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:20260202T201347Z
LOCATION:274
DTSTART;TZID=America/Chicago:20251118T153000
DTEND;TZID=America/Chicago:20251118T170000
UID:submissions.supercomputing.org_SC25_sess304@linklings.com
SUMMARY:Precision and Real Number Representations
DESCRIPTION:Numerical Performance of the Implicitly Restarted Arnoldi Meth
 od in OFP8, Bfloat16, Posit, and Takum Arithmetics\n\nThe computation of s
 elect eigenvalues and eigenvectors of large, sparse matrices is fundamenta
 l to a wide range of applications. Accordingly, evaluating the numerical p
 erformance of emerging alternatives to the IEEE 754 floating-point standar
 d, such as OFP8 (E4M3 and E5M2), bfloat16, and the tapered...\n\n\nLaslo H
 unhold (University of Cologne), James Quinlan (University of Southern Main
 e), and Stefan Wesner (University of Cologne)\n---------------------\nRAPT
 OR: Practical Numerical Profiling of Scientific Applications\n\nThe prolif
 eration of low-precision units in modern high-performance architectures in
 creasingly burdens domain scientists. Historically, the choice in HPC was 
 easy: Can we get away with 32-bit floating-point operations and lower band
 width requirements, or is FP64 necessary? Driven by artificial intel...\n\
 n\nFaveo Hoerold (ETH Zürich, RIKEN Center for Computational Science (R-CC
 S)); Ivan Radanov Ivanov (Institute of Science Tokyo, RIKEN Center for Com
 putational Science (R-CCS)); Akash Dhruv (Argonne National Laboratory (ANL
 )); William S. Moses (University of Illinois Urbana-Champaign); Anshu Dube
 y (Argonne National Laboratory (ANL)); and Mohamed Wahib and Jens Domke (R
 IKEN Center for Computational Science (R-CCS))\n---------------------\nA N
 ested Krylov Method Using Half-Precision Arithmetic\n\nLow-precision compu
 ting is essential for efficiently utilizing memory bandwidth and computing
  cores. While many mixed-precision algorithms have been developed for iter
 ative sparse linear solvers, effectively leveraging half-precision (fp16) 
 arithmetic remains challenging. This study introduces a nov...\n\n\nKengo 
 Suzuki and Takeshi Iwashita (Kyoto University)\n---------------------\nHig
 h-Performance Branch-Free Algorithms for Extended-Precision Floating-Point
  Arithmetic\n\nWe present new branch-free algorithms for floating-point ar
 ithmetic at double, triple, or quadruple the native machine precision. The
 se algorithms are the fastest known by at least an order of magnitude and 
 are conjectured to be optimal, not only in an asymptotic sense, but in the
 ir exact FLOP count...\n\n\nDavid Kai Zhang and Alex Aiken (Stanford Unive
 rsity)\n\nTag: Algorithms, Applications, Architectures & Networks\n\nRecor
 ding: Livestreamed, Recorded\n\nRegistration Category: Technical Program R
 eg Pass\n\nSession Chair: Hartwig Anzt (Technical University of Munich; Un
 iversity of Tennessee, Knoxville)
END:VEVENT
END:VCALENDAR