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:20260522T150130Z
LOCATION:D171
DTSTART;TZID=America/Chicago:20181112T140000
DTEND;TZID=America/Chicago:20181112T150000
UID:submissions.supercomputing.org_SC18_sess150_pec339@linklings.com
SUMMARY:Correctness of Floating Point Programs - Exception Handling and Re
 producibility
DESCRIPTION:James Demmel (University of California, Berkeley)\n\nWe consid
 er two related aspects of analyzing and guaranteeing correctness of floati
 ng point programs: exception handling and reproducibility. Exception handl
 ing refers to reliable and consistent propagation of errors due to overflo
 w, invalid operations (like sqrt(-1)), convergence failures, etc. Reproduc
 ibility refers to getting bitwise reproducible results from multiple runs 
 of the same program, e.g., despite parallelism causing floating point sums
  to be evaluated in different order with different roundoff errors. We des
 cribe the efforts of two standards committees, the Basic Linear Algebra Su
 bprograms (BLAS) Standard, and the IEEE 754 Floating Point Standard, to ad
 dress these issues, and how these efforts should make it easier to accompl
 ish these goals for higher level applications, such as linear algebra libr
 aries.\n\nTag: Applications, Correctness, Debugging, Floating Point, MPI, 
 OpenMP, Runtime Systems, Tools, Verification\n\nRegistration Category: Wor
 kshop Reg Pass\n\nSession Chairs: Ignacio Laguna (Lawrence Livermore Natio
 nal Laboratory (LLNL)) and Cindy Rubio-González (University of California,
  Davis)\n\n
END:VEVENT
END:VCALENDAR