15th Scheduling for Large Scale Systems Workshop - Sciencesconf.org

Week Tue. 07 Wed. 08 Thu. 09 Fri. 10 List

	Tue. 07	Wed. 08	Thu. 09	Fri. 10
09:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 17:00 18:00 19:00 20:00 21:00	Lunch 12:30 - 14:00 (1h30) Lunch Introduction 14:45 - 15:00 (15min) Introduction G. Pichon & L. Marchal Programming Heterogeneous Architectures Using Hierarchical Tasks 15:00 - 15:30 (30min) Programming Heterogeneous Architectures Using Hierarchical Tasks Gwénolé Lucas Mixed Precision LU Factorization using GPU Tensor Cores 15:30 - 16:00 (30min) Mixed Precision LU Factorization using GPU Tensor Cores Florent Lopez Task-Based Parallel Programming for Scalable Algorithms 16:00 - 16:30 (30min) Task-Based Parallel Programming for Scalable Algorithms Antoine Jégo Refreshment 16:30 - 17:00 (30min) Refreshment Learning Optimal Schedules in Markovian Bandits: Pitfalls and Benefits. 17:00 - 17:30 (30min) Learning Optimal Schedules in Markovian Bandits: Pitfalls and Benefits. Bruno Gaujal Reservation strategies for stochastic jobs 17:30 - 18:00 (30min) Reservation strategies for stochastic jobs Guillaume Pallez Multi-Phase Task-Based HPC Applications: Quickly Learning how to Run Fast 18:00 - 18:30 (30min) Multi-Phase Task-Based HPC Applications: Quickly Learning how to Run Fast Arnaud Legrand Dinner 19:30 - 21:00 (1h30) Dinner	Scheduling Strategies for Overloaded Real-Time Systems. 9:00 - 9:30 (30min) Scheduling Strategies for Overloaded Real-Time Systems. Frédéric Vivien Algorithm-Based Fault Tolerance for Parallel Stencil Computations 9:30 - 10:00 (30min) Algorithm-Based Fault Tolerance for Parallel Stencil Computations Aurélien Cavelan Multi-objective Hybrid Autoscaling of Microservices in Kubernetes Clusters 10:00 - 10:30 (30min) Multi-objective Hybrid Autoscaling of Microservices in Kubernetes Clusters Hamid Fard Coffee break 10:30 - 11:00 (30min) Coffee break Mapping Tree-shaped Workflows on Memory-heterogeneous Architectures 11:00 - 11:30 (30min) Mapping Tree-shaped Workflows on Memory-heterogeneous Architectures Svetlana Kulagina Process Mapping on any Topology with TopoMatch 11:30 - 12:00 (30min) Process Mapping on any Topology with TopoMatch Emmanuel Jeannot Lunch 12:30 - 14:00 (1h30) Lunch Data Distribution for Symmetric Linear Algebra Kernels 15:30 - 16:00 (30min) Data Distribution for Symmetric Linear Algebra Kernels Mathieu Vérité IO-sets: Simple and efficient approaches for I/O bandwidth management 16:00 - 16:30 (30min) IO-sets: Simple and efficient approaches for I/O bandwidth management Nicolas Vidal Memory Aware Scheduling of Tasks Sharing Data on Multiple GPUs with Dynamic Runtime Systems 16:30 - 17:00 (30min) Memory Aware Scheduling of Tasks Sharing Data on Multiple GPUs with Dynamic Runtime Systems Maxime Gonthier Refreshment 17:00 - 17:30 (30min) Refreshment A Selective Nesting Approach for the Sparse Multi-threaded Cholesky Factorization 17:30 - 18:00 (30min) A Selective Nesting Approach for the Sparse Multi-threaded Cholesky Factorization Valentin Le Fèvre Combining Uncore Frequency and Dynamic Power Capping to Improve Power Savings 18:00 - 18:30 (30min) Combining Uncore Frequency and Dynamic Power Capping to Improve Power Savings Amina Guermouche On the use of simulation for scheduling (research) 18:30 - 19:00 (30min) On the use of simulation for scheduling (research) Henri Casanova Dinner 19:30 - 21:00 (1h30) Dinner	Investigations of Low-Rank Clustering Techniques for Sparse Direct Solvers 9:00 - 9:30 (30min) Investigations of Low-Rank Clustering Techniques for Sparse Direct Solvers Brian Bantsoukissa Modeling Memory Contention between Communications and Computations in Distributed HPC Systems 9:30 - 10:00 (30min) Modeling Memory Contention between Communications and Computations in Distributed HPC Systems Philippe Swartvagher Designing Next-Generation Linear Algebra Libraries for Large-Scale Matrix Computations 10:00 - 10:30 (30min) Designing Next-Generation Linear Algebra Libraries for Large-Scale Matrix Computations Hatem Ltaief Coffee break 10:30 - 11:00 (30min) Coffee break Memory Saving Techniques for Deep Neural Network Training 11:00 - 11:30 (30min) Memory Saving Techniques for Deep Neural Network Training Lionel Eyraud-Dubois An Efficient Parallel Implementation of a Perfect Hashing Method for Hypergraphs 11:30 - 12:00 (30min) An Efficient Parallel Implementation of a Perfect Hashing Method for Hypergraphs Somesh Singh Lunch 12:30 - 14:00 (1h30) Lunch Excursion 14:00 - 17:00 (3h) Excursion Dinner 19:30 - 21:00 (1h30) Dinner	An Exact Algorithm for the Linear Tape Scheduling Problem 9:00 - 9:30 (30min) An Exact Algorithm for the Linear Tape Scheduling Problem Valentin Honoré Shelf schedules for independent moldable tasks to minimize the energy consumption 9:30 - 10:00 (30min) Shelf schedules for independent moldable tasks to minimize the energy consumption Anne Benoit Fixed-Parameter Tractability of Scheduling Dependent Tasks on m identical processors subject to Release Times and Deadlines 10:00 - 10:30 (30min) Fixed-Parameter Tractability of Scheduling Dependent Tasks on m identical processors subject to Release Times and Deadlines Alix Munier-Kordon Coffee break 10:30 - 11:00 (30min) Coffee break Learning-Augmented Online Algorithms 11:00 - 11:30 (30min) Learning-Augmented Online Algorithms Bertrand Simon Resilient Scheduling of Moldable Parallel Jobs to Cope with Silent Errors 11:30 - 12:00 (30min) Resilient Scheduling of Moldable Parallel Jobs to Cope with Silent Errors Lucas Pérotin Lunch 12:30 - 14:00 (1h30) Lunch