Jiaqi Gu
Arizona State University Campus Immersion, AZ·Engineering·Early-career
AI is driving demand for ever faster computing and data movement. Meeting that demand with electronics alone is becoming expensive and power-hungry.
- Fields
Engineering
Computer Science
Physics
- Topics
integrated photonics
silicon photonics
electronic-photonic design automation
- Grants
- 1 known grant, through May 2031
What they work on
- Develop a learned electromagnetic solver, a machine-learning model of how light moves through photonic devices, and a circuit-level co-simulator for fast simulation of mixed electronic-photonic chips.
- Create fabrication-robust inverse design methods that model manufacturing process variations, so that computer-designed photonic devices keep working after fabrication and need fewer costly redesigns.
- Build scalable physical design automation that synthesizes large photonic circuit layouts while following manufacturing rules and performance constraints.
- Integrate these tools into a system-level design-space exploration engine that links device and layout effects to end-to-end speed, energy, area and robustness of photonic AI systems.
More about the research
Integrated photonics, which uses light on a chip to carry and process information, offers a faster, lower-energy path through hybrid electronic-photonic systems. But photonic chips are still slow and costly to design and build, partly because the design software, models and workflows are immature and hard to access.
Why it matters
Faster, cheaper design of photonic chips could lower the energy and hardware cost of running AI workloads. An open, reproducible toolflow that reduces design iterations and improves manufacturing yield could lower barriers for chip designers and researchers. It could also speed adoption of light-based hardware in computing, communication and sensing systems.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Omiya Hassan
Boise State University, ID·Engineering
Co-design an electro-optical application-specific integrated circuit that pairs photonic (light-based) and electronic processing units, assigning AI training and inference to the best-suited unit.
Weidong Cao
George Washington University, DC·Engineering
Build AnalogEDA-Hub, an open-source platform with multi-modal datasets, learning-based tools and standard design environments, so researchers can benchmark AI methods for analog circuit design in a reproducible way.
Qian Yu
University of California-Santa Barbara, CA·Engineering
Develop a highly compressed training method for physics-informed neural networks (PINNs) that uses only forward passes and no backpropagation, so it can run on photonic chips without photonic memory.
The school
Arizona State University Campus Immersion: 36 labs on PI Pages, $1.0B a year on research, 625 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.