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:20260421T090513Z
LOCATION:Bldg. 8 - Room B 101
DTSTART;TZID=Europe/Stockholm:20260701T150000
DTEND;TZID=Europe/Stockholm:20260701T153000
UID:submissions.pasc-conference.org_PASC26_sess164_msa143@linklings.com
SUMMARY:In-situ Data Analysis meets Computational Storage Devices
DESCRIPTION:Niclas Schroeter (DKRZ, Otto-von-Guericke-Universitat Magdebur
 g)\n\nSimulations from domains such as climate science produce increasing 
 amounts of data as we approach Exascale. The current workflow for generati
 ng knowledge from the data relies on post-mortem analysis, which requires 
 storing the raw data. The amount of storage space needed to facilitate thi
 s analysis workflow will soon exceed the capabilities of even the largest 
 computing centers. Many scientists have advocated for in-situ data analysi
 s to circumvent the need to store the raw data, while also decreasing the 
 time to insight. This is achieved by conducting the data analysis concurre
 ntly to the simulation, immediately producing the analysis results without
  retaining the raw data. This presentation will highlight an in-situ data 
 analysis framework leveraging a concept called Active Storage, which shift
 s the computation for the analysis onto the hardware of the file system it
 self, thus reducing the amount of data movement, while also solving the is
 sue of underutilization for file system hardware. This framework also serv
 es as a suitable vehicle to test different computational storage devices, 
 evaluate their interfaces and explore how they can be used for HPC data an
 alysis workloads, ideally in a transparent manner.\n\nDomain: Computationa
 l Methods and Applied Mathematics\n\nSession Chairs: Jakob Luettgau (INRIA
 ), Kira Duwe (CERN), and Michael Kuhn (Otto von Guericke University Magdeb
 urg)\n\n
END:VEVENT
END:VCALENDAR