Improving Multi-DNN Inference Performance under Embedded GPU Environments with Overhead Minimization

Author(s):  
Cheolsun Lim ◽  
Myungsun Kim
Keyword(s):  
Author(s):  
Marco Antonio Simoes Teixeira ◽  
Nicolas Dalmedico ◽  
Higor Barbosa Santos ◽  
Andre Schneider De Oliveira ◽  
Lucia Valeria Ramos De Arruda ◽  
...  

Author(s):  
Mulham Fawakherji ◽  
Ciro Potena ◽  
Domenico D. Bloisi ◽  
Marco Imperoli ◽  
Alberto Pretto ◽  
...  

2020 ◽  
Author(s):  
Yazhou Li ◽  
Yahong Rosa Zheng

This paper presents two methods, tegrastats GUI version jtop and Nsight Systems, to profile NVIDIA Jetson embedded GPU devices on a model race car which is a great platform for prototyping and field testing autonomous driving algorithms. The two profilers analyze the power consumption, CPU/GPU utilization, and the run time of CUDA C threads of Jetson TX2 in five different working modes. The performance differences among the five modes are demonstrated using three example programs: vector add in C and CUDA C, a simple ROS (Robot Operating System) package of the wall follow algorithm in Python, and a complex ROS package of the particle filter algorithm for SLAM (Simultaneous Localization and Mapping). The results show that the tools are effective means for selecting operating mode of the embedded GPU devices.


Author(s):  
Zaifeng Pan ◽  
Feng Zhang ◽  
Yanliang Zhou ◽  
Jidong Zhai ◽  
Xipeng Shen ◽  
...  
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document