BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260630T135035Z
UID:948dca5e-0e7c-4551-b84e-5e4763192e87
DTSTART:20220622T070000Z
DTEND:20220624T140000Z
DESCRIPTION:\nThis course is part of PRACE Advanced HPC Workshop and will b
 e delivered as an ONLINE EVENT for remote participation\n\nOverview\n\nMos
 t HPC systems are clusters of shared memory nodes. To use such systems eff
 iciently both memory consumption and communication time has to be optimize
 d. Therefore\, hybrid programming may combine the distributed memory para
 llelization on the node interconnect (e.g.\, with MPI) with the shared mem
 ory parallelization inside of each node (e.g.\, with OpenMP or MPI-3.0 sha
 red memory). This course analyzes the strengths and weaknesses of several 
 parallel programming models on clusters of SMP nodes. Multi-socket-multi-c
 ore systems in highly parallel environments are given special consideratio
 n. MPI-3.0 has introduced a new shared memory programming interface\, whic
 h can be combined with inter-node MPI communication. It can be used for di
 rect neighbor accesses similar to OpenMP or for direct halo copies\, and e
 nables new hybrid programming models. These models are compared with vario
 us hybrid MPI+OpenMP approaches and pure MPI. Numerous case studies and mi
 cro-benchmarks demonstrate the performance-related aspects of hybrid progr
 amming.\n\nHands-on sessions are included on all days. Tools for hybrid p
 rogramming such as thread/process placement support and performance analys
 is are presented in a "how-to" section. This course provides scientific tr
 aining in Computational Science and\, in addition\, the scientific exchan
 ge of the participants among themselves.\n\nThis online course is a PRACE 
 training event. It is organised by LRZ in cooperation with HLRS\, NHR@FAU 
 and the VSC Research Center\, TU Wien.\n\nPreliminary Agenda\n\n1st day\n\
 n08:45   Join online\n09:00      Welcome\n09:05      Motivation\n0
 9:15      Introduction\n09:30      Programming Models\n09:35     
     - MPI + OpenMP\n10:00            Practical (how to compile and
  start)\n10:30   Break\n10:45         - continue: MPI + OpenMP\n11
 :30   Break\n11:45         - continue: MPI + OpenMP\n12:30      
       Practical (how to do pinning)\n13:00   Lunch\n14:00        
     Practical (hybrid through OpenMP parallelization)\n15:30        
     Q &amp\; A\, Discussion\n16:00   End of first day\n\n2nd day\n\n08:
 45   Join online\n09:00         - Overlapping Communication and Com
 putation\n09:30            Practical (taskloops)\n10:30   Break\n1
 0:45         - MPI + OpenMP Conclusions\n11:00         - MPI + A
 ccelerators\n11:30      Tools\n11:45   Break\n12:00      Programmi
 ng Models (continued)\n12:05         - MPI + MPI-3.0 Shared Memory\n1
 3:00   Lunch\n14:00            Practical (replicated data)\n15:30
             Q &amp\; A\, Discussion\n16:00   End of second day\n\n
 3rd day\n\n08:45   Join online\n09:00         - MPI Memory Models a
 nd Synchronization\n09:40         - Pure MPI\n10:00   Break\n10:15
          - Recap - MPI Virtual Topologies\n10:45         - Topol
 ogy Optimization\n11:15   Break\n11:30           Practical/Demo (a
 pplication aware Cartesian topology)\n12:30         - Topology Optimi
 zation (Wrap up)\n12:45       Conclusions\n13:00   Lunch\n14:00   
     Finish the hands-on labs\, Discussion\, Q &amp\; A\, Feedback\n16:00
    End of third day (course)\n\nPrerequisites\n\nBasic MPI and OpenMP kn
 owledge. For the hands-on sessions you should know Unix/Linux and either C
 /C++ or Fortran.\n\nContent Level\n\nThe content level of the course is br
 oken down as:\n\n\n	\n		\n			\n			Beginner's content:\n			\n			\n			0%\n		
 	\n		\n		\n			\n			Intermediate content:\n			\n			\n			10%\n			\n		\n		\n	
 		\n			Advanced content:\n			\n			\n			90%\n			\n		\n		\n			\n			Community
 -targeted content:\n			\n			\n			0%\n			\n		\n	\n\n\nLanguage\n\nEnglish\n
 \nLecturers\n\nDr. Claudia Blaas-Schenner (VSC Research Center\, TU Wien)
 \, Dr. habil. Georg Hager (NHR@FAU)\, Dr. Rolf Rabenseifner (HLRS\, Un
 i. Stuttgart)\n\nPrices and Eligibility\n\nThe course is open and free of 
 charge for people from academia and industry from the Member States (MS) o
 f the European Union (EU) and Associated/Other Countries to the Horizon 20
 20 programme.\n\nRegistration\n\nPlease register via the PRACE registratio
 n page with your official e-mail address to prove your affiliation. Follow
 ing your successful registration\, you will receive further information ap
 prox. 1-2 weeks before the course.\nhttps://events.prace-ri.eu/event/1334/
SUMMARY:[ONLINE] Hybrid Programming in HPC - MPI+X @ LRZ
URL;VALUE=URI:https://events.prace-ri.eu/event/1334/
END:VEVENT
END:VCALENDAR