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:20181221T160904Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T083000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess322_post209@linklings.com
SUMMARY:Tuning CFD Applications for Intel Xeon Phi with TAU Commander and 
 ParaTools ThreadSpotter
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nTuning CFD
  Applications for Intel Xeon Phi with TAU Commander and ParaTools ThreadSp
 otter\n\nBeekman, Chaimov, Shende, Malony, Bisek...\n\nTuning and understa
 nding the performance characteristics of computational fluid dynamics (CFD
 ) codes on many-core, NUMA architectures is challenging. One must determin
 e how programming choices impact algorithm performance and how best to uti
 lize the available memory caches, high-bandwidth memory, and inter---and i
 ntra---node communication. Once collected, performance data must be transl
 ated into actionable code improvements. In addition, performance engineeri
 ng experiments must be organized and tracked to quantify the benefit of an
 y attempted tuning.\n\nIn the poster we present, examine and tune two CFD 
 applications running on the IntelⓇ Xeon Phi™️ partition of a 
 CrayⓇ XC 40/50 using TAU Commander and ParaTools ThreadSpotter. TAU 
 Commander implements a streamlined, managed performance engineering workfl
 ow and highlights source regions limiting scalability through profiling an
 d aggregate summary statistics. ParaTools ThreadSpotter analyzes an applic
 ation as it is running and ranks individual performance problems. It provi
 des a report annotating source code lines with actionable recommendations 
 and quantifying performance metrics.
URL:https://sc18.supercomputing.org/presentation/?id=post209&sess=sess322
END:VEVENT
END:VCALENDAR