[clang] [TBAA] Emit distinct TBAA tags for pointers with different depths,types. (PR #76612)

Florian Hahn via cfe-commits cfe-commits at lists.llvm.org
Wed Jun 26 01:49:43 PDT 2024


https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/76612

>From 95973d30888eace1eece31aa82a5dd5986c22af8 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Sat, 30 Dec 2023 10:39:58 +0000
Subject: [PATCH] [TBAA] Emit distinct TBAA tags for pointers with different
 depths,types.

This patch extends Clang's TBAA generation code to emit distinct tags
for incompatible pointer types.

Pointers with different element types are incompatible if the pointee
types are also incompatible (modulo sugar/modifiers).

Express this in TBAA by generating different tags for pointers based
on the pointer depth and pointee type. To get the TBAA tag for the
pointee type it uses getTypeInfoHelper on the pointee type.

(Moved from https://reviews.llvm.org/D122573)
---
 clang/include/clang/Basic/CodeGenOptions.def  |   1 +
 clang/include/clang/Driver/Options.td         |   5 +
 clang/lib/CodeGen/CodeGenTBAA.cpp             |  31 +-
 clang/lib/Driver/ToolChains/Clang.cpp         |   3 +
 clang/test/CXX/drs/cwg158.cpp                 |  53 +-
 .../CodeGen/sanitize-metadata-nosanitize.c    |  61 +-
 clang/test/CodeGen/tbaa-pointers.c            | 167 ++++--
 .../attr-likelihood-iteration-stmt.cpp        | 132 ++---
 .../CodeGenOpenCL/amdgpu-enqueue-kernel.cl    | 258 ++++----
 ...arallel_reduction_codegen_tbaa_PR46146.cpp | 556 +++++++++---------
 clang/unittests/CodeGen/TBAAMetadataTest.cpp  |  36 +-
 11 files changed, 712 insertions(+), 591 deletions(-)

diff --git a/clang/include/clang/Basic/CodeGenOptions.def b/clang/include/clang/Basic/CodeGenOptions.def
index e3f6da4a84f69..43c23a3ca6c12 100644
--- a/clang/include/clang/Basic/CodeGenOptions.def
+++ b/clang/include/clang/Basic/CodeGenOptions.def
@@ -231,6 +231,7 @@ ENUM_CODEGENOPT(StructReturnConvention, StructReturnConventionKind, 2, SRCK_Defa
 
 CODEGENOPT(RelaxAll          , 1, 0) ///< Relax all machine code instructions.
 CODEGENOPT(RelaxedAliasing   , 1, 0) ///< Set when -fno-strict-aliasing is enabled.
+CODEGENOPT(RelaxedPointerAliasing   , 1, 0) ///< Set when -fno-pointer-tbaa is enabled.
 CODEGENOPT(StructPathTBAA    , 1, 0) ///< Whether or not to use struct-path TBAA.
 CODEGENOPT(NewStructPathTBAA , 1, 0) ///< Whether or not to use enhanced struct-path TBAA.
 CODEGENOPT(SaveTempLabels    , 1, 0) ///< Save temporary labels.
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index dd55838dcf384..be5db054c7750 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -3378,6 +3378,7 @@ def fstruct_path_tbaa : Flag<["-"], "fstruct-path-tbaa">, Group<f_Group>;
 def fno_struct_path_tbaa : Flag<["-"], "fno-struct-path-tbaa">, Group<f_Group>;
 def fno_strict_enums : Flag<["-"], "fno-strict-enums">, Group<f_Group>;
 def fno_strict_overflow : Flag<["-"], "fno-strict-overflow">, Group<f_Group>;
+def fno_pointer_tbaa : Flag<["-"], "fno-pointer-tbaa">, Group<f_Group>;
 def fno_temp_file : Flag<["-"], "fno-temp-file">, Group<f_Group>,
   Visibility<[ClangOption, CC1Option, CLOption, DXCOption]>, HelpText<
   "Directly create compilation output files. This may lead to incorrect incremental builds if the compiler crashes">,
@@ -3877,6 +3878,7 @@ defm strict_vtable_pointers : BoolFOption<"strict-vtable-pointers",
             " overwriting polymorphic C++ objects">,
   NegFlag<SetFalse>>;
 def fstrict_overflow : Flag<["-"], "fstrict-overflow">, Group<f_Group>;
+def fpointer_tbaa : Flag<["-"], "fpointer-tbaa">, Group<f_Group>;
 def fdriver_only : Flag<["-"], "fdriver-only">, Flags<[NoXarchOption]>,
   Visibility<[ClangOption, CLOption, DXCOption]>,
   Group<Action_Group>, HelpText<"Only run the driver.">;
@@ -7112,6 +7114,9 @@ def fuse_register_sized_bitfield_access: Flag<["-"], "fuse-register-sized-bitfie
 def relaxed_aliasing : Flag<["-"], "relaxed-aliasing">,
   HelpText<"Turn off Type Based Alias Analysis">,
   MarshallingInfoFlag<CodeGenOpts<"RelaxedAliasing">>;
+def relaxed_pointer_aliasing : Flag<["-"], "relaxed-pointer-aliasing">,
+  HelpText<"Turn off Type Based Alias Analysis for pointer accesses">,
+  MarshallingInfoFlag<CodeGenOpts<"RelaxedPointerAliasing">>;
 def no_struct_path_tbaa : Flag<["-"], "no-struct-path-tbaa">,
   HelpText<"Turn off struct-path aware Type Based Alias Analysis">,
   MarshallingInfoNegativeFlag<CodeGenOpts<"StructPathTBAA">>;
diff --git a/clang/lib/CodeGen/CodeGenTBAA.cpp b/clang/lib/CodeGen/CodeGenTBAA.cpp
index 284421f494711..0977561903f63 100644
--- a/clang/lib/CodeGen/CodeGenTBAA.cpp
+++ b/clang/lib/CodeGen/CodeGenTBAA.cpp
@@ -185,10 +185,33 @@ llvm::MDNode *CodeGenTBAA::getTypeInfoHelper(const Type *Ty) {
     return getChar();
 
   // Handle pointers and references.
-  // TODO: Implement C++'s type "similarity" and consider dis-"similar"
-  // pointers distinct.
-  if (Ty->isPointerType() || Ty->isReferenceType())
-    return createScalarTypeNode("any pointer", getChar(), Size);
+  if (Ty->isPointerType() || Ty->isReferenceType()) {
+    llvm::MDNode *AnyPtr = createScalarTypeNode("any pointer", getChar(), Size);
+    if (CodeGenOpts.RelaxedPointerAliasing)
+      return AnyPtr;
+    // Compute the depth of the pointer and generate a tag of the form "p<depth>
+    // <base type tag>".
+    unsigned PtrDepth = 0;
+    do {
+      PtrDepth++;
+      Ty = Ty->getPointeeType().getTypePtr();
+    } while (Ty->isPointerType() || Ty->isReferenceType());
+    // TODO: Implement C++'s type "similarity" and consider dis-"similar"
+    // pointers distinct for non-builtin types.
+    if (isa<BuiltinType>(Ty)) {
+      llvm::MDNode *ScalarMD = getTypeInfoHelper(Ty);
+      StringRef Name =
+          cast<llvm::MDString>(
+              ScalarMD->getOperand(CodeGenOpts.NewStructPathTBAA ? 2 : 0))
+              ->getString();
+      SmallString<256> OutName("p");
+      OutName += std::to_string(PtrDepth);
+      OutName += " ";
+      OutName += Name;
+      return createScalarTypeNode(OutName, AnyPtr, Size);
+    }
+    return AnyPtr;
+  }
 
   // Accesses to arrays are accesses to objects of their element types.
   if (CodeGenOpts.NewStructPathTBAA && Ty->isArrayType())
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index c0f6bc0c2e45a..8186070f9f0f5 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5707,6 +5707,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   if (!Args.hasFlag(options::OPT_fstrict_aliasing, StrictAliasingAliasOption,
                     options::OPT_fno_strict_aliasing, !IsWindowsMSVC))
     CmdArgs.push_back("-relaxed-aliasing");
+  if (!Args.hasFlag(options::OPT_fpointer_tbaa, options::OPT_fno_pointer_tbaa,
+                    true))
+    CmdArgs.push_back("-relaxed-pointer-aliasing");
   if (!Args.hasFlag(options::OPT_fstruct_path_tbaa,
                     options::OPT_fno_struct_path_tbaa, true))
     CmdArgs.push_back("-no-struct-path-tbaa");
diff --git a/clang/test/CXX/drs/cwg158.cpp b/clang/test/CXX/drs/cwg158.cpp
index 9301c790297e9..b72336f795d7a 100644
--- a/clang/test/CXX/drs/cwg158.cpp
+++ b/clang/test/CXX/drs/cwg158.cpp
@@ -1,3 +1,4 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
 // RUN: %clang_cc1 -triple x86_64-linux -std=c++98 %s -O3 -disable-llvm-passes -pedantic-errors -emit-llvm -o - | FileCheck %s
 // RUN: %clang_cc1 -triple x86_64-linux -std=c++11 %s -O3 -disable-llvm-passes -pedantic-errors -emit-llvm -o - | FileCheck %s
 // RUN: %clang_cc1 -triple x86_64-linux -std=c++14 %s -O3 -disable-llvm-passes -pedantic-errors -emit-llvm -o - | FileCheck %s
@@ -5,23 +6,63 @@
 
 // cwg158: yes
 
-// CHECK-LABEL: define {{.*}} @_Z1f
+// CHECK-LABEL: define dso_local noundef ptr @_Z1fPKPKiPPi(
+// CHECK-SAME: ptr noundef [[P:%.*]], ptr noundef [[Q:%.*]]) #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[P_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[Q_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[X:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    store ptr [[P]], ptr [[P_ADDR]], align 8, !tbaa [[TBAA2:![0-9]+]]
+// CHECK-NEXT:    store ptr [[Q]], ptr [[Q_ADDR]], align 8, !tbaa [[TBAA2]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[X]]) #[[ATTR2:[0-9]+]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[P_ADDR]], align 8, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[TMP0]], align 8, !tbaa [[TBAA7:![0-9]+]]
+// CHECK-NEXT:    store ptr [[TMP1]], ptr [[X]], align 8, !tbaa [[TBAA7]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[Q_ADDR]], align 8, !tbaa [[TBAA2]]
+// CHECK-NEXT:    store ptr null, ptr [[TMP2]], align 8, !tbaa [[TBAA7]]
+// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[X]], align 8, !tbaa [[TBAA7]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[X]]) #[[ATTR2]]
+// CHECK-NEXT:    ret ptr [[TMP3]]
+//
 const int *f(const int * const *p, int **q) {
-  // CHECK: load ptr, {{.*}}, !tbaa ![[INTPTR_TBAA:[^,]*]]
   const int *x = *p;
-  // CHECK: store ptr null, {{.*}}, !tbaa ![[INTPTR_TBAA]]
   *q = 0;
   return x;
 }
 
 struct A {};
 
-// CHECK-LABEL: define {{.*}} @_Z1g
+// CHECK-LABEL: define dso_local noundef ptr @_Z1gPPKM1AA3_PKiPPMS_A3_Pi(
+// CHECK-SAME: ptr noundef [[P:%.*]], ptr noundef [[Q:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[P_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[Q_ADDR:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    [[X:%.*]] = alloca ptr, align 8
+// CHECK-NEXT:    store ptr [[P]], ptr [[P_ADDR]], align 8, !tbaa [[TBAA9:![0-9]+]]
+// CHECK-NEXT:    store ptr [[Q]], ptr [[Q_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[X]]) #[[ATTR2]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[P_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[TMP0]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    store ptr [[TMP1]], ptr [[X]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[Q_ADDR]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    store ptr null, ptr [[TMP2]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[X]], align 8, !tbaa [[TBAA9]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[X]]) #[[ATTR2]]
+// CHECK-NEXT:    ret ptr [[TMP3]]
+//
 const int *(A::*const *g(const int *(A::* const **p)[3], int *(A::***q)[3]))[3] {
-  // CHECK: load ptr, {{.*}}, !tbaa ![[MEMPTR_TBAA:[^,]*]]
   const int *(A::*const *x)[3] = *p;
-  // CHECK: store ptr null, {{.*}}, !tbaa ![[MEMPTR_TBAA]]
   *q = 0;
   return x;
 }
 
+//.
+// CHECK: [[TBAA2]] = !{[[META3:![0-9]+]], [[META3]], i64 0}
+// CHECK: [[META3]] = !{!"p2 int", [[META4:![0-9]+]], i64 0}
+// CHECK: [[META4]] = !{!"any pointer", [[META5:![0-9]+]], i64 0}
+// CHECK: [[META5]] = !{!"omnipotent char", [[META6:![0-9]+]], i64 0}
+// CHECK: [[META6]] = !{!"Simple C++ TBAA"}
+// CHECK: [[TBAA7]] = !{[[META8:![0-9]+]], [[META8]], i64 0}
+// CHECK: [[META8]] = !{!"p1 int", [[META4]], i64 0}
+// CHECK: [[TBAA9]] = !{[[META4]], [[META4]], i64 0}
+//.
diff --git a/clang/test/CodeGen/sanitize-metadata-nosanitize.c b/clang/test/CodeGen/sanitize-metadata-nosanitize.c
index 6414956fb6796..c80bbeb7f4ea9 100644
--- a/clang/test/CodeGen/sanitize-metadata-nosanitize.c
+++ b/clang/test/CodeGen/sanitize-metadata-nosanitize.c
@@ -12,7 +12,7 @@
 //.
 // CHECK: Function Attrs: mustprogress nofree noinline norecurse nosync nounwind willreturn memory(write, argmem: none, inaccessiblemem: none)
 // CHECK-LABEL: define dso_local void @escape
-// CHECK-SAME: (ptr noundef [[P:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] !pcsections !2 {
+// CHECK-SAME: (ptr noundef [[P:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] !pcsections [[META2:![0-9]+]] {
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    ret void
 //
@@ -23,13 +23,13 @@ __attribute__((noinline, not_tail_called)) void escape(const volatile void *p) {
 
