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:20211207T054802Z
LOCATION:230-231-232
DTSTART;TZID=America/Chicago:20211116T163000
DTEND;TZID=America/Chicago:20211116T170000
UID:submissions.supercomputing.org_SC21_sess175_pap131@linklings.com
SUMMARY:Dr. Top-k: Delegate-Centric Top-k Computation on GPUs
DESCRIPTION:Paper\n\nDr. Top-k: Delegate-Centric Top-k Computation on GPUs
 \n\nGaihre, Zheng, Weitze, Li, Song...\n\nRecent top-k computation efforts
  explore the possibility of revising various sorting algorithms to answer 
 top-k queries on GPUs. These endeavors, unfortunately, perform significant
 ly more work than needed. This paper introduces Dr. Top-k, a Delegate-cent
 ric top-k system on GPUs that can reduce the top-k workloads significantly
 . Particularly, it contains three major contributions: First, we introduce
  a comprehensive design of the delegate-centric concept, including maximum
  delegate, delegate-based filtering, and β delegate mechanisms to hel
 p reduce the workload for top-k up to more than 99%. Second, due to the di
 fficulty and importance of deriving a proper subrange size, we perform a r
 igorous theoretical analysis, coupled with thorough experimental validatio
 ns to identify the desirable subrange size. Third, we introduce four key s
 ystem optimizations to enable fast multi-GPU top-k computation. Taken toge
 ther, this work constantly outperforms the state-of-the-art.\n\nTag: Repro
 ducibility Badge, Data Analytics, Machine Learning and Artificial Intellig
 ence\n\nRegistration Category: Tech Program Reg Pass\n\nReproducibility Ba
 dges: Artifact Available, Artifact Functional
END:VEVENT
END:VCALENDAR