8844\times latency reduction over non-logic-based prior implementations, and outperforms existing MLP-style LUT-based models on the same task by at least 2020 pp in test accuracy.

Figures & tables

Explore similar work

CardsList
  1. HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

    Apr 24, 2026Chang Sun, Zhiqiang Que, Bakhtiar Zadeh +4Efficient Neural Network InferenceFPGA-Based Neural Network Acceleration