[noalias.decl] Look through llvm.experimental.noalias.scope.decl

[jeroen.dobbelaere]

Summary

Just like llvm.assume, there are a lot of cases where we can just ignore llvm.experimental.noalias.scope.decl.

[jeroen.dobbelaere]

Rebased and updated to the new naming

[jeroen.dobbelaere]

The vectorizer should handle the 'MetadataAsValue' type as a scalar type.

[nikic]

The changes here all look reasonable to me. Ideally we would add test cases for the individual passes and land this before changing inlining, such that the inlining change by itself does not cause undue regressions.

llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp

1751 ↗

(On Diff #315336)

This doesn't do anything :)

llvm/lib/Transforms/InstCombine/InstructionCombining.cpp

2555 ↗

(On Diff #315336)

I guess this makes sense with the full version (that accepts an alloca). I don't think this can happen currently.

[jeroen.dobbelaere]

• update according to comments
• prepared for different patch order

[jeroen.dobbelaere]

FYI: I'll add testcases for the different parts later today

[jeroen.dobbelaere]

The guidance for these changes are mostly based on '::assume'. For some changes, I did not find a corresponding (breaking) assume test, so I did not add one for ::experimental_noalias_scope_decl.
For the others I did add testcases.
The change in BasicAliasAnalysis seemed not to be needed to get the testcase working, so I removed the BasicAliasAnalysis changes, but kept the testcase.
For the Vectorization. I currently focused on still allowing vectorization and reducing the amount of intrinsics duplication. It is likely that some finetuning will be needed in future to tackle correctness, but, with this patch, the situation should not be worse that what it is today.

[nikic]

LGTM

llvm/test/Transforms/EarlyCSE/noalias_scope_decl.ll

3 ↗

(On Diff #316993)

across a @llvm.experimental.noalais.scope.decl

14 ↗

(On Diff #316993)

same

31 ↗

(On Diff #316993)

For this kind of test, using update_test_checks.py with untouched output would be preferred.

[jeroen.dobbelaere]

Adapted to comments

[jeroen.dobbelaere]

Oops. Adapted to comments (but now for real).

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

unsigned getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     case Intrinsic::dbg_label:
     case Intrinsic::invariant_start:
     case Intrinsic::invariant_end:
     case Intrinsic::launder_invariant_group:
     case Intrinsic::strip_invariant_group:
     case Intrinsic::is_constant:
     case Intrinsic::lifetime_start:
     case Intrinsic::lifetime_end:
+    case Intrinsic::experimental_noalias_scope_decl:
     case Intrinsic::objectsize:
     case Intrinsic::ptr_annotation:
     case Intrinsic::var_annotation:
     case Intrinsic::experimental_gc_result:
     case Intrinsic::experimental_gc_relocate:
     case Intrinsic::coro_alloc:
     case Intrinsic::coro_begin:
     case Intrinsic::coro_free:

llvm/include/llvm/Analysis/VectorUtils.h

 namespace Intrinsic {
 typedef unsigned ID;
 }
 
 /// A helper function for converting Scalar types to vector types. If
 /// the incoming type is void, we return void. If the EC represents a
 /// scalar, we return the scalar type.
 inline Type *ToVectorTy(Type *Scalar, ElementCount EC) {
-  if (Scalar->isVoidTy() || EC.isScalar())
+  if (Scalar->isVoidTy() || Scalar->isMetadataTy() || EC.isScalar())
     return Scalar;
   return VectorType::get(Scalar, EC);
 }
 
 inline Type *ToVectorTy(Type *Scalar, unsigned VF) {
   return ToVectorTy(Scalar, ElementCount::getFixed(VF));
 }
 

llvm/lib/Analysis/AliasSetTracker.cpp

void AliasSetTracker::addUnknown(Instruction *Inst) {
   if (auto *II = dyn_cast<IntrinsicInst>(Inst)) {
     // These intrinsics will show up as affecting memory, but they are just
     // markers.
     switch (II->getIntrinsicID()) {
     default:
       break;
       // FIXME: Add lifetime/invariant intrinsics (See: PR30807).
     case Intrinsic::assume:
+    case Intrinsic::experimental_noalias_scope_decl:
     case Intrinsic::sideeffect:
     case Intrinsic::pseudoprobe:
       return;
     }
   }
   if (!Inst->mayReadOrWriteMemory())
     return; // doesn't alias anything
 

