[VectorCombine] Fix alignment in single element store

This fixes the concern in single element store scalarization that the
alignment of new store may be larger than it should be. It calculates
the largest alignment if index is constant, and a safe one if not.

Reviewed By: lebedev.ri, spatel

Differential Revision: https://reviews.llvm.org/D103419

diff --git a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
index 6689945..c184c8a 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ b/llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -831,8 +831,15 @@ bool VectorCombine::foldSingleElementStore(Instruction &I) {
     Builder.Insert(GEP);
     StoreInst *NSI = Builder.CreateStore(NewElement, GEP);
     NSI->copyMetadata(*SI);
-    if (SI->getAlign() < NSI->getAlign())
-      NSI->setAlignment(SI->getAlign());
+    Align NewAlignment = std::max(SI->getAlign(), Load->getAlign());
+    if (auto *C = dyn_cast<ConstantInt>(Idx))
+      NewAlignment = commonAlignment(
+          NewAlignment,
+          C->getZExtValue() * DL.getTypeStoreSize(NewElement->getType()));
+    else
+      NewAlignment = commonAlignment(
+          NewAlignment, DL.getTypeStoreSize(NewElement->getType()));
+    NSI->setAlignment(NewAlignment);
     replaceValue(I, *NSI);
     // Need erasing the store manually.
     I.eraseFromParent();

diff --git a/llvm/test/Transforms/VectorCombine/load-insert-store.ll b/llvm/test/Transforms/VectorCombine/load-insert-store.ll
index 14f618e..6218ecd 100644 (file)
--- a/llvm/test/Transforms/VectorCombine/load-insert-store.ll
+++ b/llvm/test/Transforms/VectorCombine/load-insert-store.ll
@@ -20,7 +20,7 @@ define void @insert_store_i16_align1(<8 x i16>* %q, i16 zeroext %s) {
 ; CHECK-LABEL: @insert_store_i16_align1(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[Q:%.*]], i32 0, i32 3
-; CHECK-NEXT:    store i16 [[S:%.*]], i16* [[TMP0]], align 1
+; CHECK-NEXT:    store i16 [[S:%.*]], i16* [[TMP0]], align 2
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -125,6 +125,7 @@ entry:
   ret void
 }
 
+; To verify align here is narrowed to scalar store size
 define void @insert_store_nonconst_large_alignment(<4 x i32>* %q, i32 zeroext %s, i32 %idx) {
 ; CHECK-LABEL: @insert_store_nonconst_large_alignment(
 ; CHECK-NEXT:  entry:
@@ -148,7 +149,7 @@ define void @insert_store_nonconst_align_maximum_8(<8 x i64>* %q, i64 %s, i32 %i
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 [[IDX:%.*]], 2
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP]])
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds <8 x i64>, <8 x i64>* [[Q:%.*]], i32 0, i32 [[IDX]]
-; CHECK-NEXT:    store i64 [[S:%.*]], i64* [[TMP1]], align 4
+; CHECK-NEXT:    store i64 [[S:%.*]], i64* [[TMP1]], align 8
 ; CHECK-NEXT:    ret void
 ;
   %cmp = icmp ult i32 %idx, 2
@@ -180,7 +181,7 @@ define void @insert_store_nonconst_align_larger(<8 x i64>* %q, i64 %s, i32 %idx)
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 [[IDX:%.*]], 2
 ; CHECK-NEXT:    call void @llvm.assume(i1 [[CMP]])
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds <8 x i64>, <8 x i64>* [[Q:%.*]], i32 0, i32 [[IDX]]
-; CHECK-NEXT:    store i64 [[S:%.*]], i64* [[TMP1]], align 2
+; CHECK-NEXT:    store i64 [[S:%.*]], i64* [[TMP1]], align 4
 ; CHECK-NEXT:    ret void
 ;
   %cmp = icmp ult i32 %idx, 2