Said to be up to 166x more energy-efficient than current embedded CPUs, Efficient is already working with customers offering early access and customer sampling by summer 2025.
The partnership combines Efficient's architecture and technology with GF's US-based manufacturing and market expertise that will enable significant improvements in edge device capabilities and battery lifetime delivering smarter, longer-lasting devices and applications across the Internet of Things, wearable and implantable health devices, space systems, and security and defence.
Most current general-purpose processors are over-designed for generality and their energy is consumed by unnecessary internal data movement and instruction control overheads.
The Efficient Fabric processor architecture is being described as a ‘paradigm shift’, that will provide reconfigurable hardware at compile time delivering up to 99% lower DC power without compromising on performance - creating a new category of ultra-low energy and high-performance processors.
When combined with the MRAM and Adaptive Body Biasing (ABB) capabilities of GF's 22FDX platform, Efficient said that it was aiming to help customers overcome significant barriers in power consumption, facilitating the deployment of more devices equipped with advanced capabilities.
"With energy efficiency at the forefront, our founding mission at Efficient was to reimagine general-purpose computing from the ground up and we are incredibly proud to bring our category-defining general-purpose processor to market," said Brandon Lucia, Co-Founder and CEO of Efficient. "Partnering with GlobalFoundries was a natural fit and we are confident that together we will empower the world's most critical industries to embrace the next evolution of energy efficient computing with ease and reliability."
According to Faisal Saleem, Senior Vice President of End-Markets at GF, "Together with Efficient, we will meet a growing market need for ML-enabled intelligent edge devices across various domains that are power efficient and deliver strong computing performance."
The Efficient Fabric processor conserves energy across various applications, including machine learning-enabled (ML) extreme-edge machine vision, continuous audio intelligence and versatile sensory and signals intelligence. It also allows developers to use their own code, supporting popular embedded languages like C and TFlite at launch, with a roadmap to support many more in the first year, to create sophisticated intelligence applications that incorporate artificial intelligence, ML, signal processing, data analytics and other general-purpose data processing tasks.
