BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:607
DTSTART;TZID=America/Denver:20231112T113000
DTEND;TZID=America/Denver:20231112T115000
UID:submissions.supercomputing.org_SC23_sess415_ws_esp107@linklings.com
SUMMARY:Automatic Search Guided Code Optimization Framework for Mixed-Prec
 ision Scientific Applications
DESCRIPTION:Jienan Yao and Wei Xue (Tsinghua University, China)\n\nThe rap
 id development in machine learning (ML) has prompted demand for low-precis
 ion arithmetic hardware that can deliver faster computing speed. Weather s
 imulation applications typically exhibit higher sensitivity towards small 
 perturbation on the input data, but the inherent uncertainty paves the way
  for opportunities in mixed-precision computing (MPC) by trading accuracy 
 for performance. Additional challenges of balancing between the lower comp
 utational cost and accuracy requirements need to be addressed before succe
 ssful MPC can be applied to weather modeling applications. Determining an 
 acceptable precision allocation for variables involves interacting with an
  exponential search space of mixed-precision configurations. We propose a 
 mixed-precision code tuning framework for automatic search of suitable pre
 cision configurations for weather modeling applications with black-box opt
 imization algorithms. The search results achieve up to 30% performance gai
 n that stays within the tolerance level, offering a workflow to facilitate
  the identification of variables sensitive to precision change.\n\nTag: Pe
 rformance Optimization\n\nRegistration Category: Workshop Reg Pass\n\nSess
 ion Chairs: Tiernan Casey (Sandia National Laboratories) and Antigoni Geor
 giadou (Oak Ridge National Laboratory (ORNL))\n\n
END:VEVENT
END:VCALENDAR