EAGER: Extending the Productive Lifetime of Scientific Computing Equipment

点击翻译按钮获取中文摘要

The growing environmental impacts of hardware acquisition and operation are significant concerns for scientific computing infrastructure deployed at universities and national laboratories. While significant interest in better models for systems operation and lifecycle exist, there are ecosystem challenges including lack of proven pathways and best practices. The Zero Carbon Compute project will convene leaders in the scientific computing infrastructure community, and connect them with leading ecosystem innovators in this space. The goal of the project is to create "best practices" that will catalyze the birth and growth of new lifecycle paths that both reduce the e-waste impact and carbon footprint of research scientific computing. The project will also work to create economic models of the extended lifecycles and broader ecosystem, focusing on economic incentives and the potential impact on the carbon footprint of scientific computing. The project will both increase computing capacity for the national scientific community and create radical reductions in power carbon footprint. The Zero Carbon Compute project will create new opportunities for computing innovation by leveraging the growing excess renewable power in US power grids and around the world. This rapidly growing excess provides both low-cost power and low-cost operation, even for aging computing equipment without increasing the carbon footprint of computing. The project will also convene the scientific computing community through a series of workshops and other methods to understand challenges and communicate the potential benefits of the proposed solutions. Materials generated from these community engagements will be used for wider outreach to the broader scientific computing community, and the cloud computing community. In addition, the project will create economic models of the extended lifecycles and broader ecosystem, focusing on economic incentives, market equilibria, and the potential impact on carbon footprint of scientific computing.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.