It’s clear that NVIDIA® Jetson modules are becoming increasingly popular every year, considering their AI compute capabilities, power efficiency, and form factors. It’s why we have sharing our expert insights in a series of blogs that look to educate you on how to tap into the power of NVIDIA® Jetson AGX Orin™.
In the previous two editions, you learned about its technical features, the major building blocks, and key embedded vision use cases.
- Read Part 1: What Is the NVIDIA Orin Series, and What Are Its Building Blocks?
- Read Part 2: Popular Embedded Vision Use Cases of NVIDIA® Jetson AGX Orin™
In the third edition of this blog series, let’s see how this high-performance processor compares with NVIDIA® Jetson predecessors.
Impact of NVIDIA® Jetson AGX Orin™
The entire NVIDIA® Jetson product family uses a common software stack that facilitates and broadens deployment. They are equipped with the same jetpack Software Development Kit (SDK), which includes a board support package (BSP), Linux OS, and CUDA.
Now, let’s see how NVIDIA® Jetson AGX Orin™ fares when compared to the other members of the Jetson family:
- NVIDIA Jetson Orin NX 8GB and 16GB modules deliver up to 70 and 100 TOPS of AI performance, respectively, in the smallest Jetson form factor. This gives you up to 3 times the performance of NVIDIA® Jetson AGX Xavier™ and up to five times the performance of NVIDIA® Jetson Xavier™
- Jetson Nano is a compact module designed for powering entry-level edge AI applications and devices.
- Jetson AGX Xavier is an upgraded version of NVIDIA® Jetson™ TX2 for deploying end-to-end AI robotic systems. This gives you more than 20 times the performance and 10 times the energy efficiency of NVIDIA® Jetson™ TX2.
- Jetson Xavier NX comes with the NVIDIA Xavier SoC with a module size of Jetson Nano. It delivers accelerated computing performance up to 21 TOPS. This compact AI supercomputer offers you more than 10 times the performance of Jetson™ TX2.
- Jetson TX2/TX2i is reputed to be the fastest and most power-efficient embedded AI computing device – built around an NVIDIA Pascal™-family GPU. It is loaded with 8GB of memory and 59.7GB/s of memory bandwidth with several hardware interfaces for pain-free integration.
Feature by feature comparison of NVIDIA Jetson Modules
In this section, let us dig a bit more into the details of how the Jetson AGX Orin series compares with other Jetson modules. The below table shows a feature-by-feature comparison between each of them:
| Jetson Nano | Jetson TX2/TX2i | Jetson NX Xavier | Jetson AGX Xavier | Jetson NX Orin | Jetson AGX Orin | |
| AI Performance | 472 GFLOPs | 1.33 TFLOPs/ 1.26 TFLOPs |
21 TOPS | 32 TOPS | 100 TOPS | 275 TOPS |
| Power | 5W / 10W | 7.5W / 15W | 10W / 15W | 10W / 15W / 30W | 10W / 15W / 25W | 15W / 30W / 50W |
| GPU | 128-core Maxwell @ 921 MHz | 256-core Pascal @ 1.3 GHz | 384-core Volta | 512-core Volta @ 1.37 GHz | 1024-core NVIDIA Ampere GPU | NVIDIA Ampere architecture with 2048 NVIDIA CUDA cores |
| CPU | 4-core ARM A57 @ 1.43 GHz | 4-core ARM Cortex-A57 @ 2 GHz, 2-core Denver2 @ 2 GHz |
6-core ARM Carmel v8.2 | 8-core ARM Carmel v.8.2 @ 2.26 GHz | 8-core Arm® Cortex®-A78AE v8.2 64-bit CPU 2MB L2 + 4MB L3 | 12-core ARM Cortex A78AE v8.2 64bit @ 2 GHz |
| Tensor cores | — | — | 48 | 64 | 32 | 64 |
| Memory | 4 GB LPDDR4, 25.6 GB/s | 8 GB 128-bit LPDDR4, 58.3 GB/s |
8 GB 128-bit LPDDR4, 51.2GB/s | 16 GB 256-bit LPDDR4, 137 GB/s | 16GB 128-bit LPDDR5 102.4 GB/s |
32 GB 256-bit LPDDR5 204.8 GB/s |
| Storage | MicroSD | 32 GB eMMC 5.1 | 16 GB eMMC 5.1 | 32 GB eMMC 5.1 | Supports external NVMe | 64GB eMMC 5.1 |
| Video encode | 1x 4K30 (H.265) 2x 1080p60 (H.265) |
1x 4K60 (H.265) 3x 4K30 (H.265) 4x 1080p60 (H.265) |
2x 4K30 (H.265) 6x 1080p60 (H.265) |
4x 4K60 (H.265) 16x 1080p60 (H.265) 32x 1080p30 (H.265) |
1x 4K60 (H.265) 3x 4K30 (H.265) 6x 1080p60 (H.265) 12x 1080p30 (H.265) |
2x 4K60 | 4x 4K30 | 8x 1080p60 | 16x 1080p30 (H.265) |
| Video decode | 1x 4K60 (H.265) 4x 1080p60 (H.265) |
2x 4K60 (H.265) 7x 1080p60 (H.265) 14x 1080p30 (H.265) |
2x 4K60 (H.265) 12x 1080p60 (H.265) 16x 1080p30 (H.265) |
2x 8K30 (H.265) 6x 4K60 (H.265) 26x 1080p60 (H.265) 72x 1080p30 (H.265) |
1x 8K30 (H.265) 2x 4K60 (H.265) 4x 4K30 (H.265) 9x 1080p60 (H.265) 18x 1080p30 (H.265) |
1x 8K30 | 3x 4K60 | 6x 4K30 | 12x 1080p60| 24x 1080p30 (H.265) |
| USB | (4x) USB 3.0 + Micro-USB 2.0 | (1x) USB 3.0 + (1x) USB 2.0 | (3x) USB 3.1 + (4x) USB 2.0 | (3x) USB 3.1 + (4x) USB 2.0 | 3x USB 3.2 | 3x USB 3.2 |
| PCI-Express lanes | 4 lanes PCIe Gen 2 | 5 lanes PCIe Gen 2 | 1 x1 (PCIe Gen3) + 1 x4 (PCIe Gen4) | 16 lanes PCIe Gen 4 | 1 x4 + 3 x1 (PCIe Gen4, Root Port & Endpoint) |
2 x8 (or 1×8 + 2×4), 1 x4, 2 x1 PCIe Gen 4 |
Table 1: NVIDIA Jetson Modules Comparison Table (Sources: NVIDIA and Connect Tech)
e-con Systems™ is an NVIDIA Elite Partner
e-con Systems™ as an NVIDIA Elite partner, provides end-to-end camera solutions for NVIDIA Jetson AGX Orin™ and other Jetson modules such as Xavier NX, AGX Xavier, Nano, and TX2 developer kits. These camera solutions will help product developers empower next-generation intelligent machines with end-to-end autonomous capabilities and build efficient embedded IoT applications.
