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:20260422T000713Z
LOCATION:401-402
DTSTART;TZID=America/Denver:20231114T103000
DTEND;TZID=America/Denver:20231114T110000
UID:submissions.supercomputing.org_SC23_sess155_pap286@linklings.com
SUMMARY:Efficient Maximal Biclique Enumeration on GPUs
DESCRIPTION:Zhe Pan, Shuibing He, and Xu Li (Zhejiang University); Xuechen
  Zhang (Washington State University, Vancouver); and Rui Wang and Gang Che
 n (Zhejiang University)\n\nMaximal biclique enumeration (MBE) in bipartite
  graphs is an important problem in data mining with many real-world applic
 ations. All existing solutions for MBE are designed for CPUs. Parallel MBE
  algorithms for GPUs are needed for MBE acceleration leveraging its many c
 omputing cores. However, enumerating maximal bicliques using GPUs has thre
 e main challenges including large memory requirement, thread divergence, a
 nd load imbalance. In this paper, we propose GMBE, the first highly-effici
 ent GPU solution for the MBE problem. To overcome the challenges, we desig
 n a stack-based iteration approach to reduce GPU memory usage, a pro-activ
 e pruning method using the vertex’s local neighborhood size to alleviate t
 hread divergence, and a load-aware task scheduling framework to achieve lo
 ad balance among threads within GPU warps and blocks. Our experimental res
 ults show that GMBE on an NVIDIA A100 GPU can achieve 70.6× speedup over t
 he state-of-the-art parallel MBE algorithm ParMBE on a 96-core CPU machine
 .\n\nTag: Accelerators, Algorithms, Graph Algorithms and Frameworks\n\nReg
 istration Category: Tech Program Reg Pass\n\nReproducibility Badges: Artif
 act Available, Artifact Functional, Results Reproduced\n\nSession Chair: M
 arco Minutoli (Advanced Micro Devices)\n\n
END:VEVENT
END:VCALENDAR