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:20211207T055339Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211114T110500
DTEND;TZID=America/Chicago:20211114T113000
UID:submissions.supercomputing.org_SC21_sess428_ws_ftxs105@linklings.com
SUMMARY:Assessing the Use Cases of Persistent Memory in High-Performance S
 cientific Computing
DESCRIPTION:Workshop\n\nAssessing the Use Cases of Persistent Memory in Hi
 gh-Performance Scientific Computing\n\nOren, Fridman\n\nAs the High Perfor
 mance Computing world moves towards the Exa-Scale era, huge amounts of dat
 a should be analyzed, manipulated and stored. In the traditional storage/m
 emory hierarchy, whenever the DRAM's capacity becomes insufficient for sto
 ring data in a node, the computation should either be distributed between 
 several compute nodes, or some portion of these data objects must be store
 d in a non-volatile block device such as a hard disk drive or an SSD stora
 ge device. Optane DataCenter Persistent Memory Module (DCPMM), a new techn
 ology introduced by Intel, provides non-volatile memory that can be plugge
 d into standard memory bus slots and therefore be accessed much faster tha
 n standard storage devices.\n\nIn this work, we present and analyze the re
 sults of a comprehensive performance assessment of several ways in which D
 CPMM can 1) replace standard storage devices, and 2) replace or augment DR
 AM for improving the performance of HPC scientific computations. To achiev
 e this goal, we have configured an HPC system such that DCPMM can service 
 I/O operations of scientific applications, replace standard storage device
 s and file systems (specifically for diagnostics and checkpoint-restarting
 ), and serve for expanding applications' main memory. Our results show tha
 t DCPMM allows scientific applications to fully utilize nodes’ locality by
  providing them with sufficiently-large main memory. Moreover, it can also
  be used for providing a high-performance replacement for persistent stora
 ge. Thus, the usage of DCPMM has the potential of replacing standard HDD a
 nd SSD storage devices in HPC architectures and enabling a more efficient 
 platform for modern supercomputing applications.\n\nTag: Online Only, Extr
 eme Scale Computing, Reliability and Resiliency\n\nRegistration Category: 
 Workshop Reg Pass
END:VEVENT
END:VCALENDAR