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:20260522T150116Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20181113T163000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess218_pap484@linklings.com
SUMMARY:Topology-Aware Space-Shared Co-Analysis of Large-Scale Molecular D
 ynamics Simulations
DESCRIPTION:Preeti Malakar (Indian Institute of Technology Kanpur); Todd M
 unson, Christopher Knight, and Venkatram Vishwanath (Argonne National Labo
 ratory); and Michael E. Papka (Argonne National Laboratory, Northern Illin
 ois University)\n\nAnalysis of scientific simulation data can be concurren
 tly executed with simulation either in time- or space-shared mode. This mi
 tigates the I/O bottleneck.  However it results in either stalling the sim
 ulation for performing the analysis or transferring data for analysis. In 
 this paper, we improve the throughput of space-shared in situ analysis of 
 large-scale simulations by topology-aware mapping and optimal process deco
 mposition. We propose node interconnect topology-aware process placement f
 or simulation and analysis to reduce the data movement time. We also prese
 nt an integer linear program for optimal 3D decompositions of simulation a
 nd analysis processes. We demonstrate our approach using molecular dynamic
 s simulation on Mira, Cori and Theta supercomputers. Our mapping schemes, 
 combined with optimal 3D process decomposition and code optimizations resu
 lted in up to 30% lower execution times for space-shared in situ analysis 
 than the default approach. Our mappings also reduce MPI collective I/O tim
 es by 10-40%.\n\nTag: Data Analytics, Performance, Programming Systems, St
 orage, Tools, Visualization\n\nRegistration Category: Tech Program Reg Pas
 s\n\nSession Chair: John Linford (NVIDIA Corporation)\n\n
END:VEVENT
END:VCALENDAR
