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:20240604T160000
DTEND;TZID=Europe/Stockholm:20240604T180000
UID:submissions.pasc-conference.org_PASC24_sess150@linklings.com
SUMMARY:MS4A - GPU Acceleration in Earth System Modeling: Strategies, Auto
 mated Refactoring Tools, Benefits and Challenges
DESCRIPTION:Minisymposium\n\nEarth System models simulate the complex inte
 ractions of the atmosphere, oceans, land and sea ice, providing valuable i
 nsights into short-term weather forecasts and long-term climate research, 
 which are important for understanding and mitigating the impacts of weathe
 r-related disasters and climate change. As the complexity and computationa
 l demands of these models increase, the need for Graphic Processing Unit (
 GPU) acceleration becomes increasingly apparent. GPUs are computational ar
 chitectures that efficiently support massive parallelism. Whilst several s
 tudies have shown promising computational performance by porting GPUs to E
 arth System models and thus enabling higher-resolution simulations, some o
 f them have also discussed the challenges of adapting existing codes to ru
 n on GPUs. To address refactoring and portability issues, automating code 
 refactoring tools have been developed to increase the efficiency of portin
 g code to GPU and improve portability and maintainability. This minisympos
 ium aims to bring together scientists, computational researchers, and mode
 l developers to explore the role of GPU acceleration in optimizing Earth S
 ystem models, share the experience, and look to the future. Topics also in
 clude optimization strategies (e.g., parallelization techniques, memory ma
 nagement, data transfer, etc.), automating code refactoring tools (e.g., P
 Syclone), benefits and challenges (e.g., speedup, memory constraints, code
  management, etc.).\n\nProgress Report on the GPU Adapatation of IFS and t
 he Destination Earth DTs\n\nThe use of GPUs and accelerator architectures 
 has become widespread in high-performance computing to achieve unprecedent
 ed throughput and computational model performance. The efficient usage of 
 GPU architectures has long been envisioned at ECMWF, but it requires signi
 ficant, often invasive code refa...\n\n\nMichael Lange (ECMWF)\n----------
 -----------\nA GPU-Accelerated Implementation of the Semi-Implicit Barotro
 pic Mode Solver for the MPAS-Ocean\n\nA semi-implicit barotropic mode solv
 er for the Model for Prediction Across Scales Ocean (MPAS-Ocean), an ocean
  component of the Energy Exascale Earth System Model (E3SM), has been port
 ed on GPU using OpenACC directives. Since the semi-implicit solver in MPAS
 -O consists of a linear iterative solver a...\n\n\nHyun-Gyu Kang, Youngsun
 g Kim, and Sarat Sreepathi (Oak Ridge National Laboratory) and Luke Van Ro
 ekel (Los Alamos National Laboratory)\n---------------------\nPorting and 
 Optimizing Momentum, CASIM and SOCRATES for GPU Architectures\n\nExploitin
 g GPUs is both an opportunity and a challenge for weather and climate code
 s. They present an opportunity as the massive parallelism they possess can
  allow these codes to achieve very high computational performance. They pr
 esent a challenge as exploiting this parallelism can require the refa...\n
 \n\nChristopher Maynard (Met Office); Wei Zhang, Matthew Norman, Min Xu, S
 alil Mahajan, and Katherine Evans (Oak Ridge National Laboratory); and Jon
 athan Wilkinson, James Manners, and Ben Shipway (Met Office)\n------------
 ---------\nPorting NEMO to GPUs with PSyclone\n\nPSyclone is a source-to-s
 ource code-generation and transformation system designed to enable perform
 ance portability and code maintainability for weather and climate codes wr
 itten in Fortran. To achieve this, it separates the scientific code, writt
 en in Fortran, from the optimisation and parallelisat...\n\n\nSergi Siso (
 Science and Technology Facilities Council)\n\nDomain: Climate, Weather, an
 d Earth Sciences, Computational Methods and Applied Mathematics\n\nSession
  Chairs: Iva Kavcic (Met Office), Christopher Michael Maynard (Met Office)
 , and Wei Zhang (Oak Ridge National Laboratory)
END:VEVENT
END:VCALENDAR