 // CHECK: Function Attrs: mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none)
 // CHECK-LABEL: define dso_local i32 @normal_function
-// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR1:[0-9]+]] !pcsections !4 {
+// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR1:[0-9]+]] !pcsections [[META4:![0-9]+]] {
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
 // CHECK-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8, !tbaa [[TBAA6:![0-9]+]]
-// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections !10
+// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections [[META11:![0-9]+]]
 // CHECK-NEXT:    notail call void @escape(ptr noundef nonnull [[X_ADDR]])
-// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA11:![0-9]+]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA12:![0-9]+]]
 // CHECK-NEXT:    ret i32 [[TMP0]]
 //
 int normal_function(int *x, int *y) {
@@ -46,7 +46,7 @@ int normal_function(int *x, int *y) {
 // CHECK-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8, !tbaa [[TBAA6]]
 // CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4
 // CHECK-NEXT:    notail call void @escape(ptr noundef nonnull [[X_ADDR]])
-// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA11]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA12]]
 // CHECK-NEXT:    ret i32 [[TMP0]]
 //
 __attribute__((disable_sanitizer_instrumentation)) int test_disable_sanitize_instrumentation(int *x, int *y) {
@@ -57,13 +57,13 @@ __attribute__((disable_sanitizer_instrumentation)) int test_disable_sanitize_ins
 
 // CHECK: Function Attrs: mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none)
 // CHECK-LABEL: define dso_local i32 @test_no_sanitize_thread
-// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR3:[0-9]+]] !pcsections !13 {
+// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR3:[0-9]+]] !pcsections [[META14:![0-9]+]] {
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
 // CHECK-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8, !tbaa [[TBAA6]]
-// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections !10
+// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections [[META11]]
 // CHECK-NEXT:    notail call void @escape(ptr noundef nonnull [[X_ADDR]])
-// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA11]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA12]]
 // CHECK-NEXT:    ret i32 [[TMP0]]
 //
 __attribute__((no_sanitize("thread"))) int test_no_sanitize_thread(int *x, int *y) {
@@ -74,13 +74,13 @@ __attribute__((no_sanitize("thread"))) int test_no_sanitize_thread(int *x, int *
 
 // CHECK: Function Attrs: mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none)
 // CHECK-LABEL: define dso_local i32 @test_no_sanitize_all
-// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR3]] !pcsections !13 {
+// CHECK-SAME: (ptr noundef [[X:%.*]], ptr nocapture noundef readonly [[Y:%.*]]) local_unnamed_addr #[[ATTR3]] !pcsections [[META14]] {
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[X_ADDR:%.*]] = alloca ptr, align 8
 // CHECK-NEXT:    store ptr [[X]], ptr [[X_ADDR]], align 8, !tbaa [[TBAA6]]
-// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections !10
+// CHECK-NEXT:    store atomic i32 1, ptr [[X]] monotonic, align 4, !pcsections [[META11]]
 // CHECK-NEXT:    notail call void @escape(ptr noundef nonnull [[X_ADDR]])
-// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA11]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[Y]], align 4, !tbaa [[TBAA12]]
 // CHECK-NEXT:    ret i32 [[TMP0]]
 //
 __attribute__((no_sanitize("all"))) int test_no_sanitize_all(int *x, int *y) {
@@ -89,23 +89,26 @@ __attribute__((no_sanitize("all"))) int test_no_sanitize_all(int *x, int *y) {
   return *y;
 }
 //.
-// CHECK: attributes #0 = { mustprogress nofree noinline norecurse nosync nounwind willreturn memory(write, argmem: none, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
-// CHECK: attributes #1 = { mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
-// CHECK: attributes #2 = { disable_sanitizer_instrumentation mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
-// CHECK: attributes #3 = { mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "no_sanitize_thread" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
-// CHECK: attributes #4 = { nounwind "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
+// CHECK: attributes #[[ATTR0]] = { mustprogress nofree noinline norecurse nosync nounwind willreturn memory(write, argmem: none, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
+// CHECK: attributes #[[ATTR1]] = { mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
+// CHECK: attributes #[[ATTR2]] = { disable_sanitizer_instrumentation mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
+// CHECK: attributes #[[ATTR3]] = { mustprogress nofree norecurse nounwind willreturn memory(write, argmem: readwrite, inaccessiblemem: none) "min-legal-vector-width"="0" "no-trapping-math"="true" "no_sanitize_thread" "stack-protector-buffer-size"="8" "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
+// CHECK: attributes #[[ATTR4:[0-9]+]] = { nounwind "target-features"="+cx8,+mmx,+sse,+sse2,+x87" }
 //.
-// CHECK: !2 = !{!"sanmd_covered!C", !3}
-// CHECK: !3 = !{i64 0}
-// CHECK: !4 = !{!"sanmd_covered!C", !5}
-// CHECK: !5 = !{i64 3}
-// CHECK: !6 = !{!7, !7, i64 0}
-// CHECK: !7 = !{!"any pointer", !8, i64 0}
-// CHECK: !8 = !{!"omnipotent char", !9, i64 0}
-// CHECK: !9 = !{!"Simple C/C++ TBAA"}
-// CHECK: !10 = !{!"sanmd_atomics!C"}
-// CHECK: !11 = !{!12, !12, i64 0}
-// CHECK: !12 = !{!"int", !8, i64 0}
-// CHECK: !13 = !{!"sanmd_covered!C", !14}
-// CHECK: !14 = !{i64 2}
+// CHECK: [[META0:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
+// CHECK: [[META1:![0-9]+]] = !{!"{{.*}}clang version {{.*}}"}
+// CHECK: [[META2]] = !{!"sanmd_covered!C", [[META3:![0-9]+]]}
+// CHECK: [[META3]] = !{i64 0}
+// CHECK: [[META4]] = !{!"sanmd_covered!C", [[META5:![0-9]+]]}
+// CHECK: [[META5]] = !{i64 3}
+// CHECK: [[TBAA6]] = !{[[META7:![0-9]+]], [[META7]], i64 0}
+// CHECK: [[META7]] = !{!"p1 int", [[META8:![0-9]+]], i64 0}
+// CHECK: [[META8]] = !{!"any pointer", [[META9:![0-9]+]], i64 0}
+// CHECK: [[META9]] = !{!"omnipotent char", [[META10:![0-9]+]], i64 0}
+// CHECK: [[META10]] = !{!"Simple C/C++ TBAA"}
+// CHECK: [[META11]] = !{!"sanmd_atomics!C"}
+// CHECK: [[TBAA12]] = !{[[META13:![0-9]+]], [[META13]], i64 0}
+// CHECK: [[META13]] = !{!"int", [[META9]], i64 0}
+// CHECK: [[META14]] = !{!"sanmd_covered!C", [[META15:![0-9]+]]}
+// CHECK: [[META15]] = !{i64 2}
 //.
diff --git a/clang/test/CodeGen/tbaa-pointers.c b/clang/test/CodeGen/tbaa-pointers.c
index b9ebe87982001..660a93f3e3529 100644
--- a/clang/test/CodeGen/tbaa-pointers.c
+++ b/clang/test/CodeGen/tbaa-pointers.c
@@ -1,80 +1,107 @@
-// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-passes %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-passes %s -emit-llvm -o - | FileCheck --check-prefixes=COMMON,DEFAULT %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-passes -relaxed-pointer-aliasing %s -emit-llvm -o - | FileCheck --check-prefixes=COMMON,RELAXED %s
 
 void p2unsigned(unsigned **ptr) {
-  // CHECK-LABEL: define void @p2unsigned(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:  %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:  store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0:!.+]]
-  // CHECK-NEXT:  [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:  store ptr null, ptr [[BASE]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:  ret void
+  // COMMON-LABEL: define void @p2unsigned(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:  %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:  store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P2INT_0:!.+]]
+  // DEFAULT-NEXT:  [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P2INT_0]]
+  // DEFAULT-NEXT:  store ptr null, ptr [[BASE]], align 8, !tbaa [[P1INT_0:!.+]]
+  // RELAXED-NEXT:  store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR:!.+]]
+  // RELAXED-NEXT:  [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:  store ptr null, ptr [[BASE]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:  ret void
   //
   *ptr = 0;
 }
 
 void p2unsigned_volatile(unsigned *volatile *ptr) {
-  // CHECK-LABEL: define void @p2unsigned_volatile(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store volatile ptr null, ptr [[BASE]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p2unsigned_volatile(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P2INT_0]]
+  // DEFAULT-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P2INT_0]]
+  // DEFAULT-NEXT:   store volatile ptr null, ptr [[BASE]], align 8, !tbaa [[P1INT_0]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store volatile ptr null, ptr [[BASE]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:   ret void
   //
   *ptr = 0;
 }
 
 void p3int(int ***ptr) {
-  // CHECK-LABEL: define void @p3int(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store ptr null, ptr [[BASE_1]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p3int(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P3INT_0:!.+]]
+  // DEFAULT-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P3INT_0]]
+  // DEFAULT-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[P2INT_0]]
+  // DEFAULT-NEXT:   store ptr null, ptr [[BASE_1]], align 8, !tbaa [[P1INT_0]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store ptr null, ptr [[BASE_1]], align 8, !tbaa [[ANYPTR]]
+
+  // COMMON-NEXT:   ret void
   //
   **ptr = 0;
 }
 
 void p4char(char ****ptr) {
-  // CHECK-LABEL: define void @p4char(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p4char(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0:!.+]]
+  // DEFAULT-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[P3CHAR_0:!.+]]
+  // DEFAULT-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[P2CHAR_0:!.+]]
+  // DEFAULT-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[P1CHAR_0:!.+]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:   ret void
   //
   ***ptr = 0;
 }
 
 void p4char_const1(const char ****ptr) {
-  // CHECK-LABEL: define void @p4char_const1(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p4char_const1(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[P3CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[P2CHAR_0]]
+  // DEFAULT-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[P1CHAR_0]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:   ret void
   //
   ***ptr = 0;
 }
 
 void p4char_const2(const char **const **ptr) {
-  // CHECK-LABEL: define void @p4char_const2(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p4char_const2(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P4CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[P3CHAR_0]]
+  // DEFAULT-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[P2CHAR_0]]
+  // DEFAULT-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[P1CHAR_0]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_0:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_1:%.+]] = load ptr, ptr [[BASE_0]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE_2:%.+]] = load ptr, ptr [[BASE_1]], align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store ptr null, ptr [[BASE_2]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:   ret void
   //
   ***ptr = 0;
 }
@@ -85,19 +112,35 @@ struct S1 {
 };
 
 void p2struct(struct S1 **ptr) {
-  // CHECK-LABEL: define void @p2struct(ptr noundef %ptr)
-  // CHECK-NEXT: entry:
-  // CHECK-NEXT:   %ptr.addr = alloca ptr, align 8
-  // CHECK-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   store ptr null, ptr [[BASE]], align 8, !tbaa [[ANY_POINTER_0]]
-  // CHECK-NEXT:   ret void
+  // COMMON-LABEL: define void @p2struct(ptr noundef %ptr)
+  // COMMON-NEXT: entry:
+  // COMMON-NEXT:   %ptr.addr = alloca ptr, align 8
+  // DEFAULT-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[P2S1_0:!.+]]
+  // DEFAULT-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[P2S1_0]]
+  // DEFAULT-NEXT:   store ptr null, ptr [[BASE]], align 8, !tbaa [[P1S1_:!.+]]
+  // RELAXED-NEXT:   store ptr %ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   [[BASE:%.+]] = load ptr, ptr %ptr.addr, align 8, !tbaa [[ANYPTR]]
+  // RELAXED-NEXT:   store ptr null, ptr [[BASE]], align 8, !tbaa [[ANYPTR]]
+  // COMMON-NEXT:   ret void
   //
   *ptr = 0;
 }
 
