BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260704T083527Z
UID:b7160b87-20e6-4e95-bc71-8ea8c5824046
DTSTART:20161128T090000Z
DTEND:20161129T173000Z
DESCRIPTION:This course covers techniques for improving the performance of 
 applications on ARCHER but optimising of the code that runs within each no
 de. Familiarity with a Unix or Linux environment is assumed. The course is
  open to all\, but is mainly targeted at existing ARCHER users.\n\nDetails
 \n\nDetails: Modern HPC systems are being constructed using increasingly p
 owerful nodes\, with larger and larger numbers of cores and enhanced vecto
 r capabilities. To extract maximum performance from applications\, it is t
 herefore necessary to understand\, and be able to overcome\, on-node perfo
 rmance bottlenecks.\n\nThis course will cover the main features of modern 
 HPC nodes\, including multiple cores\, vector floating point units\, deep 
 cache hierarchies\, and NUMA memory systems. We will cover techniques for 
 efficient programming of these features\, using batch processing options a
 nd compiler options as well as hand tuning of code. The course will also c
 ontain an introduction to the use of Cray performance analysis tools.\n\nI
 ntended learning outcomes\n\nOn completing this course\, attendees should 
 :\n\nHave an understanding of modern HPC node architectures and their impl
 ications for performance.\n	Be equipped with a toolbox of techniques for e
 xtracting good single node performance from application codes.\n	Have a ba
 sic knowledge of using Cray performance analysis tools.\nPrerequisites\n\n
 Programming Languages: Fortran\, C or C++. Familiarity with a Unix or Linu
 x environment is assumed.\n\nTimetable\n\nDay 1\n\n09:00 Node Architecture
 \, Profiling\n	11:00 BREAK\n	11:30 Practical: profiling\n	12:30 LUNCH\n	13
 :30 Optimising with the compiler\n	15:00 BREAK\n	15:30 Practical: optimisa
 tion\n	17:00 CLOSE\nDay 2\n\n09:00 Vectorisation\, Memory Hierarchy Optimi
 sation\n	11:00 BREAK\n	11:30 Practical: memory and cache blocking\n	12:30 
 LUNCH\n	13:30 Hybrid Program Optimisation\n	15:00 BREAK\n	15:30 Practical:
  OpenMP optimisation\n	16:30 CLOSE\nCourse materials page\n\nhttps://event
 s.prace-ri.eu/event/552/
SUMMARY:Single Node Performance Optimisation 28-29 Nov@ EPCC at Manchester
URL;VALUE=URI:https://events.prace-ri.eu/event/552/
END:VEVENT
END:VCALENDAR