[Mlir-commits] [mlir] [mlir][GPUToNVVM] enable fallback to generic LLVM lowering for math dialect in convert-gpu-to-nvvm pass (PR #165728)

[Mehdi Amini]

joker-eph wrote:

Do we have the infra in convert-to-llvm to inject target-specific patterns (like NVVM) right now?

https://github.com/llvm/llvm-project/pull/165728