# Enabling Mixed-Precision Quantized Neural Networks in Extreme-Edge Devices

arXiv: https://arxiv.org/abs/2007.07759 · HTML: https://mlsanity.com/paper/2007.07759/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks](https://mlsanity.com/paper/2209.00839/) (2022)
- [Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations](https://mlsanity.com/paper/2407.14274/) (2024)
- [A 3 TOPS/W RISC-V Parallel Cluster for Inference of Fine-Grain Mixed-Precision Quantized Neural Networks](https://mlsanity.com/paper/2307.01056/) (2023)
- [Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks](https://mlsanity.com/paper/2602.00567/) (2026)
- [HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2402.01226/) (2024)
- [Computer Vision Model Compression Techniques for Embedded Systems: A Survey](https://mlsanity.com/paper/2408.08250/) (2024)
- [Empowering Vector Architectures for ML: The CAMP Architecture for Matrix Multiplication](https://mlsanity.com/paper/2504.08137/) (2025)
- [MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration](https://mlsanity.com/paper/2509.15187/) (2025)
- [End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables](https://mlsanity.com/paper/2604.10117/) (2026)

## Abstract (arXiv)

The deployment of Quantized Neural Networks (QNN) on advanced microcontrollers requires optimized software to exploit digital signal processing (DSP) extensions of modern instruction set architectures (ISA). As such, recent research proposed optimized libraries for QNNs (from 8-bit to 2-bit) such as CMSIS-NN and PULP-NN. This work presents an extension to the PULP-NN library targeting the acceleration of mixed-precision Deep Neural Networks, an emerging paradigm able to significantly shrink the memory footprint of deep neural networks with negligible accuracy loss. The library, composed of 27 kernels, one for each permutation of input feature maps, weights, and output feature maps precision (considering 8-bit, 4-bit and 2-bit), enables efficient inference of QNN on parallel ultra-low-power (PULP) clusters of RISC-V based processors, featuring the RV32IMCXpulpV2 ISA. The proposed solution, benchmarked on an 8-cores GAP-8 PULP cluster, reaches peak performance of 16 MACs/cycle on 8 cores, performing 21x to 25x faster than an STM32H7 (powered by an ARM Cortex M7 processor) with 15x to 21x better energy efficiency.