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:20260422T000712Z
LOCATION:501-502
DTSTART;TZID=America/Denver:20231112T103000
DTEND;TZID=America/Denver:20231112T104500
UID:submissions.supercomputing.org_SC23_sess416_ws_hppss103@linklings.com
SUMMARY:Demonstration of Portable Performance of Scientific Machine Learni
 ng on High Performance Computing Systems
DESCRIPTION:Khalid Hossain, Riccardo Balin, Corey Adams, Thomas Uram, Kaly
 an Kumaran, and Venkatram Vishwanath (Argonne National Laboratory (ANL)) a
 nd Tanima Dey, Subrata Goswami, Janghaeng Lee, Rebecca Ramer, and Koichi Y
 amada (Intel Corporation)\n\nWith the largest datasets to date and a diver
 se set of discoveries to be made, the current generation of scientific ana
 lyses are well poised to utilize artificial intelligence (AI) and machine 
 learning (ML) on high performance computing (HPC) resources.  Like never b
 efore, these workflows can be written in one portable language, Python, wh
 ich thanks to highly-optimized ML libraries achieves excellent cross-platf
 orm performance with little to no intervention by the user.  In this demon
 stration, we explore the performance of several scientific AI/ML applicati
 ons across leading HPC resources and highlight best practices for portable
  performance.\n\nTag: Applications, Distributed Computing, Large Scale Sys
 tems, Programming Frameworks and System Software, Runtime Systems\n\nRegis
 tration Category: Workshop Reg Pass\n\nSession Chairs: Sam Foreman (Argonn
 e National Laboratory (ANL)); Daniel Margala (Lawrence Berkeley National L
 aboratory (LBNL)); Pete Mendygral (Hewlett Packard Enterprise (HPE)); Laur
 ie A. Stephey (Lawrence Berkeley National Laboratory (LBNL), National Ener
 gy Research Scientific Computing Center (NERSC)); and Rollin Thomas (Lawre
 nce Berkeley National Laboratory (LBNL), National Energy Research Scientif
 ic Computing Center (NERSC))\n\n
END:VEVENT
END:VCALENDAR