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:205-207
DTSTART;TZID=America/Denver:20231117T083000
DTEND;TZID=America/Denver:20231117T100000
UID:submissions.supercomputing.org_SC23_sess198_pan130@linklings.com
SUMMARY:Understanding the Performance, Reproducibility, Validation, Portab
 ility, and Sustainability of Coupled HPC Simulation and Deep Learning Calc
 ulations
DESCRIPTION:Ada Sedova (Oak Ridge National Laboratory (ORNL)), Andrew Shao
  (Hewlett Packard Enterprise (HPE)), Daniel Reed (University of Utah), Kar
 thik Kashinath (NVIDIA Corporation), Wesley Brewer (Oak Ridge National Lab
 oratory (ORNL)), and Daniel Martinez-Gonzalez (NASA Ames Research Center)\
 n\nRecent advances in deep learning (DL) for scientific computing have pav
 ed the way for a new type of integrated programming environment. This envi
 ronment must support the seamless integration of simulation applications w
 ith deep learning frameworks using methods such as in-memory coupling and 
 inference serving. Especially for HPC, this environment brings a slew of c
 hallenges, forcing developers to revisit decades of solved problems in sci
 entific computing: kernel optimization, verification/validation strategies
 , building/porting practices. Interfacing HPC simulation codes with DL fra
 meworks from industry—whose philosophies and strategies may differ from th
 ose within HPC—brings critical questions about how these two communities c
 an work together to develop sustainable, integrated programming environmen
 ts that are trustworthy, vetted, and portable, and where HPC communities c
 an express requirements for scientific software and can track ownership. D
 iscussions are needed about how to overcome these challenges: here, paneli
 sts from academia, national laboratories and industry will start a convers
 ation, sharing perspectives and experiences.\n\nTag: Artificial Intelligen
 ce/Machine Learning, Applications, Reproducibility\n\nRegistration Categor
 y: Tech Program Reg Pass, Workshop Reg Pass, Tutorial Reg Pass, Exhibits R
 eg Pass\n\nSession Chair: Ada Sedova (Oak Ridge National Laboratory (ORNL)
 )\n\n
END:VEVENT
END:VCALENDAR