BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234541Z
LOCATION:B306
DTSTART;TZID=America/New_York:20241120T160000
DTEND;TZID=America/New_York:20241120T161500
UID:submissions.supercomputing.org_SC24_sess542_post145@linklings.com
SUMMARY:Persistent and Partitioned MPI for Stencil Communication
DESCRIPTION:Gerald Collom and Amanda Bienz (University of New Mexico)\n\nM
 any parallel applications rely on iterative stencil operations, whose perf
 ormance is dominated by communication costs at large scales. Several MPI o
 ptimizations, such as persistent and partitioned communication, reduce ove
 rheads and improve communication efficiency through amortized setup costs 
 and reduced synchronization of threaded sends. This paper presents the per
 formance of stencil communication in the Comb benchmarking suite when usin
 g non-blocking, persistent, and partitioned communication routines. The im
 pact of each optimization is analyzed at various scales. Further, the pape
 r presents an analysis of the impact of process count, thread count, and m
 essage size on partitioned communication routines. Measured timings show t
 hat persistent MPI communication can provide a speedup of up to 37% over t
 he baseline MPI communication, and partitioned MPI communication can provi
 de a speedup of up to 68%.\n\nRegistration Category: Tech Program Reg Pass
 \n\nSession Chair: Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR