Saturday, September 30, 2023

NVIDIA Releases SimNet AI-Driven Multi-Physics Simulation Toolkit v0.2

SANTA CLARA, CA, USA, Sep 11, 2020 – NVIDIA announced the release of SimNet v0.2 with new features including support for A100 GPUs and multi-GPU/multi-node, as well as adding a larger set of neural network architectures and a greater solution space addressability. These new features allow a user to advance simulations for more advanced physics like turbulence and work with complex geometries.


SimNet Value


Previously announced in May, NVIDIA SimNet is a Physics Informed Neural Networks (PINNs) toolkit for students and researchers who are either looking to get started with AI-driven physics simulations or are looking to leverage a powerful framework to implement their domain knowledge to solve complex nonlinear physics problems with real-world applications.

SimNet v0.2 highlights

Turbulent simulations with high Reynold number: Simulation of complex geometries is difficult for standard fully connected networks even with some of the previously introduced losses like integral losses and SDF weighting. SimNet v0.2 introduces new networks such as Fourier features and its variants, SiReNs, DGM as well as features like global & local adaptive learning rate annealing, global activation functions, exact continuity or mass balance for flow problems and Halton sequences for low discrepancy point cloud that facilitate the exploration of more complex shapes and physics like turbulence modeling in CFD.




Real World Geometries: In addition to SimNet’s geometry library that allowed building objects with primitive shapes, a new SDF library in SimNet v0.2 now enables import of STL geometries from CAD packages to work with complex geometries.




Performance: SimNet v0.2 is highly scalable for multi-GPU/multi-Node. In a scalability study using 16 DGX-1 with 128 V100 GPUs, the scalability for points processed per second remained linear with a near constant time per iteration. SimNet is also supported on A100 GPUs now and leverages the TF32 precision. An initial study shows the A100 with TF32 to be faster ~2x compared to FP32 precision and about ~3x compared to V100 without significant difference in accuracy.




Give SimNet v0.2 a try by requesting access today.

Sachin R Nalawade
Sachin R Nalawade
Founder and Editor DailyCADCAM. A highly-driven astute professional and avid marketer; equipped with a solid foundation in Academia; Manufacturing, CAD, CAM, CAE industry and Implementing Marketing Initiatives for Global Brands (All Design Software and Hardware Vendors).

Latest Posts