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:20181221T160729Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20181113T153000
DTEND;TZID=America/Chicago:20181113T160000
UID:submissions.supercomputing.org_SC18_sess218_pap335@linklings.com
SUMMARY:Many-Core Graph Workload Analysis
DESCRIPTION:Paper\nData Analytics, Performance, Programming Systems, Stora
 ge, Tools, Visualization, Tech Program Reg Pass\n\nMany-Core Graph Workloa
 d Analysis\n\nEyerman, Heirman, Du Bois, Fryman, Hur\n\nGraph applications
  have specific characteristics that are not common in other application do
 mains. In this paper, we analyze multiple graph applications on current mu
 lti- and many-core processors and provide conclusions and recommendations 
 for future designs. We provide new insights on executing graph application
 s on many-core processors.\n\nOur main novel observations are (i) some mem
 ory streams do show locality, while others show no locality, (ii) thread i
 mbalance becomes a major problem with many threads, and (iii) many threads
  are required to saturate high-bandwidth memories. We recommend a selectiv
 e memory access policy, where accesses with locality are cached and prefet
 ched, while accesses without locality can remain uncached to save cache ca
 pacity. Additionally, more threads are needed, but they are not used effic
 iently due to thread imbalance. Our recommendation is to revise the graph 
 analysis algorithms to provide more parallelism, and to provide a few high
 -performance cores that speedup sections with low parallelism.
URL:https://sc18.supercomputing.org/presentation/?id=pap335&sess=sess218
END:VEVENT
END:VCALENDAR