diff --git a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp b/llvm/lib/Transforms/IPO/AttributorAttributes.cpp
--- a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp
+++ b/llvm/lib/Transforms/IPO/AttributorAttributes.cpp
@@ -5053,6 +5053,11 @@
     if (!PrivatizableType.getValue())
       return indicatePessimisticFixpoint();
 
+    // The dependence is optional so we don't give up once we give up on the
+    // alignment.
+    A.getAAFor<AAAlign>(*this, IRPosition::value(getAssociatedValue()),
+                        /* TrackDependence */ true, DepClassTy::OPTIONAL);
+
     // Avoid arguments with padding for now.
     if (!getIRPosition().hasAttr(Attribute::ByVal) &&
         !ArgumentPromotionPass::isDenselyPacked(PrivatizableType.getValue(),
@@ -5267,8 +5272,8 @@
 
   /// Extract values from \p Base according to the type \p PrivType at the
   /// call position \p ACS. The values are appended to \p ReplacementValues.
-  void createReplacementValues(Type *PrivType, AbstractCallSite ACS,
-                               Value *Base,
+  void createReplacementValues(Align Alignment, Type *PrivType,
+                               AbstractCallSite ACS, Value *Base,
                                SmallVectorImpl<Value *> &ReplacementValues) {
     assert(Base && "Expected base value!");
     assert(PrivType && "Expected privatizable type!");
@@ -5281,7 +5286,6 @@
       Base = BitCastInst::CreateBitOrPointerCast(Base, PrivType->getPointerTo(),
                                                  "", ACS.getInstruction());
 
-    // TODO: Improve the alignment of the loads.
     // Traverse the type, build GEPs and loads.
     if (auto *PrivStructType = dyn_cast<StructType>(PrivType)) {
       const StructLayout *PrivStructLayout = DL.getStructLayout(PrivStructType);
@@ -5291,7 +5295,7 @@
             constructPointer(PointeeTy->getPointerTo(), Base,
                              PrivStructLayout->getElementOffset(u), IRB, DL);
         LoadInst *L = new LoadInst(PointeeTy, Ptr, "", IP);
-        L->setAlignment(Align(1));
+        L->setAlignment(Alignment);
         ReplacementValues.push_back(L);
       }
     } else if (auto *PrivArrayType = dyn_cast<ArrayType>(PrivType)) {
@@ -5302,12 +5306,12 @@
         Value *Ptr =
             constructPointer(PointeePtrTy, Base, u * PointeeTySize, IRB, DL);
         LoadInst *L = new LoadInst(PointeePtrTy, Ptr, "", IP);
-        L->setAlignment(Align(1));
+        L->setAlignment(Alignment);
         ReplacementValues.push_back(L);
       }
     } else {
       LoadInst *L = new LoadInst(PrivType, Base, "", IP);
-      L->setAlignment(Align(1));
+      L->setAlignment(Alignment);
       ReplacementValues.push_back(L);
     }
   }
@@ -5333,6 +5337,9 @@
       return ChangeStatus::UNCHANGED;
 
     Argument *Arg = getAssociatedArgument();
+    // Query AAAlign attribute for alignment of associated argument to
+    // determine the best alignment of loads.
+    const auto &AlignAA = A.getAAFor<AAAlign>(*this, IRPosition::value(*Arg));
 
     // Callback to repair the associated function. A new alloca is placed at the
     // beginning and initialized with the values passed through arguments. The
@@ -5356,9 +5363,13 @@
     // of the privatizable type are loaded prior to the call and passed to the
     // new function version.
