BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG E 1.1
DTSTART;TZID=Europe/Stockholm:20240604T110000
DTEND;TZID=Europe/Stockholm:20240604T113000
UID:submissions.pasc-conference.org_PASC24_sess146_msa123@linklings.com
SUMMARY:HydraGNN: Scalable Machine Learning and Generative AI for Accelera
 ting Materials Design
DESCRIPTION:Minisymposium\n\nJong Youl Choi, Massimiliano Lupo Pasini, Pei
  Zhang, and Kshitij Mehta (Oak Ridge National Laboratory) and Jonghyun Bae
  and Khaled Ibrahim (Lawrence Berkeley National Laboratory)\n\nWe discuss 
 the challenges involved in developing large-scale training for generative 
 AI models aimed at material design. We employ HydraGNN, a scalable graph n
 eural network (GNN) framework, alongside DDStore, a distributed in-memory 
 data store, to facilitate large-scale data distribution across the superco
 mputing resources provided by the US Department of Energy (DOE). Our discu
 ssion includes insights into our implementation and the notable decrease i
 n I/O overhead within HPC environments. The effectiveness of HydraGNN and 
 DDStore is showcased through its application for molecular design, where a
  GNN model learns to predict the ultraviolet-visible spectrum based on a d
 ataset comprising over 10 million molecules. By enabling efficient trainin
 g scale-up to thousands of GPUs on the Summit and Perlmutter supercomputer
 s, DDStore has achieved a significant boost in DL training speed, recordin
 g up to a 6.15 times faster performance than our initial methods. We will 
 discuss the performance advancements on the new Frontier supercomputer at 
 the Oak Ridge National Laboratory (ORNL), highlighting the evolving landsc
 ape of supercomputing in AI research.\n\nDomain: Chemistry and Materials\n
 \nSession Chair: John Gounley (Oak Ridge National Laboratory)
END:VEVENT
END:VCALENDAR