NRT: Chips for All: Empowering Researchers from Diverse Disciplines to Design Hardware

Computer chips specialized for specific applications, or application-specific integrated circuits (ASICs), make applications dramatically faster and more energy efficient than when the same application runs on general-purpose processors such as those in laptops and desktops. The US CHIPS Act envisions that power and energy gains from ASICs will "enable startups and researchers to rapidly innovate at a lower cost," enabling new biomedical devices, faster gene sequencing, new cryptographic protocols to protect user privacy, and many other "killer" applications of the future.

However, chip design know-how is highly specialized, usually taught in Computer Engineering departments using specialized software tools often inaccessible to students and researchers in other departments and schools. Thus, researchers in disciplines that stand to greatly benefit from learning chip design have limited opportunities to access this knowledge.

This National Science Foundation Research Traineeship (NRT) award to New York University (NYU) will introduce an innovative new PhD traineeship model involving tailored chip design coursework, high-impact interdisciplinary research projects pairing domain experts with hardware experts, and a “Silicon Makerspace” that makes chip design software and hardware accessible and available to students across the university. The outcomes of Chips4All will enable fundamental new innovations in the domain sciences.

To engage the broader community, Brooklyn Chips Summit (BRICS), a 3-day event of talks by leading experts in chip design, seminars, and panels will be organized and open to the general public. The project anticipates training 308 trainees, 250 MS students and 58 PhD students, including 24 funded PhD trainees, from across schools at departments at NYU including Electrical and Computer Engineering, Computer Science, Biomedical Engineering, Chemistry, Physics, Mathematics and the School of Medicine.

As Moore's law flags, the semiconductor industry is increasingly focused on tailored ASICs that can unlock orders-of-magnitude improvements in performance and energy efficiency over traditional general-purpose programmable processors. To realize this vision, Chips4All seeks to train experts who possess both deep domain knowledge and hardware design skills and can collaborate in interdisciplinary teams to realize transformative ideas in silicon.

Chips4All aims to democratize hardware design skills across disciplines, creating a replicable model for cross-disciplinary hardware education in the U.S. The novel aspects of the traineeship model are (1) Accessible Chip Design Curriculum, (2) High-Impact Convergent Research, (3) Practical Experience in Chip Design concluding in a chip tapeout, and (4) Establishment of a Silicon Makerspace, easily accessible to all NYU students, faculty, and staff that seeks to build a community of users around hardware design.

The Chips4All project has several avenues for transformative societal impact including significantly improving the diagnosis and treatment of genetic disorders and cancers, portable and wearable assistive technologies, brain monitoring techniques to help address mental health and neurological diseases and enhanced user privacy in cloud computing. All Chips4All team members are committed to a diverse and inclusive environment for Chips4All trainees.

The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The program is dedicated to effective training of STEM graduate students in high priority interdisciplinary or convergent research areas through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.