NSF AI Disclosure Required
NSF requires disclosure of AI tool usage in proposal preparation. Ensure you disclose the use of FindGrants' AI drafting in your application.
CAREER: Towards Sustainable Computing with Carbon-Efficient Integrated Electro-Photonic Fabrics
NSF
About This Grant
Carbon emissions from powering information and computing technologies (ICT) are projected to increase to 8% of worldwide carbon emissions over the next decade due to the explosion of computing required in everyday consumer electronic devices and systems. Recent studies have shown that integrated electro-photonics-based fabrics (the base layer chips are built on) for communication and computing, compared to conventional electronic fabrics, can result in substantially higher energy and carbon efficiency (up to 100× in some cases) for future computing hardware platforms. This project leverages the energy efficiency of electro-photonic hardware fabrics to investigate their embodied carbon efficiency (related to carbon emissions due to hardware manufacturing and product infrastructure-related activities) following the universally accepted sustainability tenets of Reduce, Reuse, and Recycle. The goal is to develop an infrastructure for designing sustainable computing platforms using carbon-efficient electro-photonic hardware components. The project’s novelties are (1) employing the principles of heterogeneity, reconfigurability, and recycling to design multi-functional and multi-lifespan electro-photonic transceiver and accelerator architectures, (2) transforming the sustainability, performance, resource utilization, and lifetime reliability of electro-photonics-based computing platforms using carbon-efficient cross-layer design techniques, and (3)creating novel educational materials using newly developed tutorial videos and interactive simulation modules to give students a more tangible, hands-on approach to learning the fundamentals of integrated electro-photonics and sustainable computing hardware design. The project's broader significance and importance are based on (i) creating opportunities for industrial partnerships (CMC Microsystems and GlobalFoundries), (ii) promoting outreach to the local community, (iii) engaging undergraduate students in supervised research, and (iv) promoting diversity by training STEM teachers of local middle schools that primarily serve underrepresented groups. The overarching goal of this project is to reduce the impact of embodied energy and extend the operational lifetime of electro-photonic hardware components to enhance the sustainability and carbon efficiency of computing systems. This project is expected to result in (1) a framework that factors in the critical impacts of yield, variations in fabrication-process and temperature, and aging effects for modeling the embodied and use-phase carbon footprints of electro-photonic transceivers and accelerators, (2) carbon-efficient organizations of electro-photonic transceivers and accelerators with minimal carbon footprints and maximal lifespans, (3) methods to repurpose electro-photonic hardware components for multiple functionalities to minimize resource idle time and embodied carbon emissions, (4) cross-layer techniques to extend the reliable utilization of designed electro-photonic architectures across multiple lifespans, and (5) an extensive simulation framework for evaluation, validation, and comparison of different organizations of heterogeneous computing platforms comprising electro-photonic fabrics, focusing on various important metrics for energy efficiency, carbon efficiency, performance, lifetime reliability, and resource utilization. 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.
Focus Areas
Eligibility
How to Apply
Up to $235K
2030-06-30
One-time $749 fee · Includes AI drafting + templates + PDF export
AI Requirement Analysis
Detailed requirements not yet analyzed
Have the NOFO? Paste it below for AI-powered requirement analysis.