NVIDIA Jetpack 6 Components
This section provides an overview of some of the main software components provided in Jetpack 6 .
Jetpack Components
Table 1 provides the versions of the key packages included in Jetpack 6, and the version previously available in Jetpack 5.1.2:
Package | Jetpack 6 Version | Jetpack 5.0.2 Version |
---|---|---|
Linux for Tegra | 36.0 | 34.1 |
CUDA | 12.2 | 11.4 |
cuDNN | 8.9.2 | 8.3.2 |
TensorRT | 8.6.2 | 8.4.0 |
OpenCV | 4.8.0 | 4.5.4 (Developer Preview) |
Vision Programing Interface (VPI) | 3.0.3 | 2.0 |
Linux for Tegra
Linux for Tegra (L4T) is the component that provides the OS components (kernel, file system, drivers, firmware) and the bootloader. Jetpack 6 comes with L4T version 36.0 featuring:
- Linux Kernel version 5.15: the previous Jetpack version (5.1.2) came with Linux Kernel version 5.10.
- Ubuntu 22.04-based root file system: the previous Jetpack version (5.1.2) came with Ubuntu 20.04-based root file system.
- Flexible Kernel version: Starting in JetPack 6.x users can select a version of the Linux Kernel that is 5.14 or later and backport the list of Tegra patches on top.
- Toolchain: aarch64 gcc-11.3-glibc-2.31 for 64-bit Kernel and user space.
Multimedia API
Included as part of L4T, the Multimedia API allows developers to develop camera-based multimedia applications. It has two main components:
- V4L2 Sensor driver API: the V4L2 API that enables the capture devices, codecs, and scaling functionality.
- Libargus: the proprietary NVIDIA library that allows the use of the Jetson Image Signal Processor (ISP).
CUDA
Jetpack 6 includes CUDA 12.2 support. CUDA is a parallel computing API for NVIDIA GPUs. NVIDIA's CUDA Toolkit provides the development environment for creating GPU-accelerated applications in C/C++.
CUDA Deep Neural Network (cuDNN)
cuDNN is an NVIDIA library used by deep learning frameworks to accelerate common components, such as pooling, normalization, and backward convolution. Jetpack 6 comes with cuDNN 8.9.2, including bugfixes and new enhancements.
TensorRT
TensorRT is a framework created and published by NVIDIA for deep learning inference runtime. Jetpack 6 includes TensorRT 8.6.2. This version of TensorRT has support for CUDA 12.x.
OpenCV
OpenCV is an Open Source library for computer vision tasks. Jetpack 6 EA supports OpenCV version 4.8.0.
Vision Programming Interface (VPI)
VPI is a library provided by NVIDIA to easily take advantage of the power of the Programmable Vision Accelerator and the GPU. It brings Computer Vision and Image Processing algorithms implemented to run the PVA, OFA (Optical Flow Accelerator), GPU, and CPU. Jetpack 6 comes with VPI 3.0 version. To learn more about how you can use VPI along with GStreamer, visit our GstVPI section.