     Attributor::ArgumentReplacementInfo::ACSRepairCBTy ACSRepairCB =
-        [=](const Attributor::ArgumentReplacementInfo &ARI,
-            AbstractCallSite ACS, SmallVectorImpl<Value *> &NewArgOperands) {
+        [=, &AlignAA](const Attributor::ArgumentReplacementInfo &ARI,
+                      AbstractCallSite ACS,
+                      SmallVectorImpl<Value *> &NewArgOperands) {
+          // When no alignment is specified for the load instruction,
+          // natural alignment is assumed.
           createReplacementValues(
+              assumeAligned(AlignAA.getAssumedAlign()),
               PrivatizableType.getValue(), ACS,
               ACS.getCallArgOperand(ARI.getReplacedArg().getArgNo()),
               NewArgOperands);
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/2008-02-01-ReturnAttrs.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/2008-02-01-ReturnAttrs.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/2008-02-01-ReturnAttrs.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/2008-02-01-ReturnAttrs.ll
@@ -44,7 +44,7 @@
 ; IS__TUNIT_NPM-NEXT:  entry:
 ; IS__TUNIT_NPM-NEXT:    [[X_ADDR:%.*]] = alloca i32
 ; IS__TUNIT_NPM-NEXT:    store i32 [[X]], i32* [[X_ADDR]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[X_ADDR]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[X_ADDR]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = call i32 @deref(i32 [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[TMP1]]
 ;
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/attributes.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/attributes.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/attributes.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/attributes.ll
@@ -132,7 +132,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <4 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <4 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(32) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <4 x i64>, <4 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <4 x i64>, <4 x i64>* [[TMP]], align 32
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @promote_avx2(<4 x i64>* noalias nocapture nofree nonnull writeonly align 32 dereferenceable(32) [[TMP2]], <4 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <4 x i64>, <4 x i64>* [[TMP2]], align 32
 ; IS__TUNIT_NPM-NEXT:    store <4 x i64> [[TMP4]], <4 x i64>* [[ARG]], align 2
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/min-legal-vector-width.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/min-legal-vector-width.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/min-legal-vector-width.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/X86/min-legal-vector-width.ll
@@ -54,7 +54,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
@@ -141,7 +141,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
@@ -228,7 +228,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx512_legal512_prefer512_call_avx512_legal512_prefer256(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
@@ -315,7 +315,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx512_legal512_prefer256_call_avx512_legal512_prefer512(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
@@ -570,7 +570,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx2_legal256_prefer256_call_avx2_legal512_prefer256(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
