Windows slower than Linux

Description

I run the same onnx in windows and linux using trtexec, the difference is operating system, windows is much slower than linux. Why is windows so slow?

Environment

TensorRT Version: 8.2
GPU Type: 2070super
Nvidia Driver Version: 495(windows), 470(linux)
CUDA Version: 11.4
CUDNN Version: 8.2
Operating System + Version: windows10, Ubuntu18.04

Relevant Files

onnx.zip (4.9 MB)

Steps To Reproduce

trtexec --onnx=model.onnx --minShapes=input:1x3x64x64 --optShapes=input:1x3x128x128 --maxShapes=input:1x3x256x256 --workspace=1000

Hi,
Request you to share the model, script, profiler and performance output if not shared already so that we can help you better.
Alternatively, you can try running your model with trtexec command.
https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec

While measuring the model performance, make sure you consider the latency and throughput of the network inference, excluding the data pre and post-processing overhead.
Please refer below link for more details:
https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-722/best-practices/index.html#measure-performance
https://docs.nvidia.com/deeplearning/tensorrt/best-practices/index.html#model-accuracy

Thanks!