Project Trillium Machine Learning Platform

Project Trillium supports diverse AI applications and their specific requirements everywhere they need to run. Designed for unmatched versatility and scalability, it enables a new era of ultra-efficient machine learning (ML) inference, delivering scalable ML and neural network functionality at any point on the performance curve.

Download Solution Brief
Features and Benefits
Heterogeneous Compute Platform

Provides flexible support for ML workloads across all programmable Arm IP.

Open-source Software and Libraries

Allows seamless integration with existing NN frameworks, such as TensorFlow, Caffe, and Android NN.

Global Ecosystem

Supported by a vibrant and diverse ecosystem, driving innovation and choice.

Project Trillium: Arm’s Heterogeneous ML Platform

Project Trillium provides a range of performance options through a suite of products based on the world’s most innovative and advanced technologies.

 

Platform diagram
Related Products and Services
Explore More Options and Features
Machine Learning Processor

Machine Learning Processor 

An optimized, ground-up processor design for machine learning. State-of-the-art optimized fixed-function engines provide best-in-class performance and energy efficiency. Programmable engines support future innovation and algorithms.

Arm NN

Arm NN

Arm NN bridges the gap between existing NN frameworks and the underlying IP. It enables efficient translation of existing neural network frameworks, such as TensorFlow and Caffe, allowing them to run efficiently – without modification – across Arm Cortex CPUs and Arm Mali GPUs.

Graphics Processing for Arm

Mali Graphics Processors

Including both graphics and GPU Compute technology, Mali GPUs offer a diverse selection of scalable solutions for low-power to high-performance smartphones, tablets, and DTVs.

Cortex-A Processor

Cortex-A Processor

The Cortex-A processor series provides a range of solutions for devices undertaking complex compute tasks, such as hosting a rich operating system platform and supporting multiple software applications.

Cortex-M Processors

Cortex-M Processors

The Cortex-M processor series is designed to enable the most cost-sensitive and power-constrained solutions for a broad range of energy-efficient embedded devices.

Neoverse

Neoverse

Delivering world-class performance, security, and scalability to support the diverse compute requirements of next-generation infrastructure, from hyperscale to edge access.

Architecture and Technologies
A Foundation of Silicon Success

Arm-based chips, device architectures, and technologies orchestrate the performance of everything that makes modern life possible — from smartphones to agricultural sensors and from medical instruments to servers.

Open Source Accelerates Adoption of ML

To support the Machine Intelligence Initiative by Linaro, Arm has donated Arm NN, our open-source network machine learning (ML) software. We believe that open source collaboration with Linaro and other ecosystem partners helps reduce fragmentation and minimizes duplication of efforts. Through this initiative, SoC and NN vendors can continue to differentiate with their key competitive advantage. Learn more about the Linaro Machine Learning Initiative in this video.

 

Arm's Project Trillium Resources

Everything you need to know to make the right decision for your project. Includes technical documentation, industry insights, and where to go for expert advice.