@@ -657,7 +657,7 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = alloca <8 x i64>, align 32
 ; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = bitcast <8 x i64>* [[TMP]] to i8*
 ; IS__TUNIT_NPM-NEXT:    call void @llvm.memset.p0i8.i64(i8* nocapture nonnull writeonly align 32 dereferenceable(64) [[TMP3]], i8 0, i64 32, i1 false)
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* [[TMP]], align 64
 ; IS__TUNIT_NPM-NEXT:    call fastcc void @callee_avx2_legal512_prefer256_call_avx2_legal256_prefer256(<8 x i64>* noalias nocapture nofree nonnull writeonly align 64 dereferenceable(64) [[TMP2]], <8 x i64> [[TMP0]])
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = load <8 x i64>, <8 x i64>* [[TMP2]], align 64
 ; IS__TUNIT_NPM-NEXT:    store <8 x i64> [[TMP4]], <8 x i64>* [[ARG]], align 2
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/alignment.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/alignment.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/alignment.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/alignment.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
-; RUN: opt -attributor -attributor-manifest-internal  -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=4 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_NPM,NOT_CGSCC_OPM,NOT_TUNIT_NPM,IS__TUNIT____,IS________OPM,IS__TUNIT_OPM
-; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal  -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=4 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_OPM,NOT_CGSCC_NPM,NOT_TUNIT_OPM,IS__TUNIT____,IS________NPM,IS__TUNIT_NPM
+; RUN: opt -attributor -attributor-manifest-internal  -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=11 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_NPM,NOT_CGSCC_OPM,NOT_TUNIT_NPM,IS__TUNIT____,IS________OPM,IS__TUNIT_OPM
+; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-manifest-internal  -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=11 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_OPM,NOT_CGSCC_NPM,NOT_TUNIT_OPM,IS__TUNIT____,IS________NPM,IS__TUNIT_NPM
 ; RUN: opt -attributor-cgscc -attributor-manifest-internal  -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_NPM,IS__CGSCC____,IS________OPM,IS__CGSCC_OPM
 ; RUN: opt -aa-pipeline=basic-aa -passes=attributor-cgscc -attributor-manifest-internal  -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_OPM,IS__CGSCC____,IS________NPM,IS__CGSCC_NPM
 
@@ -51,3 +51,113 @@
 }
 
 declare void @z(i32)
+
+; Test2
+; Different alignemnt privatizable arguments
+define internal i32 @test(i32* %X, i64* %Y) {
+; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@test
+; IS__TUNIT_OPM-SAME: (i32* noalias nocapture nofree nonnull readonly align 4 dereferenceable(4) [[X:%.*]], i64* noalias nocapture nofree nonnull readonly align 8 dereferenceable(8) [[Y:%.*]])
+; IS__TUNIT_OPM-NEXT:    [[A:%.*]] = load i32, i32* [[X]], align 4
+; IS__TUNIT_OPM-NEXT:    [[B:%.*]] = load i64, i64* [[Y]], align 8
+; IS__TUNIT_OPM-NEXT:    [[C:%.*]] = add i32 [[A]], 1
+; IS__TUNIT_OPM-NEXT:    [[D:%.*]] = add i64 [[B]], 1
+; IS__TUNIT_OPM-NEXT:    [[COND:%.*]] = icmp sgt i64 [[D]], -1
+; IS__TUNIT_OPM-NEXT:    br i1 [[COND]], label [[RETURN1:%.*]], label [[RETURN2:%.*]]
+; IS__TUNIT_OPM:       Return1:
+; IS__TUNIT_OPM-NEXT:    ret i32 [[C]]
+; IS__TUNIT_OPM:       Return2:
+; IS__TUNIT_OPM-NEXT:    ret i32 [[A]]
+;
+; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@test
+; IS__TUNIT_NPM-SAME: (i32 [[TMP0:%.*]], i64 [[TMP1:%.*]])
+; IS__TUNIT_NPM-NEXT:    [[Y_PRIV:%.*]] = alloca i64
+; IS__TUNIT_NPM-NEXT:    store i64 [[TMP1]], i64* [[Y_PRIV]]
+; IS__TUNIT_NPM-NEXT:    [[X_PRIV:%.*]] = alloca i32
+; IS__TUNIT_NPM-NEXT:    store i32 [[TMP0]], i32* [[X_PRIV]]
+; IS__TUNIT_NPM-NEXT:    [[A:%.*]] = load i32, i32* [[X_PRIV]], align 4
+; IS__TUNIT_NPM-NEXT:    [[B:%.*]] = load i64, i64* [[Y_PRIV]], align 8
+; IS__TUNIT_NPM-NEXT:    [[C:%.*]] = add i32 [[A]], 1
+; IS__TUNIT_NPM-NEXT:    [[D:%.*]] = add i64 [[B]], 1
+; IS__TUNIT_NPM-NEXT:    [[COND:%.*]] = icmp sgt i64 [[D]], -1
+; IS__TUNIT_NPM-NEXT:    br i1 [[COND]], label [[RETURN1:%.*]], label [[RETURN2:%.*]]
+; IS__TUNIT_NPM:       Return1:
+; IS__TUNIT_NPM-NEXT:    ret i32 [[C]]
+; IS__TUNIT_NPM:       Return2:
+; IS__TUNIT_NPM-NEXT:    ret i32 [[A]]
+;
+; IS__CGSCC____-LABEL: define {{[^@]+}}@test
+; IS__CGSCC____-SAME: (i32* nocapture nofree nonnull readonly align 4 dereferenceable(4) [[X:%.*]], i64* nocapture nofree nonnull readonly align 8 dereferenceable(8) [[Y:%.*]])
+; IS__CGSCC____-NEXT:    [[A:%.*]] = load i32, i32* [[X]], align 4
+; IS__CGSCC____-NEXT:    [[B:%.*]] = load i64, i64* [[Y]], align 8
+; IS__CGSCC____-NEXT:    [[C:%.*]] = add i32 [[A]], 1
+; IS__CGSCC____-NEXT:    [[D:%.*]] = add i64 [[B]], 1
+; IS__CGSCC____-NEXT:    [[COND:%.*]] = icmp sgt i64 [[D]], -1
+; IS__CGSCC____-NEXT:    br i1 [[COND]], label [[RETURN1:%.*]], label [[RETURN2:%.*]]
+; IS__CGSCC____:       Return1:
+; IS__CGSCC____-NEXT:    ret i32 [[C]]
+; IS__CGSCC____:       Return2:
+; IS__CGSCC____-NEXT:    ret i32 [[A]]
+;
+  %A = load i32, i32* %X
+  %B = load i64, i64* %Y
+  %C = add i32 %A, 1
+  %D = add i64 %B, 1
+  %cond = icmp sgt i64 %D, -1
+  br i1 %cond, label %Return1, label %Return2
+Return1:
+  ret i32 %C
+Return2:
+  ret i32 %A
+}
+
+define internal i32 @caller(i32* %A) {
+; IS__TUNIT_OPM-LABEL: define {{[^@]+}}@caller
+; IS__TUNIT_OPM-SAME: (i32* noalias nocapture nofree nonnull readonly align 4 dereferenceable(4) [[A:%.*]])
+; IS__TUNIT_OPM-NEXT:    [[B:%.*]] = alloca i64
+; IS__TUNIT_OPM-NEXT:    store i64 1, i64* [[B]], align 8
+; IS__TUNIT_OPM-NEXT:    [[C:%.*]] = call i32 @test(i32* noalias nocapture nofree nonnull readonly align 4 dereferenceable(4) [[A]], i64* noalias nocapture nofree nonnull readonly align 8 dereferenceable(8) [[B]])
+; IS__TUNIT_OPM-NEXT:    ret i32 [[C]]
+;
+; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@caller
+; IS__TUNIT_NPM-SAME: (i32 [[TMP0:%.*]])
+; IS__TUNIT_NPM-NEXT:    [[A_PRIV:%.*]] = alloca i32
+; IS__TUNIT_NPM-NEXT:    store i32 [[TMP0]], i32* [[A_PRIV]]
+; IS__TUNIT_NPM-NEXT:    [[B:%.*]] = alloca i64
+; IS__TUNIT_NPM-NEXT:    store i64 1, i64* [[B]], align 8
+; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[A_PRIV]], align 4
+; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = load i64, i64* [[B]], align 8
+; IS__TUNIT_NPM-NEXT:    [[C:%.*]] = call i32 @test(i32 [[TMP2]], i64 [[TMP3]])
+; IS__TUNIT_NPM-NEXT:    ret i32 [[C]]
+;
+; IS__CGSCC____-LABEL: define {{[^@]+}}@caller
+; IS__CGSCC____-SAME: (i32* nocapture nofree nonnull readonly align 4 dereferenceable(4) [[A:%.*]])
+; IS__CGSCC____-NEXT:    [[B:%.*]] = alloca i64
+; IS__CGSCC____-NEXT:    store i64 1, i64* [[B]], align 8
+; IS__CGSCC____-NEXT:    [[C:%.*]] = call i32 @test(i32* nocapture nofree nonnull readonly align 4 dereferenceable(4) [[A]], i64* noalias nocapture nofree nonnull readonly align 8 dereferenceable(8) [[B]])
