BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181221T160906Z
LOCATION:C145
DTSTART;TZID=America/Chicago:20181114T150000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess468_spost106@linklings.com
SUMMARY:SimFS: A Simulation Data Virtualizing File System Interface
DESCRIPTION:ACM Student Research Competition, Poster\nStudent Program, Tec
 h Program Reg Pass, ACM Student Research Competition\n\nSimFS: A Simulatio
 n Data Virtualizing File System Interface\n\nDi Girolamo\n\nIn the big (si
 mulation) data era, simulations often produce petabytes of data to be stor
 ed in parallel filesystems or large-scale databases. This data is accessed
 , often by thousands of analysts and scientists, over the course of decade
 s. However, storing these volumes of data for long time periods of time is
  not cost effective and, in some cases, practically impossible. \n\nSimFS 
 transparently virtualizes the simulation output, relaxing the storage requ
 irements and re-simulating missing data on-demand. SimFS monitors the anal
 ysis access pattern in order to decide (1) which data to store and (2) app
 ly prefetching techniques to improve the analysis performance. SimFS enabl
 es a trade-off between on-disk solutions, where all the simulation data is
  stored on disk, and in-situ, where no data is stored and analyses are alw
 ays coupled with simulations.  Overall, by exploiting the growing computin
 g power and relaxing the storage capacity requirements, SimFS offers a via
 ble path towards exa-scale simulations.
URL:https://sc18.supercomputing.org/presentation/?id=spost106&sess=sess468
END:VEVENT
END:VCALENDAR