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:20181221T160727Z
LOCATION:D161
DTSTART;TZID=America/Chicago:20181112T111000
DTEND;TZID=America/Chicago:20181112T113000
UID:submissions.supercomputing.org_SC18_sess158_ws_lasalss112@linklings.co
 m
SUMMARY:Event-Triggered Communication in Parallel Computing
DESCRIPTION:Workshop\nAlgorithms, Heterogeneous Systems, Resiliency, Works
 hop Reg Pass\n\nEvent-Triggered Communication in Parallel Computing\n\nGho
 sh, Saha, Gupta, Tryggvason\n\nCommunication overhead in parallel systems 
 can be a significant bottleneck in scaling up parallel computation. In thi
 s paper, we propose event-triggered communication methods to reduce such c
 ommunication overhead for numerical simulation of partial differential equ
 ations. As opposed to traditional communication in which processing elemen
 ts exchange data at every iteration of the numerical algorithm, the main i
 dea behind event-triggered communication is to exchange data only\nwhen ne
 cessary as dictated by a suitably defined event. We show through numerical
  experiments that these methods have potential to reduce simulation time. 
 Strong scaling plots show that the approach may be effective on large mach
 ines as well.
URL:https://sc18.supercomputing.org/presentation/?id=ws_lasalss112&sess=se
 ss158
END:VEVENT
END:VCALENDAR