Power-Performance Characterization of TinyML Systems

• URL: http://arxiv.org/abs/2608.21646v1
• Date: Fri, 21 Aug 2026 21:34:24 GMT
• Title: Power-Performance Characterization of TinyML Systems
• Abstract summary: This paper presents a systematic performance and power characterization of diverse TinyML applications on microcontrollers (MCUs)<n>We focus on the impact of the multiple layers of abstraction that provide higher programmability at the expense of performance and energy efficiency.
• Score: 23.93944681214181
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper presents a systematic performance and power characterization of diverse TinyML applications on microcontrollers (MCUs), spanning neural network models, software libraries, operating systems, and hardware architectures. We focus on the impact of the multiple layers of abstraction that provide higher programmability at the expense of performance and energy efficiency. We propose a model to estimate the costs of different abstraction layers and make recommendations for minimizing those costs. Our findings can help designers with Neural Architecture Search (NAS) and CNN inference optimization on edge devices.

Related papers

• LSNet: See Large, Focus Small [67.05569159984691]
  We introduce LS (textbfLarge-textbfSmall) convolution, which combines large- kernel perception and small- kernel aggregation.<n>LSNet achieves superior performance and efficiency over existing lightweight networks in various vision tasks.
  arXiv  Detail & Related papers  (2025-03-29T16:00:54Z)
• PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing [48.30406812516552]
  We introduce the PLM, a Peripheral Language Model, developed through a co-design process that jointly optimize model architecture and edge system constraints.<n>PLM employs a Multi-head Latent Attention mechanism and employs the squared ReLU activation function to encourage sparsity, thereby reducing peak memory footprint.<n> evaluation results demonstrate that PLM outperforms existing small language models trained on publicly available data.
  arXiv  Detail & Related papers  (2025-03-15T15:11:17Z)
• Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation [0.43550340493919387]
  Tiny machine learning (TinyML) promises to revolutionize fields such as healthcare, environmental monitoring, and industrial maintenance.<n>The complex optimizations required for successful TinyML deployment continue to impede its widespread adoption.<n>We propose a new state-of-the-art Data Aware Neural Architecture Search technique and demonstrate its effectiveness on the novel TinyML VisionWake' dataset.
  arXiv  Detail & Related papers  (2025-02-18T09:51:03Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• A quantitative framework for evaluating architectural patterns in ML systems [49.1574468325115]
  This study proposes a framework for quantitative assessment of architectural patterns in ML systems.<n>We focus on scalability and performance metrics for cost-effective CPU-based inference.
  arXiv  Detail & Related papers  (2025-01-20T15:30:09Z)
• Energy-Aware FPGA Implementation of Spiking Neural Network with LIF Neurons [0.5243460995467893]
  Spiking Neural Networks (SNNs) stand out as a cutting-edge solution for TinyML. This paper presents a novel SNN architecture based on the 1st Order Leaky Integrate-and-Fire (LIF) neuron model. A hardware-friendly LIF design is also proposed, and implemented on a Xilinx Artix-7 FPGA.
  arXiv  Detail & Related papers  (2024-11-03T16:42:10Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review [1.049712834719005]
  This review provides an in-depth analysis of the advancements in efficient neural networks and the deployment of deep learning models on ultra-low power microcontrollers. The core of the review centres on efficient neural networks for TinyML. It covers techniques such as model compression, quantization, and low-rank factorization, which optimize neural network architectures for minimal resource utilization. The paper then delves into the deployment of deep learning models on ultra-low power MCUs, addressing challenges such as limited computational capabilities and memory resources.
  arXiv  Detail & Related papers  (2023-11-20T16:20:13Z)
• An Ultra-low Power TinyML System for Real-time Visual Processing at Edge [7.327401565768275]
  This brief presents an extremely tiny backbone to construct high efficiency CNN models for various visual tasks. A specially designed neural co-processor (NCP) is interconnected with MCU to build an ultra-low power TinyML system. The proposed TinyML system based on our model, NCP and instruction set yields considerable accuracy and achieves a record ultra-low power of 160mW.
  arXiv  Detail & Related papers  (2022-07-11T06:56:27Z)
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications [46.97774949613859]
  Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI) However, their superior performance comes at the considerable cost of computational complexity. This paper provides an overview of efficient deep learning methods, systems and applications.
  arXiv  Detail & Related papers  (2022-04-25T16:52:48Z)
• Measuring what Really Matters: Optimizing Neural Networks for TinyML [7.455546102930911]
  neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity. Introducing NNs to resource-constrained devices enables cost-efficient deployments, widespread availability, and the preservation of sensitive data. This work addresses the challenges of bringing Machine Learning to MCUs, where we focus on the ubiquitous ARM Cortex-M architecture.
  arXiv  Detail & Related papers  (2021-04-21T17:14:06Z)
• MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search [94.80212602202518]
  We propose Multi-Scale Resource-Aware Neural Architecture Search (MS-RANAS) We employ a one-shot architecture search approach in order to obtain a reduced search cost. We achieve state-of-the-art results in terms of accuracy-speed trade-off.
  arXiv  Detail & Related papers  (2020-09-29T11:56:01Z)

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.