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:20181221T160726Z
LOCATION:D220
DTSTART;TZID=America/Chicago:20181111T143000
DTEND;TZID=America/Chicago:20181111T143300
UID:submissions.supercomputing.org_SC18_sess160_ws_whpc125@linklings.com
SUMMARY:Error Analysis in HPC Applications Using Algorithmic Differentiati
 on
DESCRIPTION:Workshop\nDiversity, Education, Hot Topics, Workshop Reg Pass\
 n\nError Analysis in HPC Applications Using Algorithmic Differentiation\n\
 nMenon\n\nComputer applications running on supercomputers are used to solv
 e critical problems. These systems are expected to perform tasks not just 
 quickly, but also correctly.  Various factors that can affect correctness 
 of programs include faults, reduced precision, lossy data reduction, itera
 tion and truncation. In the presence of these errors, how do we know wheth
 er our program is producing correct results?  I have developed a method to
  understand the impact of these errors on a computer program. The method e
 mploys algorithmic differentiation (AD) to analyze the sensitivity of the 
 simulation output to errors in program variables. A tool that we developed
  based on this method evaluates a given computer program and identifies vu
 lnerable regions that need to be protected from errors.  We use this to se
 lectively protect variables against Silent Data Corruptions (SDC). We also
  use this method to study floating point sensitivity of the code and devel
 op mixed-precision configurations to achieve performance improvement witho
 ut affecting accuracy.  Using this tool we can ensure that the computer si
 mulation applications give us the correct results in the presence of these
  errors, so that scientists and policy makers relying on these results can
  make accurate predictions that can have lasting impact.
URL:https://sc18.supercomputing.org/presentation/?id=ws_whpc125&sess=sess1
 60
END:VEVENT
END:VCALENDAR