Physics-ML のためのフレームワーク
NVIDIA Modulus 最新事情
Naruhiko Tan, Solution Architect, NVIDIA Japan
• What is NVIDIA Modulus
• Physics-ML use cases
• How to get started
Agenda
What is NVIDIA Modulus
AI Powered Computational Domains
Computational Eng.
Solid & Fluid
Mechanics,
Electromagnetics,
Thermal, Acoustics,
Optics, Electrical,
Multi-body Dynamics,
Design Materials,
Systems
Earth Sciences
Climate
Modeling,
Weather
Modeling,
Ocean Modeling,
Seismic
Interpretation
Life Sciences
Genomics,
Proteomics
Computational
Physics
Particle Science,
Astrophysics
Computational
Chemistry
Quantum
Chemistry,
Molecular
Dynamics
•Process/Product Design,
Manufacturing, Testing,
•In-Service
Using AI for simulations – How?
AI for simulations
• AI has already disrupted the way we think of computation in other domains and mapping to AI unleashes parallelism
• Doing once vs repetitive – learn once and infer over and over
*HPC+AI ってよく聞くけど結局なんなの, 山崎,
GTC2022 テクニカルフォローアップセミナー
NVIDIA Modulus
Platform for developing Physics ML surrogate model
• A training and inference pipeline - using
Physics (governing equations) and Data
(simulation/observations)
• Customizable and scalable platform
• Higher level of abstraction for domain
experts
• Build generalized AI surrogates for
parameterized domain
• Near real-time high-fidelity simulation
Modulus EULA – It’s free.
Developing digital twins for weather, climate, and energy [S41823]
12
Physics-ML categorization
Physics
Data
Fully data
driven
Inductive
bias
Physics
constrained
Fully physics
driven
Modulus Framework - Verification
15
MODULUS FRAMEWORK - VERIFICATION
CFD Solid Mechanics Acoustics
Laminar
Turbulent
16
Electromagnetics Vibrations Turbulence
MODULUS FRAMEWORK - VERIFICATION
Modulus
Modulus
Modulus
15
MODULUS FRAMEWORK - VERIFICATION
CFD Solid Mechanics Acoustics
aminar
bulent
15
MODULUS FRAMEWORK - VERIFICATION
CFD Solid Mechanics Acoustics
Laminar
Turbulent
16
Electromagnetics Vibrations Turbulence
MODULUS FRAMEWORK - VERIFICATION
Modulus
Modulus
Modulus
Modulus Framework - Performance
SINGLE GPU: Tensor Core Speed-Up for PDEs
A100 FP32 vs. TF32: Results, Compute Time, Loss
Modulus Framework - Performance
MULTI-GPU: Node Scalability
Physics-ML use cases
NVIDIA'S Earth -2: Digital Twins For Weather and Climate [A41326]
Earth-2 Began by Exploring
Data-Driven Weather Prediction
Scope Global, Medium Range
Model Type Full-Model AI Surrogate
Architecture AFNO (Adaptive Fourier Neural Op.)
Resolution: 25km
Training Data: ERA5 Reanalysis
Initial Condition GFS / UFS
Inference Time 0.25 sec (2-week forecast)
Speedup vs NWP O(104-105)
Power Savings O(104)
FourCastNet
NVIDIA'S Earth -2: Digital Twins For Weather and Climate [A41326]
Deuben & Bauer (2018), 6 , 60x30, 1.8K pixels, MLP
WeatherBench, Rasp et al. (2020). 5.625 , 64x32, 2K pixels, CNN
Weyn et al. (2019), 2.5 N.H only, 72x36, 2.6k pixels, ConvLSTM
DLWP, Weyn et al. (2020). 2 , 16K pixels, Deep CNN on Cubesphere/(2021) ResNet
FourCastNet, Pathak et al. (2022), 0.25 , ~1,000,000 Pixels, ViT+AFNO
GNN, Keisler et al. (2022), 1 , 64,000 Pixels, Graph Neural Networks
FourCastNet: A new data-driven weather predictor of unprecedented resolution
NVIDIA'S Earth -2: Digital Twins For Weather and Climate [A41326]
We train FCN on ambitious amounts of data on large machines
Thanks to full-stack AI + HPC expertise we train on a growing amount of the world's petabytes of past weather data.
