BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:2.0
BEGIN:VEVENT
DTSTART:20141117T143000Z
DTEND:20141117T230000Z
LOCATION:386-87
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: I/O on HPC systems is a black art. This tutorial sheds light on the=0Astate-of-the-art in parallel I/O and provides the knowledge necessary for=0Aattendees to best leverage I/O resources available to them. We cover the=0Aentire I/O software stack from parallel file systems at the lowest layer, to=0Aintermediate layers (such as MPI-IO), and finally high-level I/O libraries=0A(such as HDF-5). We emphasize ways to use these interfaces that result in=0Ahigh performance. Benchmarks on real systems are used throughout to show=0Areal-world results.=0A=0AThis tutorial first discusses parallel file systems in detail (PFSs). We cover=0Ageneral concepts and examine three examples: GPFS, Lustre, and PanFS.=0A We examine the upper layers of the I/O stack, covering POSIX I/O,=0AMPI-IO, Parallel netCDF, and HDF5. We discuss interface features, show code=0Aexamples, and describe how application calls translate into PFS=0Aoperations. Finally we discuss I/O best practice.
SUMMARY:Parallel I/O In Practice
PRIORITY:3
END:VEVENT
END:VCALENDAR