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:20260701T140000
DTEND;TZID=Europe/Stockholm:20260701T143000
UID:submissions.pasc-conference.org_PASC26_sess164_msa144@linklings.com
SUMMARY:Storage Systems and Programming Models for Computational Storage L
 andscapes
DESCRIPTION:Michael Kuhn (Otto von Guericke University Magdeburg)\n\nStora
 ge and I/O are increasingly important due to exponentially growing data vo
 lumes and more dynamic and diverse I/O loads. Traditionally, there has bee
 n a clear separation of computation and storage with the bulk of storage a
 nd I/O requirements being handled by centralized parallel file systems. Ad
 -hoc file systems have mitigated some storage and I/O problems, but introd
 uce additional complexity and require costly data staging between file sys
 tems. Moreover, traditional applications mix computation and I/O, which ma
 kes it hard to map different parts of applications onto different componen
 ts and devices.\n\nAddressing these challenges in a holistic manner requir
 es both storage systems that are more dynamic and modular than traditional
  file systems as well as new programming models for such I/O workloads. Th
 is talk will focus on these two aspects: First, it will sketch a modular s
 torage system architecture that can deal with distributing computational a
 nd I/O workloads across systems with computational storage. Second, it wil
 l address suitable programming models considering both application and dev
 ice requirements, focusing on how task-based programming models can be use
 d to leverage computational storage for different use cases.\n\nDomain: Co
 mputational Methods and Applied Mathematics\n\nSession Chairs: Jakob Luett
 gau (INRIA), Kira Duwe (CERN), and Michael Kuhn (Otto von Guericke Univers
 ity Magdeburg)\n\n
END:VEVENT
END:VCALENDAR
