11th JLESC workshop (online)


11th JLESC Workshop

Objectives 

The workshop gathers leading researchers in high-performance computing from the JLESC partners INRIA, the University of Illinois, Argonne National Laboratory, Barcelona Supercomputing Center, Jülich Supercomputing Centre, RIKEN R-CCS and The University of Tennessee to explore the most recent and critical issues in advancing the field of HPC from petascale to the extreme scale era.

The workshop will feature sessions on these seven central topics:

  • Applications and mini-apps
  • Parallel Programming models and runtime
  • Performance tools
  • Resilience
  • Big Data, I/O and in-situ visualization
  • Numerical methods and algorithms
  • Advanced architectures

In addition, dedicated sessions on computational fluid dynamics, computational biology and climate/weather research are planned.

A key objective of the workshop is to identify new research collaborations and establish a roadmap for their implementation.

The workshop is open to Illinois, INRIA, ANL, BSC, JSC, Riken R-CCS and UTK faculties, researchers, engineers and students who want to learn more about Post-Petascale / Pre-Exascale Computing.

Agenda 


Track 1
Zoom link: 		Track 2
Zoom link:
08:00 ET Opening

Franck Cappello, Robert Speck
08:10 ET ST M1.1 (6) AI

Session chair: George Bosilca 		Multiprecision Numerics for HPC
09:40 ET ST M1.2 (6) I/O, In-situ

Session chair: Ruth Schöbel
11:10 ET Open zoom sessions (all zoom sessions will remain open until 1PM ET)

Track 1
Zoom link: 		Track 2
Zoom link:
08:00 ET ST M2.1 (6) Numerical Methods and Resilience

Session chair: Kevin Sala 		Challenges and opportunities with running AI workloads on HPC systems
09:30 ET ST M2.2 (6) Performance Tools

Session chair: Daichi Mukunoki
11:00 ET Open zoom sessions (all zoom sessions will remain open until 1PM ET)

Track 1
Zoom link: 		Track 2
Zoom link:
08:00 ET ST M3.1 (6) Programming Languages and Runtimes

Session chair: Daniel Barry 		Heterogeneous and reconfigurable architectures for the future of computing
09:30 ET ST M3.2 (6) Programming Languages and Runtimes and Advanced Architectures

Session chair: Colleen Heinemann
11:00 ET Closing

Franck Cappello, Robert Speck
11:10 ET Open zoom sessions (all zoom sessions will remain open until 1PM ET)