-// CHECK: [[ANY_POINTER_0]] = !{[[ANY_POINTER:!.+]], [[ANY_POINTER]], i64 0}
-// CHECK: [[ANY_POINTER]] = !{!"any pointer", [[CHAR:!.+]], i64 0}
-// CHECK: [[CHAR]] = !{!"omnipotent char", [[TBAA_ROOT:!.+]], i64 0}
-// CHECK: [[TBAA_ROOT]] = !{!"Simple C/C++ TBAA"}
-//
+// DEFAULT: [[P2INT_0]] = !{[[P2INT:!.+]], [[P2INT]], i64 0}
+// DEFAULT: [[P2INT]] = !{!"p2 int", [[ANY_POINTER:!.+]], i64 0}
+// RELAXED: [[ANYPTR]] = !{[[ANY_POINTER:!.+]], [[ANY_POINTER]], i64 0}
+// COMMON: [[ANY_POINTER]] = !{!"any pointer", [[CHAR:!.+]], i64 0}
+// COMMON: [[CHAR]] = !{!"omnipotent char", [[TBAA_ROOT:!.+]], i64 0}
+// COMMON: [[TBAA_ROOT]] = !{!"Simple C/C++ TBAA"}
+// DEFAULT: [[P1INT_0]] = !{[[P1INT:!.+]], [[P1INT]], i64 0}
+// DEFAULT: [[P1INT]] = !{!"p1 int", [[ANY_POINTER]], i64 0}
+// DEFAULT: [[P3INT_0]] = !{[[P3INT:!.+]], [[P3INT]], i64 0}
+// DEFAULT: [[P3INT]] = !{!"p3 int", [[ANY_POINTER]], i64 0}
+// DEFAULT: [[P4CHAR_0]] = !{[[P4CHAR:!.+]], [[P4CHAR]], i64 0}
+// DEFAULT: [[P4CHAR]] = !{!"p4 omnipotent char", [[ANY_POINTER]], i64 0}
+// DEFAULT: [[P3CHAR_0]] = !{[[P3CHAR:!.+]], [[P3CHAR]], i64 0}
+// DEFAULT: [[P3CHAR]] = !{!"p3 omnipotent char", [[ANY_POINTER]], i64 0}
+// DEFAULT: [[P2CHAR_0]] = !{[[P2CHAR:!.+]], [[P2CHAR]], i64 0}
+// DEFAULT: [[P2CHAR]] = !{!"p2 omnipotent char", [[ANY_POINTER]], i64 0}
+// DEFAULT: [[P1CHAR_0]] = !{[[P1CHAR:!.+]], [[P1CHAR]], i64 0}
+// DEFAULT: [[P1CHAR]] = !{!"p1 omnipotent char", [[ANY_POINTER]], i64 0}
diff --git a/clang/test/CodeGenCXX/attr-likelihood-iteration-stmt.cpp b/clang/test/CodeGenCXX/attr-likelihood-iteration-stmt.cpp
index 412edd6d3edc0..e842de6335046 100644
--- a/clang/test/CodeGenCXX/attr-likelihood-iteration-stmt.cpp
+++ b/clang/test/CodeGenCXX/attr-likelihood-iteration-stmt.cpp
@@ -68,23 +68,23 @@ void w_branch_elided(unsigned e){
 // CHECK-NEXT:    [[E_ADDR:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    store i32 [[E:%.*]], ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4:[0-9]+]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR3:[0-9]+]]
 // CHECK-NEXT:    store i32 0, ptr [[I]], align 4, !tbaa [[TBAA2]]
 // CHECK-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK:       for.cond:
-// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[I]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[TMP1]], [[TMP2]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[I]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[TMP0]], [[TMP1]]
 // CHECK-NEXT:    [[CMP_EXPVAL:%.*]] = call i1 @llvm.expect.i1(i1 [[CMP]], i1 true)
 // CHECK-NEXT:    br i1 [[CMP_EXPVAL]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 // CHECK:       for.cond.cleanup:
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_END:%.*]]
 // CHECK:       for.body:
 // CHECK-NEXT:    br label [[FOR_INC:%.*]]
 // CHECK:       for.inc:
-// CHECK-NEXT:    [[TMP4:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[INC:%.*]] = add i32 [[TMP4]], 1
+// CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[INC:%.*]] = add i32 [[TMP2]], 1
 // CHECK-NEXT:    store i32 [[INC]], ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
 // CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP11:![0-9]+]]
 // CHECK:       for.end:
@@ -100,23 +100,23 @@ void fl(unsigned e)
 // CHECK-NEXT:    [[E_ADDR:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    store i32 [[E:%.*]], ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR3]]
 // CHECK-NEXT:    store i32 0, ptr [[I]], align 4, !tbaa [[TBAA2]]
 // CHECK-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK:       for.cond:
-// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[I]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[TMP1]], [[TMP2]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[I]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[CMP:%.*]] = icmp ne i32 [[TMP0]], [[TMP1]]
 // CHECK-NEXT:    [[CMP_EXPVAL:%.*]] = call i1 @llvm.expect.i1(i1 [[CMP]], i1 false)
 // CHECK-NEXT:    br i1 [[CMP_EXPVAL]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 // CHECK:       for.cond.cleanup:
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_END:%.*]]
 // CHECK:       for.body:
 // CHECK-NEXT:    br label [[FOR_INC:%.*]]
 // CHECK:       for.inc:
-// CHECK-NEXT:    [[TMP4:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP4]], 1
+// CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
 // CHECK-NEXT:    store i32 [[INC]], ptr [[E_ADDR]], align 4, !tbaa [[TBAA2]]
 // CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP12:![0-9]+]]
 // CHECK:       for.end:
@@ -146,42 +146,42 @@ void f_branch_elided()
 // CHECK-NEXT:    [[__END1:%.*]] = alloca ptr, align 8
 // CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    store ptr [[E:%.*]], ptr [[E_ADDR]], align 8, !tbaa [[TBAA14:![0-9]+]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[E_ADDR]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    store ptr [[TMP1]], ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP3]], i64 0, i64 0
-// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__END1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP5]], i64 0, i64 0
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[E_ADDR]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    store ptr [[TMP0]], ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP1]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16:![0-9]+]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__END1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP2]], i64 0, i64 0
 // CHECK-NEXT:    [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[ARRAYDECAY1]], i64 4
-// CHECK-NEXT:    store ptr [[ADD_PTR]], ptr [[__END1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    store ptr [[ADD_PTR]], ptr [[__END1]], align 8, !tbaa [[TBAA16]]
 // CHECK-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK:       for.cond:
-// CHECK-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[__END1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[CMP:%.*]] = icmp ne ptr [[TMP6]], [[TMP7]]
+// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[__END1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[CMP:%.*]] = icmp ne ptr [[TMP3]], [[TMP4]]
 // CHECK-NEXT:    [[CMP_EXPVAL:%.*]] = call i1 @llvm.expect.i1(i1 [[CMP]], i1 true)
 // CHECK-NEXT:    br i1 [[CMP_EXPVAL]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 // CHECK:       for.cond.cleanup:
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__END1]]) #[[ATTR4]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR4]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__END1]]) #[[ATTR3]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR3]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_END:%.*]]
 // CHECK:       for.body:
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP12:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr [[TMP12]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    store i32 [[TMP13]], ptr [[I]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr [[TMP5]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    store i32 [[TMP6]], ptr [[I]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_INC:%.*]]
 // CHECK:       for.inc:
-// CHECK-NEXT:    [[TMP15:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, ptr [[TMP15]], i32 1
-// CHECK-NEXT:    store ptr [[INCDEC_PTR]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP16:![0-9]+]]
+// CHECK-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, ptr [[TMP7]], i32 1
+// CHECK-NEXT:    store ptr [[INCDEC_PTR]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP18:![0-9]+]]
 // CHECK:       for.end:
 // CHECK-NEXT:    ret void
 //
@@ -198,42 +198,42 @@ void frl(int (&&e) [4])
 // CHECK-NEXT:    [[__END1:%.*]] = alloca ptr, align 8
 // CHECK-NEXT:    [[I:%.*]] = alloca i32, align 4
 // CHECK-NEXT:    store ptr [[E:%.*]], ptr [[E_ADDR]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[E_ADDR]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    store ptr [[TMP1]], ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP3]], i64 0, i64 0
-// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__END1]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP5]], i64 0, i64 0
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[E_ADDR]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    store ptr [[TMP0]], ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    [[ARRAYDECAY:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP1]], i64 0, i64 0
+// CHECK-NEXT:    store ptr [[ARRAYDECAY]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[__END1]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__RANGE1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    [[ARRAYDECAY1:%.*]] = getelementptr inbounds [4 x i32], ptr [[TMP2]], i64 0, i64 0
 // CHECK-NEXT:    [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[ARRAYDECAY1]], i64 4
-// CHECK-NEXT:    store ptr [[ADD_PTR]], ptr [[__END1]], align 8, !tbaa [[TBAA14]]
+// CHECK-NEXT:    store ptr [[ADD_PTR]], ptr [[__END1]], align 8, !tbaa [[TBAA16]]
 // CHECK-NEXT:    br label [[FOR_COND:%.*]]
 // CHECK:       for.cond:
-// CHECK-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[__END1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[CMP:%.*]] = icmp ne ptr [[TMP6]], [[TMP7]]
+// CHECK-NEXT:    [[TMP3:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[__END1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[CMP:%.*]] = icmp ne ptr [[TMP3]], [[TMP4]]
 // CHECK-NEXT:    [[CMP_EXPVAL:%.*]] = call i1 @llvm.expect.i1(i1 [[CMP]], i1 false)
 // CHECK-NEXT:    br i1 [[CMP_EXPVAL]], label [[FOR_BODY:%.*]], label [[FOR_COND_CLEANUP:%.*]]
 // CHECK:       for.cond.cleanup:
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__END1]]) #[[ATTR4]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR4]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__END1]]) #[[ATTR3]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__BEGIN1]]) #[[ATTR3]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[__RANGE1]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_END:%.*]]
 // CHECK:       for.body:
-// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK-NEXT:    [[TMP12:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr [[TMP12]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    store i32 [[TMP13]], ptr [[I]], align 4, !tbaa [[TBAA2]]
-// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
+// CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR3]]
+// CHECK-NEXT:    [[TMP5:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr [[TMP5]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    store i32 [[TMP6]], ptr [[I]], align 4, !tbaa [[TBAA2]]
+// CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR3]]
 // CHECK-NEXT:    br label [[FOR_INC:%.*]]
 // CHECK:       for.inc:
-// CHECK-NEXT:    [[TMP15:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, ptr [[TMP15]], i32 1
-// CHECK-NEXT:    store ptr [[INCDEC_PTR]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA14]]
-// CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP17:![0-9]+]]
+// CHECK-NEXT:    [[TMP7:%.*]] = load ptr, ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, ptr [[TMP7]], i32 1
+// CHECK-NEXT:    store ptr [[INCDEC_PTR]], ptr [[__BEGIN1]], align 8, !tbaa [[TBAA16]]
+// CHECK-NEXT:    br label [[FOR_COND]], !llvm.loop [[LOOP19:![0-9]+]]
 // CHECK:       for.end:
 // CHECK-NEXT:    ret void
 //
diff --git a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
index a5c9f69bc2de0..8aedc80e48311 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl
@@ -62,6 +62,7 @@ kernel void test_target_features_kernel(global int *i) {
 
