Arm AI Platform (formerly Project Trillium) is the only complete, heterogenous compute platform designed for machine learning and neural network capabilities. The platform includes well-established Arm Cortex CPUs, Mali GPUs, and Ethos NPUs which make the platform versatile enough to scale to any device, from cloud to edge to endpoint solutions.
Arm Ethos-N processors
The Arm Ethos-N processor series delivers the highest throughput and efficiency in the lowest area for ML inference from cloud to edge to endpoint.
Arm Ethos-U processors
The Ethos-U series of microNPUs brings innovative AI applications with high performance and efficiency to embedded systems.
The Arm Mali family of Graphics Processing Units (GPUs) scales from the Cost Efficient Graphics Roadmap which focuses on delivering high quality graph...
The Arm Neoverse product family enables the broadest range of systems, from power constrained to performance demanding, for next generation infrastruc...
Arm Cortex-A processor
The Arm Cortex-A series of applications processors provide a range of solutions for devices undertaking complex compute tasks.
Arm Cortex-M processors
Arm Cortex-M processors are optimized for cost- and power-efficient microcontrollers deployed in small embedded devices.
Arm NN translates existing neural network frameworks, allowing them to run efficiently across Arm Cortex CPUs, Arm Mali GPUs, and Arm Ethos NPUs.
Arm Compute Library
The Arm Compute Library is a collection of low-level functions optimized for Arm Cortex-A CPUs and Arm Mali GPUs, targeting computer vision and ML.
Increase NN performance by 5x on Cortex-M processors with an optimized low footprint open-source software library