Our GMSL2 cameras for NVIDIA platforms are one of the best in the world in terms of ensuring reliable transmission with low latency.
Some of our popular cameras for NVIDIA® Jetson AGX Orin™ include:
e-CAM200_CUOAGX: 20 MP(5K) multi-camera solution for NVIDIA® Jetson AGX Orin™
This 20 MP super resolution MIPI CSI-2 camera is powered by a 1/1.8″ AR2020 CMOS image sensor from onsemi’s Hyperlux LP product family. This rolling shutter camera comes with an optional global reset release (GRR) mode to reduce the rolling shutter artifacts.
e-CAM121_CUOAGX: 12MP ultra low-light camera for NVIDIA® Jetson AGX Orin™ (up to 4 cameras)
This 12MP MIPI CSI-2 ultra-low light camera module features the Sony® Starvis™ IMX412 back-illuminated and stacked CMOS image sensor. It is capable of delivering high-quality images at a frame rate of 12MP@60 fps and 4K@60fps.
e-CAM56_CUOAGX: 5MP IMX568 color global shutter camera for NVIDIA® Jetson AGX Orin™
This 5 MP MIPI CSI-2 multi-camera is powered by a 1/1.8″ Sony Pregius S IMX568 back-side illuminated image sensor. It delivers best-in-class image output in uncompressed YUV format, featuring fixed focus capability, high sensitivity, and a global shutter mode.
e-CAM84_CUOAGX: 4K AR0830 camera for NVIDIA® Jetson AGX Orin™ (up to 4 cameras
This 8 MP MIPI CSI-2 multi-camera comes with the electronic rolling shutter 1/2.9-inch AR0830 sensor from onsemi®. It seamlessly integrates with the NVIDIA® Jetson AGX Orin™ development kit – with an onboard ISP and a wake-on motion detection feature.
e-CAM82_CUOAGX – 4K Sony STARVIS IMX485-based camera
e-CAM82_CUOAGX is an 8MP high-resolution and ultra-low-light camera for NVIDIA® Jetson AGX Orin™ that comes with a 1/1.2″ sensor and a pixel size of 2.9µm. This way, the camera helps significantly improve sensitivity and captures images with superior clarity.
Figure 1: Multiple e-CAM82_CUOAGX cameras connected to the AGX Orin box
e-CAM80_CUOAGX – a 4K camera based on the Sony STARVIS IMX415 sensor
e-CAM80_CUOAGX is an 8 MP ultra-low-light MIPI CSI-2 camera for NVIDIA® Jetson AGX Orin™ – based on the Sony STARVIS™ IMX415 CMOS image sensor. It is capable of streaming 4K at 44 fps – producing superior image quality in both visible and low light conditions.
Figure 2: e-CAM80_CUOAGX with NVIDIA Jetson AGX Orin
e-CAM20_CUOAGX – a Full HD color global shutter camera
e-CAM20_CUOAGX is a Full HD MIPI CSI-2 color global shutter camera solution, which allows to connect and synchronize up to 6 cameras with the NVIDIA® Jetson AGX Orin™ platform. This camera is based on the 1/2.6″ AR0234CS CMOS image sensor with a fine-tuned ISP – capturing excellent images even in low-light conditions.
Figure 3: Multiple e-CAM20_CUOAGX cameras connected to NVIDIA Jetson AGX Orin
Please browse our Camera Selector Page to check out our full portfolio.
If you want to integrate the right camera – designed to work with NVIDIA® Jetson – into your products, please write to camerasolutions@e-consystems.com.
Prabu is the Chief Technology Officer and Head of Camera Products at e-con Systems, and comes with a rich experience of more than 15 years in the embedded vision space. He brings to the table a deep knowledge in USB cameras, embedded vision cameras, vision algorithms and FPGAs. He has built 50+ camera solutions spanning various domains such as medical, industrial, agriculture, retail, biometrics, and more. He also comes with expertise in device driver development and BSP development. Currently, Prabu’s focus is to build smart camera solutions that power new age AI based applications.