llvm/lib/Analysis/MemorySSA.cpp

if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(DefInst)) {
     // (including creating MemoryAccesses for them): we just end up inventing
     // clobbers where they don't really exist at all. Please see D43269 for
     // context.
     switch (II->getIntrinsicID()) {
     case Intrinsic::lifetime_end:
     case Intrinsic::invariant_start:
     case Intrinsic::invariant_end:
     case Intrinsic::assume:
+    case Intrinsic::experimental_noalias_scope_decl:
       return {false, NoAlias};
     case Intrinsic::dbg_addr:
     case Intrinsic::dbg_declare:
     case Intrinsic::dbg_label:
     case Intrinsic::dbg_value:
       llvm_unreachable("debuginfo shouldn't have associated defs!");
     default:
       break;
MemoryUseOrDef *MemorySSA::createNewAccess(Instruction *I,
                                            AliasAnalysisType *AAP,
                                            const MemoryUseOrDef *Template) {
   // The assume intrinsic has a control dependency which we model by claiming
   // that it writes arbitrarily. Debuginfo intrinsics may be considered
   // clobbers when we have a nonstandard AA pipeline. Ignore these fake memory
   // dependencies here.
   // FIXME: Replace this special casing with a more accurate modelling of
   // assume's control dependency.
-  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I))
-    if (II->getIntrinsicID() == Intrinsic::assume)
+  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
+    switch (II->getIntrinsicID()) {
+    default:
+      break;
+    case Intrinsic::assume:
+    case Intrinsic::experimental_noalias_scope_decl:
       return nullptr;
+    }
+  }
 
   // Using a nonstandard AA pipelines might leave us with unexpected modref
   // results for I, so add a check to not model instructions that may not read
   // from or write to memory. This is necessary for correctness.
   if (!I->mayReadFromMemory() && !I->mayWriteToMemory())
     return nullptr;
 
   bool Def, Use;

llvm/lib/Analysis/ValueTracking.cpp

if (Function *F = CI->getCalledFunction())
       case Intrinsic::pseudoprobe:
       case Intrinsic::dbg_declare:
       case Intrinsic::dbg_value:
       case Intrinsic::dbg_label:
       case Intrinsic::invariant_start:
       case Intrinsic::invariant_end:
       case Intrinsic::lifetime_start:
       case Intrinsic::lifetime_end:
+      case Intrinsic::experimental_noalias_scope_decl:
       case Intrinsic::objectsize:
       case Intrinsic::ptr_annotation:
       case Intrinsic::var_annotation:
         return true;
       }
 
   return false;
 }

llvm/lib/Analysis/VectorUtils.cpp

 Intrinsic::ID llvm::getVectorIntrinsicIDForCall(const CallInst *CI,
                                                 const TargetLibraryInfo *TLI) {
   Intrinsic::ID ID = getIntrinsicForCallSite(*CI, TLI);
   if (ID == Intrinsic::not_intrinsic)
     return Intrinsic::not_intrinsic;
 
   if (isTriviallyVectorizable(ID) || ID == Intrinsic::lifetime_start ||
       ID == Intrinsic::lifetime_end || ID == Intrinsic::assume ||
+      ID == Intrinsic::experimental_noalias_scope_decl ||
       ID == Intrinsic::sideeffect || ID == Intrinsic::pseudoprobe)
     return ID;
   return Intrinsic::not_intrinsic;
 }
 
 /// Find the operand of the GEP that should be checked for consecutive
 /// stores. This ignores trailing indices that have no effect on the final
 /// pointer.

