Integrate TrixiGPU.jl with Enzyme.jl for Differentiable Programming - Githubissues

trixi-gpu / TrixiCUDA.jl

GPU acceleration for Trixi.jl

https://trixi-gpu.github.io/TrixiCUDA.jl/

MIT License

44 stars 6 forks source link

Integrate TrixiGPU.jl with Enzyme.jl for Differentiable Programming #43

Open junyixu opened 2 weeks ago

junyixu commented 2 weeks ago

I propose integrating the GPU version of Trixi.jl with Enzyme.jl for differentiable programming.

Benefits:

Differentiable Programming: Allows for gradient-based optimizations in CFD simulations.
Unified Workflow: Provides a seamless experience for differentiable programming.

Note: Jacobian matrices computed on CPU and GPU may differ due to:

Precision Differences: GPUs often use lower precision (e.g., FP32) compared to CPUs (e.g., FP64), affecting numerical accuracy.
Parallelism Effects: GPUs handle parallel computations differently, potentially introducing slight numerical differences.

huiyuxie commented 1 week ago

Thanks for your advice @junyixu! You mentioned about Jacobian matrices - are they the only parts that could benefit from auto differentiation on GPU?