Index: llvm/lib/Transforms/Scalar/InstSimplifyPass.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/InstSimplifyPass.cpp
+++ llvm/lib/Transforms/Scalar/InstSimplifyPass.cpp
@@ -17,6 +17,9 @@
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/Function.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/Metadata.h"
 #include "llvm/IR/Type.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
@@ -30,8 +33,61 @@
 
 STATISTIC(NumSimplified, "Number of redundant instructions removed");
 
+// @llvm.experimental.noalias.scope.decl calls declaring a scope that is never
+// used by !alias.scope metadata can be omitted.
+class NoAliasScopeDeclCleaner {
+  SmallVector<IntrinsicInst *, 8> NoAliasScopeDecls;
+  SmallPtrSet<const MDNode *, 8> UsedAliasScopes;
+  bool Handled = false;
+
+public:
+  void analyse(Instruction &I) {
+    if (Handled)
+      return;
+
+    if (auto *II = dyn_cast<IntrinsicInst>(&I))
+      if (II->getIntrinsicID() == Intrinsic::experimental_noalias_scope_decl)
+        NoAliasScopeDecls.push_back(II);
+
+    rememberUsedAliasScopes(I);
+  }
+
+  bool removeDead() {
+    if (Handled)
+      return false;
+
+    bool Changed = false;
+    for (auto *NSD : NoAliasScopeDecls) {
+      auto *MV = cast<MetadataAsValue>(
+          NSD->getOperand(Intrinsic::NoAliasScopeDeclScopeArg));
+      const MDNode *MD = cast<MDNode>(MV->getMetadata());
+      assert(MD->getNumOperands() == 1 &&
+             "llvm.experimental.noalias.scope should refer to a single scope");
+      auto &MDOperand = MD->getOperand(0);
+      if (auto *MD = dyn_cast<MDNode>(MDOperand))
+        if (!UsedAliasScopes.contains(MD)) {
+          assert(NSD->use_empty() &&
+                 "llvm.experimental.noalias.scope.decl still in use ?");
+          NSD->eraseFromParent();
+          Changed = true;
+        }
+    }
+    Handled = true;
+    return Changed;
+  }
+
+private:
+  void rememberUsedAliasScopes(Instruction &I) {
+    if (auto *MD = I.getMetadata(LLVMContext::MD_alias_scope))
+      for (auto &MDOperand : cast<MDNode>(MD)->operands())
+        if (auto *MDScope = dyn_cast<MDNode>(MDOperand))
+          UsedAliasScopes.insert(MDScope);
+  }
+};
+
 static bool runImpl(Function &F, const SimplifyQuery &SQ,
                     OptimizationRemarkEmitter *ORE) {
+  NoAliasScopeDeclCleaner NSDCleaner;
   SmallPtrSet<const Instruction *, 8> S1, S2, *ToSimplify = &S1, *Next = &S2;
   bool Changed = false;
 
@@ -54,7 +110,10 @@
         if (isInstructionTriviallyDead(&I)) {
           DeadInstsInBB.push_back(&I);
           Changed = true;
-        } else if (!I.use_empty()) {
+          continue;
+        }
+        NSDCleaner.analyse(I);
+        if (!I.use_empty()) {
           if (Value *V = SimplifyInstruction(&I, SQ, ORE)) {
             // Mark all uses for resimplification next time round the loop.
             for (User *U : I.users())
@@ -71,6 +130,9 @@
       RecursivelyDeleteTriviallyDeadInstructions(DeadInstsInBB, SQ.TLI);
     }
 
+    if (NSDCleaner.removeDead())
+      Changed = true;
+
     // Place the list of instructions to simplify on the next loop iteration
     // into ToSimplify.
     std::swap(ToSimplify, Next);
Index: llvm/test/Transforms/Coroutines/coro-retcon-resume-values.ll
===================================================================
--- llvm/test/Transforms/Coroutines/coro-retcon-resume-values.ll
+++ llvm/test/Transforms/Coroutines/coro-retcon-resume-values.ll
@@ -68,9 +68,7 @@
 ; CHECK:         [[BUFFER:%.*]] = alloca [8 x i8], align 4
 ; CHECK:         [[SLOT:%.*]] = bitcast [8 x i8]* [[BUFFER]] to i32*
 ; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl
-; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT:    store i32 7, i32* [[SLOT]], align 4
-; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT:    call void @print(i32 7)
 ; CHECK-NEXT:    ret i32 0
 
