# High performance ultra-low-precision convolutions on mobile devices

arXiv: https://arxiv.org/abs/1712.02427 · HTML: https://mlsanity.com/paper/1712.02427/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2017.

## Built on by (most cited first, 5 of 5)

- [NIPQ: Noise proxy-based Integrated Pseudo-Quantization](https://mlsanity.com/paper/2206.00820/) (2022)
- [DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables](https://mlsanity.com/paper/2304.09049/) (2023)
- [MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point](https://mlsanity.com/paper/2207.08867/) (2022)
- [Symmetry Regularization and Saturating Nonlinearity for Robust Quantization](https://mlsanity.com/paper/2208.00338/) (2022)
- [MiNL: Micro-images based Neural Representation for Light Fields](https://mlsanity.com/paper/2209.08277/) (2022)

## Abstract (arXiv)

Many applications of mobile deep learning, especially real-time computer vision workloads, are constrained by computation power. This is particularly true for workloads running on older consumer phones, where a typical device might be powered by a single- or dual-core ARMv7 CPU. We provide an open-source implementation and a comprehensive analysis of (to our knowledge) the state of the art ultra-low-precision (<4 bit precision) implementation of the core primitives required for modern deep learning workloads on ARMv7 devices, and demonstrate speedups of 4x-20x over our additional state-of-the-art float32 and int8 baselines.