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:20260522T150116Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T083000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess322_post187@linklings.com
SUMMARY:Parallel Implementation of Machine Learning-Based Many-Body Potent
 ials on CPU and GPU
DESCRIPTION:Yaoguang Zhai and Nathaniel Danandeh (University of California
 , San Diego); Zhenye Tan (University of California, San Diego; Tongji Univ
 ersity); Sicun Gao and Francesco Paesani (University of California, San Di
 ego); and Andreas W. Goetz (San Diego Supercomputer Center)\n\nMachine lea
 rning models can be used to develop highly accurate and efficient many-bod
 y potentials for molecular simulations based on the many-body expansion of
  the total energy.  A prominent example is the MB-pol water model that emp
 loys permutationally invariant polynomials (PIPs) to represent the 2-body 
 and 3-body short-range energy terms.\n\nWe have recently shown that the PI
 Ps can be replaced by Behler-Parinello neural networks (BP-NN).  We presen
 t OpenMP parallel implementations of both PIP and BP-NN models as well as 
 a CUDA implementation of the BP-NN model for GPUs.  The OpenMP implementat
 ions achieve linear speedup  with respect to the optimized single threaded
  code. The BP-NN GPU implementation outperforms the CPU implementation by 
 a factor of almost 8.  This opens the door for routine molecular dynamics 
 simulations with highly accurate many-body potentials on a diverse set of 
 hardware.\n\nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pa
 ss\n\n
END:VEVENT
END:VCALENDAR