llvm/lib/CodeGen/Analysis.cpp

for (BasicBlock::const_iterator BBI = std::prev(ExitBB->end(), 2);; --BBI) {
     if (&*BBI == &Call)
       break;
     // Debug info intrinsics do not get in the way of tail call optimization.
     if (isa<DbgInfoIntrinsic>(BBI))
       continue;
     // Pseudo probe intrinsics do not block tail call optimization either.
     if (isa<PseudoProbeInst>(BBI))
       continue;
-    // A lifetime end or assume intrinsic should not stop tail call
-    // optimization.
+    // A lifetime end, assume or noalias.decl intrinsic should not stop tail
+    // call optimization.
     if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(BBI))
       if (II->getIntrinsicID() == Intrinsic::lifetime_end ||
-          II->getIntrinsicID() == Intrinsic::assume)
+          II->getIntrinsicID() == Intrinsic::assume ||
+          II->getIntrinsicID() == Intrinsic::experimental_noalias_scope_decl)
         continue;
     if (BBI->mayHaveSideEffects() || BBI->mayReadFromMemory() ||
         !isSafeToSpeculativelyExecute(&*BBI))
       return false;
   }
 
   const Function *F = ExitBB->getParent();
   return returnTypeIsEligibleForTailCall(

llvm/lib/Transforms/Scalar/EarlyCSE.cpp

if (match(&Inst, m_Intrinsic<Intrinsic::assume>())) {
         LLVM_DEBUG(dbgs() << "EarlyCSE considering assumption: " << Inst
                           << '\n');
         AvailableValues.insert(CondI, ConstantInt::getTrue(BB->getContext()));
       } else
         LLVM_DEBUG(dbgs() << "EarlyCSE skipping assumption: " << Inst << '\n');
       continue;
     }
 
+    // Likewise, noalias intrinsics don't actually write.
+    if (match(&Inst,
+              m_Intrinsic<Intrinsic::experimental_noalias_scope_decl>())) {
+      LLVM_DEBUG(dbgs() << "EarlyCSE skipping noalias intrinsic: " << Inst
+                        << '\n');
+      continue;
+    }
+
     // Skip sideeffect intrinsics, for the same reason as assume intrinsics.
     if (match(&Inst, m_Intrinsic<Intrinsic::sideeffect>())) {
       LLVM_DEBUG(dbgs() << "EarlyCSE skipping sideeffect: " << Inst << '\n');
       continue;
     }
 
     // We can skip all invariant.start intrinsics since they only read memory,
     // and we can forward values across it. For invariant starts without

llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp

for (Instruction &I : *BB) {
 
     // We can predicate blocks with calls to assume, as long as we drop them in
     // case we flatten the CFG via predication.
     if (match(&I, m_Intrinsic<Intrinsic::assume>())) {
       ConditionalAssumes.insert(&I);
       continue;
     }
 
+    // Do not let llvm.experimental.noalias.scope.decl block the vectorization.
+    // TODO: there might be cases that it should block the vectorization. Let's
+    // ignore those for now.
+    if (match(&I, m_Intrinsic<Intrinsic::experimental_noalias_scope_decl>())) {
+      continue;
+    }
+
     // We might be able to hoist the load.
     if (I.mayReadFromMemory()) {
       auto *LI = dyn_cast<LoadInst>(&I);
       if (!LI)
         return false;
       if (!SafePtrs.count(LI->getPointerOperand())) {
         // !llvm.mem.parallel_loop_access implies if-conversion safety.
         // Otherwise, record that the load needs (real or emulated) masking

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 }
 
 void InnerLoopVectorizer::scalarizeInstruction(Instruction *Instr, VPUser &User,
                                                const VPIteration &Instance,
                                                bool IfPredicateInstr,
                                                VPTransformState &State) {
   assert(!Instr->getType()->isAggregateType() && "Can't handle vectors");
 
+  // llvm.experimental.noalias.scope.decl intrinsics must only be duplicated for
+  // the first lane and part.
+  if (auto *II = dyn_cast<IntrinsicInst>(Instr))
+    if (Instance.Lane != 0 || Instance.Part != 0)
+      if (II->getIntrinsicID() == Intrinsic::experimental_noalias_scope_decl)
+        return;
+
   setDebugLocFromInst(Builder, Instr);
 
   // Does this instruction return a value ?
   bool IsVoidRetTy = Instr->getType()->isVoidTy();
 
