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:20210527T134946Z
LOCATION:Digital
DTSTART;TZID=Europe/Stockholm:20200623T185000
DTEND;TZID=Europe/Stockholm:20200623T191500
UID:isc_hpc_ISC High Performance 2020_sess341_pap143@linklings.com
SUMMARY:Running a Pre-Exascale, Geographically Distributed, Multi-Cloud Sc
 ientific Simulation
DESCRIPTION:Research Paper\n\nRunning a Pre-Exascale, Geographically Distr
 ibuted, Multi-Cloud Scientific Simulation\n\nSfiligoi, Würthwein, Riedel, 
 Schultz\n\nAs we approach the Exascale era, it is important to verify that
  the existing frameworks and tools will still work at that scale. Moreover
 , public Cloud computing has been emerging as a viable solution for both p
 rototyping and urgent computing. Using the elasticity of the Cloud, we hav
 e thus put in place a pre-exascale HTCondor setup for running a scientific
  simulation in the Cloud, with the chosen application being IceCube’s phot
 on propagation simulation. I.e. this was not a purely demonstration run, b
 ut it was also used to produce valuable and much needed scientific results
  for the IceCube collaboration. In order to reach the desired scale, we ag
 gregated GPU resources across 8 GPU models from many geographic regions ac
 ross Amazon Web Services, Microsoft Azure, and the Google Cloud Platform. 
 Using this setup, we reached a peak of over 51k GPUs corresponding to almo
 st 380 PFLOP32s, for a total integrated compute of about 100k GPU hours. I
 n this paper we provide the description of the setup, the problems that we
 re discovered and overcome, as well as a short description of the actual s
 cience output of the exercise.\n\nTag: Pre-Recorded
URL:https://2020.isc-program.com/presentation/?id=pap143&sess=sess341
END:VEVENT
END:VCALENDAR

