Schedule
08:30 PMBS Introduction and Welcome
C155, Kay Bailey Hutchison Convention Centre, Dallas
Session 1: Machine Learning and Artificial Intelligence
Chair: Andrey Semin
08:30 - 09:00
ML-based Performance Portability for Time-Dependent Density Functional Theory in HPC Environments [abstract] [presentation]
Adrian Perez Dieguez, Khaled Ibrahim
Lawrence Berkeley National Laboratory, CA
Min Choi, Bryan Wong
University of California, Riverside, CA
Xinran Zhu
Cornell University, NY
09:00 - 09:30
A Comprehensive Evaluation of Novel AI Accelerators for Deep Learning Workloads [abstract] [presentation]
Murali Emani, Zhen Xie, Siddhisanket Raskar, Varuni Sastry, William Arnold, Bruce Wilson, Rajeev Thakur, Venkatram Vishwanath, Zhengchun Liu, Michael Papka
Argonne National Laboratory, IL
Cindy Orozco Bohorquez
Cerebras Systems, CA
Rick Weisner, Karen Li, Yongning Sheng, Yun Du, Jian Zhang
SambaNova Systems Inc., CA
Alexander Tsyplikhin, Gurdaman Khaira
Graphcore, CA
Jeremy Fowers, Ramakrishnan Sivakumar, Victoria Godsoe, Adrian Macias, Chetan Tekur, Matthew Boyd
Groq Inc., CA
Session 2: Short Papers I
Chair: Steven Wright
09:30 - 09:45
AppEKG: A Simple Unifying View of HPC Applications in Production [abstract] [presentation]
Mohammad Al-Tahat, Strahinja Trecakov, Jonathan Cook
New Mexico State University, NM
09:45 - 10:00 Best Short Paper
OMPICollTune: Autotuning MPI Collectives by Incremental Online Learning [abstract] [presentation]
Sebastian Steiner, Sascha Hunold
TU Wien, Austria
10:00 - 10:30 Break
Session 3: Heterogeneous Systems
Chair: Simon Hammond
10:30 - 11:00 Best Paper
Frontier vs the Exascale Report: Why so long? and Are We Really There Yet? [abstract] [presentation]
Peter Kogge
University of Notre Dame, IN
William Dally
NVIDIA Corporation, CA
11:00 - 11:30
Evaluating ISO C++ Parallel Algorithms on Heterogeneous HPC Systems [abstract] [presentation]
Wei-Chen Lin, Tom Deakin, Simon McIntosh-Smith
University of Bristol, UK
11:30 - 12:00
Going Green: Optimizing GPUs for Energy Efficiency Through Model-Steered Auto-Tuning [abstract] [presentation]
Richard Schoonhoven, Kees Joost Batenburg
Centrum Wiskunde and Informatica, Netherlands
Leiden Institute of Advanced Computer Science, Netherlands
Bram Veenboer
Netherlands Institute for Radio Astronomy, Netherlands
Ben van Werkhoven
Netherlands eScience Center, Netherlands
Centrum Wiskunde and Informatica, Netherlands
12:00 - 13:30 Lunch
Session 4: Performance Analysis
Chair: Gerhard Wellein
13:30 - 14:00
Performance Analysis with Unified Hardware Counter Metrics [abstract] [presentation]
Brian Gravelle, William D. Nystrom
Los Alamos National Laboratory, NM
Boyana Norris
University of Oregon, OR
14:00 - 14:30
A Methodology for Evaluating Tightly-integrated and Disaggregated Accelerated Architectures [abstract] [presentation]
Taylor Groves, Chris Daley, Rahulkumar Gayatri, Hai Ah Nam, Nan Ding, Lenny Oliker, Nicholas J. Wright, Samuel Williams
Lawrence Berkeley National Laboratory, CA
Session 5: Short Papers II
Chair: Lilia Zaourar
14:30 - 14:45
An Initial Evaluation of Arm’s Scalable Matrix Extension [abstract] [presentation]
Finn Wilkinson, Simon McIntosh-Smith
University of Bristol, UK
14:45 - 15:00
Time-series ML-regression on Graphcore IPU-M2000 and Nvidia A100 [abstract] [presentation]
Jan Balewski, Kristofer Bouchard
Lawrence Berkeley National Laboratory, CA
Zhenying Liu, Alexander Tsyplikhin, Manuel Lopez Roland
Graphcore, CA
15:00 - 15:30 Break
Session 6: Benchmarking
Chair: Simon Hammond
15:30 - 16:00
Benchmarking Fortran DO CONCURRENT on CPUs and GPUs Using BabelStream [abstract] [presentation]
Jeff R. Hammond
NVIDIA Corporation, Helsinki
Tom Deakin, James Cownie, Simon McIntosh-Smith
University of Bristol, UK
16:00 - 16:30
WfBench: Automated Generation of Scientific Workflow Benchmarks [abstract] [presentation]
Taina Coleman, Loic Pottier
University of Southern California, CA
Henri Casanova
University of Hawaii at Manoa, HI
Ketan Maheshwari, Sean Wilkinson, Frederic Suter, Mallikarjun Shankar, Rafael Ferreira da Silva
Oak Ridge National Laboratory, TN
Justin Wozniak
Argonne National Laboratory, IL
16:30 - 17:00
High-Performance GMRES Multi-Precision Benchmark: Design, Performance, and Challenges [abstract] [presentation]
Ichitaro Yamazaki, Sivasankaran Rajamanickam, Jennifer Loe, Christian Glusa
Sandia National Laboratories, NM
Piotr Luszczek, Jack Dongarra
University of Tennessee, TN
17:00 PMBS End