[VectorCombine] Preserve scoped alias metadata

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

@@ -56,9 +56,9 @@ STATISTIC(NumScalarOps, "Number of scalar unary + binary ops formed");
 STATISTIC(NumScalarCmp, "Number of scalar compares formed");
 STATISTIC(NumScalarIntrinsic, "Number of scalar intrinsic calls formed");
 
-static cl::opt<bool> DisableVectorCombine(
-    "disable-vector-combine", cl::init(false), cl::Hidden,
-    cl::desc("Disable all vector combine transforms"));
+static cl::opt<bool>
+    DisableVectorCombine("disable-vector-combine", cl::init(false), cl::Hidden,
+                         cl::desc("Disable all vector combine transforms"));
 
 static cl::opt<bool> DisableBinopExtractShuffle(
     "disable-binop-extract-shuffle", cl::init(false), cl::Hidden,
@@ -1074,8 +1074,7 @@ bool VectorCombine::scalarizeVPIntrinsic(Instruction &I) {
   InstructionCost OldCost = 2 * SplatCost + VectorOpCost;
 
   // Determine scalar opcode
-  std::optional<unsigned> FunctionalOpcode =
-      VPI.getFunctionalOpcode();
+  std::optional<unsigned> FunctionalOpcode = VPI.getFunctionalOpcode();
   std::optional<Intrinsic::ID> ScalarIntrID = std::nullopt;
   if (!FunctionalOpcode) {
     ScalarIntrID = VPI.getFunctionalIntrinsicID();
@@ -1098,8 +1097,7 @@ bool VectorCombine::scalarizeVPIntrinsic(Instruction &I) {
       (SplatCost * !Op0->hasOneUse()) + (SplatCost * !Op1->hasOneUse());
   InstructionCost NewCost = ScalarOpCost + SplatCost + CostToKeepSplats;
 
-  LLVM_DEBUG(dbgs() << "Found a VP Intrinsic to scalarize: " << VPI
-                    << "\n");
+  LLVM_DEBUG(dbgs() << "Found a VP Intrinsic to scalarize: " << VPI << "\n");
   LLVM_DEBUG(dbgs() << "Cost of Intrinsic: " << OldCost
                     << ", Cost of scalarizing:" << NewCost << "\n");
 
@@ -1805,6 +1803,8 @@ bool VectorCombine::scalarizeLoadExtract(Instruction &I) {
   // erased in the correct order.
   Worklist.push(LI);
 
+  Type *ElemType = VecTy->getElementType();
+
   // Replace extracts with narrow scalar loads.
   for (User *U : LI->users()) {
     auto *EI = cast<ExtractElementInst>(U);
@@ -1818,13 +1818,19 @@ bool VectorCombine::scalarizeLoadExtract(Instruction &I) {
     Builder.SetInsertPoint(EI);
     Value *GEP =
         Builder.CreateInBoundsGEP(VecTy, Ptr, {Builder.getInt32(0), Idx});
-    auto *NewLoad = cast<LoadInst>(Builder.CreateLoad(
-        VecTy->getElementType(), GEP, EI->getName() + ".scalar"));
+    auto *NewLoad = cast<LoadInst>(
+        Builder.CreateLoad(ElemType, GEP, EI->getName() + ".scalar"));
 
-    Align ScalarOpAlignment = computeAlignmentAfterScalarization(
-        LI->getAlign(), VecTy->getElementType(), Idx, *DL);
+    Align ScalarOpAlignment =
+        computeAlignmentAfterScalarization(LI->getAlign(), ElemType, Idx, *DL);
     NewLoad->setAlignment(ScalarOpAlignment);
 
+    if (auto *ConstIdx = dyn_cast<ConstantInt>(Idx)) {
+      size_t Offset = ConstIdx->getZExtValue() * DL->getTypeStoreSize(ElemType);
+      AAMDNodes OldAAMD = LI->getAAMetadata();
+      NewLoad->setAAMetadata(OldAAMD.adjustForAccess(Offset, ElemType, *DL));
+    }
+
     replaceValue(*EI, *NewLoad);
   }
 
@@ -2070,10 +2076,12 @@ bool VectorCombine::foldPermuteOfBinops(Instruction &I) {
   }
 
   unsigned NumOpElts = Op0Ty->getNumElements();
-  bool IsIdentity0 = ShuffleDstTy == Op0Ty &&
+  bool IsIdentity0 =
+      ShuffleDstTy == Op0Ty &&
       all_of(NewMask0, [NumOpElts](int M) { return M < (int)NumOpElts; }) &&
       ShuffleVectorInst::isIdentityMask(NewMask0, NumOpElts);
-  bool IsIdentity1 = ShuffleDstTy == Op1Ty &&
+  bool IsIdentity1 =
+      ShuffleDstTy == Op1Ty &&
       all_of(NewMask1, [NumOpElts](int M) { return M < (int)NumOpElts; }) &&
       ShuffleVectorInst::isIdentityMask(NewMask1, NumOpElts);
 

