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:20211207T055405Z
LOCATION:231-232
DTSTART;TZID=America/Chicago:20211114T140000
DTEND;TZID=America/Chicago:20211114T143000
UID:submissions.supercomputing.org_SC21_sess427_ws_canopie101@linklings.co
 m
SUMMARY:Feasibility of Running Singularity Containers with Hybrid MPI on N
 ASA High-End Computing Resources
DESCRIPTION:Workshop\n\nFeasibility of Running Singularity Containers with
  Hybrid MPI on NASA High-End Computing Resources\n\nChang, Heistand, Hood,
  Jin\n\nThis work investigates the feasibility of a Singularity solution t
 o support running MPI applications in “hybrid” MPI mode on NASA’s HECC res
 ources. Two types of applications were tested: HPC and AI/ML. On the HPC s
 ide, two JEDI containers built with Intel MPI for Earth science modeling w
 ere tested on both HECC in-house and HECC AWS Cloud CPU resources. On the 
 AI/ML side, a NVIDIA TensorFlow container built with OpenMPI was tested wi
 th a NCF recommender system and the ResNet-50 computer image system on the
  HECC in-house V100 GPUs. Our exercises demonstrate that although porting 
 containers to run with a single node using just the container MPI is quite
  straightforward, running across multiple nodes in hybrid MPI mode require
 s knowledge of Singularity, MPI libraries, the operating system image, and
  the communication infrastructure such as the transport and network layers
 .\n\nTag: Applications, Emerging Technologies, Reproducibility and Transpa
 rency, Software Engineering, System Software and Runtime Systems, Workflow
 s\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR