AMD Ryzen AI Embedded P100 is a family of edge AI processors announced by AMD at Computex 2025, targeting mobile robotics, industrial automation, and Physical AI. Built on a 4 nm process, the System-on-Chip combines three classes of acceleration in a single die: an x86 CPU based on Zen 5/5c architecture (4 to 12 cores, up to 24 MB L3 cache), an RDNA 3.5 GPU (clocks up to 2.9 GHz), and a dedicated XDNA 2 NPU delivering up to 50 TOPS of AI acceleration.
Total platform performance reaches 80 TOPS for hybrid workloads (CPU + GPU + NPU), enabling on-device execution of small language models (SLMs), visual classifiers, VLMs, and robot policy networks โ without cloud connectivity. This eliminates communication latency critical to real-time control loops.
The top SKUs in the family (P185, P185i, announced at Embedded World 2026) offer 12 Zen 5 cores, while low-power variants with Zen 5c target battery-powered devices. The platform supports up to four 4K (or two 8K) displays at 120 fps and provides functional safety features required in collaborative robotics and automotive.
P100 ships in COM Express and mITX modules from partners such as Kontron, congatec, and Advantech. Main applications: Physical AI in mobile robots (AGVs, humanoids), intelligent surveillance, medical devices, autonomous transport. It competes directly with NVIDIA Jetson Thor and Qualcomm Robotics RB6 โ with the advantage of full x86 compatibility (drop-in support for existing ROS 2/Linux stacks).
AI SoC / Edge AI SoC ยท serves as: AI acceleration, AI Inference, Computer vision processing.
Which group AMD Ryzen AI Embedded P100 belongs to and how it is built
Covers integrated System-on-Chip circuits used as central processing units in embedded systems, robotics, AIoT, and edge AI devices. In this schema, parentCategory is set to 'other' because the parentCategory enum does not include a compute category.
