Doubts about Jetson AGX Orin as PCIe EP

[rubens.lima]

I have some doubts about the Jetson AGX Orin as PCIe Endpoint:

1. The PCIe RC requesting DMA transfers to Jetson EP, vice versa. Is it possible to implement DMA in this setup?
2. Another endpoint sending an MSI over p2p message. Is it possible to handle the MSI in this Jetson EP?

[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: Installing TensorFlow for Jetson Platform - NVIDIA Docs
• 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!

[rubens.lima]

Is @carolyuu a bot?

[WayneWWW]

Hi,

The sample pcie example we provided there shall already have DMA implementation.

[rubens.lima]

Is the sample pcie example available for L4T 36.3.0/ JetPack 6.0??

[WayneWWW]

please refer to

https://docs.nvidia.com/jetson/archives/r36.4/DeveloperGuide/SD/Communications/PcieEndpointMode.html?highlight=endpoint

[rubens.lima]

I can’t update my version to 36.4.