+; IS__CGSCC____-NEXT:    ret i32 [[C]]
+;
+  %B = alloca i64
+  store i64 1, i64* %B
+  %C = call i32 @test(i32* %A, i64* %B)
+  ret i32 %C
+}
+
+define i32 @callercaller() {
+; NOT_TUNIT_NPM-LABEL: define {{[^@]+}}@callercaller()
+; NOT_TUNIT_NPM-NEXT:    [[B:%.*]] = alloca i32
+; NOT_TUNIT_NPM-NEXT:    store i32 2, i32* [[B]], align 4
+; NOT_TUNIT_NPM-NEXT:    [[X:%.*]] = call i32 @caller(i32* noalias nocapture nofree nonnull readonly align 4 dereferenceable(4) [[B]])
+; NOT_TUNIT_NPM-NEXT:    ret i32 [[X]]
+;
+; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@callercaller()
+; IS__TUNIT_NPM-NEXT:    [[B:%.*]] = alloca i32
+; IS__TUNIT_NPM-NEXT:    store i32 2, i32* [[B]], align 4
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B]], align 4
+; IS__TUNIT_NPM-NEXT:    [[X:%.*]] = call i32 @caller(i32 [[TMP1]])
+; IS__TUNIT_NPM-NEXT:    ret i32 [[X]]
+;
+  %B = alloca i32
+  store i32 2, i32* %B
+  %X = call i32 @caller(i32* %B)
+  ret i32 %X
+}
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/attrs.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/attrs.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/attrs.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/attrs.ll
@@ -107,10 +107,10 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; IS__TUNIT_NPM-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[S_CAST:%.*]] = bitcast %struct.ss* [[S]] to i32*
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[S_0_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 1
-; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[X]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 8
+; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[X]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[C:%.*]] = call i32 @f(i32 [[TMP0]], i64 [[TMP1]], i32 [[TMP2]], i32 zeroext 0)
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[C]]
 ;
@@ -126,7 +126,7 @@
 ; IS__CGSCC_OPM-NEXT:    ret i32 [[C]]
 ;
 ; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@test
-; IS__CGSCC_NPM-SAME: (i32* nocapture nofree nonnull readonly dereferenceable(4) [[X:%.*]])
+; IS__CGSCC_NPM-SAME: (i32* nocapture nofree nonnull readonly align 4 dereferenceable(4) [[X:%.*]])
 ; IS__CGSCC_NPM-NEXT:  entry:
 ; IS__CGSCC_NPM-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]]
 ; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
@@ -136,8 +136,8 @@
 ; IS__CGSCC_NPM-NEXT:    [[S_CAST:%.*]] = bitcast %struct.ss* [[S]] to i32*
 ; IS__CGSCC_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST]], align 8
 ; IS__CGSCC_NPM-NEXT:    [[S_0_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 1
-; IS__CGSCC_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[X]], align 1
+; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 8
+; IS__CGSCC_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[X]], align 4
 ; IS__CGSCC_NPM-NEXT:    [[C:%.*]] = call i32 @f(i32 [[TMP0]], i64 [[TMP1]], i32 [[TMP2]])
 ; IS__CGSCC_NPM-NEXT:    ret i32 [[C]]
 ;
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/basictest.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/basictest.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/basictest.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/basictest.ll
@@ -51,8 +51,8 @@
 ; IS__TUNIT_NPM-NEXT:    store i32 [[TMP0]], i32* [[B_PRIV]]
 ; IS__TUNIT_NPM-NEXT:    [[A:%.*]] = alloca i32
 ; IS__TUNIT_NPM-NEXT:    store i32 1, i32* [[A]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[A]], align 1
-; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B_PRIV]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[A]], align 4
+; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B_PRIV]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[C:%.*]] = call i32 @test(i32 [[TMP2]], i32 [[TMP3]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[C]]
 ;
@@ -79,7 +79,7 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@callercaller()
 ; IS__TUNIT_NPM-NEXT:    [[B:%.*]] = alloca i32
 ; IS__TUNIT_NPM-NEXT:    store i32 2, i32* [[B]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[X:%.*]] = call i32 @caller(i32 [[TMP1]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[X]]
 ;
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/byval-2.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/byval-2.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/byval-2.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/byval-2.ll
@@ -67,7 +67,7 @@
 ; IS__CGSCC_OPM-NEXT:    ret i32 0
 ;
 ; IS__CGSCC_NPM-LABEL: define {{[^@]+}}@test
-; IS__CGSCC_NPM-SAME: (i32* nocapture nofree nonnull readonly dereferenceable(4) [[X:%.*]])
+; IS__CGSCC_NPM-SAME: (i32* nocapture nofree nonnull readonly align 4 dereferenceable(4) [[X:%.*]])
 ; IS__CGSCC_NPM-NEXT:  entry:
 ; IS__CGSCC_NPM-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]]
 ; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/byval.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/byval.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/byval.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/byval.ll
@@ -123,14 +123,14 @@
 ; IS__TUNIT_NPM-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; IS__TUNIT_NPM-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[S_CAST1:%.*]] = bitcast %struct.ss* [[S]] to i32*
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST1]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST1]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[S_0_12:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_12]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_12]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[C0:%.*]] = call i32 @f(i32 [[TMP0]], i64 [[TMP1]])
 ; IS__TUNIT_NPM-NEXT:    [[S_CAST:%.*]] = bitcast %struct.ss* [[S]] to i32*
-; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[S_CAST]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[S_CAST]], align 32
 ; IS__TUNIT_NPM-NEXT:    [[S_0_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = load i64, i64* [[S_0_1]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP3:%.*]] = load i64, i64* [[S_0_1]], align 32
 ; IS__TUNIT_NPM-NEXT:    [[C1:%.*]] = call i32 @g(i32 [[TMP2]], i64 [[TMP3]])
 ; IS__TUNIT_NPM-NEXT:    [[A:%.*]] = add i32 [[C0]], [[C1]]
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[A]]
@@ -151,18 +151,18 @@
 ; IS__CGSCC_NPM-NEXT:  entry:
 ; IS__CGSCC_NPM-NEXT:    [[S:%.*]] = alloca [[STRUCT_SS:%.*]]
 ; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 0
-; IS__CGSCC_NPM-NEXT:    store i32 1, i32* [[TMP1]], align 8
+; IS__CGSCC_NPM-NEXT:    store i32 1, i32* [[TMP1]], align 32
 ; IS__CGSCC_NPM-NEXT:    [[TMP4:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
 ; IS__CGSCC_NPM-NEXT:    store i64 2, i64* [[TMP4]], align 4
 ; IS__CGSCC_NPM-NEXT:    [[S_CAST:%.*]] = bitcast %struct.ss* [[S]] to i32*
-; IS__CGSCC_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST]], align 8
