About using multi-process to execute two engine models in one program

Description

Problem description:
Hi, I can run my detection engine model or super resolution engine model separately in Jetson Orin Nano and it works fine. But when I use multithreading to run the program of both models at the same time, there will be a problem, and the picture will be torn and rippled. I hope I can find and solve this problem here.

Environment

TensorRT Version:8.6.2.3

NVIDIA GPU:jetson orin nano 8GB

NVIDIA Driver Version:

CUDA Version:12.2.140

CUDNN Version:1.0

Operating System:ubuntu 22.04 jammy jellyfish 5.15.136-tegra

Python Version (if applicable):3.10.12

Tensorflow Version (if applicable):

PyTorch Version (if applicable):2.3.0

Baremetal or Container (if so, version):

Relevant Files

Model link:

Steps To Reproduce

Download the uploaded demo and execute python srgpu.py and python yolo256.py. You can see that the super-resolution and detection effects are normal. Execute python one_cam_demo.py and you can see that the output image has problems. There are flickers and screen tearing.