Much of modern research is propelled by research collaborations across multiple institutions. These collaborations require computing environments that connect data and computational resources across combinations of university research computing centers, national-scale high performance computing facilities, and public cloud providers. The scale of the data and complexity of the science drive the need to aggregate resources from many sources into scalable computing systems.

A vast array of dependencies, specifications, and processes across these sites can cause scientists to spend more time on the technical aspects of computation and data management than on the science itself. To resolve these technical aspects, computing support staff must invest time and effort integrating domain specific software stacks with limited applicability beyond the community served. Services Layer At The Edge (SLATE) provides technology that simplifies connecting university and laboratory data center capabilities to the national cyberinfrastructure ecosystem. Introducing the SLATE stack to these sites enables science users to work on research rather than technicalities, saves support staff significant amounts of time in integrating new software stacks, and expands the reach of domain specific science gateways and multi-site research platforms.

Implementation and Development

SLATE implements “cyberinfrastructure as code” by augmenting the canonical Science DMZ pattern with a generic, programmable, secure and trusted underlayment platform. This platform hosts advanced container-centric services needed for higher-level capabilities such as data transfer nodes, software and data caches, workflow services and science gateway components. SLATE uses best-of-breed data center virtualization components (Docker and Kubernetes), and where available, software defined networking, to enable distributed automation of deployment and service lifecycle management tasks by domain experts. As such it simplifies creation of scalable platforms that connect research teams, institutions and resources to accelerate science while reducing operational costs and development cycle times. Since SLATE needs only commodity components for its functional layers, it is used in building distributed systems across all data center types and scales thus enabling creation of ubiquitous, science-driven cyberinfrastructure.

This award by the National Science Foundation’s Office of Advanced Cyberinfrastructure is jointly supported by the Computational Physics within the NSF Directorate for Mathematical and Physical Sciences.