   Instruction *Cloned = Instr->clone();
   if (!IsVoidRetTy)
     Cloned->setName(Instr->getName() + ".cloned");
bool IsPredicated = LoopVectorizationPlanner::getDecisionAndClampRange(
       Range);
 
   if (IsPredicated)
     return nullptr;
 
   Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
   if (ID && (ID == Intrinsic::assume || ID == Intrinsic::lifetime_end ||
              ID == Intrinsic::lifetime_start || ID == Intrinsic::sideeffect ||
-             ID == Intrinsic::pseudoprobe))
+             ID == Intrinsic::pseudoprobe ||
+             ID == Intrinsic::experimental_noalias_scope_decl))
     return nullptr;
 
   auto willWiden = [&](ElementCount VF) -> bool {
     Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
     // The following case may be scalarized depending on the VF.
     // The flag shows whether we use Intrinsic or a usual Call for vectorized
     // version of the instruction.
     // Is it beneficial to perform intrinsic call compared to lib call?

llvm/test/Analysis/AliasSet/intrinsics.ll

entry:
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
   %cond1 = icmp ne i32 %c, 0
   call void (i1, ...) @llvm.experimental.guard(i1 %cond1)["deopt"()]
   store i8 1, i8* %b, align 1
   ret void
 }
 
+; CHECK: Alias sets for function 'test5':
+; CHECK: Alias Set Tracker: 2 alias sets for 2 pointer values.
+; CHECK:   AliasSet[0x{{[0-9a-f]+}}, 1] must alias, Mod       Pointers: (i8* %a, LocationSize::precise(1))
+; CHECK-NOT: 1 Unknown instruction
+; CHECK:   AliasSet[0x{{[0-9a-f]+}}, 1] must alias, Mod       Pointers: (i8* %b, LocationSize::precise(1))
+define void @test5() {
+entry:
+  %a = alloca i8, align 1
+  %b = alloca i8, align 1
+  store i8 1, i8* %a, align 1
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 1, i8* %b, align 1
+  ret void
+}
+
 declare void @llvm.assume(i1)
 declare void @llvm.experimental.guard(i1, ...)
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2, !"test5: var" }
+!2 = distinct !{ !2, !"test5" }

llvm/test/Analysis/BasicAA/noalias-scope-decl.ll

+; RUN: opt < %s -basic-aa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
+target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) #0
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+define void @test1(i8* %P, i8* %Q) nounwind ssp {
+  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+  ret void
+
+; CHECK-LABEL: Function: test1:
+
+; CHECK: MayAlias:  i8* %P, i8* %Q
+; CHECK: NoModRef:  Ptr: i8* %P <->  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK: NoModRef:  Ptr: i8* %Q <->  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK: Both ModRef:  Ptr: i8* %P  <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Both ModRef:  Ptr: i8* %Q  <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.experimental.noalias.scope.decl(metadata !0) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+}
+
+
+attributes #0 = { nounwind }
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2, !"test1: var" }
+!2 = distinct !{ !2, !"test1" }

llvm/test/Analysis/CostModel/X86/free-intrinsics.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -mtriple=x86_64-- -analyze -cost-model -cost-kind=code-size %s -S -o - | FileCheck %s --check-prefix=CHECK-SIZE
 ; RUN: opt -mtriple=x86_64-- -analyze -cost-model -cost-kind=throughput %s -S -o - | FileCheck %s --check-prefix=CHECK-THROUGHPUT
 
 define i32 @trivially_free() {
 ; CHECK-SIZE-LABEL: 'trivially_free'
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; CHECK-THROUGHPUT-LABEL: 'trivially_free'
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
   call void @llvm.assume(i1 undef)
+  call void @llvm.experimental.noalias.scope.decl(metadata !4)
   call void @llvm.sideeffect()
   call void @llvm.dbg.declare(metadata i8** undef, metadata !0, metadata !DIExpression())
   call void @llvm.dbg.value(metadata i64 undef, i64 undef, metadata !DIExpression(), metadata !DIExpression())
   call void @llvm.dbg.label(metadata !2)
   %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
   call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
   %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
   %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
   %a4 = call i1 @llvm.is.constant.i32(i32 undef)
   call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
   call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
   %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 1, i1 1, i1 1)
   %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   ret i32 undef
 }
 
