Program

All times are in the US Eastern timezone

10:00AM-10:30AM Workshop opening

10:30AM-11:30AM Keynote #1: MPI in the Accelerator Era - Jim Dinan (Nvidia)

11:30AM-12:00PM Challenges of GPU-Aware Communication in MPI - Nathan Hanford (LLNL)

12:00PM-12:30PM Scalable MPI Collectives Using SHARP: Large Scale Performance Evaluation on the TACC Frontera System - Bharath Ramesh (OSU)

12:30PM-1:00PM Implementing Flexible Threading Support in Open MPI - Jan Ciesko (SNL)

1:00PM-2:30PM Lunch Break

2:30PM-3:30PM Keynote #2: Streaming Messages: a Distributed Memory Programming Model for Reconfigurable Hardware - Tiziano de Matteis (ETH Zurich)

3:30PM-4:00PM Design and Implementation Techniques for an MPI-Oriented AMT Runtime - Jonathan Lifflander (SNL)

4:00PM-4:30PM Integrating Inter-Node Communication with a Resilient Asynchronous Many-Task Runtime System - Sri Raj Paul (Georgia Tech)

4:30PM-5:00PM Extending the MPI Stages Model of Fault Tolerance - Derek Schafer (UTC)

5:00PM-5:30PM Workshop Closing Remarks

All 30 minute paper presentation slots are 25 minute live presentations followed by 5 minutes of virtual Q&A. Please ask questions through the virtual conferencing tool.