[Mlir-commits] [mlir] [mlir][amdgpu] implement amdgpu.global_load_async_to_lds for gfx1250 (PR #189279)

Alan Li llvmlistbot at llvm.org
Mon Mar 30 08:16:54 PDT 2026


https://github.com/lialan approved this pull request.

Overall LGTM. The next step is to link it with the lowering of coalesced gather dma op. 
On gfx1250, we emit async version instead. 

https://github.com/llvm/llvm-project/pull/189279


More information about the Mlir-commits mailing list