9th NCAR MultiCore Workshop (MC9)
Program
September 25, 2019 (Wednesday)
8:00am In-person registration begins / Coffee/Tea Service, Bagels, and Pastries to be provided.
John Dennis (NCAR)
8:45 Keynote: Accelerating Earth System Models with machine learning
Kelly Kochanski (University of Colorado)
9:45am BREAK (15 min)
Panel (Jed Brown moderator):
10:00 Future of Machine Learning and Physically-based Methods
Panelists: Claire Monteleoni (CU), Kelly Kochanski (CU), DJ Gagne (NCAR), David Hall (NVIDIA)
Session 1: Machine and Deep Learning (Jed Brown)
DJ Gagne (NCAR)
11:10 NVIDIA: Deep Learning Projects in Weather, Climate, and Space
David Hall (NVIDIA)
11:35 GPU Benefits for Earth System Science
Stan Posey (NVIDIA), Raghu Kumar (NVIDIA)
12:00pm LUNCH (1 hour)
Session 2: Numerical methods and solvers (Bryan Flynt)
1:00 Multigrid and Mixed-Precision: Fast Solvers for Weather and Climate Models,
Christopher Maynard (Met Office / University of Reading)
1:25 Recent Advances in Sparse Linear System Solver Stacks for Exascale
Steve Thomas (NREL)
1:50 Preconditioning Matrix-Free Operators in libCEED
Jeremy L. Thompson (University of Colorado)
2:15 Algorithmic Choices that Improve Hardware Utilization and Accuracy
Matt Norman (ORNL)
2:40pm BREAK (20 minutes)
Session 3: Porting and Optimization (John Dennis)
3:00 Microarchitecture Analysis and Optimization Techniques
Gunther Huebler (UWM)
3:25 Accelerating Solar Physics Application MURaM for GPU
Eric Wright (University of Delaware)
Wei Zhang (Oak Ridge National Laboratory)
4:15 Porting the RTE+RRTMGP radiative transfer package for next-generation supercomputers
Benjamin Hillman (Sandia National Laboratories)
4:40pm ADJOURN
September 26, 2019 (Thursday)
08:00am Coffee/Tea Service, Bagels, and Pastries to be provided.
Session 4: Vendors (Chris Maynard)
8:30 Cray Shasta for Earth System Modeling
Ilene Carpenter (Cray Inc.)
8:55 AMD Epyc for High Performance Computing workloads
Martin Hilgeman (AMD)
9:20 In-Network Computing Technology and Performance Advantages
Gerardo Cisneros-Stoianowski (Mellanox)
9:45 Insights into Intel innovations for HPC and AI
Andrey Ovsyannikov (Intel)
10:10am BREAK (15 min)
Session 5: Model development and correctness (Ilene Carpenter)
10:25 Developing a Terrestrial Dynamical Core for E3SM
Jed Brown (University of Colorado)
10:50 Evaluating the Spread of Climate Model Ensembles Based on Computing Environment Selection
Tom Robinson (SAIC/GFDL)
11:15 Experience with mixed-precision within physics parameterizations
John Dennis (NCAR)
11:40 MPAS-A on GPUs using OpenACC
Supreeth Suresh (NCAR)
12:05pm LUNCH (55 minutes)
Session 6: Language and Tools (Matthew Norman)
1:00 Progress in Porting the LFRic Weather and Climate Model to FPGAs using C and OpenCL
Mike Ashworth (University of Manchester)
1:25 Building a High-Performance Earth System Model in Julia
Maciej Waruszewski (Naval Postgraduate School)
1:50 A GPU performance analysis library providing arbitrary granularity in time and thread count
Jim Rosinski (UCAR/CPAESS)
2:15pm BREAK (15 minutes)
2:30 Keynote: The ECMWF Scalability Programme - Progress and Plans
Peter Bauer (ECMWF)
Panel (Chris Maynard moderator)
3:30 Will we ever achieve a 1 km global model?
WORKSHOP WRAP-UP 4:15 pm – 4:50 pm