TRT not showing layers on DLA Jetson AGX Orin

[totototoby]

Hi, I am having difficulty to make Jetson AGX Orin 64G dev kit to use DLA.
This is my environment: jp60 (36.2) + python3.10 + cuda 12.2 + torch 2.30 + torchvision 0.18 + tensorrt8.6
I followed the jetson_dla_tutorial(GitHub - NVIDIA-AI-IOT/jetson_dla_tutorial: A tutorial for getting started with the Deep Learning Accelerator (DLA) on NVIDIA Jetson)
My steps are as follows:

1. python export.py model_gn data/model_gn.onnx
2. trtexec --onnx=data/model_gn.onnx --shapes=input:32x3x32x32 --saveEngine=data/model_gn.engine --exportProfile=data/model_gn.json --int8 --useDLACore=0 --allowGPUFallback --useSpinWait --separateProfileRun > data/model_gn.log
   The output is attached. It never shows any layer running on DLA.
   model_gn.log (47.5 KB)
   term_out.txt (12.3 KB)

[carolyuu]

Hi,
Here are some suggestions for the common issues:

1. Performance

Please run the below command before benchmarking deep learning use case:

$ sudo nvpmodel -m 0
$ sudo jetson_clocks

2. Installation

Installation guide of deep learning frameworks on Jetson:

• TensorFlow: https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html
• PyTorch: Installing PyTorch for Jetson Platform - NVIDIA Docs
  We also have containers that have frameworks preinstalled:
  Data Science, Machine Learning, AI, HPC Containers | NVIDIA NGC

3. Tutorial

Startup deep learning tutorial:

• Jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson
• TensorRT sample: Jetson/L4T/TRT Customized Example - eLinux.org

4. Report issue

If these suggestions don’t help and you want to report an issue to us, please attach the model, command/step, and the customized app (if any) with us to reproduce locally.

Thanks!

[totototoby]

All the necessary frameworks/libraries have already been installed by following the steps in the given links. After I fixed the clock frequency, it still does not show which layers are on DLA and which are on GPU.

[AastaLLL]

Hi,

To get the layer placement detailed info, please add the --verbose log when running trtexec.

Thanks.