[llvm] e93e1b6 - AMDGPU: Fix typo

[Matt Arsenault via llvm-commits]

Author: Matt Arsenault
Date: 2020-01-22T10:17:46-05:00
New Revision: e93e1b621c4dc5c05614ccef3a19748683751f9a

URL: https://github.com/llvm/llvm-project/commit/e93e1b621c4dc5c05614ccef3a19748683751f9a
DIFF: https://github.com/llvm/llvm-project/commit/e93e1b621c4dc5c05614ccef3a19748683751f9a.diff

LOG: AMDGPU: Fix typo

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
index cb7ba1b77813..f4576f10825e 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
@@ -531,7 +531,7 @@ bool AMDGPUCodeGenPrepare::replaceMulWithMul24(BinaryOperator &I) const {
 }
 
 // Find a select instruction, which may have been casted. This is mostly to deal
-// with cases where i16 selects weer promoted here to i32.
+// with cases where i16 selects were promoted here to i32.
 static SelectInst *findSelectThroughCast(Value *V, CastInst *&Cast) {
   Cast = nullptr;
   if (SelectInst *Sel = dyn_cast<SelectInst>(V))