[PATCH] D137783: [AMDGPU][MC] Support TFE modifiers in MUBUF loads and stores.

[Dmitry Preobrazhensky via Phabricator via llvm-commits]

dp added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/BUFInstructions.td:2445
 
-multiclass MUBUF_Real_AllAddr_gfx6_gfx7_gfx10<bits<8> op> :
-  MUBUF_Real_AllAddr_gfx6_gfx7<op>, MUBUF_Real_AllAddr_gfx10<op>;
+multiclass MUBUF_Real_AllAddr_gfx6_gfx7_gfx10<bits<8> op, bit noTFE = 0> :
+  MUBUF_Real_AllAddr_gfx6_gfx7<op, noTFE>, MUBUF_Real_AllAddr_gfx10<op, noTFE>;
----------------
`noTFE` is always 0 and may be removed.


================
Comment at: llvm/lib/Target/AMDGPU/BUFInstructions.td:2824
 
+multiclass MUBUF_Real_AllAddr_gfx80<bits<7> op, bit noTFE = 0> {
+  defm NAME : MUBUF_Real_AllAddr_Helper_gfx80<op>;
----------------
It looks like `noTFE` is always 0 and may be removed.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D137783/new/

https://reviews.llvm.org/D137783