BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:710
DTSTART;TZID=America/Denver:20231112T155000
DTEND;TZID=America/Denver:20231112T161500
UID:submissions.supercomputing.org_SC23_sess427_ws_scsc103@linklings.com
SUMMARY:Implementation-Oblivious Transparent Checkpoint-Restart for MPI
DESCRIPTION:Yao Xu, Leonid Belyaev, and Twinkle Jain (Northeastern Univers
 ity); Derek Schafer (University of New Mexico); Anthony Skjellum (Tennesse
 e Tech University); and Gene Cooperman (Northeastern University)\n\nThis w
 ork presents experience with traditional use cases of checkpointing on a n
 ovel platform.  A single codebase (MANA) transparently checkpoints product
 ion workloads for major, available MPI implementations: "develop once, run
  everywhere''.  The new platform allows application developers to compile 
 their application against any of the available standards-compliant MPI imp
 lementations, and test each MPI implementation according to performance or
  other features.\n\nSince its original academic prototype, MANA has been u
 nder development for three of the past four years, and is planned to enter
  full production at NERSC in early Fall of 2023.  To the best of the autho
 rs' knowledge, MANA is currently the only production-capable, system-level
  checkpointing package running on a large supercomputer (Perlmutter at NER
 SC) using a major MPI implementation (HPE Cray MPI).  Experiments are pres
 ented on several large production workloads, showing low runtime overhead 
 with one codebase supporting four MPI implementations: HPE Cray MPI, MPICH
 , Open MPI, and ExaMPI.\n\nTag: Fault Handling and Tolerance\n\nRegistrati
 on Category: Workshop Reg Pass\n\nSession Chairs: Gene Cooperman (Northeas
 tern University); Donglai Dai (Advanced Micro Devices (AMD)); Rebecca Hart
 man-Baker (National Energy Research Scientific Computing Center (NERSC), L
 awrence Berkeley National Laboratory (LBNL)); and Bogdan Nicolae (Argonne 
 National Laboratory (ANL), Illinois Institute of Technology)\n\n
END:VEVENT
END:VCALENDAR