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:20181221T160731Z
LOCATION:D173
DTSTART;TZID=America/Chicago:20181114T113000
DTEND;TZID=America/Chicago:20181114T120000
UID:submissions.supercomputing.org_SC18_sess487_exforum153@linklings.com
SUMMARY:High Performance OpenMP for GPUs
DESCRIPTION:Exhibitor Forum\nAccelerators, GPUs\n\nHigh Performance OpenMP
  for GPUs\n\nWolfe\n\nOpenMP has a 20 year history in HPC. It was the para
 llel programming model of choice for large SMP servers, and later proved e
 ffective for hybrid MPI+OpenMP programming on scalable systems.  As core c
 ounts rose, best practices for OpenMP implementations and programming have
  evolved. The early focus was on maximizing efficiency of loop-level paral
 lelism.  More recently a global, outer-parallel approach has been used to 
 improve scalability on nodes with large numbers of CPU cores.  GPUs are op
 timized to deliver high performance and throughput on massively parallel, 
 regular, loop-structured algorithms.  In this talk, we'll survey the featu
 res of the latest OpenMP standards, describe how OpenMP programs can explo
 it the performance potential of today's GPUs, and summarize the implicatio
 ns for a high-performance OpenMP implementation that supports both multico
 re CPUs and GPU accelerators.
URL:https://sc18.supercomputing.org/presentation/?id=exforum153&sess=sess4
 87
END:VEVENT
END:VCALENDAR