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:20241120T082409Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20240604T173000
DTEND;TZID=Europe/Stockholm:20240604T180000
UID:submissions.pasc-conference.org_PASC24_sess150_msa171@linklings.com
SUMMARY:A GPU-Accelerated Implementation of the Semi-Implicit Barotropic M
 ode Solver for the MPAS-Ocean
DESCRIPTION:Minisymposium\n\nHyun-Gyu Kang, Youngsung Kim, and Sarat Sreep
 athi (Oak Ridge National Laboratory) and Luke Van Roekel (Los Alamos Natio
 nal Laboratory)\n\nA semi-implicit barotropic mode solver for the Model fo
 r Prediction Across Scales Ocean (MPAS-Ocean), an ocean component of the E
 nergy Exascale Earth System Model (E3SM), has been ported on GPU using Ope
 nACC directives. Since the semi-implicit solver in MPAS-O consists of a li
 near iterative solver and a preconditioner that requires linear algebra op
 erations, we introduced the Matrix Algebra on GPU and Multicore Architectu
 re (MAGMA) and CUBLAS which are collections of linear algebra libraries fo
 r heterogeneous architectures. We applied several methodologies such as al
 gorithmic changes of the iterative solver, refactorization of loops, and t
 he GPU-aware Message Passing Interface for the global all-to-all node comm
 unications to obtain optimized GPU performance. For runtime of main solver
  iterations including data staging, we achieved 5.4x (1.4x) speedup on 20 
 (100) Summit nodes. We will also show the GPU-accelerated solver performan
 ce using Cray LibSci_ACC supporting AMD MI250X GPU on Frontier. We will br
 iefly discuss the recent update to MPAS-Ocean that changed the baroclinic 
 time stepping method from the forward-backward to the second-order Adams B
 ashforth and its impact on the computational efficiency and model accuracy
 . This research is still underway, so methodologies may be further improve
 d for better computational performance on GPUs.\n\nDomain: Climate, Weathe
 r, and Earth Sciences, Computational Methods and Applied Mathematics\n\nSe
 ssion Chairs: Iva Kavcic (Met Office), Christopher Michael Maynard (Met Of
 fice), and Wei Zhang (Oak Ridge National Laboratory)
END:VEVENT
END:VCALENDAR