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:20190719T085745Z
LOCATION:HG D 1.1
DTSTART;TZID=Europe/Stockholm:20190614T120000
DTEND;TZID=Europe/Stockholm:20190614T123000
UID:submissions.pasc-conference.org_PASC19_sess119_msa299@linklings.com
SUMMARY:Evaluating Commercial Distributed Computing for Numerical Weather 
 Prediction
DESCRIPTION:Minisymposium\nClimate and Weather\n\nEvaluating Commercial Di
 stributed Computing for Numerical Weather Prediction\n\nWhitcomb, Arevalo\
 n\nSince the first weather forecast run on the ENIAC, numerical weather pr
 ediction has been a flagship application of high-performance computing and
  has witnessed many architectural changes to the platforms used for produc
 ing ever more sophisticated forecasts. A significant shift under way is th
 e rise of commercial entities offering a multitude of services aimed at au
 gmenting or even replacing traditional data centers. Migrating to a commer
 cial cloud computing approach from a traditional supercomputing center rep
 resents a balance of upsides and downsides that are application specific. 
 The U.S. Department of Defense has made cloud computing a priority and is 
 focused on effective cloud migration and cloud deployments of both existin
 g and new applications. To understand the opportunities and challenges to 
 the U.S. Naval meteorology and oceanography community, we have begun testi
 ng the computational performance of a global atmospheric forecast model on
  multiple vendor platforms. We will discuss observed performance and scala
 bility, lessons learned thus far, as well as plans for upcoming tests that
  we believe will further elucidate performance details to quantify the imp
 act on operations and research.
END:VEVENT
END:VCALENDAR