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:20181221T160905Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181114T083000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess323_post187@linklings.com
SUMMARY:Parallel Implementation of Machine Learning-Based Many-Body Potent
 ials on CPU and GPU
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nParallel I
 mplementation of Machine Learning-Based Many-Body Potentials on CPU and GP
 U\n\nZhai, Danandeh, Tan, Gao, Paesani...\n\nMachine learning models can b
 e used to develop highly accurate and efficient many-body potentials for m
 olecular simulations based on the many-body expansion of the total energy.
   A prominent example is the MB-pol water model that employs permutational
 ly invariant polynomials (PIPs) to represent the 2-body and 3-body short-r
 ange energy terms.\n\nWe have recently shown that the PIPs can be replaced
  by Behler-Parinello neural networks (BP-NN).  We present OpenMP parallel 
 implementations of both PIP and BP-NN models as well as a CUDA implementat
 ion of the BP-NN model for GPUs.  The OpenMP implementations achieve linea
 r speedup  with respect to the optimized single threaded code. The BP-NN G
 PU implementation outperforms the CPU implementation by a factor of almost
  8.  This opens the door for routine molecular dynamics simulations with h
 ighly accurate many-body potentials on a diverse set of hardware.
URL:https://sc18.supercomputing.org/presentation/?id=post187&sess=sess323
END:VEVENT
END:VCALENDAR