Agenda Items


Title Presenter Topic Discussion link
STM1.1Lossy Compression for AIRobert Underwood, Sheng Di, Jon C. Calhoun, and Franck CappelloAI
AI for the CIWilliam KramerAI
CANDLE/Supervisor: A Deep Learning Environment for Cancer ApplicationsJustin M WozniakAI
XPC: XFEL-based Protein ClassifierPaula Olaya (UTK)AI
State Preservation for Deep Learning Applications: Challenges and OpportunitiesBogdan Nicolae, Argonne National LaboratoryAI
AI-Driven Control for Scientific WorkflowsOrcun YILDIZ (ANL)AI
STM1.2Evaluation and optimization of the I/O scalability of IFS atmosphere model using XIOSXavier Yepes Arbós (BSC)I/O, Storage and In-Situ Processing
Mapping and Scheduling HPC Applications for optimizing I/ONicolas Vidal (Inria BSO)I/O, Storage and In-Situ Processing
E2Clab: Exploring the Computing Continuum through Repeatable, Replicable and Reproducible Edge-to-Cloud ExperimentsDaniel Rosendo (Inria)I/O, Storage and In-situ Processing
Dynamic Provisioning of Storage Resources on SupercomputersFrancois Tessier (Inria)I/O, Storage and In-Situ Processing, Performance Tools
HPC For Irregular ApplicationsValentin Honoré, University of Bordeaux / InriaI/O, Storage and In-Situ Processing, Performance Tools
Elastic large scale ensemble based Data Assimilation with Melissa-DASebastian Friedemann, Universite-Grenoble-Alpes, INRIAI/O, Storage and In-Situ Processing, Performance Tools
STM2.1Intermediate Representations for Automatic Differentiation of Parallel ProgramsJan Hückelheim, Argonne National LaboratoryNumerical Methods
Paralpha: a parallel in time and space method for solving PDEs.Gayatri Caklovic (JSC)Numerical Methods
Optimizing non-standard tensor operationsAlexander Sebastian Achilles (JSC)Numerical Methods, Apps & Mini-Apps,
Reducing Checkpointing for JAX-based Quantum Optimal ControlMarcelo Santos Bongarti (U. Memphis), Paul Hovland (ANL), Sri Hari Krishna Narayanan (ANL) Numerical Methods, Apps & Mini-Apps,
Blue Waters Operational DataBrett Bode, University of Illinois/NCSAResilience
Towards fine-tuning of multi-level checkpointing using machine learning: The case of VeloCBogdan Nicolae, Argonne National Laboratory; Kento Sato, RIKENResilience
STM2.2Evaluating Applications Bandwidth Upper-Bounds on Hypothetical NUMA SystemsNicolas Denoyelle (Argonne National Laboratory)Performance Tools
Dgemm performance is data-dependentTom Cornebize (Inria), Arnaud Legrand (Inria)Performance Tools
Tuning scientific-engineering applications by learning from expanded featuresFelipe Portella (BSC/UPC/Petrobras)Performance Tools
Solving Native Hardware Event Recognition Using the Counter Analysis ToolkitDaniel Barry (UTK)Performance Tools
Exascale potholes for HPC applicationsBrian Wylie (Juelich Supercomputing Centre)Performance tools; Applications and mini-apps; Resilience
Utilizing the Performance API to Measure Bandwidth and Arithmetic IntensityDaniel Barry (UTK), Heike Jagode (UTK), Anthony Danalis (UTK), Jack Dongarra (UTK)Performance Tools
STM3.1Model-Centric Tracing of Low-Level HPC APIsBrice Videau (ANL)Programming Languages and Runtimes
Large scale communications for task-based runtimesPhilippe SWARTVAGHER (INRIA)Programming Languages and Runtimes
"Message in a bottle" communication for the FMMIvo Kabadshow (JSC)Programming Languages and Runtimes
Integrating one-sided GASPI communications with task-based programming modelsKevin Sala (BSC)Programming Languages and Runtimes
Efficient Composition of Library SubroutineLaurent Turpin - Thierry Gautier - Christian Perez @inriaProgramming Languages and Runtimes
Latest Advances on OmpSs/OpenACC GPU Tasking and use of heterogeneous memory systemsLeonel Toledo, Barcelona Supercomputing Center (BSC)Programming Languages and Runtimes
STM3.2A common workflow registry of compute endpoints and applicationsspeaker: Daniel S. Katz (UIUC); full author list: Rosa M. Badia (BSC), Kyle Chard (ANL/UC), Jorge Ejarque (BSC), Daniel S. Katz (UIUC)Programming Languages and Runtimes
Tasking Meets GPUs: A Closer Look at Locking Laura Morgenstern (JSC)Programming Languages and Runtimes, Numerical Methods
International MPI SurveyAtsushi Hori, Jie Yin, Takahiro Ogura, Balazs Gerofi, Yutaka Ishikawa (Riken), George Bosilca (UT/ICL), Emmanuel Jeannot (Inria)Programming Languages and Runtimes, Numerical Methods
Message passing with large-scale multithreadingMarc Snir, Omri Mor. University of Illinois at Urbana ChampaignProgramming models and runtime
Speculative Scheduler for converging HPC/Big Data/MLGuillaume Pallez (Aupy), InriaAdvanced Architectures
Using SVE to accelerate HPC applicationsMiquel Moreto (BSC)Advanced Architectures