SC22 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

Birds of a Feather Archive

Charting the PMIx Roadmap

Authors: Joshua Hursey (IBM Corporation), Thomas Naughton III (Oak Ridge National Laboratory (ORNL)), Ralph Castain (Nanook Consulting), Aurelien Bouteiller (University of Tennessee)

Abstract: The PMIx Standard APIs facilitate interaction between applications, tools, middleware, and system runtimes. PMIx addresses a range of use cases including: application launch and wire-up; inspection, steering, and debugging tools; dynamic application management, fault tolerance, and cross-library coordination; and communication across container boundaries.

We invite all SC attendees to hear about the current version of the PMIx Standard, significant activity in the PMIx Standard working groups, OpenPMIx and PRRTE implementation releases, and broadening adoption of PMIx. We will recap the activities of the past year, showcase community and working group efforts, and discuss the roadmap for the next year.

Long Description: Goal: In this BOF, we will discuss the status of the PMIx Interface, the efforts of the PMIx Standard Body, the OpenPMIx implementation of PMIx and related projects, and to invite any interested attendees to participate in the development of PMIx.

Topic: The PMIx Standard is a formalization of the APIs previously developed by the OpenPMIx development community and aims to provide an implementation-independent specification to facilitate interaction between applications, tools, middleware, and system runtime environments. The interface focuses on supporting HPC application launch and wire-up; supporting tools that wish to inspect, steer, and/or debug parallel applications; providing interfaces to manage dynamic workload applications, to support fault tolerance and cross-library coordination; and facilitate communication across container boundaries. The BoF will cover in-progress proposed additions to the PMIx Standard, including support for I/O, storage, provisioning and dynamic workflows; additions that have been formally adopted, including support for tools and debuggers; and updates and new features of the OpenPMIx implementation.

This year, we will present the current PMIx Standard release and associated use cases, working groups will discuss their achievements and plans for the next year, then we will discuss the priorities and roadmap for the next year. Planned topics include: * New and proposed features for PMIx * Improvements and progress in OpenPMIx and related projects (e.g., PRRTE) * Progress in the PMIx Standard * Solicitation for proposed new features, use case scenarios, and working groups

Relevance to HPC audience: The entire HPC community (and beyond!) can benefit from the standardized APIs included in the PMIx Standard and the OpenPMIx implementation. In this BoF, we hope to encourage broad community participation in this effort, including folks working on parallel libraries (e.g., MPI, UPC, OpenSHMEM), runtime environments (e.g., SLURM, LSF, Torque), container runtimes and orchestration environments (e.g., Singularity, CharlieCloud, Docker, Kubernetes), tools (e.g., TotalView, DDT, STAT), middleware (e.g., I/O support libraries, workflow management frameworks), and the broader research community.

Previous BoFs: Prior to the pandemic, this BOF had been held for 5 years at SC and attracted approximately 25-35 attendees each year. We expect this year’s BoF will bring the community back together in person to discuss the PMIx Standard, the OpenPMIx implementation, and related projects. A slightly larger attendance is anticipated due to the time since the last BoF on this subject and broader adoption of PMIx across the community.

Expected Outcome: We anticipate attracting a wide variety of SC attendees to the proposed BoF including current PMIx Standard committee participants from IBM, Intel, Mellanox, Microsoft, Syslabs Inc., HPE/Cray, Altair, LLNL, ANL, ORNL, LANL, UTK, Ohio State, and those that have participated to a lesser extent or have expressed interest and wish to stay informed of the community's progress. We will inform attendees about the current organization of the PMIx Standard Body, the status of the standard document, activities of the PMIx Standard working groups, and progress in the OpenPMIx implementation of PMIx.


Back to Birds of a Feather Archive Listing