LAMMPS Combustion Simulation

Опубликовано 8 ноября 2021, 16:45

Watch a demo showing how Instinct MI200 enables fuel combustion research, delivering up to 2.2X greater simulation throughput¹.

Discover more: amd.com/en/events/data-center

***

Subscribe: bit.ly/Subscribe_to_AMD
Like us on Facebook: bit.ly/AMD_on_Facebook
Follow us on Twitter: bit.ly/AMD_On_Twitter
Follow us on Twitch: Twitch.tv/AMD
Follow us on Linkedin: bit.ly/AMD_on_Linkedin
Follow us on Instagram: bit.ly/AMD_on_Instagram

©2021 Advanced Micro Devices, Inc. AMD, the AMD Arrow Logo, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Other names are for informational purposes only and may be trademarks of their respective owners.

¹Testing Conducted by AMD performance lab as of 10/7/2021, on a
single socket Optimized 3rd Gen EPYC CPU powered server, with 4x AMD Instinct™ MI250X OAM (128 GB HBM2e) 560W GPUs with AMD Infinity Fabric™ technology, using LAMMPS ReaxFF/C, patch_2Jul2021 plus AMD optimizations to LAMMPS and Kokkos that are not yet available upstream resulted in a median score of 4x MI250X = 19,482,180.48 ATOM-Time Steps/s Vs. Dual AMD EPYC 7742@2.25GHz CPUs with 4x NVIDIA A100 SXM 80GB (400W) using LAMMPS classical molecular dynamics package ReaxFF/C, patch_10Feb2021 resulted in a published score of 8,850,000 (8.85E+06) ATOM-Time Steps/s. developer.nvidia.com/hpc-appli... 19,482,180.48/8,850,000=2.20x (220%) the/1.2x (120%) faster. Container details found at: ngc.nvidia.com/catalog/contain...
Information on LAMMPS: lammps.org/index.html Server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers and optimizations MI200-15A