NvBufSurfTransform on cuda stream

• Hardware Platform (both Jetson and GPU)
• DeepStream Version: 6.1.1
• JetPack Version (5.0.2)
• TensorRT Version 8.4
• NVIDIA GPU Driver Version (515)
• Issue Type: questions

Hi, with a created cuda stream, what is intuitive way to use NvBufSurfTransform API with created cuda stream. I can not understand NvBufSurfTransformSetSessionParams function and how it can affect subsequence NvBufSurfTransform and NvBufSurfTransformAsync call

Please describe your use case and the complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
• The pipeline being used

Updated

You can use NvBufSurfTransformSetSessionParams API to create a session with your own config paras. The NvBufSurfTransform module use this session to implement the related logic. But the session is an internal structure so
it is unnecessary for custom to concern its realization.

Hi, what if I want to use multiple sessions to call NvBufSurfTransform at parallel threads. How NvBufSurfTransform know which session to use when that is not pass directly as function parameters

Usually, you don’t need to pay attention to the implementation of details. You can refer the link below to learn how to control the paras in the same thread.
https://manpages.ubuntu.com/manpages/bionic/man3/pthread_key_create.3.html

So, as long as I call NvBufSurfTransformSetSessionParams in the same thread with NvBufSurfTransform, the behaviour is guaranteed?
A bit aside, NvBufSurfTransform with custom session means that the work is done on the specified CUDA stream and the stream is synchronized at the end of the function call. Am I correct?

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Yes. You can open a new topic at any time when you encounter specific problems in your actual development.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.