llvm/test/Transforms/VectorCombine/alias.ll

@@ -0,0 +1,52 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=vector-combine -S | FileCheck %s --check-prefixes=CHECK
+
+define <4 x i32> @quux(ptr addrspace(3) %arg) {
+; CHECK-LABEL: define <4 x i32> @quux(
+; CHECK-SAME: ptr addrspace(3) [[ARG:%.*]]) {
+; CHECK-NEXT:  [[BB:.*:]]
+; CHECK-NEXT:    [[EXTRACTELEMENT:%.*]] = load i8, ptr addrspace(3) [[ARG]], align 4, !tbaa [[TBAA0:![0-9]+]], !alias.scope [[META0:![0-9]+]], !noalias [[META0]]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <4 x i8>, ptr addrspace(3) [[ARG]], i32 0, i64 1
+; CHECK-NEXT:    [[EXTRACTELEMENT1:%.*]] = load i8, ptr addrspace(3) [[TMP0]], align 1, !tbaa [[TBAA0]], !alias.scope [[META0]], !noalias [[META0]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds <4 x i8>, ptr addrspace(3) [[ARG]], i32 0, i64 2
+; CHECK-NEXT:    [[EXTRACTELEMENT2:%.*]] = load i8, ptr addrspace(3) [[TMP1]], align 2, !tbaa [[TBAA0]], !alias.scope [[META0]], !noalias [[META0]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds <4 x i8>, ptr addrspace(3) [[ARG]], i32 0, i64 3
+; CHECK-NEXT:    [[EXTRACTELEMENT3:%.*]] = load i8, ptr addrspace(3) [[TMP2]], align 1, !tbaa [[TBAA0]], !alias.scope [[META0]], !noalias [[META0]]
+; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[EXTRACTELEMENT]] to i32
+; CHECK-NEXT:    [[ZEXT4:%.*]] = zext i8 [[EXTRACTELEMENT1]] to i32
+; CHECK-NEXT:    [[ZEXT5:%.*]] = zext i8 [[EXTRACTELEMENT2]] to i32
+; CHECK-NEXT:    [[ZEXT6:%.*]] = zext i8 [[EXTRACTELEMENT3]] to i32
+; CHECK-NEXT:    [[INSERTELEMENT:%.*]] = insertelement <4 x i32> poison, i32 [[ZEXT]], i64 0
+; CHECK-NEXT:    [[INSERTELEMENT7:%.*]] = insertelement <4 x i32> [[INSERTELEMENT]], i32 [[ZEXT4]], i64 1
+; CHECK-NEXT:    [[INSERTELEMENT8:%.*]] = insertelement <4 x i32> [[INSERTELEMENT7]], i32 [[ZEXT5]], i64 2
+; CHECK-NEXT:    [[INSERTELEMENT9:%.*]] = insertelement <4 x i32> [[INSERTELEMENT8]], i32 [[ZEXT6]], i64 3
+; CHECK-NEXT:    ret <4 x i32> [[INSERTELEMENT9]]
+;
+bb:
+  %load = load <4 x i8>, ptr addrspace(3) %arg, align 4, !alias.scope !0, !noalias !0, !tbaa !5
+  %extractelement = extractelement <4 x i8> %load, i64 0
+  %extractelement1 = extractelement <4 x i8> %load, i64 1
+  %extractelement2 = extractelement <4 x i8> %load, i64 2
+  %extractelement3 = extractelement <4 x i8> %load, i64 3
+  %zext = zext i8 %extractelement to i32
+  %zext4 = zext i8 %extractelement1 to i32
+  %zext5 = zext i8 %extractelement2 to i32
+  %zext6 = zext i8 %extractelement3 to i32
+  %insertelement = insertelement <4 x i32> poison, i32 %zext, i64 0
+  %insertelement7 = insertelement <4 x i32> %insertelement, i32 %zext4, i64 1
+  %insertelement8 = insertelement <4 x i32> %insertelement7, i32 %zext5, i64 2
+  %insertelement9 = insertelement <4 x i32> %insertelement8, i32 %zext6, i64 3
+  ret <4 x i32> %insertelement9
+}
+
+!0 = !{!1}
+!1 = distinct !{!1, !2}
+!2 = distinct !{!2}
+!3 = !{!"Simple C/C++ TBAA"}
+!4 = !{!"omnipotent char", !3, i64 0}
+!5 = !{!"i8", !4, i64 0}
+;.
+; CHECK: [[META0]] = !{[[META1:![0-9]+]]}
+; CHECK: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]]}
+; CHECK: [[META2]] = distinct !{[[META2]]}
+;.