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:20211114T153500
DTEND;TZID=America/Chicago:20211114T160000
UID:submissions.supercomputing.org_SC21_sess428_ws_ftxs106@linklings.com
SUMMARY:Incorporating Fault-Tolerance Awareness into System-Level Modeling
  and Simulation
DESCRIPTION:Workshop\n\nIncorporating Fault-Tolerance Awareness into Syste
 m-Level Modeling and Simulation\n\nJohnson, Lam\n\nAs the design space for
  supercomputers grows, modeling and simulation (MODSIM) becomes more impor
 tant to facilitate system-level design space exploration (DSE). Furthermor
 e, extreme-scale systems and newer technologies can lead to higher fault r
 ates, which negatively affects system performance. Therefore, it is import
 ant for system performance predictions to include the effects of faults an
 d fault-tolerance (FT) techniques, to facilitate system design.\n\nBE-SST 
 is an existing MODSIM methodology and workflow based on using abstraction 
 to simplify and accelerate MODSIM for DSE. This paper documents the incorp
 oration of fault-tolerance awareness into BE-SST, which adds the ability t
 o model the checkpointing costs of a full system using the previously vali
 dated MODSIM approach of  BE-SST  . We present the process used to extend 
 BE-SST, enabling the creation and validation of fault-tolerance aware (FT 
 aware) performance models, which can be used in BE-SST to predict the effe
 cts of system and application parameters on FT overhead. \n\nAdditionally,
  this paper presents a case study where full system performance, comprised
  of application, hardware, and FT technique, is simulated using BE-SST.  W
 e validate both FT aware and non FT aware performance models against actua
 l system performance, finding an average percent error of less than 17\% f
 or individual functions and 20\% for full application runs, demonstrating 
 an acceleration of the exploration and reduction of a large design space w
 ith an acceptable level of accuracy. Finally, we analyze how the FT aware 
 and non-FT aware models differ, and suggest DSE use cases based on their d
 ifferences.\n\nTag: Online Only, Extreme Scale Computing, Reliability and 
 Resiliency\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR