How to copy data between GPU and DLA

Hi, all

We have trouble in using DLA.

When the infer layers are not supported by DLA, we need to use --allowGPUFallback to use GPU.

I want to know how data is transferred between DLA and GPU during the fallback of GPU?

Is data transmitted directly from GPU to DLA or from DLA to CPU and then to GPU?

If possible, please explain the process of data transmission,thank you!

This forum is exclusively for developers who are part of the NVIDIA DRIVE® AGX SDK Developer Program | NVIDIA Developer To post in the forum, please use an account associated with your corporate or university email address.
This helps us ensure that the forum remains a platform for verified members of the developer program.

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