NVIDIA Jetson Orin Nano- SoM Overview

NVIDIA®Jetson Orin Nano™
Introduction
SoM Overview Carrier Boards NVIDIA developer kit Software Development Support
Jetpack 5.X
Getting Started Flashing the board using GUI Installer JetPack Components Kernel Compile CMD flash Performance Tuning Evaluating Performance Set Values Manually Tuning Power Maximizing Performance
Development in the Board
Getting into the Board Using Serial Console Using SSH Using Ubuntu Login Installing Packages
Camera Sensors Support
IMX219 IMX708
Contact Us

This section provides an overview of the Orin Nano SoM components and their capabilities.

The NVIDIA Jetson Orin Nano, delivers up to 40 tera operations per second (TOPS) on a 15W package. The Orin Nano System on Module (SoM) is a small PCB, that is similar in size to laptop memory stick. It encapsulates the computing devices such as the 6 Core ARM CPU and the, up to 1024 CUDA Cores GPU, it also holds the LPDDR5 memory packages. On Figure 1, we have the SoM.

Figure 1: NVIDIA Jetson Orin Nano SoM

Table 1 shows a summary of the hardware characteristics of the SoM:

Table 1: NVIDIA Jetson Orin Nano SoM - Hardware Summary

Feature	Jetson Orin Nano 4GB	Jetson Orin Nano 8GB
AI Performance	20 TOPS (INT8)	40 TOPS (INT8)
GPU	NVIDIA Ampere architecture with 512 NVIDIA® CUDA® cores and 16 Tensor Cores	NVIDIA Ampere architecture with 1024 NVIDIA® CUDA® cores and 32 Tensor Cores
Max GPU Freq	625 MHz
CPU	6-core Arm® Cortex®-A78AE v8.2 64-bit CPU 256kB L2 + 2MB L3
CPU Max Freq	1.5 GHz
Memory	4GB 64-bit LPDDR5 34 GB/s	8GB 128-bit LPDDR5 68 GB/s
Storage	Supports external NVMe
Decoder	1x 4K60 (H.265) 2x 4K30 (H.265) 5x 1080p60 (H.265) 11x 1080p30 (H.265) H.265, H.264, VP9, AV1
CSI Camera	Up to 4 cameras (8 via virtual channels*) 8 lanes MIPI CSI-2 D-PHY 2.1 (up to 20Gbps)

Graphics Processing Unit (GPU)

The Orin Nano comes with an NVIDIA Ampere architecture GPU. The Ampere GPU brings state-of-the-art graphics and parallel computing techniques, such as ray-tracing, CUDA, and TensorRT support. The Orin Nano 8 GB Ampere GPU is composed of the following modules:

• 2 Graphic Processing Clusters (GPCs)
• 8 Texture Processing Clusters (TPCs)
• 16 Streaming Multiprocessors (SMs), where each has:
  • L1 cache of 192KB
  • L2 cache of 4MB
  • 128 CUDA cores
  • 4 Tensor cores (3rd generation)

To learn more about the Jetson Orin AGX GPU, check out our Ampere GPU wiki.

Central Processing Unit (CPU)

Jetson Orin Nano comes with 6 Arm Cortex-A78AE CPU cores, with the following configuration:

• 64KB instruction L1 cache
• 64KB data cache
• 256KB L2 cache
• Up to 1.5 GHz frequency

The CPU cores are arranged in 2 clusters, one with 4 CPU cores, and other with 2 Cores. Each cluster has a 2MB L3 Cache. The CPU complex also features a 4MB system cache.

Codecs

Multi-Standard Decoder (NVDEC)

Supports:

• H.264
• H.265
• AV1
• VP9

Packaging Information

Table 2 shows the packaging characteristics of the Orin Nano SoM.

Table 2: NVIDIA Jetson Orin Nano SoM - Package Characteristics

Feature	Description
Module Size	39.00 mm × 67.60mm
Connector	260 pin DDR4 SODIMM Standard connector
Operating Temperature	Range from -25C to 99C
Power Input	5V