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:20240116T191700Z
LOCATION:403-404
DTSTART;TZID=America/Denver:20231116T160000
DTEND;TZID=America/Denver:20231116T163000
UID:submissions.supercomputing.org_SC23_sess163_pap178@linklings.com
SUMMARY:Choosing the Best Parallelization and Implementation Styles for Gr
 aph Analytics Codes: Lessons Learned from 1106 Programs
DESCRIPTION:Paper\n\nYiqian Liu, Noushin Azami, Avery VanAusdal, and Marti
 n Burtscher (Texas State University)\n\nGraph analytics has become a major
  workload in recent years. The underlying core algorithms tend to be irreg
 ular and data dependent, making them challenging to parallelize. Yet, thes
 e algorithms can be implemented and parallelized in many ways for CPUs and
  even more ways for GPUs. We took 6 key graph algorithms and created hundr
 eds of parallel CUDA, OpenMP, and parallel C++ versions of each of them, m
 ost of which have never been described or studied. To determine which para
 llelization and implementation styles work well and under what circumstanc
 es, we evaluated the resulting 1106 programs on 2 GPUs and 2 CPUs using 5 
 input graphs. Our results show which styles and combinations thereof work 
 well and which ones should be avoided. We found that choosing the wrong im
 plementation style can yield over a 10x performance loss on average. The w
 orst combinations of styles can cost 6 orders of magnitude in performance.
 \n\nTag: Architecture and Networks, Data Movement and Memory, Graph Algori
 thms and Frameworks, Performance Measurement, Modeling, and Tools, Program
 ming Frameworks and System Software\n\nRegistration Category: Tech Program
  Reg Pass\n\nReproducibility Badges: Artifact Available, Artifact Function
 al, Results Reproduced\n\nSession Chair: Mahantesh Halappanavar (Pacific N
 orthwest National Laboratory (PNNL))
END:VEVENT
END:VCALENDAR