NVIDIA Jetpack 5.0.2 release supports Ubuntu 20.04, Jetson AGX Orin

The NVIDIA Jetpack 5.0.2 production release is out with Ubuntu 20.04, the Jetson Linux 35.1 BSP 1 with Linux Kernel 5.10, an UEFI-based bootloader, support for Jetson AGX Orin module and developer kit, as new as updated packages such as CUDA 11.4, TensorRT 8.4.1, cuDNN 8.4.1.

NVIDIA Jetson modules and developer kits are nice little pieces of hardware for AI workloads, but the associated NVIDIA Jetpack SDK was based on the older Ubuntu 18.04 which was not suitable for some projects. But the good news is that Ubuntu 20.04 was being worked on and initially available through the Jetpack 5.0.0/5.0.1 developer previews, and NVIDIA Jetpack 5.0.2 SDK is the first production release with support for Ubuntu 20.04.

NVIDIA Jetpack 5.0.2 Ubuntu 20.04

Besides the upgrade to Ubuntu 20.04, the Jetpack 5.0.2 SDK also adds support for both the Jetson AGX Orin Developer Kit and the newly-available Jetson AGX Orin 32 GB production module. It still works with the earlier models including  Jetson AGX Xavier and Jetson Xavier NX series modules and developer kits. However, there’s no mention of Jetson TX2, Jetson Nano, and Jetson TX1 and those appear to be stuck at the Jetpack 4.6.1 SDK with Ubuntu 18.04.

Other notable updates to the Jetpack 5.0.2 release include:

  • Enables Jetson AGX Orin Developer Kit to emulate the performance of Jetson AGX Orin 64GB, Jetson AGX Orin 32GB, Jetson Orin NX 16GB, and Jetson Orin NX 8GB modules.
  • Security – Secure storage in OP-TEE using normal world (REE) file system
  • Over The Air Updates – Image-based OTA tools to upgrade Jetson AGX Xavier or Jetson Xavier NX modules running JetPack 4.x releases
  • Power – Support for Power Estimator for Jetson AGX Orin and Jetson Xavier NX series
  • Camera
    • Argus support for YUV444 and Linear RGB888 output format for Jetson AGX Xavier and Jetson Xavier NX.
    • HDR Support for Jetson AGX Orin. Digital Overlap (DOL) Mode and Piecewise Linear (PWL) are supported.
  • Multimedia
    • AV1 encoding/decoding on Jetson AGX Orin
    • Support for nvJPEG load balancing to use 2 nvJPEG engines in Jetson AGX Orin, providing 2x the encoding\decoding performance compared to JetPack 5.0/5.0.1 Developer Preview releases.
    • Pre-Processing Enhancements (PPE) module provides a framework for various video encode enhancement algorithms. Temporal Adaptive Quantization (TAQ) is supported.
  • Cloud Native – New Containers on NGC
    • JetPack container with all JetPack components like CUDA, cuDNN, TensorRT, VPI, etc within the container.
    • Cross Compilation Container which makes it simpler to cross-compile JetPack and Jetson Linux components on an x86 host machine running Linux.
    • Jetson Linux Flashing Container which includes all the prerequisites required to flash Jetson modules and developer kits from an x86 host machine running Linux.
  • Package versions:
    • Jetson Linux 35.1
    • CUDA 11.4.14
    • TensorRT 8.4.1
    • cuDNN 8.4.1
    • VPI 2.1
    • OpenCV 4.5.4
    • Vulkan 1.3
    • Nsight Systems 2022.3
    • Nsight Graphics 2022.3
    • Nsight Deep Learning Designer 2022.1

Additional details may be found in the announcement and the development tools page.

Thanks to Cristoffer for the tip.

Share this:

Support CNX Software! Donate via PayPal or cryptocurrencies, become a Patron on Patreon, or buy review samples

ROCK Pi 4C Plus
Notify of
The comment form collects your name, email and content to allow us keep track of the comments placed on the website. Please read and accept our website Terms and Privacy Policy to post a comment.
1 month ago

If you look at the software roadmap in wayback machine they mentioned that Jetpack 5 was only going to be Xavier and Orin modules: https://web.archive.org/web/20220226153606/https://developer.nvidia.com/embedded/develop/roadmap

Ghent the Slicer
1 month ago

So, the Nano is dead with no new software support. This is the same stuff Qualcomm pulls with the Android kernel – only new parts get the update and old parts can rot and die.

I guess its what you get with proprietary blobs.

1 month ago

Well the Tegra X1 that the nano is based upon was released in 2015 so they’ve supported it longer than a lot of vendors, and the Jetpack 4 series is still supported, it’s just not getting the latest features.

Ghent The Slicer
1 month ago

Lets define “supported”. The latest Nano kernel is 4.9 released 2016. It was on old software when it was released and was never bought to an updated kernel. Just try adding a wifi adapter to it. There is exactly one that works.

A Pi 3 by comparison was released 2016, and is running 5.10 kernel. Supported by a non profit, as opposed to mega $$ corp.