From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers

• URL: http://arxiv.org/abs/2606.17249v1
• Date: Mon, 15 Jun 2026 19:49:38 GMT
• Title: From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers
• Abstract summary: We present an end-to-end open-source reproduction of FastGRNN, a compact gated cell, deployed on two bare-metal targets.<n>The model occupies 566 bytes of weights and achieves macro F1 = 0.918 (seed 0; five-seed Q15 mean 0.853+-0.107) on the HAPT test set.<n>Both platforms sustain real-time 50 Hz streaming inference (9.21 ms per sample on Arduino; 13 ms on MSP430), where a 256-entry sigmoid/tanh look-up table delivers a 30.5x speedup.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets. Yet a multi-year global semiconductor supply constraint and the growing energy and carbon cost of always-online inference expose the fragility of this trajectory and motivate the opposite direction: refactoring AI and ML algorithms to fit the small, ubiquitous microcontrollers already in mass production in wearables, sensors, and edge appliances. We present an end-to-end open-source reproduction of FastGRNN, a compact gated recurrent cell, deployed on two bare-metal targets: the 8-bit Arduino (ATmega328P) and the 16-bit MSP430 (no hardware multiplier; 16 KB Flash; 512 B SRAM). Our compression pipeline combines low-rank weight factorization, iterative hard-thresholding sparsity, and per-tensor Q15 post-training quantization with explicit activation calibration. The deployed model occupies 566 bytes of weights and achieves macro F1 = 0.918 (seed 0; five-seed Q15 mean 0.853+-0.107) on the HAPT test set. It matches a PyTorch reference at 100% prediction agreement across 3,399 test windows (MCU seed 0; 99.91-100% C-equivalent across five seeds). Both platforms sustain real-time 50 Hz streaming inference (9.21 ms per sample on Arduino; 13 ms on MSP430), where a 256-entry sigmoid/tanh look-up table delivers a 30.5x speedup on the multiplier-less MSP430. Four contributions extend the original FastGRNN paper: (i) cross-platform bit-equivalent deterministic inference; (ii) characterization of recurrent warm-up latency (median 74 samples, 1.48 s; worst-case 125 samples, 2.50 s over 100 test windows); (iii) a deployable look-up-table recipe for multiplier-less embedded targets; and (iv) hardware energy characterization showing 17.7 mW active inference power, <0.09 mW idle power, and 96.7% energy reduction with the LUT.

Related papers

• SymbolicLight V2: Hybrid Neuromorphic Architecture and Sparse Execution for Low-Energy Language Inference [8.419155861590548]
  SymbolicLight V2 combines sparse event computation with continuous-state processing.<n>We implement SymbolicLight V2 on an Alveo U50C FPGA using digital fixed-point arithmetic.<n>On four Cortex-A76 cores of a ROCK 5T, complete requests reach 65.4 tokens/s at 9.80 W and 0.151 J per generated token at the adapter's AC input.
  arXiv  Detail & Related papers  (2026-09-09T06:18:49Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML [0.0]
  We present HYPER-TINYPW, a compression-as-generation approach that replaces most stored PW weights with generated weights.<n>A shared micro-MLP synthesizes PW kernels once at load time from tiny per-layer codes, caches them, and executes them with standard integer operators.<n>It preserves commodity MCU runtimes and adds only a one-off cost.
  arXiv  Detail & Related papers  (2026-03-26T01:08:52Z)
• Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels [83.99688944263843]
  Weight-De Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction.<n>At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16.<n>A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r2) intermediates, eliminating the dense product.
  arXiv  Detail & Related papers  (2026-03-23T17:57:24Z)
• TinyML Enhances CubeSat Mission Capabilities [8.462623779881566]
  The paper presents a Convolutional Neural Networks (ConvNets) model optimization and deployment pipeline for onboard image classification.<n>Our pipeline integrates structured iterative pruning, post-training INT8 quantization, and hardware-aware operator mapping to compress models.<n>We demonstrate an average reduction in RAM usage of 89.55% and Flash memory of 709% for the optimized models.
  arXiv  Detail & Related papers  (2026-03-20T17:51:07Z)
• GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model [7.2566101637741545]
  GPT-OSS-20B (Mixture-of-Experts; 20.9B total, approx. 3.61B active) is evaluated against dense baselines Qwen3-32B and Yi-34B.<n>With only 17.3% of parameters active (3.61B of 20.9B), GPT-OSS-20B provides about 31.8% higher decode throughput and 25.8% lower energy per 1000 generated tokens.
  arXiv  Detail & Related papers  (2025-08-22T03:37:27Z)
• A 71.2-$μ$W Speech Recognition Accelerator with Recurrent Spiking Neural Network [0.0502254944841629]
  We propose a compact recurrent spiking neural network with two recurrent layers, one fully connected layer, and a low time step.<n>The 2.79-MB model undergoes pruning and 4-bit fixed-point quantization, shrinking it by 96.42% to 0.1 MB.<n>The design operates in real time at 100 kHz, consuming 71.2 $mu$W, surpassing state-of-the-art designs.
  arXiv  Detail & Related papers  (2025-03-27T10:14:00Z)
• Optimizing the Deployment of Tiny Transformers on Low-Power MCUs [12.905978154498499]
  This work aims to enable and optimize the flexible, multi-platform deployment of encoder Tiny Transformers on commercial MCUs. Our framework provides an optimized library of kernels to maximize data reuse and avoid data marshaling operations into the crucial attention block. We show that our MHSA depth-first tiling scheme reduces the memory peak by up to 6.19x, while the fused-weight attention can reduce the runtime by 1.53x, and number of parameters by 25%.
  arXiv  Detail & Related papers  (2024-04-03T14:14:08Z)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization [67.74400574357472]
  LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference.<n> Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision.<n>Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods.
  arXiv  Detail & Related papers  (2024-01-31T18:58:14Z)
• Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors [64.68349896377629]
  This work presents a novel autonomous end-to-end system that addresses the monocular relative localization, through deep neural networks (DNNs), of two peer nano-drones. To cope with the ultra-constrained nano-drone platform, we propose a vertically-integrated framework, including dataset augmentation, quantization, and system optimizations. Experimental results show that our DNN can precisely localize a 10cm-size target nano-drone by employing only low-resolution monochrome images, up to 2m distance.
  arXiv  Detail & Related papers  (2023-03-03T14:14:08Z)
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays [66.62377866022221]
  Latent Replay-based Continual Learning (CL) techniques enable online, serverless adaptation in principle. We introduce a HW/SW platform for end-to-end CL based on a 10-core FP32-enabled parallel ultra-low-power processor. Our results show that by combining these techniques, continual learning can be achieved in practice using less than 64MB of memory.
  arXiv  Detail & Related papers  (2021-10-20T11:01:23Z)
• HAWQV3: Dyadic Neural Network Quantization [73.11579145354801]
  Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. We present HAWQV3, a novel mixed-precision integer-only quantization framework.
  arXiv  Detail & Related papers  (2020-11-20T23:51:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.