Time to solution decreased from 24+ hours to 67 minutes with model and data parallelism
FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators, Kurth et al. (2022), https://arxiv.org/abs/2208.05419
NVIDIA'S Earth -2: Digital Twins For Weather and Climate [A41326]
FCN skill improving with training ambition.
Could it one day outperform deterministic models? We don't yet know the limit.
Skill gap reduced by more than half
w.r.t IFS gold standard
Skill gap reduced by more than half
w.r.t IFS gold standard
Acronym Alert:
ACC: Anomaly Correlation Coefficient (metric of weather skill)
IFS: The Integrated Forecast System, a gold standard weather model
FCN: FourCastNet, our digital twin of weather.
Open-Source FourCastNet
Join us in pushing the frontiers of data-driven numerical weather prediction
https://github.com/NVlabs/FourCastNet
FourCastNet implementation using Modulus
Included in Modulus examples
https://docs.nvidia.com/deeplearning/modulus/user_guide/neural_operators/fourcastnet.html
WIND TURBINE WAKE OPTIMIZATION —
SIEMENS GAMESA
Use Case
§ Developing optimal engineering wake models to optimize wind
farm layouts
§ Simulating the effect that a turbine might have on another when
placed in close proximity
Challenges
§ Generating high-fidelity simulation data from Reynolds-averaged
Navier-Stokes (RANS) or Large Eddy Simulations (LES) can take
over a month to run, even on a 100-CPU cluster.
Solution
§ NVIDIA Omniverse and Modulus enable accurate, high-fidelity
simulations of the wake of the turbines, using low-resolution
simulations as inputs and applying super resolution using AI.
NVIDIA Solution Stack
§ Hardware: NVIDIA A100, A40, RTX 8000 GPUs
§ Software: NVIDIA Omniverse, NVIDIA Modulus
Outcome
§ Approximately 4,000X speedup for high-fidelity simulation
§ Optimizing wind farm layouts in real-time increases overall
production while reducing loads and operating costs.
Demo
WIND TURBINE WAKE OPTIMIZATION — SIEMENS GAMESA
Super resolution using AI
https://www.youtube.com/watch?v=mQuvYQmdbtw
Super Resolution Net and pix2pixHD Net are now available in Modulus
Included in Modulus examples
https://docs.nvidia.com/deeplearning/modulus/user_guide/intermediate/turbulence_super_resolution.html
How to get started
Download NVIDIA Modulus, now
https://developer.nvidia.com/modulus
Learn how to use NVIDIA Modulus
https://github.com/openhackathons-org/gpubootcamp/blob/master/hpc_ai/PINN/English/python/Start_Here.ipynb
User Guide (ex. Defining custom PDEs)
NVIDIA Modulus User Guide
https://docs.nvidia.com/deeplearning/modulus/user_guide/foundational/1d_wave_equation.html#writing-custom-pdes-and-boundary-initial-conditions
Ask questions at NVIDIA Modulus technical forum
https://forums.developer.nvidia.com/c/physics-simulation/modulus-physics-ml-model-framework/technical-support/453
Contribute to NVIDIA Modulus on GitLab!
*Need to submit GitLab repository access request from https://developer.nvidia.com/modulus-downloads
Summary
• NVIDIA Modulus is platform for developing Physics-ML surrogate model
• Physics-ML use cases
• FourCastNet
https://arxiv.org/abs/2208.05419, https://github.com/NVlabs/FourCastNet
• Super Resolution
https://blogs.nvidia.com/blog/2022/03/22/siemens-gamesa-wind-farms-digital-twins/
• How to get started
• Download
https://developer.nvidia.com/modulus
• Learn
https://docs.nvidia.com/deeplearning/modulus/index.html
https://github.com/openhackathons-org/gpubootcamp/blob/master/hpc_ai/PINN/English/python/Start_Here.ipynb
• Ask questions
https://forums.developer.nvidia.com/c/physics-simulation/modulus-physics-ml-model-framework/technical-
support/453
• Get involved
https://developer.nvidia.com/modulus-downloads
Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情

Physics-ML のためのフレームワーク NVIDIA Modulus 最新事情

  • 1.
