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 F 1
DTSTART;TZID=Europe/Stockholm:20190614T110000
DTEND;TZID=Europe/Stockholm:20190614T113000
UID:submissions.pasc-conference.org_PASC19_sess170_msa279@linklings.com
SUMMARY:ECMWF's IO and Storage Challenges in the Path to Exascale Numerica
 l Weather Prediction
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics\n\nECM
 WF's IO and Storage Challenges in the Path to Exascale Numerical Weather P
 rediction\n\nQuintino, Smart, Raoult\n\nStarting 2014, ECMWF has embarked 
 on a 10 year research programme on HPC Scalability, aiming to achieve Exas
 cale numerical weather prediction systems by 2025. ECMWF operational forec
 ast generates massive amounts of I/O in short bursts, accumulating to tens
  of TiB in hourly windows. From this output, millions of user-defined dail
 y products are generated and disseminated to member states and commercial 
 clients all over the world. These products are processed from the raw outp
 ut of the IFS model, within the time critical path and under strict delive
 ry schedule. Upcoming rise in resolution and growing popularity will incre
 ase both the size and number of these products. Based on expected model re
 solution upgrades, by 2020 we estimate the operational model will output o
 ver 100 TiB/day and need to archive over 400 TiB/day. Given that the I/O w
 orkload is already one of the strongest bottlenecks in ECMWF's workflow, t
 his is one of the main challenges to reach Exascale NWP. We present the la
 test ECMWF developments in model I/O, product generation and storage, and 
 how we are reworking our operational workflows to adapt to forthcoming new
  architectures and memory-storage hierarchies. In particular, we present r
 ecent developments in the integration of a domain-specific object store to
  ECMWF's operational pipeline.
END:VEVENT
END:VCALENDAR