 declare i32 @llvm.annotation.i32(i32, i8*, i8*, i32)
 declare void @llvm.assume(i1)
+declare void @llvm.experimental.noalias.scope.decl(metadata)
 declare void @llvm.sideeffect()
 declare void @llvm.dbg.declare(metadata, metadata, metadata)
 declare void @llvm.dbg.value(metadata, i64, metadata, metadata)
 declare void @llvm.dbg.label(metadata)
 declare {}* @llvm.invariant.start.p0i8(i64, i8*)
 declare void @llvm.invariant.end.p0i8({}*, i64, i8*)
 declare i8* @llvm.launder.invariant.group.p0i8(i8*)
 declare i8* @llvm.strip.invariant.group.p0i8(i8*)
 declare i1 @llvm.is.constant.i32(i32)
 declare void @llvm.lifetime.start.p0i8(i64, i8*)
 declare void @llvm.lifetime.end.p0i8(i64, i8*)
 declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1, i1)
 declare i8* @llvm.ptr.annotation.p0i8(i8*, i8*, i8*, i32, i8*)
 declare void @llvm.var.annotation(i8*, i8*, i8*, i32, i8*)
 
 
 !0 = !DILocalVariable(scope: !1)
 !1 = distinct !DISubprogram(name: "dummy", line: 79, isLocal: true, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true)
 !2 = !DILabel(scope: !1, name: "label", file: !3, line: 7)
 !3 = !DIFile(filename: "debug-label.c", directory: "./")
+!4 = !{ !4 }
+!5 = distinct !{ !5, !6, !"foo: var" }
+!6 = distinct !{ !6, !"foo" }

llvm/test/Analysis/CostModel/free-intrinsics-datalayout.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -analyze -cost-model -cost-kind=code-size %s -S -o - | FileCheck %s --check-prefix=CHECK-SIZE
 ; RUN: opt -analyze -cost-model -cost-kind=throughput %s -S -o - | FileCheck %s --check-prefix=CHECK-THROUGHPUT
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 
 define i32 @trivially_free() {
 ; CHECK-SIZE-LABEL: 'trivially_free'
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; CHECK-THROUGHPUT-LABEL: 'trivially_free'
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
   call void @llvm.assume(i1 undef)
+  call void @llvm.experimental.noalias.scope.decl(metadata !4)
   call void @llvm.sideeffect()
   call void @llvm.dbg.declare(metadata i8** undef, metadata !0, metadata !DIExpression())
   call void @llvm.dbg.value(metadata i64 undef, i64 undef, metadata !DIExpression(), metadata !DIExpression())
   call void @llvm.dbg.label(metadata !2)
   %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
   call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
   %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
   %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
   %a4 = call i1 @llvm.is.constant.i32(i32 undef)
   call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
   call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
   %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 1, i1 1, i1 1)
   %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   ret i32 undef
 }
 
 declare i32 @llvm.annotation.i32(i32, i8*, i8*, i32)
 declare void @llvm.assume(i1)
+declare void @llvm.experimental.noalias.scope.decl(metadata)
 declare void @llvm.sideeffect()
 declare void @llvm.dbg.declare(metadata, metadata, metadata)
 declare void @llvm.dbg.value(metadata, i64, metadata, metadata)
 declare void @llvm.dbg.label(metadata)
 declare {}* @llvm.invariant.start.p0i8(i64, i8*)
 declare void @llvm.invariant.end.p0i8({}*, i64, i8*)
 declare i8* @llvm.launder.invariant.group.p0i8(i8*)
 declare i8* @llvm.strip.invariant.group.p0i8(i8*)
 declare i1 @llvm.is.constant.i32(i32)
 declare void @llvm.lifetime.start.p0i8(i64, i8*)
 declare void @llvm.lifetime.end.p0i8(i64, i8*)
 declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1, i1)
 declare i8* @llvm.ptr.annotation.p0i8(i8*, i8*, i8*, i32, i8*)
 declare void @llvm.var.annotation(i8*, i8*, i8*, i32, i8*)
 
