# Enabling Large Neural Networks on Tiny Microcontrollers with Swapping

arXiv: https://arxiv.org/abs/2101.08744 · HTML: https://mlsanity.com/paper/2101.08744/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2021.

## Built on by (most cited first, 9 of 9)

- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [Demand Layering for Real-Time DNN Inference with Minimized Memory Usage](https://mlsanity.com/paper/2210.04024/) (2022)
- [DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning](https://mlsanity.com/paper/2401.09068/) (2024)
- [SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget](https://mlsanity.com/paper/2401.16757/) (2024)
- [Machine Learning-based Positioning using Multivariate Time Series Classification for Factory Environments](https://mlsanity.com/paper/2308.11670/) (2023)
- [Power-Performance Characterization of TinyML Systems](https://mlsanity.com/paper/2608.21646/) (2026)

## Abstract (arXiv)

Running neural networks (NNs) on microcontroller units (MCUs) is becoming increasingly important, but is very difficult due to the tiny SRAM size of MCU. Prior work proposes many algorithm-level techniques to reduce NN memory footprints, but all at the cost of sacrificing accuracy and generality, which disqualifies MCUs for many important use cases. We investigate a system solution for MCUs to execute NNs out of core: dynamically swapping NN data chunks between an MCU's tiny SRAM and its large, low-cost external flash. Out-of-core NNs on MCUs raise multiple concerns: execution slowdown, storage wear out, energy consumption, and data security. We present a study showing that none is a showstopper; the key benefit -- MCUs being able to run large NNs with full accuracy and generality -- triumphs the overheads. Our findings suggest that MCUs can play a much greater role in edge intelligence.