 //.
 // CHECK: @__block_literal_global = internal addrspace(1) constant { i32, i32, ptr } { i32 16, i32 8, ptr @__test_target_features_kernel_block_invoke }, align 8 #0
+// CHECK: @__oclc_ABI_version = weak_odr hidden local_unnamed_addr addrspace(4) constant i32 500
 //.
 // NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
 // NOCPU-LABEL: define {{[^@]+}}@callee
@@ -81,7 +82,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
 // NOCPU-LABEL: define {{[^@]+}}@test
-// NOCPU-SAME: (ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
+// NOCPU-SAME: (ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space [[META3:![0-9]+]] !kernel_arg_access_qual [[META4:![0-9]+]] !kernel_arg_type [[META5:![0-9]+]] !kernel_arg_base_type [[META5]] !kernel_arg_type_qual [[META6:![0-9]+]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
 // NOCPU-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
@@ -212,7 +213,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent nounwind
 // NOCPU-LABEL: define {{[^@]+}}@__test_block_invoke_kernel
-// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR5:[0-9]+]] !kernel_arg_addr_space !7 !kernel_arg_access_qual !8 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !10 {
+// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR5:[0-9]+]] !kernel_arg_addr_space [[META7:![0-9]+]] !kernel_arg_access_qual [[META8:![0-9]+]] !kernel_arg_type [[META9:![0-9]+]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10:![0-9]+]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
 // NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -246,7 +247,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent nounwind
 // NOCPU-LABEL: define {{[^@]+}}@__test_block_invoke_2_kernel
-// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space !7 !kernel_arg_access_qual !8 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !10 {
+// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
 // NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -285,7 +286,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent nounwind
 // NOCPU-LABEL: define {{[^@]+}}@__test_block_invoke_3_kernel
-// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR5]] !kernel_arg_addr_space !11 !kernel_arg_access_qual !12 !kernel_arg_type !13 !kernel_arg_base_type !13 !kernel_arg_type_qual !14 {
+// NOCPU-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR5]] !kernel_arg_addr_space [[META11:![0-9]+]] !kernel_arg_access_qual [[META12:![0-9]+]] !kernel_arg_type [[META13:![0-9]+]] !kernel_arg_base_type [[META13]] !kernel_arg_type_qual [[META14:![0-9]+]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[TMP2:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
 // NOCPU-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP2]], align 8
@@ -312,7 +313,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent nounwind
 // NOCPU-LABEL: define {{[^@]+}}@__test_block_invoke_4_kernel
-// NOCPU-SAME: (<{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space !7 !kernel_arg_access_qual !8 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !10 {
+// NOCPU-SAME: (<{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
 // NOCPU-NEXT:    store <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -323,7 +324,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent noinline norecurse nounwind optnone
 // NOCPU-LABEL: define {{[^@]+}}@test_target_features_kernel
-// NOCPU-SAME: (ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR6:[0-9]+]] !kernel_arg_addr_space !15 !kernel_arg_access_qual !8 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !10 {
+// NOCPU-SAME: (ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR6:[0-9]+]] !kernel_arg_addr_space [[META15:![0-9]+]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META16:![0-9]+]] !kernel_arg_base_type [[META16]] !kernel_arg_type_qual [[META10]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
 // NOCPU-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
@@ -354,7 +355,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // NOCPU: Function Attrs: convergent nounwind
 // NOCPU-LABEL: define {{[^@]+}}@__test_target_features_kernel_block_invoke_kernel
-// NOCPU-SAME: ({ i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space !7 !kernel_arg_access_qual !8 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !10 {
+// NOCPU-SAME: ({ i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR5]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META10]] {
 // NOCPU-NEXT:  entry:
 // NOCPU-NEXT:    [[TMP1:%.*]] = alloca { i32, i32, ptr }, align 8, addrspace(5)
 // NOCPU-NEXT:    store { i32, i32, ptr } [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -394,7 +395,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // GFX900: Function Attrs: convergent norecurse nounwind
 // GFX900-LABEL: define {{[^@]+}}@test
-// GFX900-SAME: (ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space !9 !kernel_arg_access_qual !10 !kernel_arg_type !11 !kernel_arg_base_type !11 !kernel_arg_type_qual !12 {
+// GFX900-SAME: (ptr addrspace(1) noundef align 1 [[A:%.*]], i8 noundef [[B:%.*]], ptr addrspace(1) noundef align 8 [[C:%.*]], i64 noundef [[D:%.*]]) #[[ATTR2:[0-9]+]] !kernel_arg_addr_space [[META10:![0-9]+]] !kernel_arg_access_qual [[META11:![0-9]+]] !kernel_arg_type [[META12:![0-9]+]] !kernel_arg_base_type [[META12]] !kernel_arg_type_qual [[META13:![0-9]+]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
 // GFX900-NEXT:    [[B_ADDR:%.*]] = alloca i8, align 1, addrspace(5)
@@ -413,17 +414,17 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[BLOCK20:%.*]] = alloca ptr, align 8, addrspace(5)
 // GFX900-NEXT:    [[BLOCK21:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
 // GFX900-NEXT:    [[VARTMP27:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
-// GFX900-NEXT:    store ptr addrspace(1) [[A]], ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA7]]
-// GFX900-NEXT:    store i8 [[B]], ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA13:![0-9]+]]
+// GFX900-NEXT:    store ptr addrspace(1) [[A]], ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA14:![0-9]+]]
+// GFX900-NEXT:    store i8 [[B]], ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA16:![0-9]+]]
 // GFX900-NEXT:    store ptr addrspace(1) [[C]], ptr addrspace(5) [[C_ADDR]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    store i64 [[D]], ptr addrspace(5) [[D_ADDR]], align 8, !tbaa [[TBAA3]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR8:[0-9]+]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR8]]
-// GFX900-NEXT:    store i32 0, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14:![0-9]+]]
+// GFX900-NEXT:    store i32 0, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17:![0-9]+]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR8]]
-// GFX900-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA16:![0-9]+]]
-// GFX900-NEXT:    [[TMP1:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
-// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[TMP]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT18:![0-9]+]]
+// GFX900-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA19:![0-9]+]]
+// GFX900-NEXT:    [[TMP1:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
+// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[TMP]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21:![0-9]+]]
 // GFX900-NEXT:    [[BLOCK_SIZE:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 0
 // GFX900-NEXT:    store i32 25, ptr addrspace(5) [[BLOCK_SIZE]], align 8
 // GFX900-NEXT:    [[BLOCK_ALIGN:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 1
@@ -431,16 +432,16 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[BLOCK_INVOKE:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 2
 // GFX900-NEXT:    store ptr @__test_block_invoke, ptr addrspace(5) [[BLOCK_INVOKE]], align 8
 // GFX900-NEXT:    [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA7]]
-// GFX900-NEXT:    store ptr addrspace(1) [[TMP2]], ptr addrspace(5) [[BLOCK_CAPTURED]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP2:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA14]]
+// GFX900-NEXT:    store ptr addrspace(1) [[TMP2]], ptr addrspace(5) [[BLOCK_CAPTURED]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 4
-// GFX900-NEXT:    [[TMP3:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA13]]
-// GFX900-NEXT:    store i8 [[TMP3]], ptr addrspace(5) [[BLOCK_CAPTURED1]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP3:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA16]]
+// GFX900-NEXT:    store i8 [[TMP3]], ptr addrspace(5) [[BLOCK_CAPTURED1]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[TMP4:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK]] to ptr
 // GFX900-NEXT:    [[TMP5:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP0]], i32 [[TMP1]], ptr addrspace(5) byval([[STRUCT_NDRANGE_T]]) [[TMP]], ptr @__test_block_invoke_kernel, ptr [[TMP4]])
-// GFX900-NEXT:    [[TMP6:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA16]]
-// GFX900-NEXT:    [[TMP7:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
-// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP2]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT18]]
+// GFX900-NEXT:    [[TMP6:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA19]]
+// GFX900-NEXT:    [[TMP7:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
+// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP2]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
 // GFX900-NEXT:    [[BLOCK_SIZE4:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 0
 // GFX900-NEXT:    store i32 41, ptr addrspace(5) [[BLOCK_SIZE4]], align 8
 // GFX900-NEXT:    [[BLOCK_ALIGN5:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 1
@@ -448,11 +449,11 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[BLOCK_INVOKE6:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 2
 // GFX900-NEXT:    store ptr @__test_block_invoke_2, ptr addrspace(5) [[BLOCK_INVOKE6]], align 8
 // GFX900-NEXT:    [[BLOCK_CAPTURED7:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP8:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA7]]
-// GFX900-NEXT:    store ptr addrspace(1) [[TMP8]], ptr addrspace(5) [[BLOCK_CAPTURED7]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP8:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA14]]
+// GFX900-NEXT:    store ptr addrspace(1) [[TMP8]], ptr addrspace(5) [[BLOCK_CAPTURED7]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[BLOCK_CAPTURED8:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 6
-// GFX900-NEXT:    [[TMP9:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA13]]
-// GFX900-NEXT:    store i8 [[TMP9]], ptr addrspace(5) [[BLOCK_CAPTURED8]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP9:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA16]]
+// GFX900-NEXT:    store i8 [[TMP9]], ptr addrspace(5) [[BLOCK_CAPTURED8]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURED9:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK3]], i32 0, i32 4
 // GFX900-NEXT:    [[TMP10:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[C_ADDR]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    store ptr addrspace(1) [[TMP10]], ptr addrspace(5) [[BLOCK_CAPTURED9]], align 8, !tbaa [[TBAA7]]
@@ -461,9 +462,9 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    store i64 [[TMP11]], ptr addrspace(5) [[BLOCK_CAPTURED10]], align 8, !tbaa [[TBAA3]]
 // GFX900-NEXT:    [[TMP12:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK3]] to ptr
 // GFX900-NEXT:    [[TMP13:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP6]], i32 [[TMP7]], ptr addrspace(5) byval([[STRUCT_NDRANGE_T]]) [[VARTMP2]], ptr @__test_block_invoke_2_kernel, ptr [[TMP12]])
-// GFX900-NEXT:    [[TMP14:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA16]]
-// GFX900-NEXT:    [[TMP15:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
-// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP11]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT18]]
+// GFX900-NEXT:    [[TMP14:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA19]]
+// GFX900-NEXT:    [[TMP15:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
+// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP11]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
 // GFX900-NEXT:    [[BLOCK_SIZE13:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 0
 // GFX900-NEXT:    store i32 41, ptr addrspace(5) [[BLOCK_SIZE13]], align 8
 // GFX900-NEXT:    [[BLOCK_ALIGN14:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 1
@@ -471,11 +472,11 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[BLOCK_INVOKE15:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 2
 // GFX900-NEXT:    store ptr @__test_block_invoke_3, ptr addrspace(5) [[BLOCK_INVOKE15]], align 8
 // GFX900-NEXT:    [[BLOCK_CAPTURED16:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP16:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA7]]
-// GFX900-NEXT:    store ptr addrspace(1) [[TMP16]], ptr addrspace(5) [[BLOCK_CAPTURED16]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP16:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[A_ADDR]], align 8, !tbaa [[TBAA14]]
+// GFX900-NEXT:    store ptr addrspace(1) [[TMP16]], ptr addrspace(5) [[BLOCK_CAPTURED16]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[BLOCK_CAPTURED17:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 6
-// GFX900-NEXT:    [[TMP17:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA13]]
-// GFX900-NEXT:    store i8 [[TMP17]], ptr addrspace(5) [[BLOCK_CAPTURED17]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP17:%.*]] = load i8, ptr addrspace(5) [[B_ADDR]], align 1, !tbaa [[TBAA16]]
+// GFX900-NEXT:    store i8 [[TMP17]], ptr addrspace(5) [[BLOCK_CAPTURED17]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURED18:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK12]], i32 0, i32 4
 // GFX900-NEXT:    [[TMP18:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[C_ADDR]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    store ptr addrspace(1) [[TMP18]], ptr addrspace(5) [[BLOCK_CAPTURED18]], align 8, !tbaa [[TBAA7]]
@@ -502,11 +503,11 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[TMP24:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[C_ADDR]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    store ptr addrspace(1) [[TMP24]], ptr addrspace(5) [[BLOCK_CAPTURED26]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    [[BLOCK21_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK21]] to ptr
-// GFX900-NEXT:    store ptr [[BLOCK21_ASCAST]], ptr addrspace(5) [[BLOCK20]], align 8, !tbaa [[TBAA13]]
-// GFX900-NEXT:    [[TMP25:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA16]]
-// GFX900-NEXT:    [[TMP26:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
-// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP27]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT18]]
-// GFX900-NEXT:    [[TMP27:%.*]] = load ptr, ptr addrspace(5) [[BLOCK20]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    store ptr [[BLOCK21_ASCAST]], ptr addrspace(5) [[BLOCK20]], align 8, !tbaa [[TBAA16]]
+// GFX900-NEXT:    [[TMP25:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA19]]
+// GFX900-NEXT:    [[TMP26:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
+// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[VARTMP27]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
+// GFX900-NEXT:    [[TMP27:%.*]] = load ptr, ptr addrspace(5) [[BLOCK20]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[TMP28:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK21]] to ptr
 // GFX900-NEXT:    [[TMP29:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP25]], i32 [[TMP26]], ptr addrspace(5) byval([[STRUCT_NDRANGE_T]]) [[VARTMP27]], ptr @__test_block_invoke_4_kernel, ptr [[TMP28]])
 // GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[BLOCK20]]) #[[ATTR8]]
@@ -523,17 +524,17 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
 // GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
-// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
-// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA13]]
+// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
 // GFX900-NEXT:    ret void
 //
 //
 // GFX900: Function Attrs: convergent nounwind
 // GFX900-LABEL: define {{[^@]+}}@__test_block_invoke_kernel
-// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] !kernel_arg_addr_space !19 !kernel_arg_access_qual !20 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !22 {
+// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] !kernel_arg_addr_space [[META22:![0-9]+]] !kernel_arg_access_qual [[META23:![0-9]+]] !kernel_arg_type [[META24:![0-9]+]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25:![0-9]+]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), i8 }>, align 8, addrspace(5)
 // GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -549,11 +550,11 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
 // GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
-// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
-// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA13]]
+// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
 // GFX900-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8, !tbaa [[TBAA3]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
@@ -565,7 +566,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // GFX900: Function Attrs: convergent nounwind
 // GFX900-LABEL: define {{[^@]+}}@__test_block_invoke_2_kernel
-// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space !19 !kernel_arg_access_qual !20 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !22 {
+// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space [[META22]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META24]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
 // GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -581,28 +582,28 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
 // GFX900-NEXT:    [[LP_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
 // GFX900-NEXT:    store ptr [[DOTBLOCK_DESCRIPTOR]], ptr addrspace(5) [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
-// GFX900-NEXT:    store ptr addrspace(3) [[LP]], ptr addrspace(5) [[LP_ADDR]], align 4, !tbaa [[TBAA7]]
+// GFX900-NEXT:    store ptr addrspace(3) [[LP]], ptr addrspace(5) [[LP_ADDR]], align 4, !tbaa [[TBAA26:![0-9]+]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 6
-// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA13]]
+// GFX900-NEXT:    [[TMP0:%.*]] = load i8, ptr [[BLOCK_CAPTURE_ADDR]], align 8, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
-// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR1]], align 8, !tbaa [[TBAA14]]
 // GFX900-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr addrspace(1) [[TMP1]], i64 0
-// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA13]]
+// GFX900-NEXT:    store i8 [[TMP0]], ptr addrspace(1) [[ARRAYIDX]], align 1, !tbaa [[TBAA16]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
 // GFX900-NEXT:    [[TMP2:%.*]] = load i64, ptr [[BLOCK_CAPTURE_ADDR2]], align 8, !tbaa [[TBAA3]]
 // GFX900-NEXT:    [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
 // GFX900-NEXT:    [[TMP3:%.*]] = load ptr addrspace(1), ptr [[BLOCK_CAPTURE_ADDR3]], align 8, !tbaa [[TBAA7]]
 // GFX900-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[TMP3]], i64 0
 // GFX900-NEXT:    store i64 [[TMP2]], ptr addrspace(1) [[ARRAYIDX4]], align 8, !tbaa [[TBAA3]]
-// GFX900-NEXT:    [[TMP4:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[LP_ADDR]], align 4, !tbaa [[TBAA7]]
+// GFX900-NEXT:    [[TMP4:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[LP_ADDR]], align 4, !tbaa [[TBAA26]]
 // GFX900-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr addrspace(3) [[TMP4]], i64 0
-// GFX900-NEXT:    store i32 1, ptr addrspace(3) [[ARRAYIDX5]], align 4, !tbaa [[TBAA14]]
+// GFX900-NEXT:    store i32 1, ptr addrspace(3) [[ARRAYIDX5]], align 4, !tbaa [[TBAA17]]
 // GFX900-NEXT:    ret void
 //
 //
 // GFX900: Function Attrs: convergent nounwind
 // GFX900-LABEL: define {{[^@]+}}@__test_block_invoke_3_kernel
-// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR6]] !kernel_arg_addr_space !23 !kernel_arg_access_qual !24 !kernel_arg_type !25 !kernel_arg_base_type !25 !kernel_arg_type_qual !26 {
+// GFX900-SAME: (<{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0:%.*]], ptr addrspace(3) [[TMP1:%.*]]) #[[ATTR6]] !kernel_arg_addr_space [[META28:![0-9]+]] !kernel_arg_access_qual [[META29:![0-9]+]] !kernel_arg_type [[META30:![0-9]+]] !kernel_arg_base_type [[META30]] !kernel_arg_type_qual [[META31:![0-9]+]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[TMP2:%.*]] = alloca <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
 // GFX900-NEXT:    store <{ i32, i32, ptr, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[TMP0]], ptr addrspace(5) [[TMP2]], align 8
@@ -627,7 +628,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // GFX900: Function Attrs: convergent nounwind
 // GFX900-LABEL: define {{[^@]+}}@__test_block_invoke_4_kernel
-// GFX900-SAME: (<{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space !19 !kernel_arg_access_qual !20 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !22 {
+// GFX900-SAME: (<{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space [[META22]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META24]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[TMP1:%.*]] = alloca <{ i32, i32, ptr, i64, ptr addrspace(1) }>, align 8, addrspace(5)
 // GFX900-NEXT:    store <{ i32, i32, ptr, i64, ptr addrspace(1) }> [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -638,22 +639,22 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // GFX900: Function Attrs: convergent norecurse nounwind
 // GFX900-LABEL: define {{[^@]+}}@test_target_features_kernel
-// GFX900-SAME: (ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR2]] !kernel_arg_addr_space !27 !kernel_arg_access_qual !20 !kernel_arg_type !28 !kernel_arg_base_type !28 !kernel_arg_type_qual !22 {
+// GFX900-SAME: (ptr addrspace(1) noundef align 4 [[I:%.*]]) #[[ATTR2]] !kernel_arg_addr_space [[META32:![0-9]+]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META33:![0-9]+]] !kernel_arg_base_type [[META33]] !kernel_arg_type_qual [[META25]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[I_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
 // GFX900-NEXT:    [[DEFAULT_QUEUE:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
 // GFX900-NEXT:    [[FLAGS:%.*]] = alloca i32, align 4, addrspace(5)
 // GFX900-NEXT:    [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
 // GFX900-NEXT:    [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
-// GFX900-NEXT:    store ptr addrspace(1) [[I]], ptr addrspace(5) [[I_ADDR]], align 8, !tbaa [[TBAA7]]
+// GFX900-NEXT:    store ptr addrspace(1) [[I]], ptr addrspace(5) [[I_ADDR]], align 8, !tbaa [[TBAA34:![0-9]+]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[DEFAULT_QUEUE]]) #[[ATTR8]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR8]]
-// GFX900-NEXT:    store i32 0, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
+// GFX900-NEXT:    store i32 0, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
 // GFX900-NEXT:    call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR8]]
 // GFX900-NEXT:    [[TMP0:%.*]] = call i64 @llvm.amdgcn.s.memtime()
-// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA16]]
-// GFX900-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA14]]
-// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[TMP]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT18]]
+// GFX900-NEXT:    [[TMP1:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[DEFAULT_QUEUE]], align 8, !tbaa [[TBAA19]]
+// GFX900-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(5) [[FLAGS]], align 4, !tbaa [[TBAA17]]
+// GFX900-NEXT:    call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 4 [[TMP]], ptr addrspace(5) align 4 [[NDRANGE]], i64 4, i1 false), !tbaa.struct [[TBAA_STRUCT21]]
 // GFX900-NEXT:    [[TMP3:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) [[TMP1]], i32 [[TMP2]], ptr addrspace(5) byval([[STRUCT_NDRANGE_T]]) [[TMP]], ptr @__test_target_features_kernel_block_invoke_kernel, ptr addrspacecast (ptr addrspace(1) @__block_literal_global to ptr))
 // GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[NDRANGE]]) #[[ATTR8]]
 // GFX900-NEXT:    call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[FLAGS]]) #[[ATTR8]]
@@ -673,7 +674,7 @@ kernel void test_target_features_kernel(global int *i) {
 //
 // GFX900: Function Attrs: convergent nounwind
 // GFX900-LABEL: define {{[^@]+}}@__test_target_features_kernel_block_invoke_kernel
-// GFX900-SAME: ({ i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space !19 !kernel_arg_access_qual !20 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !22 {
+// GFX900-SAME: ({ i32, i32, ptr } [[TMP0:%.*]]) #[[ATTR6]] !kernel_arg_addr_space [[META22]] !kernel_arg_access_qual [[META23]] !kernel_arg_type [[META24]] !kernel_arg_base_type [[META24]] !kernel_arg_type_qual [[META25]] {
 // GFX900-NEXT:  entry:
 // GFX900-NEXT:    [[TMP1:%.*]] = alloca { i32, i32, ptr }, align 8, addrspace(5)
 // GFX900-NEXT:    store { i32, i32, ptr } [[TMP0]], ptr addrspace(5) [[TMP1]], align 8
@@ -682,74 +683,81 @@ kernel void test_target_features_kernel(global int *i) {
 // GFX900-NEXT:    ret void
 //
 //.
-// NOCPU: attributes #0 = { "objc_arc_inert" }
-// NOCPU: attributes #1 = { convergent noinline norecurse nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
-// NOCPU: attributes #2 = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" }
-// NOCPU: attributes #3 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
-// NOCPU: attributes #4 = { convergent noinline nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
-// NOCPU: attributes #5 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
-// NOCPU: attributes #6 = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+s-memtime-inst" "uniform-work-group-size"="false" }
-// NOCPU: attributes #7 = { nocallback nofree nosync nounwind willreturn }
-// NOCPU: attributes #8 = { convergent nounwind }
+// NOCPU: attributes #[[ATTR0:[0-9]+]] = { "objc_arc_inert" }
+// NOCPU: attributes #[[ATTR1]] = { convergent noinline norecurse nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// NOCPU: attributes #[[ATTR2]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" }
+// NOCPU: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
+// NOCPU: attributes #[[ATTR4]] = { convergent noinline nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// NOCPU: attributes #[[ATTR5]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// NOCPU: attributes #[[ATTR6]] = { convergent noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+s-memtime-inst" "uniform-work-group-size"="false" }
+// NOCPU: attributes #[[ATTR7:[0-9]+]] = { nocallback nofree nosync nounwind willreturn }
+// NOCPU: attributes #[[ATTR8]] = { convergent nounwind }
 //.
-// GFX900: attributes #0 = { "objc_arc_inert" }
-// GFX900: attributes #1 = { convergent norecurse nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
-// GFX900: attributes #2 = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" "uniform-work-group-size"="false" }
-// GFX900: attributes #3 = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) }
-// GFX900: attributes #4 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
-// GFX900: attributes #5 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
-// GFX900: attributes #6 = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
-// GFX900: attributes #7 = { nocallback nofree nosync nounwind willreturn }
-// GFX900: attributes #8 = { nounwind }
-// GFX900: attributes #9 = { convergent nounwind }
+// GFX900: attributes #[[ATTR0:[0-9]+]] = { "objc_arc_inert" }
+// GFX900: attributes #[[ATTR1]] = { convergent norecurse nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
+// GFX900: attributes #[[ATTR2]] = { convergent norecurse nounwind "amdgpu-flat-work-group-size"="1,256" "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" "uniform-work-group-size"="false" }
+// GFX900: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) }
+// GFX900: attributes #[[ATTR4:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
+// GFX900: attributes #[[ATTR5]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
+// GFX900: attributes #[[ATTR6]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "enqueued-block" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx900" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-sram-ecc" }
+// GFX900: attributes #[[ATTR7:[0-9]+]] = { nocallback nofree nosync nounwind willreturn }
+// GFX900: attributes #[[ATTR8]] = { nounwind }
+// GFX900: attributes #[[ATTR9]] = { convergent nounwind }
 //.
-// NOCPU: !0 = !{i32 1, !"amdhsa_code_object_version", i32 500}
-// NOCPU: !1 = !{i32 1, !"wchar_size", i32 4}
-// NOCPU: !2 = !{i32 2, i32 0}
-// NOCPU: !3 = !{i32 1, i32 0, i32 1, i32 0}
-// NOCPU: !4 = !{!"none", !"none", !"none", !"none"}
-// NOCPU: !5 = !{!"char*", !"char", !"long*", !"long"}
-// NOCPU: !6 = !{!"", !"", !"", !""}
-// NOCPU: !7 = !{i32 0}
-// NOCPU: !8 = !{!"none"}
-// NOCPU: !9 = !{!"__block_literal"}
-// NOCPU: !10 = !{!""}
-// NOCPU: !11 = !{i32 0, i32 3}
-// NOCPU: !12 = !{!"none", !"none"}
-// NOCPU: !13 = !{!"__block_literal", !"void*"}
-// NOCPU: !14 = !{!"", !""}
-// NOCPU: !15 = !{i32 1}
-// NOCPU: !16 = !{!"int*"}
+// NOCPU: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 500}
+// NOCPU: [[META1:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
+// NOCPU: [[META2:![0-9]+]] = !{i32 2, i32 0}
+// NOCPU: [[META3]] = !{i32 1, i32 0, i32 1, i32 0}
+// NOCPU: [[META4]] = !{!"none", !"none", !"none", !"none"}
+// NOCPU: [[META5]] = !{!"char*", !"char", !"long*", !"long"}
+// NOCPU: [[META6]] = !{!"", !"", !"", !""}
+// NOCPU: [[META7]] = !{i32 0}
+// NOCPU: [[META8]] = !{!"none"}
+// NOCPU: [[META9]] = !{!"__block_literal"}
+// NOCPU: [[META10]] = !{!""}
+// NOCPU: [[META11]] = !{i32 0, i32 3}
+// NOCPU: [[META12]] = !{!"none", !"none"}
+// NOCPU: [[META13]] = !{!"__block_literal", !"void*"}
+// NOCPU: [[META14]] = !{!"", !""}
+// NOCPU: [[META15]] = !{i32 1}
+// NOCPU: [[META16]] = !{!"int*"}
 //.
-// GFX900: !0 = !{i32 1, !"amdhsa_code_object_version", i32 500}
-// GFX900: !1 = !{i32 1, !"wchar_size", i32 4}
-// GFX900: !2 = !{i32 2, i32 0}
-// GFX900: !3 = !{!4, !4, i64 0}
-// GFX900: !4 = !{!"long", !5, i64 0}
-// GFX900: !5 = !{!"omnipotent char", !6, i64 0}
-// GFX900: !6 = !{!"Simple C/C++ TBAA"}
-// GFX900: !7 = !{!8, !8, i64 0}
-// GFX900: !8 = !{!"any pointer", !5, i64 0}
-// GFX900: !9 = !{i32 1, i32 0, i32 1, i32 0}
-// GFX900: !10 = !{!"none", !"none", !"none", !"none"}
-// GFX900: !11 = !{!"char*", !"char", !"long*", !"long"}
-// GFX900: !12 = !{!"", !"", !"", !""}
-// GFX900: !13 = !{!5, !5, i64 0}
-// GFX900: !14 = !{!15, !15, i64 0}
-// GFX900: !15 = !{!"int", !5, i64 0}
-// GFX900: !16 = !{!17, !17, i64 0}
-// GFX900: !17 = !{!"queue_t", !5, i64 0}
-// GFX900: !18 = !{i64 0, i64 4, !14}
-// GFX900: !19 = !{i32 0}
-// GFX900: !20 = !{!"none"}
-// GFX900: !21 = !{!"__block_literal"}
-// GFX900: !22 = !{!""}
-// GFX900: !23 = !{i32 0, i32 3}
-// GFX900: !24 = !{!"none", !"none"}
-// GFX900: !25 = !{!"__block_literal", !"void*"}
-// GFX900: !26 = !{!"", !""}
-// GFX900: !27 = !{i32 1}
-// GFX900: !28 = !{!"int*"}
+// GFX900: [[META0:![0-9]+]] = !{i32 1, !"amdhsa_code_object_version", i32 500}
+// GFX900: [[META1:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
+// GFX900: [[META2:![0-9]+]] = !{i32 2, i32 0}
+// GFX900: [[TBAA3]] = !{[[META4:![0-9]+]], [[META4]], i64 0}
+// GFX900: [[META4]] = !{!"long", [[META5:![0-9]+]], i64 0}
+// GFX900: [[META5]] = !{!"omnipotent char", [[META6:![0-9]+]], i64 0}
+// GFX900: [[META6]] = !{!"Simple C/C++ TBAA"}
+// GFX900: [[TBAA7]] = !{[[META8:![0-9]+]], [[META8]], i64 0}
+// GFX900: [[META8]] = !{!"p1 long", [[META9:![0-9]+]], i64 0}
+// GFX900: [[META9]] = !{!"any pointer", [[META5]], i64 0}
+// GFX900: [[META10]] = !{i32 1, i32 0, i32 1, i32 0}
+// GFX900: [[META11]] = !{!"none", !"none", !"none", !"none"}
+// GFX900: [[META12]] = !{!"char*", !"char", !"long*", !"long"}
+// GFX900: [[META13]] = !{!"", !"", !"", !""}
+// GFX900: [[TBAA14]] = !{[[META15:![0-9]+]], [[META15]], i64 0}
+// GFX900: [[META15]] = !{!"p1 omnipotent char", [[META9]], i64 0}
+// GFX900: [[TBAA16]] = !{[[META5]], [[META5]], i64 0}
+// GFX900: [[TBAA17]] = !{[[META18:![0-9]+]], [[META18]], i64 0}
+// GFX900: [[META18]] = !{!"int", [[META5]], i64 0}
+// GFX900: [[TBAA19]] = !{[[META20:![0-9]+]], [[META20]], i64 0}
+// GFX900: [[META20]] = !{!"queue_t", [[META5]], i64 0}
+// GFX900: [[TBAA_STRUCT21]] = !{i64 0, i64 4, [[TBAA17]]}
+// GFX900: [[META22]] = !{i32 0}
+// GFX900: [[META23]] = !{!"none"}
+// GFX900: [[META24]] = !{!"__block_literal"}
+// GFX900: [[META25]] = !{!""}
+// GFX900: [[TBAA26]] = !{[[META27:![0-9]+]], [[META27]], i64 0}
+// GFX900: [[META27]] = !{!"p1 void", [[META9]], i64 0}
+// GFX900: [[META28]] = !{i32 0, i32 3}
+// GFX900: [[META29]] = !{!"none", !"none"}
+// GFX900: [[META30]] = !{!"__block_literal", !"void*"}
+// GFX900: [[META31]] = !{!"", !""}
+// GFX900: [[META32]] = !{i32 1}
+// GFX900: [[META33]] = !{!"int*"}
+// GFX900: [[TBAA34]] = !{[[META35:![0-9]+]], [[META35]], i64 0}
+// GFX900: [[META35]] = !{!"p1 int", [[META9]], i64 0}
 //.
 //// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
 // CHECK: {{.*}}
diff --git a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
index fac42732022ad..b8d1cd0f73e59 100644
--- a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
+++ b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen_tbaa_PR46146.cpp
@@ -43,7 +43,7 @@ void test() {
 // CHECK1:       user_code.entry:
 // CHECK1-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
 // CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA14:![0-9]+]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA15:![0-9]+]]
 // CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined(ptr [[DOTTHREADID_TEMP_]], ptr [[DOTZERO_ADDR]]) #[[ATTR4:[0-9]+]]
 // CHECK1-NEXT:    call void @__kmpc_target_deinit()
 // CHECK1-NEXT:    ret void
@@ -66,78 +66,78 @@ void test() {
 // CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[REF_TMP2:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x ptr], align 8
-// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA17:![0-9]+]]
+// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA17]]
 // CHECK1-NEXT:    [[ISTART:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
 // CHECK1-NEXT:    [[IEND:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
 // CHECK1-NEXT:    [[PARTIAL_SUM:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 8)
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
 // CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_distribute_static_init_4(ptr @[[GLOB2:[0-9]+]], i32 [[TMP1]], i32 92, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
-// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 99
 // CHECK1-NEXT:    br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
 // CHECK1:       cond.true:
 // CHECK1-NEXT:    br label [[COND_END:%.*]]
 // CHECK1:       cond.false:
-// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END]]
 // CHECK1:       cond.end:
 // CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ 99, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
-// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
 // CHECK1:       omp.inner.for.cond:
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
 // CHECK1-NEXT:    br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
 // CHECK1:       omp.inner.for.cond.cleanup:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
 // CHECK1:       omp.inner.for.body:
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
 // CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
-// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA16:![0-9]+]]
+// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA19:![0-9]+]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP2]]) #[[ATTR4]]
-// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP2]], align 4, !tbaa [[TBAA16]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP2]]) #[[ATTR12:[0-9]+]]
+// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP2]], align 4, !tbaa [[TBAA19]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP2]]) #[[ATTR11:[0-9]+]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP2]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP8]], 4
-// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP9]], 1
 // CHECK1-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[ADD4]], 4
-// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
-// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA21:![0-9]+]]
 // CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
-// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA21]]
 // CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
-// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA21]]
 // CHECK1-NEXT:    call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined_wrapper, ptr [[CAPTURED_VARS_ADDRS]], i64 3)
 // CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
 // CHECK1:       omp.body.continue:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
 // CHECK1:       omp.inner.for.inc:
-// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP13]], 1
-// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
 // CHECK1:       omp.inner.for.end:
 // CHECK1-NEXT:    br label [[OMP_LOOP_EXIT:%.*]]
@@ -161,13 +161,13 @@ void test() {
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23:![0-9]+]]
+// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA24:![0-9]+]]
+// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA24]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8
 // CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8
-// CHECK1-NEXT:    call void @_ZNSt7complexIfEC2ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[THIS1]], ptr nonnull align 4 dereferenceable(4) [[TMP0]], ptr nonnull align 4 dereferenceable(4) [[TMP1]]) #[[ATTR12]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIfEC2ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[THIS1]], ptr nonnull align 4 dereferenceable(4) [[TMP0]], ptr nonnull align 4 dereferenceable(4) [[TMP1]]) #[[ATTR11]]
 // CHECK1-NEXT:    ret void
 //
 //
@@ -197,79 +197,79 @@ void test() {
 // CHECK1-NEXT:    [[REF_TMP15:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[REF_TMP16:%.*]] = alloca float, align 4
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x ptr], align 8
-// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP5]], [[TMP6]]
 // CHECK1-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
 // CHECK1-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 1
 // CHECK1-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 1
 // CHECK1-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
-// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP8]], [[TMP9]]
 // CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
 // CHECK1:       omp.precond.then:
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA16]]
+// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP]], align 4, !tbaa [[TBAA19]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP6]]) #[[ATTR4]]
-// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP6]], align 4, !tbaa [[TBAA16]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP6]]) #[[ATTR12]]
+// CHECK1-NEXT:    store float 0.000000e+00, ptr [[REF_TMP6]], align 4, !tbaa [[TBAA19]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP6]]) #[[ATTR11]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP6]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
 // CHECK1-NEXT:    [[TMP11:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_for_static_init_4u(ptr @[[GLOB3:[0-9]+]], i32 [[TMP12]], i32 33, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_COND:%.*]]
 // CHECK1:       omp.dispatch.cond:
-// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP8:%.*]] = icmp ugt i32 [[TMP13]], [[TMP14]]
 // CHECK1-NEXT:    br i1 [[CMP8]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
 // CHECK1:       cond.true:
-// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END:%.*]]
 // CHECK1:       cond.false:
-// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END]]
 // CHECK1:       cond.end:
 // CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ [[TMP15]], [[COND_TRUE]] ], [ [[TMP16]], [[COND_FALSE]] ]
-// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD9:%.*]] = add i32 [[TMP19]], 1
 // CHECK1-NEXT:    [[CMP10:%.*]] = icmp ult i32 [[TMP18]], [[ADD9]]
 // CHECK1-NEXT:    br i1 [[CMP10]], label [[OMP_DISPATCH_BODY:%.*]], label [[OMP_DISPATCH_CLEANUP:%.*]]
@@ -278,30 +278,30 @@ void test() {
 // CHECK1:       omp.dispatch.body:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
 // CHECK1:       omp.inner.for.cond:
-// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD11:%.*]] = add i32 [[TMP21]], 1
 // CHECK1-NEXT:    [[CMP12:%.*]] = icmp ult i32 [[TMP20]], [[ADD11]]
 // CHECK1-NEXT:    br i1 [[CMP12]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
 // CHECK1:       omp.inner.for.cond.cleanup:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
 // CHECK1:       omp.inner.for.body:
-// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL:%.*]] = mul i32 [[TMP23]], 1
 // CHECK1-NEXT:    [[ADD13:%.*]] = add i32 [[TMP22]], [[MUL]]
-// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP14]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP15]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP24]] to float
-// CHECK1-NEXT:    store float [[CONV]], ptr [[REF_TMP15]], align 4, !tbaa [[TBAA16]]
+// CHECK1-NEXT:    store float [[CONV]], ptr [[REF_TMP15]], align 4, !tbaa [[TBAA19]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[REF_TMP16]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CONV17:%.*]] = sitofp i32 [[TMP25]] to float
-// CHECK1-NEXT:    store float [[CONV17]], ptr [[REF_TMP16]], align 4, !tbaa [[TBAA16]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP15]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP16]]) #[[ATTR12]]
-// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]]) #[[ATTR12]]
+// CHECK1-NEXT:    store float [[CONV17]], ptr [[REF_TMP16]], align 4, !tbaa [[TBAA19]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIfEC1ERKfS2_(ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP15]], ptr nonnull align 4 dereferenceable(4) [[REF_TMP16]]) #[[ATTR11]]
+// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]], ptr nonnull align 4 dereferenceable(8) [[REF_TMP14]]) #[[ATTR11]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP16]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[REF_TMP15]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP14]]) #[[ATTR4]]
@@ -309,25 +309,25 @@ void test() {
 // CHECK1:       omp.body.continue:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
 // CHECK1:       omp.inner.for.inc:
-// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD18:%.*]] = add i32 [[TMP26]], 1
-// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
 // CHECK1:       omp.inner.for.end:
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_INC:%.*]]
 // CHECK1:       omp.dispatch.inc:
-// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD19:%.*]] = add i32 [[TMP27]], [[TMP28]]
-// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD20:%.*]] = add i32 [[TMP29]], [[TMP30]]
-// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_COND]]
 // CHECK1:       omp.dispatch.end:
 // CHECK1-NEXT:    [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_for_static_fini(ptr @[[GLOB3]], i32 [[TMP32]])
 // CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
 // CHECK1-NEXT:    store ptr [[PARTIAL_SUM5]], ptr [[TMP33]], align 8
@@ -335,7 +335,7 @@ void test() {
 // CHECK1-NEXT:    [[TMP35:%.*]] = icmp eq i32 [[TMP34]], 1
 // CHECK1-NEXT:    br i1 [[TMP35]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
 // CHECK1:       .omp.reduction.then:
-// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[TMP2]], ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]]) #[[ATTR12]]
+// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 4 dereferenceable(8) ptr @_ZNSt7complexIfEpLIfEERS0_RKS_IT_E(ptr nonnull align 4 dereferenceable(8) [[TMP2]], ptr nonnull align 4 dereferenceable(8) [[PARTIAL_SUM5]]) #[[ATTR11]]
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
@@ -354,30 +354,30 @@ void test() {
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIfEpLIfEERS0_RKS_IT_E
-// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]], ptr nonnull align 4 dereferenceable(8) [[__C:%.*]]) #[[ATTR6:[0-9]+]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]], ptr nonnull align 4 dereferenceable(8) [[__C:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__C_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[CALL:%.*]] = call float @_ZNKSt7complexIfE4realEv(ptr nonnull align 4 dereferenceable(8) [[TMP0]]) #[[ATTR12]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[CALL:%.*]] = call float @_ZNKSt7complexIfE4realEv(ptr nonnull align 4 dereferenceable(8) [[TMP0]]) #[[ATTR11]]
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA18:![0-9]+]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA26:![0-9]+]]
 // CHECK1-NEXT:    [[ADD:%.*]] = fadd float [[TMP1]], [[CALL]]
-// CHECK1-NEXT:    store float [[ADD]], ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[CALL2:%.*]] = call float @_ZNKSt7complexIfE4imagEv(ptr nonnull align 4 dereferenceable(8) [[TMP2]]) #[[ATTR12]]
+// CHECK1-NEXT:    store float [[ADD]], ptr [[__RE_]], align 4, !tbaa [[TBAA26]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[CALL2:%.*]] = call float @_ZNKSt7complexIfE4imagEv(ptr nonnull align 4 dereferenceable(8) [[TMP2]]) #[[ATTR11]]
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA20:![0-9]+]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA28:![0-9]+]]
 // CHECK1-NEXT:    [[ADD3:%.*]] = fadd float [[TMP3]], [[CALL2]]
-// CHECK1-NEXT:    store float [[ADD3]], ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
+// CHECK1-NEXT:    store float [[ADD3]], ptr [[__IM_]], align 4, !tbaa [[TBAA28]]
 // CHECK1-NEXT:    ret ptr [[THIS1]]
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_shuffle_and_reduce_func
-// CHECK1-SAME: (ptr [[TMP0:%.*]], i16 signext [[TMP1:%.*]], i16 signext [[TMP2:%.*]], i16 signext [[TMP3:%.*]]) #[[ATTR7:[0-9]+]] {
+// CHECK1-SAME: (ptr [[TMP0:%.*]], i16 signext [[TMP1:%.*]], i16 signext [[TMP2:%.*]], i16 signext [[TMP3:%.*]]) #[[ATTR6:[0-9]+]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i16, align 2
@@ -386,13 +386,13 @@ void test() {
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST:%.*]] = alloca [1 x ptr], align 8
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_ELEMENT:%.*]] = alloca %"class.std::complex", align 4
 // CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2, !tbaa [[TBAA21:![0-9]+]]
-// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2, !tbaa [[TBAA21]]
+// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2, !tbaa [[TBAA29:![0-9]+]]
+// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2, !tbaa [[TBAA29]]
 // CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2, !tbaa [[TBAA21]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2, !tbaa [[TBAA29]]
 // CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
 // CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
@@ -433,7 +433,7 @@ void test() {
 // CHECK1-NEXT:    [[TMP34:%.*]] = load ptr, ptr [[TMP33]], align 8
 // CHECK1-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP36:%.*]] = load ptr, ptr [[TMP35]], align 8
-// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP36]], ptr align 4 [[TMP34]], i64 8, i1 false), !tbaa.struct [[TBAA_STRUCT23:![0-9]+]]
+// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[TMP36]], ptr align 4 [[TMP34]], i64 8, i1 false), !tbaa.struct [[TBAA_STRUCT31:![0-9]+]]
 // CHECK1-NEXT:    br label [[IFCONT6:%.*]]
 // CHECK1:       else5:
 // CHECK1-NEXT:    br label [[IFCONT6]]
@@ -442,24 +442,24 @@ void test() {
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_inter_warp_copy_func
-// CHECK1-SAME: (ptr [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR7]] {
+// CHECK1-SAME: (ptr [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR6]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCNT_ADDR:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP2:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
 // CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[TMP4]], 31
 // CHECK1-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[NVPTX_WARP_ID:%.*]] = ashr i32 [[TMP5]], 5
 // CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[DOTADDR]], align 8
-// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[PRECOND:%.*]]
 // CHECK1:       precond:
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[TMP7]], 2
 // CHECK1-NEXT:    br i1 [[TMP8]], label [[BODY:%.*]], label [[EXIT:%.*]]
 // CHECK1:       body:
@@ -478,7 +478,7 @@ void test() {
 // CHECK1-NEXT:    br label [[IFCONT]]
 // CHECK1:       ifcont:
 // CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4]], i32 [[TMP2]])
-// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[IS_ACTIVE_THREAD:%.*]] = icmp ult i32 [[TMP3]], [[TMP14]]
 // CHECK1-NEXT:    br i1 [[IS_ACTIVE_THREAD]], label [[THEN2:%.*]], label [[ELSE3:%.*]]
 // CHECK1:       then2:
@@ -486,37 +486,37 @@ void test() {
 // CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP6]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP17:%.*]] = load ptr, ptr [[TMP16]], align 8, !tbaa [[TBAA10]]
 // CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr i32, ptr [[TMP17]], i32 [[TMP7]]
-// CHECK1-NEXT:    [[TMP19:%.*]] = load volatile i32, ptr addrspace(3) [[TMP15]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[TMP18]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP19:%.*]] = load volatile i32, ptr addrspace(3) [[TMP15]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[TMP18]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[IFCONT4:%.*]]
 // CHECK1:       else3:
 // CHECK1-NEXT:    br label [[IFCONT4]]
 // CHECK1:       ifcont4:
 // CHECK1-NEXT:    [[TMP20:%.*]] = add nsw i32 [[TMP7]], 1
-// CHECK1-NEXT:    store i32 [[TMP20]], ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[TMP20]], ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[PRECOND]]
 // CHECK1:       exit:
 // CHECK1-NEXT:    ret void
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined_wrapper
-// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR7]] {
+// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR6]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i16, align 2
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[GLOBAL_ARGS:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
 // CHECK1-NEXT:    call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
 // CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
 // CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
-// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA32:![0-9]+]]
 // CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
-// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA32]]
 // CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 2
-// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIfEvv_l16_omp_outlined_omp_outlined(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]], ptr [[TMP6]], ptr [[TMP8]]) #[[ATTR4]]
 // CHECK1-NEXT:    ret void
 //
@@ -534,7 +534,7 @@ void test() {
 // CHECK1:       user_code.entry:
 // CHECK1-NEXT:    [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
 // CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTTHREADID_TEMP_]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined(ptr [[DOTTHREADID_TEMP_]], ptr [[DOTZERO_ADDR]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @__kmpc_target_deinit()
 // CHECK1-NEXT:    ret void
@@ -557,78 +557,78 @@ void test() {
 // CHECK1-NEXT:    [[REF_TMP:%.*]] = alloca double, align 8
 // CHECK1-NEXT:    [[REF_TMP2:%.*]] = alloca double, align 8
 // CHECK1-NEXT:    [[CAPTURED_VARS_ADDRS:%.*]] = alloca [3 x ptr], align 8
-// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA17]]
 // CHECK1-NEXT:    [[ISTART:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
 // CHECK1-NEXT:    [[IEND:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 4)
 // CHECK1-NEXT:    [[PARTIAL_SUM:%.*]] = call align 16 ptr @__kmpc_alloc_shared(i64 16)
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 99, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[IB]]) #[[ATTR4]]
 // CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_distribute_static_init_4(ptr @[[GLOB2]], i32 [[TMP1]], i32 92, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
-// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 99
 // CHECK1-NEXT:    br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
 // CHECK1:       cond.true:
 // CHECK1-NEXT:    br label [[COND_END:%.*]]
 // CHECK1:       cond.false:
-// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END]]
 // CHECK1:       cond.end:
 // CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ 99, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
-// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
 // CHECK1:       omp.inner.for.cond:
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP1:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
 // CHECK1-NEXT:    br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
 // CHECK1:       omp.inner.for.cond.cleanup:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
 // CHECK1:       omp.inner.for.body:
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
 // CHECK1-NEXT:    [[ADD:%.*]] = add nsw i32 0, [[MUL]]
-// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD]], ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA24:![0-9]+]]
+// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA34:![0-9]+]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP2]]) #[[ATTR4]]
-// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP2]], align 8, !tbaa [[TBAA24]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP2]]) #[[ATTR12]]
+// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP2]], align 8, !tbaa [[TBAA34]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP2]]) #[[ATTR11]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP2]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP8]], 4
-// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[MUL3]], ptr [[ISTART]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[IB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD4:%.*]] = add nsw i32 [[TMP9]], 1
 // CHECK1-NEXT:    [[MUL5:%.*]] = mul nsw i32 [[ADD4]], 4
-// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[MUL5]], ptr [[IEND]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
-// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[TMP10]], align 8, !tbaa [[TBAA21]]
 // CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 1
-// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[IEND]], ptr [[TMP11]], align 8, !tbaa [[TBAA21]]
 // CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [3 x ptr], ptr [[CAPTURED_VARS_ADDRS]], i64 0, i64 2
-// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[TMP12]], align 8, !tbaa [[TBAA21]]
 // CHECK1-NEXT:    call void @__kmpc_parallel_51(ptr @[[GLOB1]], i32 [[TMP1]], i32 1, i32 -1, i32 -1, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined, ptr @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined_wrapper, ptr [[CAPTURED_VARS_ADDRS]], i64 3)
 // CHECK1-NEXT:    br label [[OMP_BODY_CONTINUE:%.*]]
 // CHECK1:       omp.body.continue:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
 // CHECK1:       omp.inner.for.inc:
-// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP13]], 1
-// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD6]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
 // CHECK1:       omp.inner.for.end:
 // CHECK1-NEXT:    br label [[OMP_LOOP_EXIT:%.*]]
@@ -652,13 +652,13 @@ void test() {
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA36:![0-9]+]]
+// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA36]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8
 // CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8
-// CHECK1-NEXT:    call void @_ZNSt7complexIdEC2ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[THIS1]], ptr nonnull align 8 dereferenceable(8) [[TMP0]], ptr nonnull align 8 dereferenceable(8) [[TMP1]]) #[[ATTR12]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIdEC2ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[THIS1]], ptr nonnull align 8 dereferenceable(8) [[TMP0]], ptr nonnull align 8 dereferenceable(8) [[TMP1]]) #[[ATTR11]]
 // CHECK1-NEXT:    ret void
 //
 //
@@ -688,79 +688,79 @@ void test() {
 // CHECK1-NEXT:    [[REF_TMP15:%.*]] = alloca double, align 8
 // CHECK1-NEXT:    [[REF_TMP16:%.*]] = alloca double, align 8
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x ptr], align 8
-// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[ISTART]], ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[IEND]], ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    store ptr [[PARTIAL_SUM]], ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[ISTART_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[IEND_ADDR]], align 8, !tbaa [[TBAA17]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[PARTIAL_SUM_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IV]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP3]], ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_1]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, ptr [[TMP1]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTCAPTURE_EXPR_2]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[SUB:%.*]] = sub i32 [[TMP5]], [[TMP6]]
 // CHECK1-NEXT:    [[SUB3:%.*]] = sub i32 [[SUB]], 1
 // CHECK1-NEXT:    [[ADD:%.*]] = add i32 [[SUB3]], 1
 // CHECK1-NEXT:    [[DIV:%.*]] = udiv i32 [[ADD]], 1
 // CHECK1-NEXT:    [[SUB4:%.*]] = sub i32 [[DIV]], 1
-// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[SUB4]], ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP7]], ptr [[I]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP9:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP:%.*]] = icmp slt i32 [[TMP8]], [[TMP9]]
 // CHECK1-NEXT:    br i1 [[CMP]], label [[OMP_PRECOND_THEN:%.*]], label [[OMP_PRECOND_END:%.*]]
 // CHECK1:       omp.precond.then:
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_LB]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_UB]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP10:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP10]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_STRIDE]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 1, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[DOTOMP_IS_LAST]]) #[[ATTR4]]
-// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTOMP_IS_LAST]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 16, ptr [[PARTIAL_SUM5]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
-// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA24]]
+// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP]], align 8, !tbaa [[TBAA34]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP6]]) #[[ATTR4]]
-// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP6]], align 8, !tbaa [[TBAA24]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP6]]) #[[ATTR12]]
+// CHECK1-NEXT:    store double 0.000000e+00, ptr [[REF_TMP6]], align 8, !tbaa [[TBAA34]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP6]]) #[[ATTR11]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP6]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
 // CHECK1-NEXT:    [[TMP11:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, ptr [[TMP11]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_for_static_init_4u(ptr @[[GLOB3]], i32 [[TMP12]], i32 33, ptr [[DOTOMP_IS_LAST]], ptr [[DOTOMP_LB]], ptr [[DOTOMP_UB]], ptr [[DOTOMP_STRIDE]], i32 1, i32 1)
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_COND:%.*]]
 // CHECK1:       omp.dispatch.cond:
-// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP13:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CMP8:%.*]] = icmp ugt i32 [[TMP13]], [[TMP14]]
 // CHECK1-NEXT:    br i1 [[CMP8]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
 // CHECK1:       cond.true:
-// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP15:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END:%.*]]
 // CHECK1:       cond.false:
-// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP16:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[COND_END]]
 // CHECK1:       cond.end:
 // CHECK1-NEXT:    [[COND:%.*]] = phi i32 [ [[TMP15]], [[COND_TRUE]] ], [ [[TMP16]], [[COND_FALSE]] ]
-// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[COND]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP17]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP19:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD9:%.*]] = add i32 [[TMP19]], 1
 // CHECK1-NEXT:    [[CMP10:%.*]] = icmp ult i32 [[TMP18]], [[ADD9]]
 // CHECK1-NEXT:    br i1 [[CMP10]], label [[OMP_DISPATCH_BODY:%.*]], label [[OMP_DISPATCH_CLEANUP:%.*]]
@@ -769,30 +769,30 @@ void test() {
 // CHECK1:       omp.dispatch.body:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND:%.*]]
 // CHECK1:       omp.inner.for.cond:
-// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP20:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD11:%.*]] = add i32 [[TMP21]], 1
 // CHECK1-NEXT:    [[CMP12:%.*]] = icmp ult i32 [[TMP20]], [[ADD11]]
 // CHECK1-NEXT:    br i1 [[CMP12]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
 // CHECK1:       omp.inner.for.cond.cleanup:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_END:%.*]]
 // CHECK1:       omp.inner.for.body:
-// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP22:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[MUL:%.*]] = mul i32 [[TMP23]], 1
 // CHECK1-NEXT:    [[ADD13:%.*]] = add i32 [[TMP22]], [[MUL]]
-// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD13]], ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 16, ptr [[REF_TMP14]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP15]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP24:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CONV:%.*]] = sitofp i32 [[TMP24]] to double
-// CHECK1-NEXT:    store double [[CONV]], ptr [[REF_TMP15]], align 8, !tbaa [[TBAA24]]
+// CHECK1-NEXT:    store double [[CONV]], ptr [[REF_TMP15]], align 8, !tbaa [[TBAA34]]
 // CHECK1-NEXT:    call void @llvm.lifetime.start.p0(i64 8, ptr [[REF_TMP16]]) #[[ATTR4]]
-// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP25:%.*]] = load i32, ptr [[I7]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[CONV17:%.*]] = sitofp i32 [[TMP25]] to double
-// CHECK1-NEXT:    store double [[CONV17]], ptr [[REF_TMP16]], align 8, !tbaa [[TBAA24]]
-// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP15]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP16]]) #[[ATTR12]]
-// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]]) #[[ATTR12]]
+// CHECK1-NEXT:    store double [[CONV17]], ptr [[REF_TMP16]], align 8, !tbaa [[TBAA34]]
+// CHECK1-NEXT:    call void @_ZNSt7complexIdEC1ERKdS2_(ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP15]], ptr nonnull align 8 dereferenceable(8) [[REF_TMP16]]) #[[ATTR11]]
+// CHECK1-NEXT:    [[CALL:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]], ptr nonnull align 8 dereferenceable(16) [[REF_TMP14]]) #[[ATTR11]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP16]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 8, ptr [[REF_TMP15]]) #[[ATTR4]]
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 16, ptr [[REF_TMP14]]) #[[ATTR4]]
@@ -800,25 +800,25 @@ void test() {
 // CHECK1:       omp.body.continue:
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_INC:%.*]]
 // CHECK1:       omp.inner.for.inc:
-// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD18:%.*]] = add i32 [[TMP26]], 1
-// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD18]], ptr [[DOTOMP_IV]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_INNER_FOR_COND]]
 // CHECK1:       omp.inner.for.end:
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_INC:%.*]]
 // CHECK1:       omp.dispatch.inc:
-// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP27:%.*]] = load i32, ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD19:%.*]] = add i32 [[TMP27]], [[TMP28]]
-// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD19]], ptr [[DOTOMP_LB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP29:%.*]] = load i32, ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    [[TMP30:%.*]] = load i32, ptr [[DOTOMP_STRIDE]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[ADD20:%.*]] = add i32 [[TMP29]], [[TMP30]]
-// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[ADD20]], ptr [[DOTOMP_UB]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[OMP_DISPATCH_COND]]
 // CHECK1:       omp.dispatch.end:
 // CHECK1-NEXT:    [[TMP31:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8
-// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP32:%.*]] = load i32, ptr [[TMP31]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    call void @__kmpc_for_static_fini(ptr @[[GLOB3]], i32 [[TMP32]])
 // CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
 // CHECK1-NEXT:    store ptr [[PARTIAL_SUM5]], ptr [[TMP33]], align 8
@@ -826,7 +826,7 @@ void test() {
 // CHECK1-NEXT:    [[TMP35:%.*]] = icmp eq i32 [[TMP34]], 1
 // CHECK1-NEXT:    br i1 [[TMP35]], label [[DOTOMP_REDUCTION_THEN:%.*]], label [[DOTOMP_REDUCTION_DONE:%.*]]
 // CHECK1:       .omp.reduction.then:
-// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[TMP2]], ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]]) #[[ATTR12]]
+// CHECK1-NEXT:    [[CALL21:%.*]] = call nonnull align 8 dereferenceable(16) ptr @_ZNSt7complexIdEpLIdEERS0_RKS_IT_E(ptr nonnull align 8 dereferenceable(16) [[TMP2]], ptr nonnull align 8 dereferenceable(16) [[PARTIAL_SUM5]]) #[[ATTR11]]
 // CHECK1-NEXT:    br label [[DOTOMP_REDUCTION_DONE]]
 // CHECK1:       .omp.reduction.done:
 // CHECK1-NEXT:    call void @llvm.lifetime.end.p0(i64 4, ptr [[I7]]) #[[ATTR4]]
@@ -845,30 +845,30 @@ void test() {
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNSt7complexIdEpLIdEERS0_RKS_IT_E
-// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]], ptr nonnull align 8 dereferenceable(16) [[__C:%.*]]) #[[ATTR6]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]], ptr nonnull align 8 dereferenceable(16) [[__C:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__C_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    store ptr [[__C]], ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[CALL:%.*]] = call double @_ZNKSt7complexIdE4realEv(ptr nonnull align 8 dereferenceable(16) [[TMP0]]) #[[ATTR12]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[CALL:%.*]] = call double @_ZNKSt7complexIdE4realEv(ptr nonnull align 8 dereferenceable(16) [[TMP0]]) #[[ATTR11]]
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA26:![0-9]+]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA38:![0-9]+]]
 // CHECK1-NEXT:    [[ADD:%.*]] = fadd double [[TMP1]], [[CALL]]
-// CHECK1-NEXT:    store double [[ADD]], ptr [[__RE_]], align 8, !tbaa [[TBAA26]]
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[CALL2:%.*]] = call double @_ZNKSt7complexIdE4imagEv(ptr nonnull align 8 dereferenceable(16) [[TMP2]]) #[[ATTR12]]
+// CHECK1-NEXT:    store double [[ADD]], ptr [[__RE_]], align 8, !tbaa [[TBAA38]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__C_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    [[CALL2:%.*]] = call double @_ZNKSt7complexIdE4imagEv(ptr nonnull align 8 dereferenceable(16) [[TMP2]]) #[[ATTR11]]
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA28:![0-9]+]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA40:![0-9]+]]
 // CHECK1-NEXT:    [[ADD3:%.*]] = fadd double [[TMP3]], [[CALL2]]
-// CHECK1-NEXT:    store double [[ADD3]], ptr [[__IM_]], align 8, !tbaa [[TBAA28]]
+// CHECK1-NEXT:    store double [[ADD3]], ptr [[__IM_]], align 8, !tbaa [[TBAA40]]
 // CHECK1-NEXT:    ret ptr [[THIS1]]
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_shuffle_and_reduce_func1
-// CHECK1-SAME: (ptr [[TMP0:%.*]], i16 signext [[TMP1:%.*]], i16 signext [[TMP2:%.*]], i16 signext [[TMP3:%.*]]) #[[ATTR7]] {
+// CHECK1-SAME: (ptr [[TMP0:%.*]], i16 signext [[TMP1:%.*]], i16 signext [[TMP2:%.*]], i16 signext [[TMP3:%.*]]) #[[ATTR6]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i16, align 2
@@ -877,13 +877,13 @@ void test() {
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST:%.*]] = alloca [1 x ptr], align 8
 // CHECK1-NEXT:    [[DOTOMP_REDUCTION_ELEMENT:%.*]] = alloca %"class.std::complex.0", align 8
 // CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2, !tbaa [[TBAA21]]
+// CHECK1-NEXT:    store i16 [[TMP1]], ptr [[DOTADDR1]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    store i16 [[TMP2]], ptr [[DOTADDR2]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    store i16 [[TMP3]], ptr [[DOTADDR3]], align 2, !tbaa [[TBAA29]]
 // CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2, !tbaa [[TBAA21]]
+// CHECK1-NEXT:    [[TMP5:%.*]] = load i16, ptr [[DOTADDR1]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load i16, ptr [[DOTADDR2]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i16, ptr [[DOTADDR3]], align 2, !tbaa [[TBAA29]]
 // CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP9:%.*]] = load ptr, ptr [[TMP8]], align 8
 // CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [1 x ptr], ptr [[DOTOMP_REDUCTION_REMOTE_REDUCE_LIST]], i64 0, i64 0
@@ -937,7 +937,7 @@ void test() {
 // CHECK1-NEXT:    [[TMP41:%.*]] = load ptr, ptr [[TMP40]], align 8
 // CHECK1-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP4]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP43:%.*]] = load ptr, ptr [[TMP42]], align 8
-// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[TMP43]], ptr align 8 [[TMP41]], i64 16, i1 false), !tbaa.struct [[TBAA_STRUCT29:![0-9]+]]
+// CHECK1-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[TMP43]], ptr align 8 [[TMP41]], i64 16, i1 false), !tbaa.struct [[TBAA_STRUCT41:![0-9]+]]
 // CHECK1-NEXT:    br label [[IFCONT6:%.*]]
 // CHECK1:       else5:
 // CHECK1-NEXT:    br label [[IFCONT6]]
@@ -946,24 +946,24 @@ void test() {
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_omp_reduction_inter_warp_copy_func2
-// CHECK1-SAME: (ptr [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR7]] {
+// CHECK1-SAME: (ptr [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR6]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTCNT_ADDR:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[TMP2:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
 // CHECK1-NEXT:    store ptr [[TMP0]], ptr [[DOTADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP3:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[TMP4:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[NVPTX_LANE_ID:%.*]] = and i32 [[TMP4]], 31
 // CHECK1-NEXT:    [[TMP5:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
 // CHECK1-NEXT:    [[NVPTX_WARP_ID:%.*]] = ashr i32 [[TMP5]], 5
 // CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[DOTADDR]], align 8
-// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 0, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[PRECOND:%.*]]
 // CHECK1:       precond:
-// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP7:%.*]] = load i32, ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[TMP7]], 4
 // CHECK1-NEXT:    br i1 [[TMP8]], label [[BODY:%.*]], label [[EXIT:%.*]]
 // CHECK1:       body:
@@ -982,7 +982,7 @@ void test() {
 // CHECK1-NEXT:    br label [[IFCONT]]
 // CHECK1:       ifcont:
 // CHECK1-NEXT:    call void @__kmpc_barrier(ptr @[[GLOB4]], i32 [[TMP2]])
-// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    [[IS_ACTIVE_THREAD:%.*]] = icmp ult i32 [[TMP3]], [[TMP14]]
 // CHECK1-NEXT:    br i1 [[IS_ACTIVE_THREAD]], label [[THEN2:%.*]], label [[ELSE3:%.*]]
 // CHECK1:       then2:
@@ -990,37 +990,37 @@ void test() {
 // CHECK1-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [1 x ptr], ptr [[TMP6]], i64 0, i64 0
 // CHECK1-NEXT:    [[TMP17:%.*]] = load ptr, ptr [[TMP16]], align 8, !tbaa [[TBAA10]]
 // CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr i32, ptr [[TMP17]], i32 [[TMP7]]
-// CHECK1-NEXT:    [[TMP19:%.*]] = load volatile i32, ptr addrspace(3) [[TMP15]], align 4, !tbaa [[TBAA14]]
-// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[TMP18]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    [[TMP19:%.*]] = load volatile i32, ptr addrspace(3) [[TMP15]], align 4, !tbaa [[TBAA15]]
+// CHECK1-NEXT:    store i32 [[TMP19]], ptr [[TMP18]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[IFCONT4:%.*]]
 // CHECK1:       else3:
 // CHECK1-NEXT:    br label [[IFCONT4]]
 // CHECK1:       ifcont4:
 // CHECK1-NEXT:    [[TMP20:%.*]] = add nsw i32 [[TMP7]], 1
-// CHECK1-NEXT:    store i32 [[TMP20]], ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i32 [[TMP20]], ptr [[DOTCNT_ADDR]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    br label [[PRECOND]]
 // CHECK1:       exit:
 // CHECK1-NEXT:    ret void
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined_wrapper
-// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR7]] {
+// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR6]] {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i16, align 2
 // CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
 // CHECK1-NEXT:    [[GLOBAL_ARGS:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA21]]
-// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA14]]
+// CHECK1-NEXT:    store i16 [[TMP0]], ptr [[DOTADDR]], align 2, !tbaa [[TBAA29]]
+// CHECK1-NEXT:    store i32 [[TMP1]], ptr [[DOTADDR1]], align 4, !tbaa [[TBAA15]]
 // CHECK1-NEXT:    store i32 0, ptr [[DOTZERO_ADDR]], align 4
 // CHECK1-NEXT:    call void @__kmpc_get_shared_variables(ptr [[GLOBAL_ARGS]])
 // CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ARGS]], align 8
 // CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 0
-// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP4:%.*]] = load ptr, ptr [[TMP3]], align 8, !tbaa [[TBAA32]]
 // CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 1
-// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP6:%.*]] = load ptr, ptr [[TMP5]], align 8, !tbaa [[TBAA32]]
 // CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr, ptr [[TMP2]], i64 2
-// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    [[TMP8:%.*]] = load ptr, ptr [[TMP7]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z17complex_reductionIdEvv_l16_omp_outlined_omp_outlined(ptr [[DOTADDR1]], ptr [[DOTZERO_ADDR]], ptr [[TMP4]], ptr [[TMP6]], ptr [[TMP8]]) #[[ATTR4]]
 // CHECK1-NEXT:    ret void
 //
@@ -1031,40 +1031,40 @@ void test() {
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA24]]
+// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA24]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[TMP0]], align 4, !tbaa [[TBAA16]]
-// CHECK1-NEXT:    store float [[TMP1]], ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA24]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load float, ptr [[TMP0]], align 4, !tbaa [[TBAA19]]
+// CHECK1-NEXT:    store float [[TMP1]], ptr [[__RE_]], align 4, !tbaa [[TBAA26]]
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[TMP2]], align 4, !tbaa [[TBAA16]]
-// CHECK1-NEXT:    store float [[TMP3]], ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA24]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load float, ptr [[TMP2]], align 4, !tbaa [[TBAA19]]
+// CHECK1-NEXT:    store float [[TMP3]], ptr [[__IM_]], align 4, !tbaa [[TBAA28]]
 // CHECK1-NEXT:    ret void
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIfE4realEv
-// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR6]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA18]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__RE_]], align 4, !tbaa [[TBAA26]]
 // CHECK1-NEXT:    ret float [[TMP0]]
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIfE4imagEv
-// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR6]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 4 dereferenceable(8) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA20]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load float, ptr [[__IM_]], align 4, !tbaa [[TBAA28]]
 // CHECK1-NEXT:    ret float [[TMP0]]
 //
 //
@@ -1074,39 +1074,39 @@ void test() {
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__RE_ADDR:%.*]] = alloca ptr, align 8
 // CHECK1-NEXT:    [[__IM_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
+// CHECK1-NEXT:    store ptr [[__RE]], ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA36]]
+// CHECK1-NEXT:    store ptr [[__IM]], ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA36]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[TMP0]], align 8, !tbaa [[TBAA24]]
-// CHECK1-NEXT:    store double [[TMP1]], ptr [[__RE_]], align 8, !tbaa [[TBAA26]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[__RE_ADDR]], align 8, !tbaa [[TBAA36]]
+// CHECK1-NEXT:    [[TMP1:%.*]] = load double, ptr [[TMP0]], align 8, !tbaa [[TBAA34]]
+// CHECK1-NEXT:    store double [[TMP1]], ptr [[__RE_]], align 8, !tbaa [[TBAA38]]
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA10]]
-// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[TMP2]], align 8, !tbaa [[TBAA24]]
-// CHECK1-NEXT:    store double [[TMP3]], ptr [[__IM_]], align 8, !tbaa [[TBAA28]]
+// CHECK1-NEXT:    [[TMP2:%.*]] = load ptr, ptr [[__IM_ADDR]], align 8, !tbaa [[TBAA36]]
+// CHECK1-NEXT:    [[TMP3:%.*]] = load double, ptr [[TMP2]], align 8, !tbaa [[TBAA34]]
+// CHECK1-NEXT:    store double [[TMP3]], ptr [[__IM_]], align 8, !tbaa [[TBAA40]]
 // CHECK1-NEXT:    ret void
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIdE4realEv
-// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR6]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__RE_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 0
-// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA26]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__RE_]], align 8, !tbaa [[TBAA38]]
 // CHECK1-NEXT:    ret double [[TMP0]]
 //
 //
 // CHECK1-LABEL: define {{[^@]+}}@_ZNKSt7complexIdE4imagEv
-// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR6]] comdat align 2 {
+// CHECK1-SAME: (ptr nonnull align 8 dereferenceable(16) [[THIS:%.*]]) #[[ATTR5]] comdat align 2 {
 // CHECK1-NEXT:  entry:
 // CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca ptr, align 8
-// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA10]]
+// CHECK1-NEXT:    store ptr [[THIS]], ptr [[THIS_ADDR]], align 8, !tbaa [[TBAA23]]
 // CHECK1-NEXT:    [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
 // CHECK1-NEXT:    [[__IM_:%.*]] = getelementptr inbounds %"class.std::complex.0", ptr [[THIS1]], i32 0, i32 1
-// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA28]]
+// CHECK1-NEXT:    [[TMP0:%.*]] = load double, ptr [[__IM_]], align 8, !tbaa [[TBAA40]]
 // CHECK1-NEXT:    ret double [[TMP0]]
 //
diff --git a/clang/unittests/CodeGen/TBAAMetadataTest.cpp b/clang/unittests/CodeGen/TBAAMetadataTest.cpp
index 9f64008358e4f..43269448ec945 100644
--- a/clang/unittests/CodeGen/TBAAMetadataTest.cpp
+++ b/clang/unittests/CodeGen/TBAAMetadataTest.cpp
@@ -39,7 +39,6 @@ auto OmnipotentCharC = MMTuple(
   MConstInt(0, 64)
 );
 
