[PATCH] D136432: [AMDGPU] Combine BFI instructions.

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp:2194
+  SDNode *CurrentOr = N;
+  while (CurrentOr && CurrentOr->hasOneUse()) {
+    SDValue O0 = CurrentOr->getOperand(0);
----------------
The top level OR can have multiple uses.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp:2215
+
+  // Require that at least two nesting levels have been visited
+  // The constants are required to be a partition of -1
----------------
Why? Is there any disadvantage to letting this function select a single BFI?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D136432/new/

https://reviews.llvm.org/D136432