BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085744Z
LOCATION:HG F 3
DTSTART;TZID=Europe/Stockholm:20190614T093000
DTEND;TZID=Europe/Stockholm:20190614T100000
UID:submissions.pasc-conference.org_PASC19_sess181_pap_jan112@linklings.co
m
SUMMARY:A Discontinuous Galerkin Fast Spectral Method for Multi-Species Fu
ll Boltzmann on Streaming Multi-Processors
DESCRIPTION:Paper\nComputer Science and Applied Mathematics\n\nA Discontin
uous Galerkin Fast Spectral Method for Multi-Species Full Boltzmann on Str
eaming Multi-Processors\n\nJaiswal, Hu, Brillon, Alexeenko\n\nWhen the mol
ecules of a gaseous system are far apart, say in microscale gas flows wher
e the surface to volume ratio is high and hence the surface forces dominan
t, the molecule-surface interactions lead to the formation of a local ther
modynamically non-equilibrium region extending few mean free paths from th
e surface. The dynamics of such systems is accurately described by Boltzma
nn equation. However, the multi-dimensional nature of Boltzmann equation p
resents a huge computational challenge. With the recent mathematical devel
opments and the advent of petascale, the dynamics of full Boltzmann equati
on is now tractable. We present an implementation of the recently introduc
ed multi-species discontinuous Galerkin fast spectral (DGFS) method for so
lving full Boltzmann on streaming multi-processors. The present implementa
tion solves the inhomogeneous Boltzmann equation in span of few minutes, m
aking it at least two order-of-magnitude faster than the present state-of-
art stochastic method---direct simulation Monte Carlo---widely used for so
lving Boltzmann equation. Various performance metrics, such as weak/strong
scaling have been presented. A parallel efficiency of 0.96--0.99 is demon
strated on 36 Nvidia Tesla-P100 GPUs.
Full paper: https://doi.o
rg/10.1145/3324989.3325714
END:VEVENT
END:VCALENDAR