    Physics-ML のためのフレームワーク NVIDIA Modulus最新事情 Naruhiko Tan, Solution Architect, NVIDIA Japan
  • 2.
    • What isNVIDIA Modulus • Physics-ML use cases • How to get started Agenda
  • 3.
  • 4.
    AI Powered ComputationalDomains Computational Eng. Solid & Fluid Mechanics, Electromagnetics, Thermal, Acoustics, Optics, Electrical, Multi-body Dynamics, Design Materials, Systems Earth Sciences Climate Modeling, Weather Modeling, Ocean Modeling, Seismic Interpretation Life Sciences Genomics, Proteomics Computational Physics Particle Science, Astrophysics Computational Chemistry Quantum Chemistry, Molecular Dynamics •Process/Product Design, Manufacturing, Testing, •In-Service
  • 5.
    Using AI forsimulations – How? AI for simulations • AI has already disrupted the way we think of computation in other domains and mapping to AI unleashes parallelism • Doing once vs repetitive – learn once and infer over and over *HPC+AI ってよく聞くけど結局なんなの, 山崎, GTC2022 テクニカルフォローアップセミナー
  • 6.
    NVIDIA Modulus Platform fordeveloping Physics ML surrogate model • A training and inference pipeline - using Physics (governing equations) and Data (simulation/observations) • Customizable and scalable platform • Higher level of abstraction for domain experts • Build generalized AI surrogates for parameterized domain • Near real-time high-fidelity simulation Modulus EULA – It’s free.
  • 7.
    Developing digital twinsfor weather, climate, and energy [S41823] 12 Physics-ML categorization Physics Data Fully data driven Inductive bias Physics constrained Fully physics driven
  • 8.
    Modulus Framework -Verification 15 MODULUS FRAMEWORK - VERIFICATION CFD Solid Mechanics Acoustics Laminar Turbulent 16 Electromagnetics Vibrations Turbulence MODULUS FRAMEWORK - VERIFICATION Modulus Modulus Modulus 15 MODULUS FRAMEWORK - VERIFICATION CFD Solid Mechanics Acoustics aminar bulent 15 MODULUS FRAMEWORK - VERIFICATION CFD Solid Mechanics Acoustics Laminar Turbulent 16 Electromagnetics Vibrations Turbulence MODULUS FRAMEWORK - VERIFICATION Modulus Modulus Modulus
  • 9.
    Modulus Framework -Performance SINGLE GPU: Tensor Core Speed-Up for PDEs A100 FP32 vs. TF32: Results, Compute Time, Loss
  • 10.
    Modulus Framework -Performance MULTI-GPU: Node Scalability
  • 11.
  • 12.
    NVIDIA'S Earth -2:Digital Twins For Weather and Climate [A41326] Earth-2 Began by Exploring Data-Driven Weather Prediction Scope Global, Medium Range Model Type Full-Model AI Surrogate Architecture AFNO (Adaptive Fourier Neural Op.) Resolution: 25km Training Data: ERA5 Reanalysis Initial Condition GFS / UFS Inference Time 0.25 sec (2-week forecast) Speedup vs NWP O(104-105) Power Savings O(104) FourCastNet
  • 13.
    NVIDIA'S Earth -2:Digital Twins For Weather and Climate [A41326] Deuben & Bauer (2018), 6 , 60x30, 1.8K pixels, MLP WeatherBench, Rasp et al. (2020). 5.625 , 64x32, 2K pixels, CNN Weyn et al. (2019), 2.5 N.H only, 72x36, 2.6k pixels, ConvLSTM DLWP, Weyn et al. (2020). 2 , 16K pixels, Deep CNN on Cubesphere/(2021) ResNet FourCastNet, Pathak et al. (2022), 0.25 , ~1,000,000 Pixels, ViT+AFNO GNN, Keisler et al. (2022), 1 , 64,000 Pixels, Graph Neural Networks FourCastNet: A new data-driven weather predictor of unprecedented resolution
  • 14.
