IWAHPCE 2022
The IWAHPCE 2022 workshop was held in conjunction with HPC Asia 2022 in Kobe, Japan, January 12-14, 2022.
The workshop was held from 15:00 to 17:30 JST on Friday, January 14, 2022.
Advance Program
| Time | Title |
|---|---|
| 15:00-15:05 | Welcome, Mitsuhisa Sato |
| 15:05-15:35 | Performance tuning of the Helmholtz matrix-vector product kernel in the computational fluid dynamics solver Nek5000/RS for the A64FX processor Miwako Tsuji, Misun Min, Stefan Kerkemeier, Paul Fischer, Elia Merzari, Mitsuhisa Sato |
| 15:35-16:05 | Communication-Computation Overlapping for Preconditioned Parallel Iterative Solvers with Dynamic Loop Scheduling Kengo Nakajima, Balazs Gerofi, Masashi Horikoshi, Yutaka Ishikawa |
| 16:05-16:35 | Simple code adaptation to speed-up Smilei on the ARM-based Fujitsu A64FX processor Mathieu Lobet, Francesco Massimo, Arnaud Beck, Guillaume Bouchard, Frederic Perez, Tommaso Vinci, Mickael Grech |
| 16:35-17:00 | Experiences with Porting the FLASH Code to Ookami, an HPE Apollo 80 A64FX Platform Catherine Feldman, Benjamin Michalowicz, Eva Siegmann, Tony Curtis, Alan Calder, Robert Harrison |
| 17:00-17:25 | Onboarding Users to A64FX via Open OnDemand Aaron Jezghani, Kevin Manalo, Will Powell, Jeffrey Valdez, Jeffrey Young |
| 17:25-17:30 | Closing |
Workshop Overview
The objective of this workshop is to provide the opportunity to share practices and experiences about high-performance Arm computing systems and their performance and applications.
The world’s fastest Japanese supercomputer Fugaku used Fujitsu A64FX Arm-based manycore processors, and Astra at Sandia National Laboratories was the first large-scale Arm-based supercomputer using Marvell ThunderX2. The last few years have seen an explosion of 64-bit Arm-based processors targeted toward server and infrastructure workloads, often with a specialization toward domains such as HPC, cloud, and machine learning. Arm Neoverse N1 became the foundation for processors such as Amazon Graviton2 and Ampere Altra, with the EPI project incorporating the successor design into SiPearl Rhea. NVIDIA Grace had also been announced for future supercomputing deployments, and GPU-integrated Arm clusters were emerging as a category of HPC clusters.
In this workshop, papers were invited on the practice and experience of Arm-based high-performance computing systems and on optimization and performance analysis of high-performance workloads for this generation of Arm-based processors.
Topics
Topics of interest included:
- HPC Applications on Arm-based systems
- Performance Analysis, Performance Modeling & Measurement of Arm-based systems
- SVE Vectorisation analysis
- Programming Models & Systems Software related to Arm-based systems
- Networking and accelerators such as GPUs for Arm-based systems
- Artificial Intelligence and Machine Learning using Arm-based systems
- Emerging Technologies of Arm-based systems
Important Dates
- Paper submission due: 15 November 2021
- Paper notification: 29 November 2021
- Final camera-ready paper submission due: 6 December 2021
Submission site: EasyChair IWAHPCE 2022.
Organizers and Program Committee
Organizer and Workshop Chair
- Mitsuhisa Sato, RIKEN R-CCS
Organizing Program Committee
- Jeffrey Young, Georgia Tech
- Christelle Piechurski, GENCI
- Stephen Poole, Los Alamos National Laboratory
- Valerio Schiavoni, University of Neuschatel
- Michele Weiland, Edinburgh Parallel Computing Centre