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:D165
DTSTART;TZID=America/Chicago:20181112T115000
DTEND;TZID=America/Chicago:20181112T121000
UID:submissions.supercomputing.org_SC18_sess161_ws_pmbss101@linklings.com
SUMMARY:miniVite: A Graph Analytics Benchmarking Tool for Massively Parall
 el Systems
DESCRIPTION:Workshop\nBenchmarks, Parallel Programming Languages, Librarie
 s, and Models, Performance, Simulation, Workshop Reg Pass\n\nminiVite: A G
 raph Analytics Benchmarking Tool for Massively Parallel Systems\n\nGhosh, 
 Halappanavar, Tumeo, Kalyanaraman, Gebremedhin\n\nBenchmarking of high per
 formance computing systems can help provide critical insights for efficien
 t design of computing systems and software applications. Although a large 
 number of tools for benchmarking exist, there is a lack of representative 
 benchmarks for the class of irregular computations as exemplified by graph
  analytics. We therefore propose miniVite as a representative graph analyt
 ics benchmark tool to test a variety of distributed-memory systems. Graph 
 clustering, popularly known as community detection, is a prototypical grap
 h operation used in numerous scientific computing and analytics applicatio
 ns. The goal of clustering is to partition a graph into clusters (or commu
 nities) such that each cluster consists of vertices that are densely conne
 cted within the cluster and sparsely connected to the rest of the graph. M
 odularity optimization is a popular technique for identifying clusters in 
 a graph. Efficient parallelization of modularity optimization-based algori
 thms is challenging. One successful approach was conceived in Vite, a dist
 ributed-memory implementation of the Louvain method that incorporates seve
 ral heuristics. We develop miniVite as a representative but simplified var
 iant of Vite, to serve as a prototypical graph analytics benchmarking tool
 . Similar to many graph algorithms, miniVite is characterized by irregular
  communication patterns, high communication to computation ratios, and loa
 d imbalances among participating processes, thus making it a representativ
 e benchmarking tool. \n\nUnlike some graph-based methods such as breadth-f
 irst search and betweenness centrality, miniVite represents highly complex
  computational patterns stressing a variety of system features. This can i
 n turn help provide crucial insight for codesign of future computing syste
 ms. We believe that miniVite will serve as a platform for benchmarking sys
 tems and design communication primitives that will be applicable to a broa
 d set of irregular computing applications as well as a platform for the de
 sign of efficient graph algorithms.
URL:https://sc18.supercomputing.org/presentation/?id=ws_pmbss101&sess=sess
 161
END:VEVENT
END:VCALENDAR