PerfNetRT: Platform-Aware Performance Modeling for Optimized Deep Neural Networks

Ying Chiao Liao, Chuan Chi Wang, Chia Heng Tu, Ming Chang Kao, Wen Yew Liang, Shih Hao Hung

研究成果: Conference contribution

摘要

As deep learning techniques based on artificial neural networks have been widely applied to diverse application domains, the delivered performance of such deep learning models on the target hardware platforms should be taken into account during the system design process in order to meet the application-specific timing requirements. Specifically, there are neural network optimization frameworks available for boosting the execution efficiency of a trained model on the vendor-specific hardware platforms, e.g., OpenVINO [1] for Intel hardware and TensorRT [2] for NVIDIA GPUs, and it is important that system designers have access to the estimated performance of the optimized models running on the specific hardware so as to make better design decisions. In this work, we have developed PerfNetRT to facilitate the design making process by offering the estimated inference time of a trained model that is optimized for the NVIDIA GPU using TensorRT. Our preliminary results show that PerfNetRT is able to produce accurate estimates of the inference time for the popular models, including LeNet [3], AlexNet [4] and VGG16 [5], which are optimized with TensorRT running on NVIDIA GTX 1080Ti.

原文English
主出版物標題Proceedings - 2020 International Computer Symposium, ICS 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面153-158
頁數6
ISBN(電子)9781728192550
DOIs
出版狀態Published - 2020 十二月
事件2020 International Computer Symposium, ICS 2020 - Tainan, Taiwan
持續時間: 2020 十二月 172020 十二月 19

出版系列

名字Proceedings - 2020 International Computer Symposium, ICS 2020

Conference

Conference2020 International Computer Symposium, ICS 2020
國家/地區Taiwan
城市Tainan
期間20-12-1720-12-19

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 電腦科學應用
  • 資訊系統
  • 資訊系統與管理
  • 計算數學

指紋

深入研究「PerfNetRT: Platform-Aware Performance Modeling for Optimized Deep Neural Networks」主題。共同形成了獨特的指紋。

引用此