[mlir][NVGPU] Adding Support for cp_async_zfill via Inline Asm
authorManish Gupta <manigupta@google.com>
Fri, 2 Sep 2022 21:20:11 +0000 (21:20 +0000)
committerThomas Raoux <thomasraoux@google.com>
Fri, 2 Sep 2022 21:29:26 +0000 (21:29 +0000)
commitfbf69f95b614e3428a5322005070986eae1dfb5a
tree513905e396551bb874bdfdb8fa6f86633bd706b6
parent0f6103af97e71ef17d2ac3d8bb00bc2f173a2ffb
 [mlir][NVGPU] Adding Support for cp_async_zfill via Inline Asm

`cp_async_zfill` is currently not present in the nvvm backend, this patch adds `cp_async_zfill` support by adding inline asm when lowering from `nvgpu` to `nvvm`.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D132269
mlir/include/mlir/Dialect/NVGPU/IR/NVGPU.td
mlir/lib/Conversion/NVGPUToNVVM/NVGPUToNVVM.cpp
mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir