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:20260522T150129Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20181113T133000
DTEND;TZID=America/Chicago:20181113T150000
UID:submissions.supercomputing.org_SC18_sess178@linklings.com
SUMMARY:Large-Scale Algorithms
DESCRIPTION:TriCore: Parallel Triangle Counting on GPUs\n\nTriangle counti
 ng algorithm enumerates the triangles in a graph by identifying the common
  neighbors between two vertices of every edge. In this work, we present Tr
 iCore, a new GPU-based high-performance and scalable triangle counting sys
 tem that consists of three main techniques. First, we design a ...\n\n\nYa
 ng Hu (George Washington University); Hang Liu (University of Massachusett
 s, Lowell); and H. Howie Huang (George Washington University)\n-----------
 ----------\nDistributed-Memory Hierarchical Compression of Dense SPD Matri
 ces\n\nWe present a distributed-memory algorithm for the hierarchical comp
 ression of SPD matrices. Our method is based on GOFMM, an algorithm that a
 ppeared in doi:10.1145/3126908.3126921.\n\nFor many SPD matrices, GOFMM en
 ables compression and approximate matrix-vector multiplication in NlogN ti
 me---as oppos...\n\n\nChenhan D. Yu (University of Texas), Severin Reiz (T
 echnical University Munich), and George Biros (University of Texas)\n-----
 ----------------\nLarge-Scale Hierarchical K-Means for Heterogeneous Many-
 Core Supercomputers\n\nThis paper presents a novel design and implementati
 on of k-means clustering algorithm targeting the Sunway TaihuLight superco
 mputer. We introduce a multi-level parallel partition approach that not on
 ly partitions by dataflow and centroid, but also by dimension. Our multi-l
 evel (nkd) approach unlocks...\n\n\nLiandeng Li (Tsinghua University; Nati
 onal Supercomputing Center, Wuxi); Teng Yu (University of St Andrews); Wen
 lai Zhao and Haohuan Fu (Tsinghua University; National Supercomputing Cent
 er, Wuxi); Chenyu Wang (University of St Andrews; National Supercomputing 
 Center, Wuxi); Li Tan (Beijing Technology and Business University); Guangw
 en Yang (Tsinghua University; National Supercomputing Center, Wuxi); and J
 ohn Thomson (University of St Andrews)\n\nTag: Algorithms, Architectures, 
 Data Analytics, Deep Learning, Networks, Scientific Computing, Visualizati
 on\n\nRegistration Category: Tech Program Reg Pass\n\nFinalist: BSP Finali
 st\n\nSession Chair: Tom Peterka (Argonne National Laboratory (ANL))
END:VEVENT
END:VCALENDAR