[LoopVectorizer] Fix PR #65212: vectorization of reduction loop wasn't respecting original store alignment

Author: nunoplopes

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -3943,7 +3943,8 @@ void InnerLoopVectorizer::fixReduction(VPReductionPHIRecipe *PhiR,
   // inside the loop, create the final store here.
   if (StoreInst *SI = RdxDesc.IntermediateStore) {
     StoreInst *NewSI =
-        Builder.CreateStore(ReducedPartRdx, SI->getPointerOperand());
+        Builder.CreateAlignedStore(ReducedPartRdx, SI->getPointerOperand(),
+                                   SI->getAlign());
     propagateMetadata(NewSI, SI);
 
     // If the reduction value is used in other places,

llvm/test/Transforms/LoopVectorize/reduction-align.ll

@@ -18,7 +18,7 @@ define void @fn(ptr %hbuf, ptr %ref, i32 %height) {
 ; CHECK-NEXT:    [[TMP0:%.*]] = load i16, ptr [[REF]], align 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i16, ptr [[HBUF]], align 1
 ; CHECK-NEXT:    [[ADD:%.*]] = add i16 [[TMP1]], [[TMP0]]
-; CHECK-NEXT:    store i16 [[ADD]], ptr [[HBUF]], align 2
+; CHECK-NEXT:    store i16 [[ADD]], ptr [[HBUF]], align 1
 ; CHECK-NEXT:    [[INC]] = add i32 [[I]], 1
 ; CHECK-NEXT:    br label [[FOR_COND]]
 ; CHECK:       for.end: