BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000711Z
LOCATION:501-502
DTSTART;TZID=America/Denver:20231113T142000
DTEND;TZID=America/Denver:20231113T144000
UID:submissions.supercomputing.org_SC23_sess440_ws_ai4s119@linklings.com
SUMMARY:Enabling Performant Thermal Conductivity Modeling with DeePMD and 
 LAMMPS on CPUs
DESCRIPTION:Nariman Piroozan and Nalini Kumar (Intel Corporation)\n\nThe a
 bility to retain DFT-level accuracy and reduce the high computational cost
 s has been made possible using Deep Potential models which allow accurate 
 prediction of interatomic force and energy distributions, when trained on 
 DFT data. DeePMD-kit is a Python/C++ package which implements such a model
 . In this paper, we extend DeePMD to accurately predict the thermal conduc
 tivity for crystalline Au and Ag systems of up to 2 million atoms. We demo
 nstrate that both DeePMD training and DeePMD inference with LAMMPS can be 
 run efficiently on CPU-based systems. On a single node of 4th generation I
 ntel® Xeon® Scalable 9480 processors, we can train the model in less than 
 5 minutes.  Using this trained model with LAMMPS on 128 dual-socket nodes 
 with Intel® Xeon® Scalable 8480+ processors, we can accurately determine t
 he thermal conductivity of crystalline Au and Ag systems, within 5% of exp
 erimental results, in under one hour.\n\nTag: Artificial Intelligence/Mach
 ine Learning\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs
 : Murali Emani (Argonne National Laboratory (ANL)); Gokcen Kestor (Barcelo
 na Supercomputing Center (BSC); University of California, Merced); and Don
 g Li (University of California, Merced)\n\n
END:VEVENT
END:VCALENDAR