Project Trillium

Project Trillium, Arm’s Machine Learning (ML) platform, enables a new era of advanced, ultra-efficient inference at the edge. Specifically designed for ML and neural network (NN) capabilities, the architecture is versatile enough to scale to any device, from IoT to connected cars and servers.

Project Trillium completes the Arm heterogeneous ML compute platform with the Arm ML processor and open-source Arm NN software.

  • Arm ML processor

    Based on a new, class-leading architecture, the Arm Machine Learning processor provides a huge uplift in efficiency compared to CPUs, GPUs and DSPs.

  • Mali GPUs

    The Arm Mali family of Graphics Processing Units (GPUs) scales from the Cost Efficient Graphics Roadmap which focuses on delivering high quality graph...

  • Arm Neoverse

    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

    Arm NN translates existing neural network frameworks, allowing them to run efficiently across Arm Cortex-A CPUs and Arm Mali GPUs.

  • 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.