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:20211207T054809Z
LOCATION:230-231-232
DTSTART;TZID=America/Chicago:20211117T163000
DTEND;TZID=America/Chicago:20211117T170000
UID:submissions.supercomputing.org_SC21_sess160_pap527@linklings.com
SUMMARY:cuTS: Scaling Subgraph Isomorphism on Distributed Multi-GPU System
 s Using Trie Based Data Structure
DESCRIPTION:Paper\n\ncuTS: Scaling Subgraph Isomorphism on Distributed Mul
 ti-GPU Systems Using Trie Based Data Structure\n\nXiang, Khan, Serra, Hala
 ppanavar, Sukumaran-Rajam\n\nSubgraph isomorphism is a pattern-matching al
 gorithm widely used in many domains such as chem-informatics, bioinformati
 cs, databases, and social network analysis. It is computationally expensiv
 e and is a proven NP-hard problem. The massive parallelism in GPUs is well
  suited for solving subgraph isomorphism. However, current GPU implementat
 ions are far from the achievable performance. Moreover, the enormous memor
 y requirement of current approaches limits the problem size that can be ha
 ndled. This work analyzes the fundamental challenges associated with proce
 ssing subgraph isomorphism on GPUs and develops an efficient GPU implement
 ation. We also develop a GPU-friendly trie-based data structure to drastic
 ally reduce the intermediate storage space requirement, enabling large ben
 chmarks to be processed. We also develop the first distributed sub-graph i
 somorphism algorithm for GPUs. Our experimental evaluation demonstrates th
 e efficacy of our approach by comparing the execution time and number of c
 ases that can be handled against the state-of-the-art GPU implementations.
 \n\nTag: Reproducibility Badge, Algorithms\n\nRegistration Category: Tech 
 Program Reg Pass\n\nAward Finalist: Best Paper Finalist, Best Student Pape
 r Finalists\n\nReproducibility Badges: Artifact Available, Artifact Functi
 onal, Results Reproduced
END:VEVENT
END:VCALENDAR