Efficient Teams Up with GlobalFoundries to Develop Ultra-Low Power MRAM Processors
The partnership will combine Efficient’s novel architecture and technology with GF’s U.S.-based manufacturing, global reach and market expertise to enable a quantum leap in edge device capabilities and battery lifetime. Through this partnership, Efficient will provide the computing power to smarter, longer-lasting devices and applications across the Internet of Things, wearable and implantable health devices, space systems, and security and defense.
Current general-purpose processors are over-designed for generality, with most of their energy consumed by unnecessary internal data movement and instruction control overheads. The Efficient Fabric processor architecture is a paradigm shift, providing reconfigurable hardware at compile time for up to 99% lower DC power without compromising performance, setting a new benchmark for CPUs and creating a new category of ultra-low energy and high-performance processors. Efficient is bringing edge computing capabilities to use cases that were previously impossible due to limited energy availability. When combined with the MRAM and Adaptive Body Biasing (ABB) capabilities of GF’s 22FDX platform, Efficient is primed to enable its customers to overcome significant barriers in power consumption, facilitating the deployment of devices equipped with advanced capabilities worldwide.
“We are excited to partner with a brilliant team of engineers at Efficient who are bringing a novel approach to processing architecture and setting a new benchmark for energy-efficient computing using GF’s 22FDX platform,” said 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.