BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Practical HPC Tools Series - HyperQueue: Running Millions of Tasks
  on HPC Systems Made Easy
DTSTART:20261123T090000Z
DTEND:20261123T110000Z
DTSTAMP:20261117T185000Z
UID:indico-event-663@events.hpc-portal.eu
CONTACT:training@it4i.cz
DESCRIPTION:This course is organised in collaboration with MAX CoE\, EuroC
 C Czechia and EuroCC Germany.\nAnnotation\nMany scientific workflows consi
 st of huge numbers of small tasks\, which traditional HPC schedulers such 
 as SLURM and PBS handle poorly. This tutorial\, presented by the core deve
 lopers of HyperQueue\, introduces this open-source scheduler and meta-sche
 duler for large pipelines.\nStarting from the basics\, we show how to run 
 millions of tasks on SLURM- or PBS-managed clusters. HyperQueue requests a
 llocations automatically and distributes tasks into them with minimal over
 head. It also works on systems without any batch scheduler. It installs as
  a single binary without admin rights and is already preinstalled on many 
 supercomputers.\nParticipants will learn to submit and monitor tasks and t
 o define complex resource requests for heterogeneous clusters. We conclude
  with best practices and tips drawn from our experience supporting real-wo
 rld pipelines.\nBenefits for the attendees\, what will they learn:\n\n\nRe
 cognise when the “many small tasks” pattern overwhelms SLURM or PBS\, 
 and how a meta-scheduler solves it.\n\n\nInstall HyperQueue on their own m
 achine or use an existing installation on a supercomputer. \n\n\nSubmit\, 
 monitor\, and manage large numbers of tasks\, including task dependencies.
  \n\n\nLet HyperQueue request SLURM/PBS allocations automatically instead 
 of submitting jobs by hand. \n\n\nDefine complex resource requests (e.g. G
 PUs\, CPU counts\, custom resources) and use heterogeneous clusters effect
 ively. \n\nKeep scheduling overhead low when scaling to millions of tasks.
 \nApply best practices and avoid common pitfalls\, with tips from real-wor
 ld pipelines shared by the HyperQueue developers.\n\n \nLevel\nbeginner\,
  intermediate \nPrerequisites\nNo prior HyperQueue experience is required
 \, only basic familiarity with the command line and HPC clusters.\nLanguag
 e\nEnglish\nTutor\nAda Böhm holds a Ph.D. in Computer Science and is a re
 searcher at the IT4Innovations National Supercomputing Center\, Czech Repu
 blic. She works on task scheduling and distributed computing for HPC and i
 s a core author of HyperQueue. Her work also covers Rust systems programmi
 ng\, and infrastructure for quantum computing. She has a background in for
 mal methods and automata theory.\n\nhttps://events.hpc-portal.eu/event/663
 /
LOCATION:Zoom/IT4Innovations (HYBRID)
URL:https://events.hpc-portal.eu/event/663/
END:VEVENT
END:VCALENDAR
