Date: 13th March 2025
Location: Room O7 - Orchid Jr 4311 (Level 4), Sands Expo and Convention Centre, Singapore
Scope
The rapid evolution of ARM architecture has catalyzed significant advancements in high-performance computing (HPC) and artificial intelligence (AI), particularly in scientific research. This workshop aims to explore the potential of ARM-based systems as a transformative force in computational science. With the growing demand for efficient, scalable, and energy-conscious computing solutions, ARM's unique architecture offers compelling advantages, including enhanced performance per watt and flexibility across diverse applications.
Participants will engage with leading experts in the field, discussing the integration of ARM-based platforms in various scientific domains, such as genomics, climate modeling, and particle physics. We will showcase case studies demonstrating successful implementations of ARM systems in HPC environments, highlighting innovations in algorithm design and optimization techniques that leverage ARM's capabilities.
Additionally, the workshop will address the challenges and opportunities presented by the adoption of ARM architecture, including software compatibility, ecosystem development, and future directions for research. Interactive sessions will facilitate collaboration among attendees, fostering dialogue on best practices and strategies for maximizing the potential of ARM technology in scientific workflows.
By bridging the gap between hardware advancements and scientific applications, this workshop aspires to inspire new research collaborations and drive the next wave of innovation in computational science. We invite researchers, industry professionals, and students to join us in exploring the future of ARM-based systems and their impact on scientific discovery. Together, we can harness the power of ARM architecture to propel scientific endeavors into new frontiers, ensuring that the next generation of research is both efficient and impactful.
Keynote Speakers |
|||
 |
 |
||
Satoshi MatsuokaDirectorRIKEN Center for Computational Science
|
William M. TangProfessor in the Department of Astrophysical SciencesPrinceton University
|
||
Invited Speakers
|
|
|
|
|
|
Jeff Adie NVIDIA |
Chun Fan Peking University |
Torsten Hoefler ETH Zurich |
Zhong Jin Chinese Academy of Sciences |
Shanghai Jiao Tong University |
|
|
|||
|
Kengo Nakajima The University of Tokyo |
Dhabaleswar Panda Ohio State University |
| Morning Session: Chair Filippo Spiga | |
| Time | Speaker |
| 9:30-10:15 | Keynote 1 William M. Tang: Validated AI-Powered Machine Learning for Accelerating Delivery of Scientific Grand Challenges |
| 10:15-10:45 | Talk 1 James Lin: Invisible Performance Roof: Hunting Processor Performance Variability |
| 10:45-11:00 | Tea Break |
| 11:00-11:30 | Talk 2 Dhabaleswar Panda: Optimization of MVAPICH MPI Library for ARM-based Systems |
| 11:30-12:00 | Talk 3 Jeff Adie: Lessons learned running Numerical Weather Prediction on the NVIDIA Grace platform |
| 12:00-13:30 | Lunch Time |
| Afternoon Session: Chair James Lin | |
| 13:30-14:15 | Keynote 2 Satoshi Matsuoka: Breaking Away from Supercomputer Legacy through Modern AI Towards AI for Science on FugakuNEXT |
| 14:15-14:45 | Talk 4 Torsten Hoefler: ARMing GPUs: On the Memory Subsystem of Grace Hopper GH200 |
| 14:45-15:00 | Tea Break |
| 15:00-15:30 | Talk 5 Zhong Jin: Several Scientific Applications using Heterogeneous Computing |
| 15:30-16:00 | Talk 6 Kengo Nakajima: Innovative Supercomputing by Integrations of Simulations/Data/Learning on Large-scale Heterogeneous Systems |
| 16:00-16:30 | Talk 7 Chun Fan: PKU HPC Platform: System Software Innovation and Benchmarking on ARM-Optimized Applications |
Organizing Committee
General Chair: |
James Lin |
Shanghai Jiao Tong University |
Simon See |
NVIDIA |
|
Vice Chair: |
Filippo Spiga |
NVIDIA |
Financial Chair: |
Yiqin Gao |
Shanghai Jiao Tong University |
Local Chair: |
Shenggan Cheng |
National University of Singapore |
Web Chair: |
Xingze Wang |
Shanghai Jiao Tong University |