Description

The Integrated Research Infrastructure (IRI) program stands out with its innovative strategy to more effectively enable science across the DOE user facilities at scale. It is set to radically accelerate discovery and innovation within the DOE with a unique approach that empowers scientists to seamlessly and securely combine DOE research tools, infrastructure, and user facilities into their orchestrated workflows. A key component of this approach is the introduction of collaborative interfaces for users and orchestration tools, enabling workflows that run seamlessly across multiple user facilities.

In recent years, user facilities have already started working on novel interfaces. Notable examples of API are the SuperFacility at NERSC, FireCREST at CSCS, TAPIS at TACC, SENSE at ESnet, and WSaaS at OLCF. Many of these projects have the larger DOE user community in mind; however, they are still developed locally from peer engagements with the user communities of each specific user facility. They are limited by specific facility technologies, such as an HPC facility’s hardware configuration, and this limited scope of engagement lacks solutions for multi-facility job resiliency, failover, and monitoring. Today, despite the use of common toolchains and similar HPC providers, the landscape of novel HPC interfaces is still rather fragmented, with no common interface emerging that functions across all user facilities. This is a major hurdle for scientists aiming to build resilient workflows with multiple facilities in mind, locking them into one specific computing and data environment and exposing them to risks like major interruptions. Hence, the success of IRI hinges on the delivery of collaborative interfaces that scientists can use to build resilient and performant cross-facility workflows.

The IRI interfaces technical subcommittee is formed by key staff across ASCR with a charter to identify specific interface design, functionality, and compatibility requirements. For this endeavor to be successful, deep engagement with a broad spectrum of stakeholders is necessary to ensure that the developed interfaces cater to a wide range of use cases.

This BoF covers a novel field in supercomputing that has never been held before at SC. We will summarize the current efforts of the IRI interfaces working group and individual ASCR user facilities to develop new interfaces. After that we invite the HPC community to provide feedback to help guide these IRI efforts. We are looking forward to a stimulating discussion

Agenda

12:15-12:20   Welcome and opening remarks -- Bjoern Enders, National Energy Research Scientific Computing Center (NERSC)

12:20-12:25   Introduction to the IRI interfaces subcommittee and charter -- John McAuley Energy Sciences Network (ESnet)

12:25-12:50   Lightning Talks

• Cross-Facility Science Workflows Automation and Orchestration, Xi Yang, Energy Sciences Network (ESnet)

• Superfacility API and Jupyter -- Bjoern Enders, National Energy Research Scientific Computing Center (NERSC)

• Services for integrating Data Portals -- Ryan Prout, Oakridge Leadership Computing Facility (OLCF) 

• Globus Platform Interfaces for Automating Science -- Kyle Chard, Argonne National Lab (ANL)

• FirecREST: an Open-Source API for HPC -- Juan Pablo Dorsch, CSCS

12:50 -1:10   Panel discussion and Open Q&A

1:10-1:15   Closing remarks