SciML / DiffEqGPU.jl

GPU-acceleration routines for DifferentialEquations.jl and the broader SciML scientific machine learning ecosystem
https://docs.sciml.ai/DiffEqGPU/stable/
MIT License
272 stars 27 forks source link

Allow large problems to work with stiff ODE solvers in `EnsembleGPUKernel` #287

Closed utkarsh530 closed 1 year ago

utkarsh530 commented 1 year ago

The PR allows us to solve relatively larger state parameter-parallel models. It is made possible by removing the constraint in StaticArrays.jl, which forces to allocate when size > 14. The problem is mainly in the Linear Algebra routines such as lu and \ .