EnCharge AI, a company commercializing next-generation AI accelerators, announced a partnership with Princeton University, supported by the U.S. Defense Advanced Research Projects Agency (DARPA), to develop advanced processors capable of running AI models more efficiently than previously thought.
DARPA’s Optimum Processing Technology Inside Memory Arrays (OPTIMA) program is a $78 million initiative to develop fast, power-efficient, and scalable compute-in-memory accelerators that can unlock new possibilities for commercial and defense-relevant AI workloads. As part of OPTIMA, DARPA was awarded an $18.6 million grant for a multi-year project proposed by Princeton University and EnCharge AI.
These developments in AI created skyrocketing processing requirements, which are currently addressed by massive server farms with high cost and power requirements. Broadening the adoption of AI from the cloud to real-time, mission-critical applications at the edge will require moving beyond existing processing technologies.
DARPA’S OPTIMA recognized the need for breakthroughs rather than optimization of existing GPUs and other digital accelerators. DARPA specifically sought to fund innovative approaches enabling transformative advances in science, devices, and systems while using existing VLSI manufacturing techniques and excluding research that primarily results in evolutionary improvements to the existing state of practice.
The key to this Princeton University-EnCharge AI project is Dr. Naveen Verma, Professor of Electrical and Computer Engineering at Princeton and co-founder and CEO of EnCharge AI. Many of the innovations the OPTIMA project seeks to develop were discovered in Dr. Verma’s Princeton lab, in part thanks to previous funding from DARPA and DoD.
The project will explore advancements and end-to-end workload execution of AI applications using the next generation of switched-capacitor analog in-memory computing chips pioneered by Dr. Verma’s lab and commercialized by EnCharge AI.
The switched-capacitor analog in-memory computing techniques are proven over several generations of silicon developed at Princeton to offer order-of-magnitude improvements in compute efficiency compared to digital accelerators while retaining precision and scalability that is impossible with electrical current-based analog computing approaches.
The participation in OPTIMA comes on the heels of EnCharge AI’s recently announced $22.6 million funding round involving new investors VentureTech Alliance, RTX Ventures, and ACVC Partners to develop full-stack AI compute solutions that will fundamentally transform how AI is used from edge to cloud.
KEY QUOTES:
“The future is about decentralizing AI inference, unleashing it from the data center, and bringing it to phones, laptops, vehicles, and factories. While EnCharge is bringing the first generation of this technology to market now, we are excited for DARPA’s support in accelerating the next generation to see how far we can take performance and efficiency.”
- Dr. Naveen Verma, Professor of Electrical and Computer Engineering at Princeton and co-founder and CEO of EnCharge AI
“EnCharge brings together leaders from Princeton, IBM, Nvidia, Intel, AMD, Meta, Google and other companies that have led computing into the modern era. At some point, many of us realized that innovation within existing computing architectures as well as silicon technology-node scaling was slowing at exactly the time when AI was creating massive new demands for computing power and efficiency. While GPUs are the best available tool today, we are excited that DARPA is supporting the development of a new generation of chips to unlock the potential of AI.”
- EnCharge AI CTO Dr. Kailash Gopalakrishnan
