Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
This addresses the problem of high-fidelity physics simulations for industrial engineering tasks, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles the challenge of scaling neural PDE solvers to industrial-scale geometries with over 10^8 cells, introducing Transolver-3, which handles meshes with over 160 million cells and achieves impressive performance on aircraft and automotive design benchmarks.
Deep learning has emerged as a transformative tool for the neural surrogate modeling of partial differential equations (PDEs), known as neural PDE solvers. However, scaling these solvers to industrial-scale geometries with over $10^8$ cells remains a fundamental challenge due to the prohibitive memory complexity of processing high-resolution meshes. We present Transolver-3, a new member of the Transolver family as a highly scalable framework designed for high-fidelity physics simulations. To bridge the gap between limited GPU capacity and the resolution requirements of complex engineering tasks, we introduce two key architectural optimizations: faster slice and deslice by exploiting matrix multiplication associative property and geometry slice tiling to partition the computation of physical states. Combined with an amortized training strategy by learning on random subsets of original high-resolution meshes and a physical state caching technique during inference, Transolver-3 enables high-fidelity field prediction on industrial-scale meshes. Extensive experiments demonstrate that Transolver-3 is capable of handling meshes with over 160 million cells, achieving impressive performance across three challenging simulation benchmarks, including aircraft and automotive design tasks.