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:20230124T171523Z
LOCATION:C155
DTSTART;TZID=America/Chicago:20221114T094500
DTEND;TZID=America/Chicago:20221114T100000
UID:submissions.supercomputing.org_SC22_sess453_ws_pmbss109@linklings.com
SUMMARY:OMPICollTune: Autotuning MPI Collectives by Incremental Online Lea
 rning
DESCRIPTION:Workshop\n\nOMPICollTune: Autotuning MPI Collectives by Increm
 ental Online Learning\n\nHunold, Steiner\n\nCollective communication opera
 tions are fundamental cornerstones in many high-performance applications. 
 MPI libraries typically implement a selection logic that attempts to make 
 good algorithmic choices for specific collective communication problem. It
  has been shown in the literature that the hard-coded algorithm selection 
 logic found in MPI libraries can be improved by prior offline tuning.\n\nW
 e go a fundamentally different way of improving the algorithm selection fo
 r MPI collectives. We integrate the probing of different algorithms direct
 ly into the MPI library. Whenever an MPI application is started, the tuner
 , instead of the default selection logic, finds the next algorithm to comp
 lete an issued MPI collective call and records its runtime. With the recor
 ded performance data, the tuner is able to build a performance model that 
 allows selecting an efficient algorithm. \n\nWe show in a case study using
  miniAMR that our approach can effectively tune the performance of Allredu
 ce.\n\nSession Format: Recorded\n\nTag: Applications, Architectures, Bench
 marking, Exascale Computing, Modeling and Simulation, Performance, Perform
 ance Portability\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR