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
  • [21] Automatic Tuning of MPI Runtime Parameter Settings by Using Machine Learning
    Pellegrini, Simone
    Fahringer, Thomas
    Jordan, Herbert
    Moritsch, Hans
    PROCEEDINGS OF THE 2010 COMPUTING FRONTIERS CONFERENCE (CF 2010), 2010, : 115 - 116
  • [22] Predicting maximum temperatures over India 10-days ahead using machine learning models
    Ratnam, J. V.
    Behera, Swadhin K.
    Nonaka, Masami
    Martineau, Patrick
    Patil, Kalpesh R.
    SCIENTIFIC REPORTS, 2023, 13 (01):
  • [23] Predicting maximum temperatures over India 10-days ahead using machine learning models
    J. V. Ratnam
    Swadhin K. Behera
    Masami Nonaka
    Patrick Martineau
    Kalpesh R. Patil
    Scientific Reports, 13 (1)
  • [24] TinyML Techniques for running Machine Learning models on Edge Devices
    Mukherjee, Arijit
    Ukil, Arijit
    Dey, Swarnava
    Kulkarni, Gitesh
    SECOND INTERNATIONAL CONFERENCE ON AIML SYSTEMS 2022, 2022,
  • [25] Real-time classification of ground conditions ahead of a TBM using supervised machine learning algorithms
    Sebbeh-Newton, Sylvanus
    Seidu, Jamel
    Ankah, Mawuko Luke Yaw
    Ewusi-Wilson, Rodney
    Zabidi, Hareyani
    Amakye, Louis
    MODELING EARTH SYSTEMS AND ENVIRONMENT, 2024, 10 (05) : 6173 - 6186
  • [26] Real-time day ahead energy management for smart home using machine learning algorithm
    Vasudevan, Nisha
    Venkatraman, Vasudevan
    Ramkumar, A.
    Sheela, A.
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2021, 41 (05) : 5665 - 5676
  • [27] Comparing multi-step ahead building cooling load prediction using shallow machine learning and deep learning models
    Chalapathy, Raghavendra
    Khoa, Nguyen Lu Dang
    Sethuvenkatraman, Subbu
    SUSTAINABLE ENERGY GRIDS & NETWORKS, 2021, 28
  • [28] Stock Price Prediction Using Time Series, Econometric, Machine Learning, and Deep Learning Models
    Chatterjee, Ananda
    Bhowmick, Hrisav
    Sen, Jaydip
    2021 IEEE Mysore Sub Section International Conference, MysuruCon 2021, 2021, : 289 - 296
  • [29] Stock price prediction using time series, econometric, machine learning, and deep learning models
    Chatterjee, Ananda
    Bhowmick, Hrisav
    Sen, Jaydip
    arXiv, 2021,
  • [30] Predicting Time to Dialysis and Unplanned Dialysis Start Using Machine Learning Models
    Shukla, Mahesh
    Garrett, Brendan C.
    Azari, Ali
    Kipping, Emily
    Culleton, Bruce F.
    JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY, 2021, 32 (10): : 284 - 284