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:20200129T163557Z
LOCATION:702
DTSTART;TZID=America/Denver:20191118T103000
DTEND;TZID=America/Denver:20191118T110000
UID:submissions.supercomputing.org_SC19_sess127_ws_waccpd108@linklings.com
SUMMARY:GPU Implementation of a Sophisticated Implicit Low-Order Finite El
ement Solver with FP21-32-64 Computation Using OpenACC
DESCRIPTION:Workshop\n\nGPU Implementation of a Sophisticated Implicit Low
-Order Finite Element Solver with FP21-32-64 Computation Using OpenACC\n\n
Yamaguchi, Fujita, Ichimura, Naruse, Lalith...\n\nAccelerating application
s with portability and maintainability is one of the big challenges in sci
ence and engineering.\nPreviously, we have developed a fast implicit low-o
rder three-dimensional finite element solver, which has a complicated algo
rithm including artificial intelligence and transprecision computing. In a
ddition, all possible tunings for the target architecture were implemented
; accordingly, the solver has inferior portability and maintainability.\n\
nIn this paper, we apply OpenACC to the solver. The directive-based implem
entation of OpenACC enables GPU computation to be introduced with a smalle
r developmental cost even for complex codes. In performance measurements o
n AI Bridging Cloud Infrastructure (ABCI), we evaluated that a reasonable
speedup was attained on GPUs, given that the elapsed time of the entire so
lver was reduced to 1/14 of that on CPUs based on the original CPU impleme
ntation. Our proposed template to use transprecision computing with our c
ustom FP21 data type is available to the public; therefore, it can provide
a successful example for other scientific computing applications.\n\nTag:
Workshop Reg Pass, Accelerators, Parallel Application Frameworks, Paralle
l Programming Languages, Libraries, and Models, Scientific Computing, Soft
ware Engineering\n\nRegistration Category: Workshop Reg Pass, Accelerators
, Parallel Application Frameworks, Parallel Programming Languages, Librari
es, and Models, Scientific Computing, Software Engineering
URL:https://sc19.supercomputing.org/presentation/?id=ws_waccpd108&sess=ses
s127
END:VEVENT
END:VCALENDAR