-
 auto OmnipotentCharCXX = MMTuple(
   MMString("omnipotent char"),
   MMTuple(
@@ -111,28 +110,23 @@ TEST(TBAAMetadataTest, BasicTypes) {
           MConstInt(0))));
   ASSERT_TRUE(I);
 
-  I = matchNext(I,
-      MInstruction(Instruction::Store,
-        MValType(PointerType::getUnqual(Compiler.Context)),
-        MMTuple(
-          MMTuple(
-            MMString("any pointer"),
-            OmnipotentCharC,
-            MConstInt(0)),
-          MSameAs(0),
-          MConstInt(0))));
+  auto AnyPointerC =
+      MMTuple(MMString("any pointer"), OmnipotentCharC, MConstInt(0, 64));
+
+  I = matchNext(
+      I, MInstruction(
+             Instruction::Store,
+             MValType(PointerType::getUnqual(Compiler.Context)),
+             MMTuple(MMTuple(MMString("p1 void"), AnyPointerC, MConstInt(0)),
+                     MSameAs(0), MConstInt(0))));
   ASSERT_TRUE(I);
 
-  I = matchNext(I,
-      MInstruction(Instruction::Store,
-        MValType(PointerType::getUnqual(Compiler.Context)),
-        MMTuple(
-          MMTuple(
-            MMString("any pointer"),
-            OmnipotentCharC,
-            MConstInt(0)),
-          MSameAs(0),
-          MConstInt(0))));
+  I = matchNext(
+      I, MInstruction(
+             Instruction::Store,
+             MValType(PointerType::getUnqual(Compiler.Context)),
+             MMTuple(MMTuple(MMString("p1 int"), AnyPointerC, MConstInt(0)),
+                     MSameAs(0), MConstInt(0))));
   ASSERT_TRUE(I);
 }
 



More information about the cfe-commits mailing list