NVIDIA Jetson Orin Overview and Developer Resources
NVIDIA Jetson Orin
Welcome to RidgeRun's guide to NVIDIA®Jetson AGX Orin™
NVIDIA®Jetson AGX Orin™ is the newest member of the NVIDIA®Jetson system-on-module (SoM) family with 8X the performance of the NVIDIA® Jetson AGX Xavier™.
The following video from NVIDIA provides a nice overview of the NVIDIA Jetson AGX Orin.
NVIDIA Jetson Orin
NVIDIA Jetson AGX Orin SoM
What is new in Jetson AGX Orin?
NVIDIA® Jetson AGX Orin™ comes in two flavors, the 32GB and 64GB modules. Here is a summary of its main new features:
- CPU Complex: The AGX Orin 64GB has 12-core Arm A78AE CPU.
- GPU Architecture: Orin comes with NVIDIA Ampere GPUs (2048 CUDA cores and 64 Tensor cores), this is four times the number of CUDA cores available in Xavier's Volta GPU (512 CUDA cores and 64 Tensor cores).
- Memory: Up to 64GB, four times the maximum memory size of the Jetson Xavier AGX.
- Memory Bandwidth: 204 GB/s of memory bandwidth.
- On Edge AI Performance: Up to 275 TOPS (INT8) on AGX Orin 64GB.
- Optical Flow Accelerator: Only available on AGX Orin, it targets stereo disparity and optical flow estimation.
- Improved Deep Learning Accelerator: with depth-wise convolution capability and dedicated hardware scheduler.
- MIPI C-PHY v2.0: Up to 164 Gbps with 16 trio links.
RidgeRun knows how important documentation is for your project and how a single source of information may decrease the time-to-market of your product.
That's why we've decided to share our expertise with the developer community, creating a centralized wiki with technical documentation, tutorials, examples, and much more!
RidgeRun NVIDIA Jetson Orin Development and Support
RidgeRun is an official NVIDIA Partner, and we created this set of documentation with procedures and examples tested by RidgeRun engineers to support our joint customers. If you have any questions on the content, please contact us through our contact us page.
With over 20 years of experience in embedded Linux development, RidgeRun helps companies design, optimize, and deploy solutions across NVIDIA Jetson, Qualcomm, NXP, and other embedded platforms. Our engineering expertise covers the complete product development lifecycle, from custom hardware bring-up and board support packages (BSPs) to CUDA acceleration, GStreamer multimedia pipelines, computer vision, and fully customized embedded applications RidgeRun provides support for embedded Linux Camera Driver development for NVIDIA's platforms, specializing in the use of hardware accelerators in multimedia applications.
RidgeRun also develops specialized software products to simplify integration and accelerate time to market. One example is RidgeRun Video Stitcher 2.0, which builds on a previous generation deployed in 20 customer products. The latest version supports NVIDIA Jetson Orin with CUDA and OpenGL processing backends, enabling GPU-accelerated multi-camera video stitching for panoramic and 360-degree video applications.
RidgeRun NVIDIA Jetson Orin wiki contains detailed guides and information on how to get started with the NVIDIA Jetson AGX Orin and start using its full capabilities.
To get up-to-speed with your NVIDIA Jetson AGX Orin board, start by clicking below:

FAQ
- Does RidgeRun offer software products for NVIDIA Jetson Orin?
- Yes. RidgeRun develops embedded software solutions for NVIDIA Jetson Orin, including GPU-accelerated multimedia, computer vision, and video processing applications. Developers can explore RidgeRun's software products and request free evaluation binaries for supported products. One example is RidgeRun Video Stitcher 2.0, which builds on a previous generation deployed in 20 customer products and supports multi-camera panoramic video stitching on NVIDIA Jetson Orin using CUDA and OpenGL acceleration.
For direct inquiries, please refer to the contact information available on our Contact page. Alternatively, you may complete and submit the form provided at the same link. We will respond to your request at our earliest opportunity.
Links to RidgeRun Resources and RidgeRun Artificial Intelligence Solutions can be found in the footer below.