BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163559Z
LOCATION:605
DTSTART;TZID=America/Denver:20191117T140000
DTEND;TZID=America/Denver:20191117T143000
UID:submissions.supercomputing.org_SC19_sess109_ws_exampi105@linklings.com
SUMMARY:RDMA-Based Library for Collective Operations in MPI
DESCRIPTION:Workshop\n\nRDMA-Based Library for Collective Operations in MP
 I\n\nMargolin, Barak\n\nIn most MPI implementations, abstraction layers se
 parate the collective operation algorithms from the communication primitiv
 es, thus hindering its optimization with network acceleration technologies
 , such as RDMA. Open UCX is an RDMA-based point-ot-point communication lib
 rary, that can reduce the latency between processes in MPI applications, p
 articularly in large-scale system. This paper presents a design and implem
 entation of a library for MPI collective operations, by extending Open UCX
 . Our approach is transparent to MPI applications, and can reduce the late
 ncy of repeated calls to such operations by an average of 8% for relativel
 y small message sizes and as much as 90% for larger messages.\n\nTag: Work
 shop Reg Pass, Exascale, MPI, Networks, Parallel Programming Languages, Li
 braries, and Models\n\nRegistration Category: Workshop Reg Pass, Exascale,
  MPI, Networks, Parallel Programming Languages, Libraries, and Models
URL:https://sc19.supercomputing.org/presentation/?id=ws_exampi105&sess=ses
 s109
END:VEVENT
END:VCALENDAR