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:20181221T160729Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20181113T113000
DTEND;TZID=America/Chicago:20181113T120000
UID:submissions.supercomputing.org_SC18_sess179_pap450@linklings.com
SUMMARY:Scaling Embedded In Situ Indexing with DeltaFS
DESCRIPTION:Paper\nClouds and Distributed Computing, File Systems, I/O, St
 orage, Tech Program Reg Pass\n\nScaling Embedded In Situ Indexing with Del
 taFS\n\nZheng, Cranor, Guo, Ganger, Amvrosiadis...\n\nAnalysis of large-sc
 ale simulation output is a core element of scientific inquiry, but analysi
 s queries may experience significant I/O overhead when the data is not str
 uctured for efficient retrieval. While in-situ processing allows for impro
 ved time-to-insight for many applications, scaling in-situ frameworks to h
 undreds of thousands of cores can be difficult in practice. The DeltaFS in
 -situ indexing is a new approach for in-situ processing of massive amounts
  of data to achieve efficient point and small-range queries. This paper de
 scribes the challenges and lessons learned when scaling this in-situ proce
 ssing function to hundreds of thousands of cores. We propose techniques fo
 r scalable all-to-all communication that is memory and bandwidth efficient
 , concurrent indexing, and specialized LSM-Tree formats. Combining these t
 echniques allows DeltaFS to control the cost of in-situ processing while m
 aintaining 3 orders of magnitude query speedup when scaling alongside the 
 popular VPIC particle-in-cell code to 131,072 cores.
URL:https://sc18.supercomputing.org/presentation/?id=pap450&sess=sess179
END:VEVENT
END:VCALENDAR