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:20230124T171521Z
LOCATION:C146
DTSTART;TZID=America/Chicago:20221113T114000
DTEND;TZID=America/Chicago:20221113T120500
UID:submissions.supercomputing.org_SC22_sess424_ws_scalah105@linklings.com
SUMMARY:MARs: Memory Access Rearrangements in Open MPI
DESCRIPTION:Workshop\n\nMARs: Memory Access Rearrangements in Open MPI\n\n
 Li, Schuchart, Bosilca\n\nThe datatype engine in Message Passing Interface
  (MPI) libraries supports the communication layer by handling the transfer
  of non-contiguous datatypes. Basic datatypes (integer, float, etc.) serve
  as building blocks for more complex, and potentially non-contiguous, deri
 ved datatypes. In this context, the datatype engine facilitates the descri
 ption of complex datatypes and provides an efficient and portable interfac
 e between complex types and the network communication layer. In this paper
 , we focus on the Open MPI datatype engine with its compact type represent
 ations and pipeline techniques used to hide communication latency. We iden
 tified cases where the current datatype representation is sub-optimal and 
 provide an alternative based on range descriptions and Memory Access Rearr
 angements (MARs) for more efficient pack/unpack operations. As a result, w
 e obtain a performance improvement between 1.2x and 3.2x compared to the c
 urrent datatype description in Open MPI.\n\nSession Format: Recorded\n\nTa
 g: Algorithms, Exascale Computing, Extreme Scale Computing, Heterogeneous 
 Systems, Post-Moore Computing, Quantum Computing\n\nRegistration Category:
  Workshop Reg Pass
END:VEVENT
END:VCALENDAR