 
 !0 = !DILocalVariable(scope: !1)
 !1 = distinct !DISubprogram(name: "dummy", line: 79, isLocal: true, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true)
 !2 = !DILabel(scope: !1, name: "label", file: !3, line: 7)
 !3 = !DIFile(filename: "debug-label.c", directory: "./")
+!4 = !{ !4 }
+!5 = distinct !{ !5, !6, !"foo: var" }
+!6 = distinct !{ !6, !"foo" }

llvm/test/Analysis/CostModel/free-intrinsics-no_info.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -analyze -cost-model -cost-kind=code-size %s -S -o - | FileCheck %s --check-prefix=CHECK-SIZE
 ; RUN: opt -analyze -cost-model -cost-kind=throughput %s -S -o - | FileCheck %s --check-prefix=CHECK-THROUGHPUT
 
 define i32 @trivially_free() {
 ; CHECK-SIZE-LABEL: 'trivially_free'
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; CHECK-THROUGHPUT-LABEL: 'trivially_free'
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.assume(i1 undef)
+; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.experimental.noalias.scope.decl(metadata !0)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.sideeffect()
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a4 = call i1 @llvm.is.constant.i32(i32 undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 true, i1 true, i1 true)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
 ; CHECK-THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %a0 = call i32 @llvm.annotation.i32(i32 undef, i8* undef, i8* undef, i32 undef)
   call void @llvm.assume(i1 undef)
+  call void @llvm.experimental.noalias.scope.decl(metadata !4)
   call void @llvm.sideeffect()
   call void @llvm.dbg.declare(metadata i8** undef, metadata !0, metadata !DIExpression())
   call void @llvm.dbg.value(metadata i64 undef, i64 undef, metadata !DIExpression(), metadata !DIExpression())
   call void @llvm.dbg.label(metadata !2)
   %a1 = call {}* @llvm.invariant.start.p0i8(i64 1, i8* undef)
   call void @llvm.invariant.end.p0i8({}* undef, i64 1, i8* undef)
   %a2 = call i8* @llvm.launder.invariant.group.p0i8(i8* undef)
   %a3 = call i8* @llvm.strip.invariant.group.p0i8(i8* undef)
   %a4 = call i1 @llvm.is.constant.i32(i32 undef)
   call void @llvm.lifetime.start.p0i8(i64 1, i8* undef)
   call void @llvm.lifetime.end.p0i8(i64 1, i8* undef)
   %a5 = call i64 @llvm.objectsize.i64.p0i8(i8* undef, i1 1, i1 1, i1 1)
   %a6 = call i8* @llvm.ptr.annotation.p0i8(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   call void @llvm.var.annotation(i8* undef, i8* undef, i8* undef, i32 undef, i8* undef)
   ret i32 undef
 }
 
 declare i32 @llvm.annotation.i32(i32, i8*, i8*, i32)
 declare void @llvm.assume(i1)
+declare void @llvm.experimental.noalias.scope.decl(metadata)
 declare void @llvm.sideeffect()
 declare void @llvm.dbg.declare(metadata, metadata, metadata)
 declare void @llvm.dbg.value(metadata, i64, metadata, metadata)
 declare void @llvm.dbg.label(metadata)
 declare {}* @llvm.invariant.start.p0i8(i64, i8*)
 declare void @llvm.invariant.end.p0i8({}*, i64, i8*)
 declare i8* @llvm.launder.invariant.group.p0i8(i8*)
 declare i8* @llvm.strip.invariant.group.p0i8(i8*)
 declare i1 @llvm.is.constant.i32(i32)
 declare void @llvm.lifetime.start.p0i8(i64, i8*)
 declare void @llvm.lifetime.end.p0i8(i64, i8*)
 declare i64 @llvm.objectsize.i64.p0i8(i8*, i1, i1, i1)
 declare i8* @llvm.ptr.annotation.p0i8(i8*, i8*, i8*, i32, i8*)
 declare void @llvm.var.annotation(i8*, i8*, i8*, i32, i8*)
 
