BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160009Z
LOCATION:Track 1
DTSTART;TZID=America/New_York:20201118T153000
DTEND;TZID=America/New_York:20201118T160000
UID:submissions.supercomputing.org_SC20_sess302_gb105@linklings.com
SUMMARY:Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to
  100 Million Atoms with Machine Learning
DESCRIPTION:ACM Gordon Bell Finalist, Awards Presentation\n\nPushing the L
 imit of Molecular Dynamics with Ab Initio Accuracy to 100 Million Atoms wi
 th Machine Learning\n\nJia, Wang, Chen, Lu, Lin...\n\nFor 35 years, ab ini
 tio molecular dynamics (AIMD) has been the method of choice for modeling c
 omplex atomistic phenomena from first principles. Most AIMD applications, 
 however, are limited by computational cost to systems with thousands of at
 oms at most. We report that a machine learning-based simulation protocol (
 Deep Potential Molecular Dynamics), while retaining ab initio accuracy, ca
 n simulate more than 1 nanosecond-long trajectory of over 100 million atom
 s per day, using a highly optimized code (GPU DeePMDkit) on the Summit sup
 ercomputer. Our code can efficiently scale up to the entire Summit superco
 mputer, attaining 91 PFLOPS in double precision (45.5% of the peak) and 16
 2/275 PFLOPS in mixed-single/half precision. The great accomplishment of t
 his work is that it opens the door to simulating unprecedented size and ti
 me scales with ab initio accuracy. It also poses new challenges to the nex
 t-generation supercomputer for a better integration of machine learning an
 d physical modeling.\n\nRegistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR