NVIDIA® Jetson AGX Orin™ is already taking the market by storm with its unmatched performance and ability to power new-age embedded vision systems. It is said to be 8X more powerful than its predecessor Jetson AGX Xavier. In today’s blog post, we do a deep dive into some of the most popular embedded vision uses of NVIDIA Jetson AGX Orin.
What is NVIDIA® Jetson AGX Orin™?
NVIDIA® Jetson AGX Orin™ is the latest release in the ever-popular NVIDIA® Jetson™ series of processors that have been helping embedded camera applications perform better than before. The newest Jetson AGX Orin modules are packed with enough AI processing power to ensure maximum performance, no matter the complexity of the application use case. Driven by the same AI software and cloud-native workflows of other NVIDIA platforms, NVIDIA® Jetson AGX Orin™ also comes with pre-trained models to conduct tasks like object detection and classification.
Building blocks of NVIDIA® Jetson AGX Orin™
- GPU (Graphics Processing Unit): NVIDIA GPU architecture – almost 3.7 times the performance of the GPU on Jetson AGX Xavier™.
- DLA (Deep Learning Accelerator): NVDLA 2.0 – nine times the performance of NVDLA 1.0 while running complex networks and dynamic tasks.
- CPU (Central Processing Unit): Cortex-A78AE – almost 1.9 times the performance of the 8-core NVIDIA Carmel CPU integrated on Jetson AGX Xavier.
To learn more about Jetson AGX Orin and its building blocks, please visit the following article:
What is the NVIDIA Orin Series? What are the building blocks of NVIDIA Orin?
Why NVIDIA® Jetson AGX Orin™ is suitable for AI applications
One of Jetson AGX Orin’s biggest advantages is that it comes with a performance of up to 275 TOPS (Tera/Trillion Operations Per Second). Undoubtedly, it is suitable for AI-based applications requiring a lot of processing power to carry out complex and data-heavy tasks that leave little room for inaccuracies.