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:20181221T160728Z
LOCATION:D172
DTSTART;TZID=America/Chicago:20181112T121000
DTEND;TZID=America/Chicago:20181112T123500
UID:submissions.supercomputing.org_SC18_sess168_ws_ia121@linklings.com
SUMMARY:Scale-Free Graph Processing on a NUMA Machine
DESCRIPTION:Workshop\nArchitectures, Data Analytics, Graph Algorithms, Wor
 kshop Reg Pass\n\nScale-Free Graph Processing on a NUMA Machine\n\nAasawat
 , Reza, Ripeanu\n\nModern shared-memory systems embrace the NUMA architect
 ure which has proven to be more scalable than the SMP architecture. In man
 y ways, a NUMA system resembles a shared-nothing distributed system: physi
 cally distinct processing units and memory regions. Memory accesses to rem
 ote NUMA domains are more expensive than local accesses. This poses the op
 portunity to transfer the know-how and design of distributed graph process
 ing to develop shared-memory graph processing solutions optimized for NUMA
  systems. To this end, we explore if a distributed-memory like middleware 
 that makes graph partitioning and communication between partitions explici
 t, can improve the performance on a NUMA system. We design and implement a
  NUMA aware graph processing framework that embraces design philosophies o
 f distributed graph processing system: in particular explicit partitioning
  and inter-partition communication, and at the same time exploits optimiza
 tion opportunities specific to single-node systems. We demonstrate up to 1
 3.9x speedup over a state-of-the-art NUMA-aware framework, Polymer and up 
 to 3.7x scalability on a four-socket NUMA machine using graphs with tens o
 f billions of edges.
URL:https://sc18.supercomputing.org/presentation/?id=ws_ia121&sess=sess168
END:VEVENT
END:VCALENDAR