BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260627T145206Z
UID:655dada9-7f54-43e7-8050-6fb4276ea9e6
DTSTART:20140902T083000Z
DTEND:20140903T153000Z
DESCRIPTION:\n	Please note this course will be held in Daresbury:\n	STFC Da
 resbury Laboratory\n	Sci-Tech Daresbury\n	Daresbury\n	Warrington\n	WA4 4AD
 \nOne of the greatest challenges to running parallel applications onlarge 
 numbers of processors is how to handle file IO: standard IO routinesare no
 t designed with parallelism in mind. Parallel file systems such as Lustre 
 are optimised for large data transfers\, and performance can be far from o
 ptimal if many files are opened at once.\nThe IO part of the MPI standard 
 gives programmers access to efficient parallel IO in a portable fashion. H
 owever\, there are a large number of different routines available and some
  can be difficult to use in practice. Despite its apparent complexity\, MP
 I-IO adopts a very straightforward high-level model. If used correctly\, a
 lmost all the complexities of aggregating data from multiple processes can
  be dealt with automatically by the library.\nThe first day of the course 
 will cover the MPI-IO standard\, developing IO routines for a regular doma
 in decomposition example. It will also briefly cover higher-level standard
 s such as HDF5 and NetCDF.\nThe second day will concentrate on ARCHER\, co
 vering how to configure the Lustre file system for best performance and ho
 w to tune the Cray MPI-IO library. Case studies from real codes will also 
 be presented.\nPrerequisites: The course assumes a good understanding of b
 asic MPI programming in Fortran\, C or C++. Knowledge of MPI derived datat
 ypes would be useful but not essential.\n\nhttps://events.prace-ri.eu/even
 t/306/
SUMMARY:Efficient Parallel IO on ARCHER @ EPCC
URL;VALUE=URI:https://events.prace-ri.eu/event/306/
END:VEVENT
END:VCALENDAR