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:20260701T160000
UID:submissions.pasc-conference.org_PASC26_sess164@linklings.com
SUMMARY:MS5G - Computational Storage for Scientific Computing
DESCRIPTION:The exponential growth of data handled by HPC systems is drive
 n by growing simulation fidelity and an explosion of affordable, high-reso
 lution sensing devices. The rise of machine learning applications and othe
 r large-scale data analysis tasks imposes workload patterns on existing st
 orage solutions that often lead to large, avoidable data copies and transf
 ers, as well as contention near storage devices and in the network. This c
 reates challenges for the reproducibility of science and thus limits trust
  in science. Computational storage is a promising solution to lower barrie
 rs to public data access and reduce the time and cost for many workloads t
 hat require search across or aggregation of large volumes of data. The ses
 sion will feature four speakers from academia, government labs, and indust
 ry to give their perspectives on the challenges and opportunities of compu
 tational storage for scientific computing and how the technology may help 
 to increase trust in science despite the data deluge.\n\nOpportunities for
  Computational Storage in Scientific Computing\n\nThis talk will give an o
 verview of computational storage as a promising technology both to lower b
 arriers to public data access while also reducing the time and cost for ma
 ny existing workloads that require search across or aggregation of large v
 olumes of data. The talk will give an overview of diff...\n\n\nJakob Luett
 gau (INRIA)\n---------------------\nStorage Systems and Programming Models
  for Computational Storage Landscapes\n\nStorage and I/O are increasingly 
 important due to exponentially growing data volumes and more dynamic and d
 iverse I/O loads. Traditionally, there has been a clear separation of comp
 utation and storage with the bulk of storage and I/O requirements being ha
 ndled by centralized parallel file systems. A...\n\n\nMichael Kuhn (Otto v
 on Guericke University Magdeburg)\n---------------------\nIn-situ Data Ana
 lysis meets Computational Storage Devices\n\nSimulations from domains such
  as climate science produce increasing amounts of data as we approach Exas
 cale. The current workflow for generating knowledge from the data relies o
 n post-mortem analysis, which requires storing the raw data. The amount of
  storage space needed to facilitate this analysis...\n\n\nNiclas Schroeter
  (DKRZ, Otto-von-Guericke-Universitat Magdeburg)\n---------------------\nP
 ower Efficiency as seen from the storage perspective\n\nWith computational
  resources increasingly commoditized, performance optimization now priorit
 izes power efficiency. Effective energy optimization, however, necessitate
 s preliminary empirical observations. If power monitoring is well establis
 hed for compute nodes, storage servers tend to be overlooked...\n\n\nJean-
 Thomas Acquaviva (DDN)\n\nDomain: Computational Methods and Applied Mathem
 atics\n\nSession Chairs: Jakob Luettgau (INRIA), Kira Duwe (CERN), and Mic
 hael Kuhn (Otto von Guericke University Magdeburg)
END:VEVENT
END:VCALENDAR