CuAD: Source-to-Source Automatic Differentiation of CUDA Kernels for Discrete Adjoints in Computational Fluid Dynamics
physics.flu-dyn, physics.comp-ph
Submitted: 2026-10-19
Updated: 2026-10-20
Related papers
- Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
- A neural operator framework for data-driven discovery of stability and receptivity in physical systems
- Physics Foundation Models for Efficient Control of Fluid Flows
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
- Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
- A mass invariant in a compressible turbulent medium