Clifford Neural Layers improve PDE modeling by introducing Clifford Algebra into neural networks. In this project we focus on optimizing the inference of 2/3D Clifford convolutional layers and multivector activation layers for one core CPU performance. Overall, by testing on a real network block involving Clifford convolutional layers and multivector activation layers, we observe that our implementation is 30% faster than standard PyTorch implementation in relatively large data + network size (>L2 cache). We open source our code base at https://github.com/egretwAlker/c-opt-clifford-layers
@article{arxiv.2507.01040,
title = {Fast Clifford Neural Layers},
author = {Tianxiang Xia and Max Neuwinger and Lin Xiao},
journal= {arXiv preprint arXiv:2507.01040},
year = {2025}
}