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:20260522T150116Z
LOCATION:A2 Ballroom
DTSTART;TZID=America/Chicago:20181114T153000
DTEND;TZID=America/Chicago:20181114T160000
UID:submissions.supercomputing.org_SC18_sess466_gb102@linklings.com
SUMMARY:A Fast Scalable Implicit Solver for Nonlinear Time-Evolution Earth
 quake City Problem on Low-Ordered Unstructured Finite Elements with Artifi
 cial Intelligence and Transprecision Computing
DESCRIPTION:Tsuyoshi Ichimura, Kohei Fujita, and Takuma Yamaguchi (Univers
 ity of Tokyo); Akira Naruse (Nvidia Corporation); Jack C. Wells (Oak Ridge
  National Laboratory); Thomas C. Schulthess (Swiss National Supercomputing
  Centre); Tjerk P. Straatsma and Christopher J. Zimmer (Oak Ridge National
  Laboratory); Maxime Martinasso (Swiss National Supercomputing Centre); an
 d Kengo Nakajima, Muneo Hori, and Lalith Maddegedara (University of Tokyo)
 \n\nTo address problems that occur due to earthquakes in urban areas, we p
 ropose a method that utilizes artificial intelligence (AI) and transprecis
 ion computing to accelerate a nonlinear dynamic low-order unstructured fin
 ite-element solver. The AI is used to improve the convergence of iterative
  solver leading to 5.56-fold reduction in arithmetic count from a standard
  solver, and FP16-FP21-FP32-FP64 computing is used to accelerate the spars
 e matrix-vector product kernel, which demonstrated 71.4% peak FP64 perform
 ance on Summit. This is 25.3 times faster than a standard solver and 3.99 
 times faster than the state-of-the-art SC14 Gordon Bell Finalist solver. F
 urthermore, the proposed solver demonstrated high scalability (88.8% on th
 e K computer and 89.5% on Piz Daint), leading to 14.7% peak FP64 performan
 ce on 4096 nodes of Summit. The proposed approach utilizing AI and FP16 ar
 ithmetic has implications for accelerating other implicit solvers used for
  earthquake city simulations as well as various fields.\n\n
END:VEVENT
END:VCALENDAR