IXPUG Annual Conference 2021

TACC logo sm

IXPUG Annual Conference 2021 


Frontera medsize

Experts from around the world are invited to join us live online!

 

Registration: REGISTER NOW to attend live online via Zoom, hosted by TACC: https://tacc.zoom.us/webinar/register/WN_7I4kXdY_Qm6wmKa-AtN84g
  
Dates: October 19-21, 2021
 
Agenda: All times listed are Central Time. Presentations will be posted to the IXPUG website following the live event.
Tuesday, October 19th
Start End Title Presenter Presentation
Session 1: Welcome to IXPUG 2021 (Chair: Amit Ruhela)
10:00 10:05 Welcome – Day 1 Amit Ruhela  
10:05 10:20 Welcome to TACC Dr. Dan Stanzione, Executive Director at TACC  
10:20 11:20 Keynote: Computational Modeling of Nanomaterials for Biomedical Applications

​Dr. Lela Vuković is an Assistant Professor in the Department of Chemistry and Biochemistry at the University of Texas at El Paso (UTEP). Dr. Vuković's laboratory focuses on using computational methods to advance the applications of nucleic acids in biology and nanotechnology, and to design molecules with high-affinity target binding. Specific research projects in the lab involve the development of computational methods for the design of new nanosensors to detect the presence of molecules important to brain function, and the computational modeling of nanoparticles that disrupt viral pathways. Prior to joining the faculty at UTEP, Dr. Vuković was a Postdoctoral Fellow under the advisement of Dr. Klaus Schulten in the NSF Frontier Center for the Physics of Living Cells at the University of Illinois at Urbana-Champaign.

 
11:20 11:50 Talk: Unified Memory API for Heterogeneous Memory Sergei Vinogradov  
11:50 12:20 Talk: Tensor Computing with High Productivity, Performance, and Portability across Intel Spatial and Vector Architectures Hongbo Rong and Xiaochen Hao  
Session 2: Performance Portability (Chair: Thomas Steinke)
12:45 13:45 Keynote: Balancing Performance, Portability, and Productivity with oneAPI Jason Sewall and John Pennycook  
13:45 14:15 Talk: A General-Purpose Parallel and Heterogeneous Task Programming System Using Modern C++  Tsung-Wei Huang   
Session 3: Tutorial (Chair: Amit Ruhela)
14:30 16:00 Tutorial: Performance Modelling of Future GPUs with Offload Advisor Zakhar Matveev, Dmitry Petrov, Mariya Petrova and Vladimir Tsymbal  
Wednesday, October 20th
Start End Title Presenter Presentation
Session 4: Day 2 (Chair: Amit Ruhela)
10:00 10:15 Welcome – Day 2 Amit Ruhela  
10:15 11:15 Keynote: The Role of Simulations in Understanding Compressible Turbulence: What We Know, What We Want to Know, and How Extreme Simulations Can Help

Dr. Diego Donzis is an Associate Professor and a Presidential Impact Fellow in the Department of Aerospace Engineering at Texas A&M University. As director of the Turbulence and Advanced Computations Laboratory (TACL), Dr. Donzis leads a research group focused on fundamental aspects of turbulent flows and turbulent mixing using state-of-the-art simulations at massive scales. Dr. Donzis is one of the first users of the Frontera supercomputer where he worked on shock-turbulence interactions, universality in the emergence of turbulent behavior, and aero-optics—research funded by the NSF, the Air Force Office of Scientific Research, and the Army Research Lab.

 
11:15 11:45 Talk: HiCMA++: A Modern Low-Rank Matrix Algebra C++ Framework Mohammed Al Farhan, Huda Ibeid, Hatem Ltaief and David Keyes  
11:45 12:15 Talk: OneAPI to Rule Them All: A Testcase with Tile Low-Rank Matrix-Vector Multiplication for Scientific Applications Yuxi Hong, Mohammed A. Al Farhan, Jesse Cranney, Damien Gratadour, Huda Ibeid, Hatem Ltaief, Matteo Ravasi, Philippe Thierry and David Keyes  
Session 5: Site Updates (Chair: Nalini Kumar)
12:45 13:00 Site Update: The University of Tokyo Toshihiro Hanawa  
13:00 13:15 Site Update: Zuse Institute Berlin Thomas Steinke  
13:15 13:30 Site Update: Texas Advanced Computing Center John Cazes  
13:30 13:45 Site Update: Argonne National Lab David Martin  
Session 6: Tutorial (Chair: Clay Hughes)
14:00 16:00 Tutorial: Workflow and Profiling for Heterogenous Compute Kevin O'Leary and Cory Levels  
Thursday, October 21st
Start End Title Presenter Presentation
Session 7: Day 3 (Chair: David Martin)
10:00 10:15 Welcome – Day 3 Amit Ruhela  
10:15 11:15 Keynote: Extreme Computing and Extreme Events in the Environment

