Broadening horizons of cutting-edge computing

Deliang Fan has nothing lower than daring expectations for his endeavors to broaden the capabilities of computing methods and applied sciences. His far-reaching aspirations contain designing superior computational {hardware} to assist innovate in a few of the most technologically advanced areas of engineering and science.

He particularly desires to make vital advances in high-performance, energy-efficient computing for large information processing and make massive steps in creating extra vigorous synthetic intelligence, or AI, computing.
ASU electrical and computer engineer Deliang Fan in his lab.
Ira A. Fulton Schools of Engineering Assistant Professor Deliang Fan has earned National Science Foundation help for his electrical and pc engineering analysis to advance the rising discipline of hybrid in-memory computing methods. These methods promise extra sturdy efficiency in lots of areas of know-how, together with robotics, autonomous cars and pc imaginative and prescient. Photo by Erika Gronek/ASU
Download Full Image

Fan, {an electrical} and pc engineer and assistant professor within the Ira A. Fulton Schools of Engineering  at Arizona State University, says his final objective is to “design, implement and conduct the experimentation to validate the performance of a new hybrid in-memory computing system.”

In-memory computing is a means of operating pc calculations fully in pc reminiscence. For instance, random-access reminiscence, or RAM, is short-term reminiscence the place information is saved as wanted by a pc’s processor.

“The key concept is to leverage the memory device or circuit properties to implement logic functions within a memory array to directly process stored data,” Fan says, “and to do this without moving data to a separate central logic unit, thus minimizing energy-dominating data communication.”

The thought, he says, is to “optimize energy efficiency, inference accuracy, spatiotemporal dynamics, robustness and on-device learning, which will greatly advance AI-based big data processing fields, such as computer vision, autonomous driving and robotics.”

Based on his progress thus far, the National Science Foundation, or NSF, is satisfied Fan is ready to tackle these formidable challenges. He was not too long ago given a 2022 NSF CAREER Award that can present $500,000 over 5 years to fund his analysis.

The CAREER Award program helps college college members early of their careers who’re deemed to have the potential to excel in each analysis and training, to function function fashions of their tutorial departments and to guide advances in fields by which progress will serve nationwide pursuits and priorities.

Fan’s Efficient, Secure, and Intelligent Computing Laboratory staff is trying to construct “a revolutionary and ultra-efficient ‘AI-in-memory’ computing system that could execute AI computation directly within the memory where the data is stored, without the massive data movement,” says Fan, who teaches within the School of Electrical, Computer and Energy Engineering, one of many seven Fulton Schools.

If the undertaking is profitable, it is going to present a brand new form of in-memory computing structure that can function quicker and be 100 occasions extra vitality environment friendly than present state-of-the-art central processing models or graphics processing models.

“This tiny but powerful computing system will bring computing solutions to the existing smart Internet of Things technologies, robots, self-driving cars, smart-connected health technologies, on-device learning capability and many other things,” Fans says. “It will provide a much cheaper, faster and low-power AI computing platform.”

The undertaking will embrace intensive instructional parts. Fan plans to recruit each undergraduate and graduate college students to take part in conducting analysis for the undertaking.

More instructional efforts shall be made by way of a number of Ok–12 STEM outreach applications designed to assist youthful college students study the fundamentals about pc engineering and AI fields.

In addition, a brand new course within the rising space of in-memory computing is being developed, with plans to supply the course within the School of Electrical, Computer and Energy Engineering.

Source hyperlink

Leave a Reply

Your email address will not be published.