    NVIDIA'S Earth -2:Digital Twins For Weather and Climate [A41326] We train FCN on ambitious amounts of data on large machines Thanks to full-stack AI + HPC expertise we train on a growing amount of the world's petabytes of past weather data. Time to solution decreased from 24+ hours to 67 minutes with model and data parallelism FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators, Kurth et al. (2022), https://arxiv.org/abs/2208.05419
  • 15.
    NVIDIA'S Earth -2:Digital Twins For Weather and Climate [A41326] FCN skill improving with training ambition. Could it one day outperform deterministic models? We don't yet know the limit. Skill gap reduced by more than half w.r.t IFS gold standard Skill gap reduced by more than half w.r.t IFS gold standard Acronym Alert: ACC: Anomaly Correlation Coefficient (metric of weather skill) IFS: The Integrated Forecast System, a gold standard weather model FCN: FourCastNet, our digital twin of weather.
  • 16.
    Open-Source FourCastNet Join usin pushing the frontiers of data-driven numerical weather prediction https://github.com/NVlabs/FourCastNet
  • 17.
    FourCastNet implementation usingModulus Included in Modulus examples https://docs.nvidia.com/deeplearning/modulus/user_guide/neural_operators/fourcastnet.html
  • 18.
    WIND TURBINE WAKEOPTIMIZATION — SIEMENS GAMESA Use Case § Developing optimal engineering wake models to optimize wind farm layouts § Simulating the effect that a turbine might have on another when placed in close proximity Challenges § Generating high-fidelity simulation data from Reynolds-averaged Navier-Stokes (RANS) or Large Eddy Simulations (LES) can take over a month to run, even on a 100-CPU cluster. Solution § NVIDIA Omniverse and Modulus enable accurate, high-fidelity simulations of the wake of the turbines, using low-resolution simulations as inputs and applying super resolution using AI. NVIDIA Solution Stack § Hardware: NVIDIA A100, A40, RTX 8000 GPUs § Software: NVIDIA Omniverse, NVIDIA Modulus Outcome § Approximately 4,000X speedup for high-fidelity simulation § Optimizing wind farm layouts in real-time increases overall production while reducing loads and operating costs. Demo
  • 19.
    WIND TURBINE WAKEOPTIMIZATION — SIEMENS GAMESA Super resolution using AI https://www.youtube.com/watch?v=mQuvYQmdbtw
  • 20.
    Super Resolution Netand pix2pixHD Net are now available in Modulus Included in Modulus examples https://docs.nvidia.com/deeplearning/modulus/user_guide/intermediate/turbulence_super_resolution.html
  • 21.
    How to getstarted
  • 22.
    Download NVIDIA Modulus,now https://developer.nvidia.com/modulus
  • 23.
    Learn how touse NVIDIA Modulus https://github.com/openhackathons-org/gpubootcamp/blob/master/hpc_ai/PINN/English/python/Start_Here.ipynb
  • 24.
    User Guide (ex.Defining custom PDEs) NVIDIA Modulus User Guide https://docs.nvidia.com/deeplearning/modulus/user_guide/foundational/1d_wave_equation.html#writing-custom-pdes-and-boundary-initial-conditions
  • 25.
    Ask questions atNVIDIA Modulus technical forum https://forums.developer.nvidia.com/c/physics-simulation/modulus-physics-ml-model-framework/technical-support/453
  • 26.
    Contribute to NVIDIAModulus on GitLab! *Need to submit GitLab repository access request from https://developer.nvidia.com/modulus-downloads
  • 27.
    Summary • NVIDIA Modulusis platform for developing Physics-ML surrogate model • Physics-ML use cases • FourCastNet https://arxiv.org/abs/2208.05419, https://github.com/NVlabs/FourCastNet • Super Resolution https://blogs.nvidia.com/blog/2022/03/22/siemens-gamesa-wind-farms-digital-twins/ • How to get started • Download https://developer.nvidia.com/modulus • Learn https://docs.nvidia.com/deeplearning/modulus/index.html https://github.com/openhackathons-org/gpubootcamp/blob/master/hpc_ai/PINN/English/python/Start_Here.ipynb • Ask questions https://forums.developer.nvidia.com/c/physics-simulation/modulus-physics-ml-model-framework/technical- support/453 • Get involved https://developer.nvidia.com/modulus-downloads