IXPUG Annual Conference 2022
Hosted by Argonne National Laboratory
The 2022 IXPUG Annual Conference will be hosted by Argonne National Laboratory. HPC users and enthusiasts across the globe are invited to attend and participate. Join us to share your experiences with all aspects of adopting and employing state-of-the-art technologies and practices for optimal application execution on Intel XPU platforms. Through our interactive, open forum IXPUG brings together speakers across supercomputing, including renowned industry leaders, and experts from Intel. Together we share real-world experiences, best practices, and techniques for maximizing software productivity and efficiency.
Conference Dates: September 28-30, 2022
Venue: Argonne National Laboratory, Building 240 (Lemont, Illinois) in-person and live online via Zoom
Zoom: Online participants may join via Zoom: https://argonne.zoomgov.com/j/1611626663
Slack Channel: Join the IXPUG Slack channel during the conference: https://join.slack.com/t/ixpug/shared_invite/zt-1fmsrsj2q-emm~phMac3RDV4yIV7stGA
Registration: The registration deadlines have passed. For late registration consideration, please follow the instructions at https://events.cels.anl.gov/event/336/
Lodging: Conference attendees are encouraged to stay at the conveniently located Argonne Guest House – please mention “IXPUG Annual Conference” when making your reservation. Specify the following when completing the Argonne Guest House online registration form: ARGONNE CONTACT Rose Lynch This email address is being protected from spambots. You need JavaScript enabled to view it. and ARGONNE CONTACT PHONE (630) 252-3426.
Wednesday, September 28 (Day 1) | ||
Time | Title | Presenter |
8:30-8:40 | Welcome |
David Martin, Argonne National Laboratory |
8:40-9:30 | Keynote on the future of HPC and scientific discovery [View Presentation] | Rick Stevens, Argonne National Laboratory |
Session Chair: Clay Hughes | ||
Track: Programming | ||
9:30-10:00 |
Mapping Cores, CHAs, and Addresses in the Xeon Platinum 8380 [View Presentation] |
John D. McCalpin, Texas Advanced Computing Center, University of Texas at Austin |
10:00-10:30 | Improving MPI+Threads with MPIX_Stream [View Presentation] | Ken Raffenetti, Argonne National Laboratory |
10:30-11:00 | Break | |
11:00-11:30 | Recovery of Distributed Iterative Solvers for Linear Systems with Non-Volatile RAM [View Presentation] | Yehonatan Fridman, Israel Atomic Energy Commission and Ben-Gurion University |
11:30:12:00 | Data Transfers and Host/Device Communication using OneAPI for FPGA | Phillip Lane, Sandia National Laboratories |
12:00-13:30 | Lunch | |
Session Chair: Nalini Kumar | ||
Track: Porting | ||
13:30-14:00 | Migrating from CUDA to C++ with SYCL |
Chekuri Choudary, Intel Corporation |
14:00-14:30 |
Porting Multi-Dimensional Numerical Integration Methods from CUDA to oneAPI |
Ioannis Sakiotis, Old Dominion University |
14:30-15:00 | Migrating Compaction Kernels from CUDA to HIP and SYCL | Zheming Jin, Oak Ridge National Laboratory |
15:00-15:30 | Break | |
15:30-16:00 | Platform Independent Implementation of GPU Support in the Tensor Transposition Library, LibreTT | Victor Anisimov, Argonne National Laboratory |
Track: Performance | ||
16:00-16:30 | Practical MPI Collective Autotuning using Machine Learning at Exascale | Michael Wilkins, Northwestern University |
Track: Performance/Porting | ||
16:30-17:00 | Porting and performance benchmarking of a compressible flow solver on Intel GPU computing platforms | Umesh Unnikrishnan, Argonne National Laboratory |
17:00-17:30 | Break | |
17:30-19:30 | Dinner | |
Thursday, September 29 (Day 2) | ||
Time | Title | Presenter |
9:00-9:10 | Welcome |
David Martin, Argonne National Laboratory |
9:10-10:00 | Keynote: New Era for Intel HPC Acceleration: Architecture, Systems & Software [Presentation] | Hong Jiang, Intel Corporation |
Session Chair: R. Glenn Brook | ||
Track: Performance | ||
10:00-10:30 | Autotuning Hybrid MPI/OpenMP Applications for Energy Efficiency at Large Scales | Xingfu Wu, Argonne National Laboratory |
10:30-11:00 | Break | |
11:00-11:30 | Performance Portability is (sort of) a Lie: Lessons Learned from the Parthenon Collaboration | Daniel Holladay, Los Alamos National Laboratory |
11:30-12:00 | Aurora and ALCF Site Update | Susan Coghlan, Argonne National Laboratory |
12:00-13:30 | Lunch and Aurora tours | |
Session Chair: Amit Ruhela | ||
13:30-14:00 | Site Updates |
Hatem Ltaief, King Abdullah University of Science & Technology |
