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:20181221T160725Z
LOCATION:D175
DTSTART;TZID=America/Chicago:20181111T103000
DTEND;TZID=America/Chicago:20181111T105000
UID:submissions.supercomputing.org_SC18_sess155_ws_waccpd110@linklings.com
SUMMARY:Using Compiler Directives for Performance Portability in Scientifi
 c Computing: Kernels from Molecular Simulation
DESCRIPTION:Workshop\nAccelerators, Heterogeneous Systems, Parallel Progra
 mming Languages, Libraries, and Models, Workshop Reg Pass\n\nUsing Compile
 r Directives for Performance Portability in Scientific Computing: Kernels 
 from Molecular Simulation\n\nSedova, Tillack, Tharrington\n\nAchieving per
 formance portability for high-performance computing (HPC) applications in 
 scientific fields has become an increasingly important initiative due to l
 arge differences in emerging supercomputer architectures. Here we test som
 e key kernels from molecular dynamics (MD) to determine whether the use of
  the OpenACC directive-based programming model when applied to these kerne
 ls can result in performance within an acceptable range for these types of
  programs in the HPC setting. We find that for easily parallelizable kerne
 ls, performance on the GPU remains within this range. On the CPU, OpenACC-
 parallelized pairwise distance kernels would not meet the performance stan
 dards required, when using AMD Opteron “Interlagos” processors, but with I
 BM Power 9 processors, performance remains within an acceptable range for 
 small batch sizes. These kernels provide a test for achieving performance 
 portability with compiler directives for problems with memory-intensive co
 mponents as are often found in scientific applications.
URL:https://sc18.supercomputing.org/presentation/?id=ws_waccpd110&sess=ses
 s155
END:VEVENT
END:VCALENDAR