Dr. Kiran Bhaganagar, Professor, Department of Mechanical Engineering; Associate Fellow American Institute of Aeronautics & Astraunautics (AIAA); Director for Laboratory of Turbulence, Sensing & Intelligent Systems; Director of NASA Center for Advanced Measurements in Extreme Environments (CAMEE) at University of Texas at San Antonio. Bhaganagar had rigorous training as a Ph.D. student under the guidance Prof John Lumley, world’s leading experts on turbulence. Bhaganagar’s expertise is in the area of turbulence model development for atmospheric plumes, rough-wall turbulent boundary layer, leeway drag due to the combined interactions of wind and wave turbulence. Recently, Bhaganagar served as a principal investigator for the following: United States Coastal Guard, Integrated high-fidelity approach towards improved leeway drift prediction, NASA MIRO Center for Advanced Measurements in Extreme Environments; US Army, Novel Technology for detection and prediction of spreading of air-borne chemical agent. Bhaganagar has contributed to numerical tools, including WRF-LES to simulate 2-way feedback between the ABL and the plume, DNS of rough-wall turbulent channel flow, LES of wake effects of wind turbine, a novel technology for leeway detection due to the interaction of wind and current.

 
11:15 11:45 Talk: Assessing the Use Cases of Persistent Memory in High-Performance Scientific Computing Yehonatan Fridman, Yaniv Snir, Matan Rusanovsky, Kfir Zvi, Harel Levin, Danny Hendler, Hagit Attiya and Gal Oren  
11:45 12:15 Talk: Clustering Real-time Test Failure Output for Triage and Analysis Richard Barella  
Session 8: Tutorial (Chair: Thomas Steinke)
12:45 14:15 Tutorial: DAOS Update and Tutorial Mohamad Chaarawi  
14:15 14:30 Conference Closing Remarks – Day3 Amit Ruhela  
 
 
Event Description: This Intel eXtreme Performance Users Group (IXPUG) conference is focused on all aspects of adopting and employing state-of-the-art technologies and practices for optimal application execution on Intel XPU platforms. The challenges surrounding application performance and scalability will be covered across all levels, including tuning and optimization of diverse sets of applications on large-scale HPC systems. This includes system hardware beyond the processor (memory, interconnects, etc.), accelerators (e.g., GPUs, FPGAs), as well as topics related to oneAPI, software tools, programming models, HPC workloads, and more.
 
Key themes: high-performance computing, data analytics, artificial intelligence (machine learning and deep learning), HPC in the cloud, and COVID-19 related biomedical simulations and data analytics applications.
 
The conference draws expert software developers, scientists, researchers, academics, systems analysts, students, and end-users. It will feature keynote/invited talks, 30-minute technical sessions, lightning talks, hands-on tutorials, and site updates. Each year IXPUG brings together speakers from a wide variety of HPC organizations, renowned industry leaders, and Intel experts to share their real-world experiences, best practices, and techniques for maximizing software productivity and efficiency. Be part of this interactive, open forum with live Q&A!
 
Submission Guidelines
A short abstract should be submitted by Wednesday, September 22, 2021 AoE (UPDATED DEADLINE!) via EasyChair and the content should reflect the topics of interest that are listed below. Published or work-in-progress research in respective areas are encouraged. All final presentations are due by October 15, 2021. We would like you to include keywords that pertain to the techniques, Intel products, and associated domains that pertain to your technical work. Please see the full list below:
  • 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 processor, Intel Xe graphics, Intel® FPGA, Intel® Optane, Intel® Lustre Software and 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, Geophysics, Life Sciences, Material Science, Medical imaging, Molecular Dynamics, Nanotechnology, Physics, Visualization, High Energy Physics, etc.

Abstract 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 using extreme scale systems: Usability, In-situ Visualization, Programming Challenges, Algorithms and Methods, etc.
  • Application characterization on emerging technologies: Novel Memories (NVM), processors (Intel® Xeon Scalable processor, Intel® GPUs, Intel® FPGA, etc.)
  • Experience with incorporating machine learning and deep learning in HPC applications and workflows including performance analysis, optimization, and best practices

Important Dates

  • Abstract submission deadline: September 22, 2021 (AOE) UPDATED DEADLINE!
  • Acceptance notification: October 1, 2021
  • Presenters’ consent deadline: October 4, 2021
  • Final presentations due from speakers: October 15, 2021
  • IXPUG sessions (event dates): October 19-21, 2021

IXPUG 2021 Program Committee

  • Amit Ruhela (Chair), Texas Advanced Computing Center (TACC)
  • Aksel Alpay, Heidelberg University
  • R. Glenn Brook, University of Tennessee Knoxville
  • Melyssa Fratkin, Texas Advanced Computing Center (TACC)
  • Maria Girone, CERN openlab
  • Toshihiro Hanawa, The University of Tokyo
  • Clayton Hughes, Sandia National Laboratories
  • Hatem Ltaief, King Abdullah University of Science & Technology
  • James Lin, Shanghai Jiao Tong University
  • David Keyes, King Abdullah University of Science & Technology
  • Nalini Kumar, Intel Corporation
  • David Martin, Argonne National Laboratory
  • Thomas Steinke, Zuse Institute Berlin
  • Joe Zerr, Los Alamos National Laboratory

Publication
IXPUG Annual Conference 2021 presentations will be published on the IXPUG website. All presenters will retain the copyright to their work.

Registration
REGISTER NOW to attend live online via Zoom, hosted by TACC: https://tacc.zoom.us/webinar/register/WN_7I4kXdY_Qm6wmKa-AtN84g

Contact
Questions? Email This email address is being protected from spambots. You need JavaScript enabled to view it.