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:20260522T150110Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181114T083000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess323_post234@linklings.com
SUMMARY:Distributed Adaptive Radix Tree for Efficient Metadata Search on H
 PC Systems
DESCRIPTION:Wei Zhang (Texas Tech University), Houjun Tang and Suren Byna 
 (Lawrence Berkeley National Laboratory), and Yong Chen (Texas Tech Univers
 ity)\n\nAffix-based search allows users to retrieve data without the need 
 to remember all relevant information precisely. While building an inverted
  index to facilitate efficient affix-based search is a common practice for
  standalone databases and desktop file systems, they are often insufficien
 t for high-performance computing (HPC) systems due to the massive amount o
 f data and the distributed nature of the storage. In this poster, we prese
 nt Distributed Adaptive Radix Tree (DART) which enables scalable and effic
 ient affix-based search. DART maintains a balanced keyword distribution an
 d optimizes for excessive keyword requests dynamically at scale. Our evalu
 ation shows that compared with the “full string hashing” used by the commo
 nly adopted DHT approach, DART achieves up to 55x throughput speedup for p
 refix and suffix search, and has a comparable throughput for exact and inf
 ix search. Also, DART maintains balanced keyword distribution and alleviat
 es excessive query workload on popular keywords.\n\nRegistration Category:
  Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR