mlsanityData to 14 Oct 2026

Power-Performance Characterization of TinyML Systems

arXiv 2608.21646 ↗First posted 21 Aug 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

17 of 32 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  3. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  4. 2021MLPerf Tiny Benchmarkcited by 124
  5. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  6. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
  7. 2020Benchmarking TinyML Systems: Challenges and Directioncited by 91
  8. 2019Benchmarking TPU, GPU, and CPU Platforms for Deep Learningcited by 52
  9. 2021An Evaluation of Edge TPU Accelerators for Convolutional Neural Networkscited by 39
  10. 2019PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processorscited by 35
  11. 2021DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devicescited by 26
  12. 2019High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processorscited by 19
5 more
  1. 2019Neural Network Inference on Mobile SoCscited by 17
  2. 2019Neural networks on microcontrollers: saving memory at inference via operator reorderingcited by 15
  3. 2018High Performance Zero-Memory Overhead Direct Convolutionscited by 14
  4. 2021Enabling Large Neural Networks on Tiny Microcontrollers with Swappingcited by 9
  5. 2021Measuring what Really Matters: Optimizing Neural Networks for TinyMLcited by 8

Built on by

Not cited yet.