 
 !0 = !DILocalVariable(scope: !1)
 !1 = distinct !DISubprogram(name: "dummy", line: 79, isLocal: true, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: true)
 !2 = !DILabel(scope: !1, name: "label", file: !3, line: 7)
 !3 = !DIFile(filename: "debug-label.c", directory: "./")
+!4 = !{ !4 }
+!5 = distinct !{ !5, !6, !"foo: var" }
+!6 = distinct !{ !6, !"foo" }

llvm/test/Analysis/MemorySSA/noalias-scope-decl.ll

+; RUN: opt -basic-aa -memoryssa -enable-new-pm=0 -analyze < %s 2>&1 | FileCheck %s
+; RUN: opt -aa-pipeline=basic-aa -passes='print<memoryssa>,verify<memoryssa>' -disable-output < %s 2>&1 | FileCheck %s
+;
+; Ensures that llvm.experimental.noalias.scope.decl is treated as not reading or writing memory.
+
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+define i32 @foo(i32* %a, i32* %b, i1 %c) {
+; CHECK: 1 = MemoryDef(liveOnEntry)
+; CHECK-NEXT: store i32 4
+  store i32 4, i32* %a, align 4
+; CHECK-NOT: MemoryDef
+; CHECK: call void @llvm.experimental.noalias.scope.decl
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK: MemoryUse(1)
+; CHECK-NEXT: %1 = load i32
+  %1 = load i32, i32* %a, align 4
+  ret i32 %1
+}
+
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2, !"foo: var" }
+!2 = distinct !{ !2, !"foo" }

llvm/test/Transforms/EarlyCSE/noalias-scope-decl.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S < %s -early-cse -earlycse-debug-hash | FileCheck %s
+
+; Store-to-load forwarding across a @llvm.experimental.noalias.scope.decl.
+
+define float @s2l(float* %p) {
+; CHECK-LABEL: @s2l(
+; CHECK-NEXT:    store float 0.000000e+00, float* [[P:%.*]], align 4
+; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK-NEXT:    ret float 0.000000e+00
+;
+  store float 0.0, float* %p
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  %t = load float, float* %p
+  ret float %t
+}
+
+; Redundant load elimination across a @llvm.experimental.noalias.scope.decl.
+
+define float @rle(float* %p) {
+; CHECK-LABEL: @rle(
+; CHECK-NEXT:    [[R:%.*]] = load float, float* [[P:%.*]], align 4
+; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK-NEXT:    [[T:%.*]] = fadd float [[R]], [[R]]
+; CHECK-NEXT:    ret float [[T]]
+;
+  %r = load float, float* %p
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  %s = load float, float* %p
+  %t = fadd float %r, %s
+  ret float %t
+}
+
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2 }
+!2 = distinct !{ !2 }

