Program

PROGRAM

Thursday, May 25th

Chair:

09:00

Keynote: Performance Portability for Next-Generation Heterogeneous Systems (abstract)

Chair:

10:00	John D. McCalpin Bandwidth Limits in the Intel Xeon Max (Sapphire Rapids with HBM) Processors (abstract)
10:30	Dean Chester, Aruna Ramanan and Mark Atkins Modelling Next Generation High Performance Computing Fabrics (abstract)

11:00-11:30Coffee Break

Chair:

11:30	Michael Hennecke, Johann Lombardi, Jeff Olivier, Tom Nabarro, Liang Zhen, Yawei Niu, Shilong Wang and Xuezhao Liu DAOS beyond PMem: Architecture and Initial Performance Results (abstract)
12:00	Yehonatan Fridman, Guy Tamir and Gal Oren Portability and Scalability of OpenMP Offloading on State-of-the-art Accelerators (abstract)
12:30	Sai Prabhakar Rao Chenna, Nalini Kumar, Leonardo Borges, Michael Steyer, Philippe Thierry and Maria Garzaran Enabling Multi-level Network Modeling in Structural Simulation Toolkit for Next-Generation HPC Network Design Space Exploration (abstract)

13:00-14:00Lunch Break

Chair:

14:00

Keynote: Building a Productive, Open, Accelerated Programming Model for Now and the Future (abstract)

Chair:

15:00	Yinzhi Wang, John D. McCalpin, Junjie Li, Matthew Cawood, John Cazes, Hanning Chen, Lars Koesterke, Hang Liu, Chun-Yaung Lu, Robert McLay, Kent Milfield, Amit Ruhela, Dave Semeraro and Wenyang Zhang Application Performance Analysis: a Report on the Impact of Memory Bandwidth (abstract) PRESENTER: John D. McCalpin
15:30	John Swinburne, Robert Bollig and James Erwin Omni-Path Express (OPX) Libfabric Provider Performance Evaluation (abstract)

16:00-16:30Coffee Break

Chair:

16:30

Apache Spark performance optimization over Frontera HPC cluster (abstract)

Chair:

17:00

Keynote: Next-Gen Acceleration with Multi-Hybrid Devices – Is GPU Enough? (abstract)