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:20181221T160904Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181115T083000
DTEND;TZID=America/Chicago:20181115T170000
UID:submissions.supercomputing.org_SC18_sess324_post179@linklings.com
SUMMARY:A Low-Communicaton Method to Solve Poisson's Equation on Locally-S
tructured Grids
DESCRIPTION:Poster\nTech Program Reg Pass, Exhibits Reg Pass\n\nA Low-Comm
unicaton Method to Solve Poisson's Equation on Locally-Structured Grids\n\
nVan Straalen, McCorquodale, Colella, Kavouklis\n\nThis poster describes a
new algorithm, Method of Local Corrections (MLC), and a high-performance
implementation for solving Poisson's equation with infinite-domain boundar
y conditions, on locally-refined nested rectangular grids. The data motio
n is comparable to that of only a single V-cycle of multigrid, and hence i
s an order of magnitude smaller than traditional multigrid iteration. The
computational kernels are 3D FFTs on small domains. Strong scaling tests o
n 64 to 4096 cores on NERSC Cori I (Haswell) show over 60% efficiency, and
weak scaling by replication tests over 64 to 32768 cores show 92% efficie
ncy on the same platform. We find comparable solve times between HPGMG on
a uniform grid with one billion grid points, and MLC on the same number of
grid points adaptively distributed. MLC is designed for AMR, able to sol
ve problems with much higher resolution at the finest level than an algori
thm on a uniform grid.
URL:https://sc18.supercomputing.org/presentation/?id=post179&sess=sess324
END:VEVENT
END:VCALENDAR