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 3
DTSTART;TZID=Europe/Stockholm:20240604T173000
DTEND;TZID=Europe/Stockholm:20240604T180000
UID:submissions.pasc-conference.org_PASC24_sess139_msa256@linklings.com
SUMMARY:Scaling Coupled Simulation and AI Workflows on Aurora with Dragon
DESCRIPTION:Minisymposium\n\nChristine Simpson, Riccardo Balin, Archit Vas
 an, and Sam Foreman (Argonne National Laboratory); Peter Mendygral, Colin 
 Wahl, and Nick Hill (HPE); and Venkatram Vishwanath (Argonne National Labo
 ratory)\n\nThe advent of exascale computing has enabled computational work
 flows coupling simulation and AI of unprecedented scale and complexity. Ho
 wever, the scale of these workflows presents challenges for the efficient 
 distribution of data between the various compute tasks spread across large
  node counts. In this talk, we present the Dragon open-source library as a
  tool for designing and executing data-intensive scientific workflows on m
 odern HPC systems. In particular, Dragon’s sharded memory model allows com
 pute tasks to access data stored in memory regardless of node locality by 
 means of automated RDMA transfers, which are made available to the user th
 rough high-level data transfer APIs written in C, C++, and Python.  This e
 nables the transfer of interdependent data across different components of 
 the workflow, avoiding costly I/O to the filesystem or deploying a databas
 e. We demonstrate the use of Dragon and its performance on the Aurora supe
 rcomputer at the Argonne Leadership Computing Facility with a workflow des
 igned to identify new candidates for cancer drugs by combining simulation 
 with ML training and inference to accelerate high-throughput screening of 
 22 billion molecular compounds.\n\nDomain: Chemistry and Materials, Climat
 e, Weather, and Earth Sciences, Engineering, Computational Methods and App
 lied Mathematics\n\nSession Chair: Alessandro Rigazzi (HPE)
END:VEVENT
END:VCALENDAR