+; IS__CGSCC_NPM-NEXT:    [[TMP0:%.*]] = load i32, i32* [[S_CAST]], align 32
 ; IS__CGSCC_NPM-NEXT:    [[S_0_1:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 1
+; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i64, i64* [[S_0_1]], align 8
 ; IS__CGSCC_NPM-NEXT:    [[C0:%.*]] = call i32 @f(i32 [[TMP0]], i64 [[TMP1]])
 ; IS__CGSCC_NPM-NEXT:    [[S_CAST1:%.*]] = bitcast %struct.ss* [[S]] to i32*
-; IS__CGSCC_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[S_CAST1]], align 8
+; IS__CGSCC_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[S_CAST1]], align 32
 ; IS__CGSCC_NPM-NEXT:    [[S_0_12:%.*]] = getelementptr [[STRUCT_SS]], %struct.ss* [[S]], i32 0, i32 1
-; IS__CGSCC_NPM-NEXT:    [[TMP3:%.*]] = load i64, i64* [[S_0_12]], align 1
+; IS__CGSCC_NPM-NEXT:    [[TMP3:%.*]] = load i64, i64* [[S_0_12]], align 32
 ; IS__CGSCC_NPM-NEXT:    [[C1:%.*]] = call i32 @g(i32 [[TMP2]], i64 [[TMP3]])
 ; IS__CGSCC_NPM-NEXT:    [[A:%.*]] = add i32 [[C0]], [[C1]]
 ; IS__CGSCC_NPM-NEXT:    ret i32 [[A]]
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/control-flow2.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/control-flow2.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/control-flow2.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/control-flow2.ll
@@ -56,7 +56,7 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@foo()
 ; IS__TUNIT_NPM-NEXT:    [[A:%.*]] = alloca i32
 ; IS__TUNIT_NPM-NEXT:    store i32 17, i32* [[A]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[A]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[A]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[X:%.*]] = call i32 @callee(i1 false, i32 [[TMP1]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[X]]
 ;
diff --git a/llvm/test/Transforms/Attributor/ArgumentPromotion/profile.ll b/llvm/test/Transforms/Attributor/ArgumentPromotion/profile.ll
--- a/llvm/test/Transforms/Attributor/ArgumentPromotion/profile.ll
+++ b/llvm/test/Transforms/Attributor/ArgumentPromotion/profile.ll
@@ -17,7 +17,7 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@caller()
 ; IS__TUNIT_NPM-NEXT:    [[X:%.*]] = alloca i32
 ; IS__TUNIT_NPM-NEXT:    store i32 42, i32* [[X]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[X]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[X]], align 4
 ; IS__TUNIT_NPM-NEXT:    call void @promote_i32_ptr(i32 [[TMP1]]), !prof !0
 ; IS__TUNIT_NPM-NEXT:    ret void
 ;
diff --git a/llvm/test/Transforms/Attributor/IPConstantProp/2009-09-24-byval-ptr.ll b/llvm/test/Transforms/Attributor/IPConstantProp/2009-09-24-byval-ptr.ll
--- a/llvm/test/Transforms/Attributor/IPConstantProp/2009-09-24-byval-ptr.ll
+++ b/llvm/test/Transforms/Attributor/IPConstantProp/2009-09-24-byval-ptr.ll
@@ -104,9 +104,9 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@unions()
 ; IS__TUNIT_NPM-NEXT:  entry:
 ; IS__TUNIT_NPM-NEXT:    [[MYSTR_CAST:%.*]] = bitcast %struct.MYstr* @mystr to i8*
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i8, i8* [[MYSTR_CAST]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i8, i8* [[MYSTR_CAST]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[MYSTR_0_1:%.*]] = getelementptr [[STRUCT_MYSTR:%.*]], %struct.MYstr* @mystr, i32 0, i32 1
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_1]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_1]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[RESULT:%.*]] = call i32 @vfu2(i8 [[TMP0]], i32 [[TMP1]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[RESULT]]
