ARM Unleashes New Machine Learning Mobile Processors


ARM has unleashed its latest move in artificial intelligence (AI), Project Trillium, that comprises a machine learning (ML) processor, an object-detection (OD) processor, and a library of neural network software. The platform is intended to improve artificial intelligence operations in mobile devices at the edge of networks, according to ARM.

The new ARM ML processor offers performance greater than 4.6TOPS in mobile devices and an efficiency of 3TOPS per watt. It also provides a massive efficiency uplift from CPUs, GPUs, DSPs, and accelerators.

The ARM ML processor is specifically designed for ML applications. For mobile computing, the processor claims more than 4.6 trillion operations per second (TOPs). It is also very efficient claiming an efficiency of over three trillion operations per second per watt (TOPs/W), making it ideal for thermal and cost-constrained environments.


Initial launch of ARM ML, according to ARM, will focus on mobile processors, while future Arm ML will cater to applications ranging from sensors and smart speakers to mobile, home entertainment, and beyond.

“The rapid acceleration of artificial intelligence into edge devices is placing increased requirements for innovation to address compute while maintaining a power-efficient footprint. To meet this demand, Arm is announcing its new ML platform, Project Trillium,” said Rene Haas, president, IP Products Group, Arm.

“New devices will require the high-performance ML and AI capabilities these new processors deliver. Combined with the high degree of flexibility and scalability that our platform provides, our partners can push the boundaries of what will be possible across a broad range of devices.”

The Arm OD processor has been designed to efficiently identify people and other objects with virtually unlimited objects per frame. It boasts up to 80x the performance of a traditional DSP, and can offer real-time detection with Full HD processing at 60 frames per second (fps). Applications are seen in mobile devices and facial recognition in mobile phones.

Google Unveils 72-qubit Quantum Processor Chip

Finally, the ARM NN software can be used by developers to get the highest performance from ML applications by utilizing the hardware capabilities and performance listed above.

The new suite of Arm ML IP will be available for early preview in April of this year, with general availability in mid-2018.

More information:



Please enter your comment!
Please enter your name here

Are you human? *