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:20190719T085754Z
LOCATION:HG D 1.1
DTSTART;TZID=Europe/Stockholm:20190614T103000
DTEND;TZID=Europe/Stockholm:20190614T123000
UID:submissions.pasc-conference.org_PASC19_sess119@linklings.com
SUMMARY:MS43 - Computational Performance Evaluation for Hardware and Softw
 are Alternatives to Increase the HPC Efficiency of Earth System Models
DESCRIPTION:Minisymposium\nClimate and Weather\n\nReduced Numerical Precis
 ion in Atmosphere Models and Computational Performance Evaluation\n\nDuebe
 n, Acosta\n\nIn atmosphere models values of relevant physical parameters a
 re often uncertain by more than 100% and weather forecast skill is decreas
 ing significantly after a couple of days. Still, numerical operations are 
 typically calculated with 15 decimal digits of numerical precision for rea
 l numbers. If we ...\n\n---------------------\nImproving Ocean Model Compu
 tational Performance by using Mixed-Precision Approaches\n\nTinto, Acosta,
  Castrillo, Serradell, Doblas-Reyes\n\nMixed-precision approaches can prov
 ide substantial speed-ups for both computing- and memory-bound codes requi
 ring little effort. Most scientific codes have overengineered the numerica
 l precision leading to a situation where models are using more resources t
 han required without having a clue about wh...\n\n---------------------\nN
 ew Methodologies for Computational Performance Evaluation of Climate and W
 eather Models\n\nAcosta, Castrillo, Paronuzzi, Serradell, Tinto...\n\nHPC 
 has evolved in the last years from a technology crucial to the academic re
 search community to a point where it is acknowledged as a key piece of num
 erical modelling, highlighting different challenges which should be solved
 . However, these challenges cannot be met by mere extrapolation but requir
 ...\n\n---------------------\nEvaluating Commercial Distributed Computing 
 for Numerical Weather Prediction\n\nWhitcomb, Arevalo\n\nSince the first w
 eather forecast run on the ENIAC, numerical weather prediction has been a 
 flagship application of high-performance computing and has witnessed many 
 architectural changes to the platforms used for producing ever more sophis
 ticated forecasts. A significant shift under way is the rise ...\n
END:VEVENT
END:VCALENDAR