llvm/test/Transforms/LoopVectorize/noalias-scope-decl.ll

+; RUN: opt < %s  -loop-vectorize -force-vector-width=4 -force-vector-interleave=2  -S | FileCheck %s
+
+define void @test1(float* noalias nocapture %a, float* noalias nocapture readonly %b) {
+entry:
+  br label %for.body
+
+; CHECK-LABEL: @test1
+; CHECK: vector.body:
+; CHECK: @llvm.experimental.noalias.scope.decl
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK: for.body:
+; CHECK: @llvm.experimental.noalias.scope.decl
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK: ret void
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv
+  %0 = load float, float* %arrayidx, align 4
+  %cmp1 = fcmp ogt float %0, 1.000000e+02
+  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  %add = fadd float %0, 1.000000e+00
+  %arrayidx5 = getelementptr inbounds float, float* %a, i64 %indvars.iv
+  store float %add, float* %arrayidx5, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv, 1599
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+%struct.data = type { float*, float* }
+
+define void @test2(%struct.data* nocapture readonly %d) {
+entry:
+  %b = getelementptr inbounds %struct.data, %struct.data* %d, i64 0, i32 1
+  %0 = load float*, float** %b, align 8
+  %ptrint = ptrtoint float* %0 to i64
+  %maskedptr = and i64 %ptrint, 31
+  %maskcond = icmp eq i64 %maskedptr, 0
+  %a = getelementptr inbounds %struct.data, %struct.data* %d, i64 0, i32 0
+  %1 = load float*, float** %a, align 8
+  %ptrint2 = ptrtoint float* %1 to i64
+  %maskedptr3 = and i64 %ptrint2, 31
+  %maskcond4 = icmp eq i64 %maskedptr3, 0
+  br label %for.body
+
+; CHECK-LABEL: @test2
+; CHECK: vector.body:
+; CHECK: @llvm.experimental.noalias.scope.decl(metadata [[SCOPE0_LIST:!.*]])
+; CHECK: @llvm.experimental.noalias.scope.decl(metadata [[SCOPE4_LIST:!.*]])
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK: for.body:
+; CHECK: @llvm.experimental.noalias.scope.decl(metadata [[SCOPE0_LIST]])
+; CHECK: @llvm.experimental.noalias.scope.decl(metadata [[SCOPE4_LIST]])
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK: ret void
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  %arrayidx = getelementptr inbounds float, float* %0, i64 %indvars.iv
+  %2 = load float, float* %arrayidx, align 4
+  %add = fadd float %2, 1.000000e+00
+  tail call void @llvm.experimental.noalias.scope.decl(metadata !4)
+  %arrayidx5 = getelementptr inbounds float, float* %1, i64 %indvars.iv
+  store float %add, float* %arrayidx5, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv, 1599
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @predicated_noalias_scope_decl(float* noalias nocapture readonly %a, float* noalias nocapture %b, i32 %n) {
+
+; Check that the vector.body still contains a llvm.experimental.noalias.scope.decl
+
+; CHECK-LABEL: @predicated_noalias_scope_decl(
+; CHECK:   vector.body:
+; CHECK:   call void @llvm.experimental.noalias.scope.decl
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK:   scalar.ph:
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK:   if.else:
+; CHECK:   call void @llvm.experimental.noalias.scope.decl
+; CHECK-NOT: @llvm.experimental.noalias.scope.decl
+; CHECK: }
+
+entry:
+  %cmp15 = icmp eq i32 %n, 0
+  br i1 %cmp15, label %for.cond.cleanup, label %for.body.preheader
+
+for.body.preheader:                               ; preds = %entry
+  %0 = zext i32 %n to i64
+  br label %for.body
+
+for.cond.cleanup.loopexit:                        ; preds = %if.end5
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  ret void
+
+for.body:                                         ; preds = %for.body.preheader, %if.end5
+  %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %if.end5 ]
+  %cmp1 = icmp ult i64 %indvars.iv, 495616
+  br i1 %cmp1, label %if.end5, label %if.else
+
+if.else:                                          ; preds = %for.body
+  %cmp2 = icmp ult i64 %indvars.iv, 991232
+  tail call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  br label %if.end5
+
+if.end5:                                          ; preds = %for.body, %if.else
+  %x.0 = phi float [ 4.200000e+01, %if.else ], [ 2.300000e+01, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %a, i64 %indvars.iv
+  %1 = load float, float* %arrayidx, align 4
+  %mul = fmul float %x.0, %1
+  %arrayidx7 = getelementptr inbounds float, float* %b, i64 %indvars.iv
+  store float %mul, float* %arrayidx7, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %cmp = icmp eq i64 %indvars.iv.next, %0
+  br i1 %cmp, label %for.cond.cleanup.loopexit, label %for.body
+}
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2 }
+!2 = distinct !{ !2 }
+!3 = distinct !{ !3, !2 }
+!4 = !{ !3 }
+
+; CHECK: [[SCOPE0_LIST]] = !{[[SCOPE0:!.*]]}
+; CHECK: [[SCOPE0]] = distinct !{[[SCOPE0]], [[SCOPE0_DOM:!.*]]}
+; CHECK: [[SCOPE0_DOM]] = distinct !{[[SCOPE0_DOM]]}
+; CHECK: [[SCOPE4_LIST]] = !{[[SCOPE4:!.*]]}
+; CHECK: [[SCOPE4]] = distinct !{[[SCOPE4]], [[SCOPE0_DOM]]}