BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Different Workloads on HPC
DTSTART:20260305T090000Z
DTEND:20260305T120000Z
DTSTAMP:20260315T150800Z
UID:indico-event-110@events.plgrid.pl
CONTACT:training@cyfronet.pl\;events-noreply@plgrid.pl
DESCRIPTION:Speakers: Klemens Noga (ACC Cyfronet AGH)\, Oskar Klimas (ACK 
 Cyfronet AGH)\n\nThe training focuses on different ways to allocate resour
 ces on supercomputers and parallelisation schemes used to speed up calcula
 tions.\nModern supercomputers are massive parallel machines with up to hun
 dreds of cores on a single node and even thousands of nodes connected via 
 fast network interface. To utilise those machines fully\, one needs to kno
 w about parallelisation techniques and queuing system options of resource 
 allocation. This training will show different ways that Slurm allocates re
 sources and how to apply them to different computations and workloads.\nLe
 vel\n\nTarget audience\nTraining is intended for users who have started ru
 nning their own calculations and need to learn about different methods of 
 allocating resources at ACC Cyfronet AGH. \nAgenda\n\nIntroduction: seria
 l vs parallel\,\nEmbarrassingly parallel (so parallel it's embarrassing!)\
 ,\nIntranode standards and you:\n\nMPI\,\nOpenMP\,\nhybrid (MPI+OpenMP)\,\
 nsrun\;\n\n\nGoing multinode\,\nAccelerating with a GPU card\,\nEven more 
 different workloads:\n\nWhen HPC goes HTC (array jobs)\,\nChaining calcula
 tions with job dependencies.\n\n\n\nRequirements\nWe recommend doing this 
 training after familiarizing with the contents of Running Calculations the
  HPC way training provided at ACC Cyfronet AGH. \nTechnical prerequisite
 s:\n\nPLGrid account at https://portal.plgrid.pl/\;\nan active affiliatio
 n at https://portal.plgrid.pl/users/affiliations\;\naccess to Ares superc
 omputer\,\n\nif a participant has the access\, no further action\,\nif not
 \, one need to apply at https://portal.plgrid.pl/services/103 and the acc
 ess will be granted when joining the team (see below)\,\nparticipants are 
 not required to have their own grant allocations\;\n\n\naccess to JupyterH
 ubHPC\, apply at https://portal.plgrid.pl/services/110\;\nmembership in th
 e plggtraining team - the activation link will be sent after registration.
 \n\nThe above prerequisites are required to actively participate in the ha
 nds-on exercises.In case of no active affiliation or PLGrid account\, plea
 se contact the organisers at training@cyfronet.pl. \nParticipants' compu
 ters should be equipped with software that allows SSH connections. On Wind
 ows\, it is recommended to use Windows Terminal (not to be confused with P
 owershell after checking if OpenSSH is installed (run ssh -V in the termin
 al). We advise against using Putty.\nAt 10:30 am on 23rd February 2026\, a
  Dry-run will be held. Participants are invited to come to learn how to lo
 g in to Ares supercomputer before the training and resolve any problems wi
 th the Training Team.\nVenue\nThe workshop will be conducted online on the
  Zoom platform. The meeting link will be sent to registered participants.\
 nLanguage\nEnglish\nDuration\n3 hours\nRegistration\nThe Registration and 
 the Waiting list close automatically after 17th February 2026. The Registr
 ation may close prematurely if the limit number of participants is hit bef
 orehand\, but the Waiting List will be available until the deadline above.
 \n\n\nhttps://events.plgrid.pl/event/110/
LOCATION:https://cyfronet.zoom.us/j/94176138049 (online)
URL:https://events.plgrid.pl/event/110/
END:VEVENT
END:VCALENDAR