Schedule
09:00 PMBS Introduction and Welcome
Steven A. Wright
University of York, York, UK
Session 1: Best Papers
Chair: Steven A. Wright
09:10 - 09:30 Best Short Paper
Physical Oscillator Model for Supercomputing [abstract] [paper]
Ayesha Afzal, Georg Hager, Gerhard Wellein
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
09:30 - 10:00 Best Paper
Comparative evaluation of bandwidth-bound applications on the Intel Xeon CPU MAX Series [abstract] [paper]
István Z. Reguly
Pázmány Péter Catholic University, Hungary
10:00 - 10:30 Break
Session 2: Architecture Evaluations
Chair: Lilia Zaourar
10:30 - 11:00
SPEChpc 2021 Benchmarks on Ice Lake and Sapphire Rapids Infiniband Clusters: A Performance and Energy Case Study [abstract] [paper]
Ayesha Afzal, Georg Hager, Gerhard Wellein
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
11:00 - 11:30
Reducing Memory Requirements for the IPU using Butterfly Factorizations [abstract] [paper]
Seyed-Kazem Shekofteh, Christian Alles, Holger Fröning
Heidelberg University, Heidelberg, Germany
Session 3: Short Papers
Chair: Simon Hammond
11:30 - 11:50
Verifying Performance Guidelines for MPI Collectives at Scale [abstract] [paper]
Sascha Hunold
Faculty of Informatics, TU Wien, Vienna, Austria
11:50 - 12:10
A Performance Model for Estimating the Cost of Scaling to Practical Quantum Advantage [abstract] [paper]
Daan Camps, Katherine Klymko, Brian Austin, Nicholas J. Wright
National Energy Research Scientific Computing Center Berkeley, California, USA
12:10 - 12:30
Hardware Specialization: Estimating Monte Carlo Cross-Section Lookup Kernel Performance and Area [abstract] [paper]
Kazutomo Yoshii, John R. Tramm, Bryce Allen, Andrew Siegel, Pete Beckman
Argonne National Laboratory Lemont, IL, USA
Tomohiro Ueno, Kentaro Sano
RIKEN Center for Computational Science, Kobe, Hyougo, Japan
12:30 - 13:30 Lunch
Session 4: Benchmarking
Chair: Steven A. Wright
13:30 - 14:00
Power Analysis of NERSC Production Workloads [abstract] [paper]
Zhengji Zhao, Ermal Rrapaj, Sridutt Bhalachandra, Brian Austin, Hai Ah Nam, Nicholas Wright
Lawrence Berkeley National Laboratory, Berkeley, CA, USA
14:00 - 14:30
Adaptive Stopping Rule for Performance Measurements [abstract] [paper]
Viyom Mittal, Pedro Bruel, Dejan Milojicic, Eitan Frachtenberg
Hewlett Packard Labs, USA
14:30 - 15:00
Latency and Bandwidth Microbenchmarks of US Department of Energy Systems in the June 2023 Top 500 List [abstract] [paper]
Christopher M. Siefert, Carl Pearson, Stephen L. Olivier, Jonathan J. Hu, Timothy J. Fuller
Sandia National Laboratories Albuquerque, NM, USA
Andrey Prokopenko
Oak Ridge National Laboratory Oak Ridge, TN, USA
15:00 - 15:30 Break
Session 5: Scheduling
Chair: Sascha Hunold
15:30 - 16:00
Risk-Aware Scheduling Algorithms for Variable Capacity Resources [abstract] [paper]
Lucas Perotin, Anne Benoit, Yves Robert
Laboratoire LIP, ENS Lyon, Lyon, France
Chaojie Zhang
Microsoft Research, Seattle, WA
Rajini Wijayawardana, Andrew A. Chien
University of Chicago, Chicago, IL
16:00 - 16:30
A Reinforcement Learning Based Backfilling Strategy for HPC Batch Jobs [abstract] [paper]
Elliot Kolker-Hicks, Di Zhang, Dong Dai
University of North Carolina at Charlotte, Charlotte, NC, USA
Session 6: Modeling
Chair: Naohito Nakasato
16:30 - 17:00
Evaluating the Potential of Elastic Jobs in HPC Systems [abstract] [paper]
David Eberius, Md. Wasi-ur-Rahman, David Ozog
Intel Corporation, USA
17:00 - 17:30
Modelling Data Locality of Sparse Matrix-Vector Multiplication on the A64FX [abstract] [paper]
Sergej Breiter, Karl Fürlinger
Ludwig-Maximilians-Universität München, Munich, Germany
James D. Trotter
Simula Research Laboratory Oslo, Norway
17:30 PMBS End