Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVM

被引:0
|
作者
Liu, Chen [1 ]
Jobst, Matthias [1 ]
Jobst, Matthias [1 ]
Guo, Liyuan [1 ]
Shi, Xinyue [1 ]
Partzsch, Johannes [1 ]
Mayr, Christian [1 ]
机构
[1] Tech Univ Dresden, Dresden, Germany
来源
PROCEEDINGS 2023 IEEE/ACM INTERNATIONAL WORKSHOP ON COMPILERS, DEPLOYMENT, AND TOOLING FOR EDGE AI, CODAI 2023 | 2023年
关键词
TVM; MicroTVM; model deployment; BYOC; UMA;
D O I
10.1145/3615338.3618125
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the past few years, more and more AI applications have been applied to edge devices. However, models trained by data scientists with machine learning frameworks, such as PyTorch or TensorFlow, can not be seamlessly executed on edge. In this paper, we develop an end-to-end code generator parsing a pre-trained model to C source libraries for the backend using MicroTVM, a machine learning compiler framework extension addressing inference on bare metal devices. An analysis shows that specific compute-intensive operators can be easily offloaded to the dedicated accelerator with a Universal Modular Accelerator (UMA) interface, while others are processed in the CPU cores. By using the automatically generated ahead-of-time C runtime, we conduct a hand gesture recognition experiment on an ARM Cortex M4F core.
引用
收藏
页码:37 / 40
页数:4
相关论文
共 50 条
  • [41] Machine Learning at the Edge Using Neural Network Processor
    Lee, Edwin
    Parker, Michael
    Cervantes, Michael
    Plotner, Ben
    2023 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE, HPEC, 2023,
  • [42] Advanced bridge visual inspection using real-time machine learning in edge devices
    Zakaria, Mahta
    Karaaslan, Enes
    Catbas, F. Necati
    ADVANCES IN BRIDGE ENGINEERING, 2022, 3 (01):
  • [43] Machine Learning Models for Edge Placement Error Based Etch Bias
    Meng, Yang
    Kim, Young-Chang
    Guo, Shujie
    Shu, Zhongli
    Zhang, Yingchun
    Liu, Qingwei
    IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2021, 34 (01) : 42 - 48
  • [44] Power Efficient Machine Learning Models Deployment on Edge IoT Devices
    Fanariotis, Anastasios
    Orphanoudakis, Theofanis
    Kotrotsios, Konstantinos
    Fotopoulos, Vassilis
    Keramidas, George
    Karkazis, Panagiotis
    SENSORS, 2023, 23 (03)
  • [45] Estimation of Daily Photovoltaic Power One Day Ahead With Hybrid Deep Learning and Machine Learning Models
    Agir, Tuba T.
    ENERGY SCIENCE & ENGINEERING, 2025,
  • [46] Comprehensive Prediction of Stock Prices Using Time Series, Statistical, Machine Learning, and Deep Learning Models
    Sen, Jaydip
    Kumar, Abhishek
    Thomas, Aji
    Todi, Nishant Kumar
    Olemmyan, Olive
    Tripathi, Swapnil
    Arora, Vaibhav
    TechRxiv, 2023,
  • [47] Deploying Machine Learning Models Using Progressive Web Applications: Implementation Using a Neural Network Prediction Model for Pneumonia Related Child Mortality in The Gambia
    Mohammed, Nuredin I.
    Jarde, Alexander
    Mackenzie, Grant
    D'Alessandro, Umberto
    Jeffries, David
    FRONTIERS IN PUBLIC HEALTH, 2022, 9
  • [48] Time consideration in machine learning models for train comfort prediction using LSTM networks
    Martinez-Llop, Pablo Garrido
    Bobi, Juan de Dios Sanz
    Ortega, Manuel Olmedo
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [49] Forecasting time series water levels on Mekong river using machine learning models
    Thanh-Tung Nguyen
    Quynh Nguyen Huu
    Li, Mark Junjie
    2015 SEVENTH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE), 2015, : 292 - 297
  • [50] Predicting the time to get back to work using statistical models and machine learning approaches
    Bouliotis, George
    Underwood, M.
    Froud, R.
    BMC MEDICAL RESEARCH METHODOLOGY, 2024, 24 (01)