BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260706T070405Z
UID:9c1b4ae4-1a80-4895-bd66-1a78a3fc0993
DTSTART:20180212T080000Z
DTEND:20180216T160000Z
DESCRIPTION:Description:\n\nIn the roadmap toward next-generation supercomp
 uters it is evident that heterogeneous architectures (integrating traditio
 nal CPUs and throughput CPUs\, such as GPU and Xeon PHI ) are taking an im
 portant share in the HPC market\, and the consolidation of this kind of ar
 chitectures requires an important effort in software development and appli
 cations refactoring.\n\nThis school focus on software development techniqu
 es to address the implementation of new HPC applications and the re-factor
 y of existing ones\, in the era of heterogeneous \, energy efficient\, mas
 sively parallel architectures.\n\nSoftware engineering techniques and high
  productivity languages will complement more traditional lectures on paral
 lel programming\, to allow the implementation of application that can be m
 aintained across a complex and fast evolving HPC architectures.\n\nThe sch
 ool\, in the hands-on session\, will give the possibility to exercise usin
 g both Nvidia accelerators (P100 cards) and Intel many core processors (Xe
 on Phi) integrated in D.A.V.I.D.E. and Marconi supercomputers.\n\nTopics:\
 n\nHeterogeneous architectures\n	Elements of software engineering\n	Parall
 el programming techniques for throughput CPUs  (Nvidia and Intel)\n	Para
 llel programming techniques for massively parallel applications\n	Introdu
 ction to Python for high performance computing\n	Models for applications i
 ntegrating MPI\, OpenMP OpenACC\, CUDA and CUDA Fortran paradigms\nTarget 
 audience:\n\nThe school is aimed at PRACE users\, final year master studen
 ts\, PhD students\, and young researchers in computational sciences and en
 gineering\, with different backgrounds\, interested in applying the emergi
 ng technologies on high performance computing to their research.\n\nPre-re
 quisites:\n\nBasic knowledge of parallel programming with MPI and/or OpenM
 P\, knowledge of FORTRAN and C languages.\nBasic knowledge of parallel com
 puter architectures.\n\nApplication deadline:\n\n21 January\, 2018 REGIST
 RATION CLOSED\n\nSTUDENTS ADMITTED AND NOT ADMITTED WILL BE CONTACTED VIA 
 EMAIL ON MONDAY 29TH.\n\nAdmitted students:\n\nAttendance is free.\n\nA g
 rant of 250 EUR (for students working abroad) and 150 EUR (for students
  working in Italy) will be available for participants not funded by their
  institution and not working or living in the Bologna area. Documentation
  will be required. Lunch will be provided by Cineca. Each student will be 
 given a two month access to the Cineca's supercomputing resources.\n\nThe 
 number of participants is limited to 22 students.\nApplicants will be sele
 cted according to their experience\, qualifications and scientific interes
 t BASED ON WHAT WRITTEN IN THE REGISTRATION FORM.\n\nDUE TO PRIVACY REASON
  THE STUDENTS ADMITTED AND NOT ADMITTED WILL BE CONTACTED VIA EMAIL ON MON
 DAY 29TH. IF YOU SUBMITTED AND DON'T RECEIVE THE EMAIL\, PLEASE WRITE AT 
 corsi.hpc@cineca.it.  \n\nAcknowledgement:\n\nThe support of CINI for t
 he software engineering module is gratefully acknowledged.\n\n \n\nhttps:
 //events.prace-ri.eu/event/697/
SUMMARY:14th Advanced School on Parallel Computing @ Cineca
URL;VALUE=URI:https://events.prace-ri.eu/event/697/
END:VEVENT
END:VCALENDAR