Index: llvm/test/Transforms/Coroutines/coro-retcon-value.ll
===================================================================
--- llvm/test/Transforms/Coroutines/coro-retcon-value.ll
+++ llvm/test/Transforms/Coroutines/coro-retcon-value.ll
@@ -89,7 +89,6 @@
 ; CHECK-NEXT:    [[INC:%.*]] = add i32 [[LOAD]], 1
 ; CHECK-NEXT:    store i32 [[INC]], i32* [[SLOT]], align 4
 ; CHECK-NEXT:    call void @print(i32 [[INC]])
-; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT:    ret i32 0
 
 declare token @llvm.coro.id.retcon(i32, i32, i8*, i8*, i8*, i8*)
Index: llvm/test/Transforms/Coroutines/coro-retcon.ll
===================================================================
--- llvm/test/Transforms/Coroutines/coro-retcon.ll
+++ llvm/test/Transforms/Coroutines/coro-retcon.ll
@@ -78,7 +78,6 @@
 ; CHECK-NEXT:    [[LOAD:%.*]] = load i32, i32* [[SLOT]], align 4
 ; CHECK-NEXT:    [[INC:%.*]] = add i32 [[LOAD]], 1
 ; CHECK-NEXT:    call void @print(i32 [[INC]])
-; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT:    ret i32 0
 
 define hidden { i8*, i8* } @g(i8* %buffer, i16* %ptr) {
Index: llvm/test/Transforms/Coroutines/ex2.ll
===================================================================
--- llvm/test/Transforms/Coroutines/ex2.ll
+++ llvm/test/Transforms/Coroutines/ex2.ll
@@ -49,9 +49,7 @@
   ret i32 0
 ; CHECK-NOT:  call i8* @CustomAlloc
 ; CHECK:      call void @print(i32 4)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 5)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 6)
 ; CHECK-NEXT: ret i32 0
 }
Index: llvm/test/Transforms/Coroutines/ex3.ll
===================================================================
--- llvm/test/Transforms/Coroutines/ex3.ll
+++ llvm/test/Transforms/Coroutines/ex3.ll
@@ -53,9 +53,7 @@
   ret i32 0
 ; CHECK-NOT:  i8* @malloc
 ; CHECK:      call void @print(i32 4)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 -5)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 5)
 ; CHECK:      ret i32 0
 }
Index: llvm/test/Transforms/Coroutines/ex4.ll
===================================================================
--- llvm/test/Transforms/Coroutines/ex4.ll
+++ llvm/test/Transforms/Coroutines/ex4.ll
@@ -50,9 +50,7 @@
   call void @llvm.coro.destroy(i8* %hdl)
   ret i32 0
 ; CHECK:      call void @print(i32 4)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 5)
-; CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl
 ; CHECK-NEXT: call void @print(i32 6)
 ; CHECK:      ret i32 0
 }
Index: llvm/test/Transforms/InstSimplify/noalias-scope-decl.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/InstSimplify/noalias-scope-decl.ll
@@ -0,0 +1,83 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -instsimplify -S < %s | FileCheck %s
+
+define void @test01(i8* %ptr) {
+; CHECK-LABEL: @test01(
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr
+  ret void
+}
+
+define void @test02(i8* %ptr) {
+; CHECK-LABEL: @test02(
+; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !alias.scope !0
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !alias.scope !0
+  ret void
+}
+
+define void @test03(i8* %ptr) {
+; CHECK-LABEL: @test03(
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !alias.scope !3
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !alias.scope !4
+  ret void
+}
+
+define void @test04(i8* %ptr) {
+; CHECK-LABEL: @test04(
+; CHECK-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata !0)
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !alias.scope !4
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !alias.scope !5
+  ret void
+}
+
+define void @test11(i8* %ptr) {
+; CHECK-LABEL: @test11(
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !noalias !0
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !noalias !0
+  ret void
+}
+
+define void @test12(i8* %ptr) {
+; CHECK-LABEL: @test12(
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !noalias !3
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !noalias !4
+  ret void
+}
+
+define void @test13(i8* %ptr) {
+; CHECK-LABEL: @test13(
+; CHECK-NEXT:    store i8 42, i8* [[PTR:%.*]], align 1, !noalias !4
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.experimental.noalias.scope.decl(metadata !0)
+  store i8 42, i8* %ptr, !noalias !5
+  ret void
+}
+
+declare void @llvm.experimental.noalias.scope.decl(metadata)
+
+!0 = !{ !1 }
+!1 = distinct !{ !1, !2 }
+!2 = distinct !{ !2 }
+!3 = !{ !4 }
+!4 = distinct !{ !4, !2 }
+!5 = !{ !1, !4 }
Index: llvm/test/Transforms/PhaseOrdering/inlining-alignment-assumptions.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/inlining-alignment-assumptions.ll
+++ llvm/test/Transforms/PhaseOrdering/inlining-alignment-assumptions.ll
@@ -95,7 +95,6 @@
 
