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:20260522T150117Z
LOCATION:C155/156
DTSTART;TZID=America/Chicago:20181115T133000
DTEND;TZID=America/Chicago:20181115T150000
UID:submissions.supercomputing.org_SC18_sess288_pan104@linklings.com
SUMMARY:Approximating for Faster, Better and Cheaper Scientific Computing
DESCRIPTION:Hatem Ltaief (King Abdullah University of Science and Technolo
 gy); George Biros (University of Texas); Jack Dongarra (University of Tenn
 essee; Oak Ridge National Laboratory, University of Manchester); Fernanda 
 Foertter (Nvidia Corporation); Sherry Li (Lawrence Berkeley National Labor
 atory); Satoshi Matsuoka (Tokyo Institute of Technology, RIKEN); and Willi
 am Tang (Princeton University)\n\nHPC simulations and big data application
 s face similar challenges when solving extreme-scale scientific problems: 
 high algorithmic complexity and large memory footprint. CMOS and memory te
 chnology scaling have continuously mitigated these challenges with an expo
 nential growth in processor performance and a constant increase in speed a
 nd capacity, respectively. The free lunch is perhaps over but now artifici
 al intelligence comes to the rescue, with the sheer volume of data to be c
 runched.\n\nThis has caused the community to explore disruptive hardware a
 nd software solutions to overcome both challenges. One of the trends consi
 sts of exploring numerical approximations, e.g., mixed/low precision and h
 ierarchical low-rank matrix computations, with hardware support for a vari
 ety of precisions.\n\nThe panelists investigate alternatives to today’s st
 ate-of-the-art chips and numerical algorithms. The main idea consists in t
 rading-off accuracy for performance throughout the hardware and software e
 cosystems in the context of exascale scientific computing.\n\nRegistration
  Category: Tech Program Reg Pass\n\n
END:VEVENT
END:VCALENDAR