BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055404Z
LOCATION:223
DTSTART;TZID=America/Chicago:20211115T162000
DTEND;TZID=America/Chicago:20211115T164500
UID:submissions.supercomputing.org_SC21_sess332_ws_pdsw109@linklings.com
SUMMARY:Verifying IO Synchronization from MPI Traces
DESCRIPTION:Workshop\n\nVerifying IO Synchronization from MPI Traces\n\nYe
 llapragada, Wang, Snir\n\nThe paper addresses the following question: Are 
 IO operations of HPC applications properly synchronized? We focus on paral
 lel file systems that satisfy POSIX semantics. The outcome of I/O operatio
 ns is well-defined provided that conflicting accesses to a file location a
 re not concurrent, but are ordered. Accesses to distinct processes are ord
 ered by the executed MPI communication. We derive the happens-before relat
 ion between I/O calls of HPC runs by analyzing traces collected during pro
 gram execution. Various optimizations reduce the analysis overhead. We col
 lected traces from 17 representative HPC applications. We found that 10 of
  them do not perform conflicting I/O accesses and, hence, are properly syn
 chronized by default. The remaining 7 applications properly synchronize th
 e conflicting I/O accesses.\n\nTag: Data Analytics, Data Management, File 
 Systems and I/O, Storage\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR