[Mlir-commits] [mlir] [mlir][gpu] Support Cluster of Thread Blocks in `gpu.launch_func` (PR #72871)

[Fabian Mora]

fabianmcg wrote:

> The PR already implements `SelectObjectAttr.cpp` and adds a test to `gpu.mlir`. Is it not enough?

I missed it, I was looking only at `GPUCommon/GPUToLLVMConversion.cpp`, so nvm, that's enough, maybe just remove the old path 

https://github.com/llvm/llvm-project/pull/72871