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:20181221T160731Z
LOCATION:C140/142
DTSTART;TZID=America/Chicago:20181115T113000
DTEND;TZID=America/Chicago:20181115T120000
UID:submissions.supercomputing.org_SC18_sess208_pap167@linklings.com
SUMMARY:faimGraph: High Performance Management of Fully-Dynamic Graphs Und
 er Tight Memory Constraints on the GPU
DESCRIPTION:Paper\nApplications, Graph Algorithms, Security, Tech Program 
 Reg Pass\n\nfaimGraph: High Performance Management of Fully-Dynamic Graphs
  Under Tight Memory Constraints on the GPU\n\nWinter, Mlakar, Zayer, Seide
 l, Steinberger\n\nIn this paper, we present a fully-dynamic graph data str
 ucture for the Graphics Processing Unit (GPU). It delivers high update rat
 es while keeping a low memory footprint using autonomous memory management
  directly on the GPU. The data structure is fully-dynamic, allowing not on
 ly for edge but also vertex updates. Performing the memory management on t
 he GPU allows for fast initialization times and efficient update procedure
 s without additional intervention or reallocation procedures from the host
 .  faimGraph is the first GPU graph framework that fully reclaims unused m
 emory, permitting long time application with highly changing graph structu
 res. Performance evaluations show that our approach outperforms that previ
 ous state-of-the-art in for all types of graph updates. Furthermore, evalu
 ate algorithmic performance using a PageRank and a Static Triangle Countin
 g (STC) implementation, demonstrating the suitability of the framework eve
 n for memory access intensive algorithms.
URL:https://sc18.supercomputing.org/presentation/?id=pap167&sess=sess208
END:VEVENT
END:VCALENDAR