Track: Hardware | ||
14:00-14:30 | Deploying Multiphysics Computational Fluid Dynamics Simulations to the Cloud | Akash Dhruv, Argonne National Laboratory |
14:30-15:00 | The Evolution of Storage and Memory Hierarchy and the DAOS Role in It |
Andrey Kudryavtsev, Intel Corporation |
15:00-15:30 | New Method for Reducing Data Size by Encoding Quantum Bits in Classical Data | Nagi Mekhiel, Ryerson University |
15:30-16:00 | Break | |
16:00-16:30 | Breaking the Microsecond Barrier with OPX | Doug Fuller, Cornelis Networks, Inc. |
16:30-17:00 | Creating Ultimate Chiplet-Based Systems | Ramin Farjadrad, Eliyan Corp. |
Track: AI | ||
17:00-17:30 | Developing Performant and Reproducible AI Workflows for Scientific Discovery on Intel® Xeon® Scalable processors | Kin Long Kelvin Lee, Intel Corporation |
Track: Hardware | ||
17:30-18:00 | Overcoming the Development and Deployment Challenges for FPGAs at Cloud Scale | Deshanand Singh, Intel Corporation |
18:00-19:30 | Reception | |
Friday, September 30 (Day 3) | ||
Time | Title | Presenter |
9:00-9:10 | Welcome |
David Martin, Argonne National Laboratory |
9:10-9:45 | AI Keynote: Frontiers in Scientific Discovery at the Interface of AI and HPC | Eliu Huerta, Argonne National Laboratory |
Session Chair: David Martin | ||
9:45-10:45 | Speeding Up End-to-End Development of AI at Large Scale | Joshua Mora, Intel Corporation |
10:45-11:00 | Break | |
11:00-12:30 | HPC AI Workload Best Practices: Training and Inference Optimizations on Next Gen Intel® Xeon® Scalable processors (codenamed Sapphire Rapids) |
Nalini Kumar, Intel Corporation |
- Techniques: Artificial Intelligence (Machine Learning/Deep Learning), Algorithms & Methods, Compiler Flags, Software Environment & Tools, Libraries & Tools, Parallel- Programming (Communications, Thread & Process Management Experience, All), Multi-node, Memory Management, Vectorization, Troubleshooting, etc.
- Products: Intel® Xeon® Scalable processors, Intel Xe graphics, Intel® FPGAs, Intel® Optane, Distributed Asynchronous Object Storage (DAOS), Visualization Technology, Intel® SW Tools, Intel® oneAPI, etc.
- Domains: Astrophysics, Bioinformatics, Chemistry, Climate & Weather, Computational Fluid Dynamics, Data Analytics, Energy/Oil & Gas, Financial Services, Genomics Analytics, Geophysics, Life Sciences, Material Science, Medical Imaging, Molecular Dynamics, Nanotechnology, Physics, Visualization, High Energy Physics, etc.
Topics of Interest
- Implications of workload behavior on system design at extreme scale (Power, Reliability, Scalability, Performance, Processor Design, Memory System, I/O)
- Software environments and tools for computing at extreme scale (Instrumentation, Debugging/Correctness, Thread and Process Management, Libraries and Language Development)
- Experience with incorporating machine learning and deep learning in HPC applications and workflows including performance analysis, optimization, and best practices
- Experience using extreme scale systems: Usability, In-situ Visualization, Programming Challenges, Algorithms and Methods, etc.
- Application characterization on emerging technologies: Non-volatile memory (NVMe), processors (Intel® Xeon® Scalable processors, Intel® GPUs, Intel® FPGAs, etc.)
Important Dates
- Abstract submission deadline: August 12, 2022 (AoE)
- Acceptance notification: August 19, 2022
- Presenters’ consent deadline: September 9, 2022
- Final presentations due from speakers: September 23, 2022
- IXPUG sessions (event dates): September 28-30, 2022
IXPUG 2022 Program Committee
- Organizing Chair: David Martin, Argonne National Laboratory
- Co-Chair: R. Glenn Brook, Cornelis Networks
- Co-Chair: Christopher Mauney, Los Alamos National Laboratory
- Aksel Alpay, Heidelberg University
- Melyssa Fratkin, Texas Advanced Computing Center (TACC)
- Maria Girone, CERN openlab
- Toshihiro Hanawa, The University of Tokyo
- Clayton Hughes, Sandia National Laboratories
- David Keyes, King Abdullah University of Science & Technology
- Nalini Kumar, Intel Corporation
- James Lin, Shanghai Jiao Tong University
- Hatem Ltaief, King Abdullah University of Science & Technology
- Amit Ruhela, Texas Advanced Computing Center (TACC)
- Thomas Steinke, Zuse Institute Berlin
Publication
IXPUG Annual Conference 2022 presentations will be published on the IXPUG website. All presenters will retain the copyright to their work.
Contact
Questions? Email This email address is being protected from spambots. You need JavaScript enabled to view it.