 define amdgpu_kernel void @caller2() {
 ; CHECK-LABEL: @caller2(
-; CHECK-NEXT:    tail call void @llvm.experimental.noalias.scope.decl([[META0:metadata !.*]])
 ; CHECK-NEXT:    ret void
 ;
   %alloca = alloca i64, align 8, addrspace(5)
Index: llvm/test/Transforms/PhaseOrdering/instcombine-sroa-inttoptr.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/instcombine-sroa-inttoptr.ll
+++ llvm/test/Transforms/PhaseOrdering/instcombine-sroa-inttoptr.ll
@@ -70,7 +70,6 @@
 ; CHECK-NEXT:    [[I2:%.*]] = alloca [[TMP0:%.*]], align 8
 ; CHECK-NEXT:    [[I1_SROA_0_0_I5_SROA_IDX:%.*]] = getelementptr inbounds [[TMP0]], %0* [[ARG:%.*]], i64 0, i32 0
 ; CHECK-NEXT:    [[I1_SROA_0_0_COPYLOAD:%.*]] = load i32*, i32** [[I1_SROA_0_0_I5_SROA_IDX]], align 8
-; CHECK-NEXT:    tail call void @llvm.experimental.noalias.scope.decl([[META0:metadata !.*]])
 ; CHECK-NEXT:    [[I_SROA_0_0_I6_SROA_IDX:%.*]] = getelementptr inbounds [[TMP0]], %0* [[I2]], i64 0, i32 0
 ; CHECK-NEXT:    store i32* [[I1_SROA_0_0_COPYLOAD]], i32** [[I_SROA_0_0_I6_SROA_IDX]], align 8
 ; CHECK-NEXT:    tail call void @_Z7escape01S(%0* nonnull byval(%0) align 8 [[I2]])
@@ -110,7 +109,6 @@
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    [[I1_SROA_0_0_I4_SROA_IDX:%.*]] = getelementptr inbounds [[TMP0:%.*]], %0* [[ARG:%.*]], i64 0, i32 0
 ; CHECK-NEXT:    [[I1_SROA_0_0_COPYLOAD:%.*]] = load i32*, i32** [[I1_SROA_0_0_I4_SROA_IDX]], align 8
-; CHECK-NEXT:    tail call void @llvm.experimental.noalias.scope.decl([[META3:metadata !.*]])
 ; CHECK-NEXT:    [[I5:%.*]] = tail call i32 @_Z4condv()
 ; CHECK-NEXT:    [[I6_NOT:%.*]] = icmp eq i32 [[I5]], 0
 ; CHECK-NEXT:    br i1 [[I6_NOT]], label [[BB10:%.*]], label [[BB7:%.*]]