Jetson AGX Orin
A high-performance edge AI computing platform introduced by NVIDIA, widely used for local inference and perception workloads in embedded scenarios such as robots and drones.
Timeline (last 90 days)
NVIDIA Deep Learning Accelerator (DLA) is a fixed-function inference accelerator integrated by NVIDIA into Tegra/Orin series SoCs, specifically handling deep learning operators such as convolution.
The DLA on Jetson AGX Orin provides multiple independently configurable accelerator instances, and each instance can host one inference pipeline.
NVIDIA's official developer blog published the technical article "Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA".
EmbodiedIntentBench uses CPU and GPU configuration replay on the Jetson AGX Orin, and the results show that the relative success rates of local and remote policies vary with the hardware configuration.
The Jetson AGX Thor is equipped with NVIDIA's next-generation GPU architecture and a dedicated deep learning accelerator, with significant improvements in memory bandwidth and power efficiency compared to the previous-generation Jetson AGX Orin.
The Jetson Nano has a compute performance of 472 GFLOPS, and the Jetson AGX Orin has a compute performance of 275 TOPS INT8.
All Facts (6)
NVIDIA Deep Learning Accelerator (DLA) is a fixed-function inference accelerator integrated by NVIDIA into Tegra/Orin series SoCs, specifically handling deep learning operators such as convolution.
50%UnverifiedThe DLA on Jetson AGX Orin provides multiple independently configurable accelerator instances, and each instance can host one inference pipeline.
50%UnverifiedEmbodiedIntentBench uses CPU and GPU configuration replay on the Jetson AGX Orin, and the results show that the relative success rates of local and remote policies vary with the hardware configuration.
50%UnverifiedThe Jetson AGX Thor is equipped with NVIDIA's next-generation GPU architecture and a dedicated deep learning accelerator, with significant improvements in memory bandwidth and power efficiency compared to the previous-generation Jetson AGX Orin.
50%UnverifiedThe Jetson Nano has a compute performance of 472 GFLOPS, and the Jetson AGX Orin has a compute performance of 275 TOPS INT8.
50%UnverifiedNVIDIA's official developer blog published the technical article "Run Native DLA Inference in Python on NVIDIA Jetson AGX Orin Using cuDLA".
50%