BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000712Z
LOCATION:403-404
DTSTART;TZID=America/Denver:20231114T143000
DTEND;TZID=America/Denver:20231114T150000
UID:submissions.supercomputing.org_SC23_sess165_pap324@linklings.com
SUMMARY:MBFGraph: An SSD-Based External Graph System for Evolving Graphs
DESCRIPTION:Chun-Yi Liu (Micron Technology Inc), Wonil Choi (Hanyang Unive
 rsity), and Soheil Khadirsharbiyani and Mahmut Kandemir (Pennsylvania Stat
 e University)\n\nThe challenge of executing extensive graph analyses in-me
 mory intensifies with growing graph sizes. This has given rise to disk-bas
 ed external graph analytics systems that prioritize cost-effective HDDs/SS
 Ds over pricier memory solutions. In response to this issue, our paper int
 roduces and assesses the MBFGraph external graph system. This system lever
 ages millions of Bloom filters within 1KB or 2KB graph data blocks to dimi
 nish graph analysis execution delays. Through our innovative MBF-query and
  MBF-construct algorithms, MBFGraph utilizes these Bloom filters as approx
 imate indices, enabling the reading of only pertinent sections of dynamic 
 graph data, thereby facilitating scalable analytics. Our tests revealed th
 at, on a 475GB graph, MBFGraph cut down the execution duration of BFS and 
 Pagerank by 24% and 60% respectively, using a mere 4GB memory. This is in 
 comparison to a sequential, tailored-for-workload, disk-based external gra
 ph analytics system.\n\nTag: Cloud Computing, Data Analysis, Visualization
 , and Storage, Graph Algorithms and Frameworks\n\nRegistration Category: T
 ech Program Reg Pass\n\nAward Finalist: Best Paper Finalist\n\nReproducibi
 lity Badges: Artifact Available, Artifact Functional, Results Reproduced\n
 \nSession Chair: Kasimir Gabert (Sandia National Laboratories)\n\n
END:VEVENT
END:VCALENDAR
