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:20220812T074358Z
LOCATION:Osaka Room
DTSTART;TZID=Europe/Stockholm:20220628T163000
DTEND;TZID=Europe/Stockholm:20220628T183000
UID:submissions.pasc-conference.org_PASC22_sess160@linklings.com
SUMMARY:MS4A - Storage Systems at Extreme Scale for Data-Centric Workflows
DESCRIPTION:Minisymposium\n\nIn the past few years, applications in scient
 ific domains such as weather and forecast have evolved into complex data-c
 entric workflows. This evolution has resulted in a data deluge which has b
 een observed in large computing centers such as the National Energy Resear
 ch Scientific Computing Center (NERSC), where the volume of data stored in
 creased by a factor of 40 in the last ten years. However, the gap between 
 computing and I/O capabilities continues to grow: the ratio of I/O bandwid
 th to computing power has decreased by an order of magnitude over the last
  ten years for the top 3 supercomputers listed in the top500. Faced with t
 his critical situation, storage systems must adapt. In this minisymposium,
  we will examine the needs of scientific workflows in terms of massive dat
 a management through a concrete example. Then, we will explore the solutio
 ns proposed by the computer science research community, both from an infra
 structure and a execution software stack perspective. We will see how thes
 e lines of research can improve data orchestration in scientific workflows
  where storage is central, and identify which research topics remain to be
  further developed.\n\nExtreme-scale I/O and Storage Resources in Heteroge
 neous Modular Supercomputing Architectures\n\nNeuwirth\n\nEmerging from th
 e DEEP project series, the <em>Modular Supercomputing Architecture</em> (M
 SA) concept breaks with the traditional HPC system architecture approach (
 based on replicating many identical compute nodes, possibly integrating he
 terogeneous processing resources within each node) by integrat...\n\n-----
 ----------------\nData-Centric Workflows in Exascale Weather Forecasting -
  A Destination Earth Perspective\n\nQuintino, Sarmany, Smart, Hawkes, Dano
 varo...\n\nNumerical Weather Prediction (NWP) is a highly data intensive H
 PC application. ECMWF operational weather forecasts generates massive amou
 nts of I/O in short bursts, accumulating to tens of TiB in hourly forecast
  cycle windows. From this output, millions of user-defined daily products 
 are generated a...\n\n---------------------\nOak Ridge National Laboratory
  Storage Ecosystem\n\nLeverman\n\nOak Ridge National Laboratory's storage 
 ecosystem is in constant flux due to the changing requirements from users.
  The ORNL Leadership Computing Facility (OLCF) manages storage systems tha
 t are dynamically created for the duration of a job, storage systems suppo
 rting data with a 90-day lifetime, and...\n\n---------------------\nThere 
 is Life Beyond POSIX: Storage in both HPC and Data-Intensive Applications\
 n\nPerez\n\nHPC applications have widely used POSIX files as basis of thei
 r storage. However, POSIX has a number of limitations, e.g. limited flexib
 ility in handling complex data or performance limitations in certain non-g
 eneral purpose applications. <br /><br />On the other hand, the areas of H
 PC and Big Data ...\n\n\nDomain: Climate, Weather and Earth Sciences, Comp
 uter Science and Applied Mathematics
END:VEVENT
END:VCALENDAR