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:20181221T160742Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T171500
DTEND;TZID=America/Chicago:20181113T190000
UID:submissions.supercomputing.org_SC18_sess343_drs114@linklings.com
SUMMARY:Fast and Generic Concurrent Message-Passing
DESCRIPTION:Doctoral Showcase\nWorkshop Reg Pass, Tutorial Reg Pass, Tech 
 Program Reg Pass, Exhibits Reg Pass, Exhibits - Exhibit Hall Only Reg Pass
 \n\nFast and Generic Concurrent Message-Passing\n\nDang, Snir\n\nCommunica
 tion hardware and software have a significant impact on the performance&nb
 sp;of clusters and supercomputers. Message-passing model and the Message-P
 assing Interface (MPI) is a widely used model of communications in th
 e High-Performance<br />Computing (HPC) community. However, MPI has recent
 ly faced new challenges due to the emergence of many-core architectur
 e and of programming models with dynamic task parallelism, assuming a
  large number of concurrent threads. These applications come from imp
 ortant classes of applications such as graph and data analytics.<br /
 ><br />In this thesis, we studied MPI under the new assumptions. We identi
 fied several factors in the standard which were inherently problemati
 c for scalability and performance. Next, we analyzed graph, threading
  and data-flow frameworks to understand the communication. We then pr
 oposed a communication engine (LCI) targetting these frameworks. Our 
 thesis benefits MPI by developing several patches in production MPI. 
 Furthermore, LCI presents a simple and ground-up design which benefit
 s various frameworks of study.
URL:https://sc18.supercomputing.org/presentation/?id=drs114&sess=sess343
END:VEVENT
END:VCALENDAR