 ;
@@ -192,9 +192,9 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@unions_v2()
 ; IS__TUNIT_NPM-NEXT:  entry:
 ; IS__TUNIT_NPM-NEXT:    [[MYSTR_CAST:%.*]] = bitcast %struct.MYstr* @mystr to i8*
-; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i8, i8* [[MYSTR_CAST]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP0:%.*]] = load i8, i8* [[MYSTR_CAST]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[MYSTR_0_1:%.*]] = getelementptr [[STRUCT_MYSTR:%.*]], %struct.MYstr* @mystr, i32 0, i32 1
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_1]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_1]], align 8
 ; IS__TUNIT_NPM-NEXT:    [[RESULT:%.*]] = call i32 @vfu2_v2(i8 [[TMP0]], i32 [[TMP1]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[RESULT]]
 ;
@@ -208,7 +208,7 @@
 ; IS__CGSCC_NPM-NEXT:    [[MYSTR_CAST1:%.*]] = bitcast %struct.MYstr* @mystr to i8*
 ; IS__CGSCC_NPM-NEXT:    [[TMP0:%.*]] = load i8, i8* [[MYSTR_CAST1]], align 8
 ; IS__CGSCC_NPM-NEXT:    [[MYSTR_0_12:%.*]] = getelementptr [[STRUCT_MYSTR:%.*]], %struct.MYstr* @mystr, i32 0, i32 1
-; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_12]], align 1
+; IS__CGSCC_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[MYSTR_0_12]], align 8
 ; IS__CGSCC_NPM-NEXT:    [[RESULT:%.*]] = call i32 @vfu2_v2(i8 [[TMP0]], i32 [[TMP1]])
 ; IS__CGSCC_NPM-NEXT:    ret i32 [[RESULT]]
 ;
diff --git a/llvm/test/Transforms/Attributor/internal-noalias.ll b/llvm/test/Transforms/Attributor/internal-noalias.ll
--- a/llvm/test/Transforms/Attributor/internal-noalias.ll
+++ b/llvm/test/Transforms/Attributor/internal-noalias.ll
@@ -155,8 +155,8 @@
 ; IS__TUNIT_NPM-LABEL: define {{[^@]+}}@visible_local_2()
 ; IS__TUNIT_NPM-NEXT:    [[B:%.*]] = alloca i32, align 4
 ; IS__TUNIT_NPM-NEXT:    store i32 5, i32* [[B]], align 4
-; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B]], align 1
-; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[B]], align 1
+; IS__TUNIT_NPM-NEXT:    [[TMP1:%.*]] = load i32, i32* [[B]], align 4
+; IS__TUNIT_NPM-NEXT:    [[TMP2:%.*]] = load i32, i32* [[B]], align 4
 ; IS__TUNIT_NPM-NEXT:    [[CALL:%.*]] = call i32 @noalias_args_argmem_ro(i32 [[TMP1]], i32 [[TMP2]])
 ; IS__TUNIT_NPM-NEXT:    ret i32 [[CALL]]
 ;
diff --git a/llvm/test/Transforms/Attributor/misc_crash.ll b/llvm/test/Transforms/Attributor/misc_crash.ll
--- a/llvm/test/Transforms/Attributor/misc_crash.ll
+++ b/llvm/test/Transforms/Attributor/misc_crash.ll
@@ -77,7 +77,7 @@
 }
 
 define void @func4() {
-; CHECK-LABEL: define {{[^@]+}}@func4
+; CHECK-LABEL: define {{[^@]+}}@func4()
 ; CHECK-NEXT:    call void @func5()
 ; CHECK-NEXT:    ret void
 ;
@@ -86,13 +86,13 @@
 }
 
 define internal void @func5(i32 %0) {
-; CHECK-LABEL: define {{[^@]+}}@func5
-; CHECK-NEXT:    [[TMP1:%.*]] = alloca i8*
-; CHECK-NEXT:    br label %block
+; CHECK-LABEL: define {{[^@]+}}@func5()
+; CHECK-NEXT:    [[TMP:%.*]] = alloca i8*
+; CHECK-NEXT:    br label [[BLOCK:%.*]]
 ; CHECK:       block:
-; CHECK-NEXT:    store i8* blockaddress(@func5, %block), i8** [[TMP1]]
-; CHECK-NEXT:    [[TMP2:%.*]] = load i8*, i8** [[TMP1]]
-; CHECK-NEXT:    call void @func6(i8* [[TMP2]])
+; CHECK-NEXT:    store i8* blockaddress(@func5, [[BLOCK]]), i8** [[TMP]], align 8
+; CHECK-NEXT:    [[ADDR:%.*]] = load i8*, i8** [[TMP]], align 8
+; CHECK-NEXT:    call void @func6(i8* [[ADDR]])
 ; CHECK-NEXT:    ret void
 ;
   %tmp = alloca i8*