diff --git a/llvm/lib/CodeGen/ExpandMemCmp.cpp b/llvm/lib/CodeGen/ExpandMemCmp.cpp
--- a/llvm/lib/CodeGen/ExpandMemCmp.cpp
+++ b/llvm/lib/CodeGen/ExpandMemCmp.cpp
@@ -282,6 +282,8 @@
         ByteType, Builder.CreateBitCast(RhsSource, ByteType->getPointerTo()),
         OffsetBytes);
   }
+  Align LhsAlign = max(LhsSource->getPointerAlignment(DL), Align(1));
+  Align RhsAlign = max(RhsSource->getPointerAlignment(DL), Align(1));
   LhsSource = Builder.CreateBitCast(LhsSource, LoadSizeType->getPointerTo());
   RhsSource = Builder.CreateBitCast(RhsSource, LoadSizeType->getPointerTo());
 
@@ -290,13 +292,13 @@
   if (auto *C = dyn_cast<Constant>(LhsSource))
     Lhs = ConstantFoldLoadFromConstPtr(C, LoadSizeType, DL);
   if (!Lhs)
-    Lhs = Builder.CreateLoad(LoadSizeType, LhsSource);
+    Lhs = Builder.CreateAlignedLoad(LoadSizeType, LhsSource, LhsAlign);
 
   Value *Rhs = nullptr;
   if (auto *C = dyn_cast<Constant>(RhsSource))
     Rhs = ConstantFoldLoadFromConstPtr(C, LoadSizeType, DL);
   if (!Rhs)
-    Rhs = Builder.CreateLoad(LoadSizeType, RhsSource);
+    Rhs = Builder.CreateAlignedLoad(LoadSizeType, RhsSource, RhsAlign);
 
   // Swap bytes if required.
   if (NeedsBSwap) {
diff --git a/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll b/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
--- a/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
+++ b/llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
@@ -4,35 +4,28 @@
 declare i32 @bcmp(i8*, i8*, i64) nounwind readonly
 declare i32 @memcmp(i8*, i8*, i64) nounwind readonly
 
-define i1 @bcmp_b2(i8* %s1, i8* %s2) {
+define i1 @test_b2(i8* %s1, i8* %s2) {
 entry:
   %bcmp = call i32 @bcmp(i8* %s1, i8* %s2, i64 15)
   %ret = icmp eq i32 %bcmp, 0
   ret i1 %ret
 
-; CHECK-LABEL: bcmp_b2:
+; CHECK-LABEL: test_b2:
 ; CHECK-NOT:   bl bcmp
 ; CHECKN:      ldr  x
 ; CHECKN-NEXT: ldr  x
 ; CHECKN-NEXT: ldur x
 ; CHECKN-NEXT: ldur x
-; CHECKS:      ldr  x
-; CHECKS-NEXT: ldr  x
-; CHECKS-NEXT: ldr  w
-; CHECKS-NEXT: ldr  w
-; CHECKS-NEXT: ldrh w
-; CHECKS-NEXT: ldrh w
-; CHECKS-NEXT: ldrb w
-; CHECKS-NEXT: ldrb w
+; CHECKS-30:      ldrb
 }
 
-define i1 @bcmp_bs(i8* %s1, i8* %s2) optsize {
+define i1 @test_bs(i8* %s1, i8* %s2) optsize {
 entry:
   %memcmp = call i32 @memcmp(i8* %s1, i8* %s2, i64 31)
   %ret = icmp eq i32 %memcmp, 0
   ret i1 %ret
 
-; CHECK-LABEL: bcmp_bs:
+; CHECK-LABEL: test_bs:
 ; CHECKN-NOT:  bl memcmp
 ; CHECKN:      ldp  x
 ; CHECKN-NEXT: ldp  x
diff --git a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
--- a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
+++ b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
@@ -35,8 +35,8 @@
 define signext i32 @zeroEqualityTest01(i8* %x, i8* %y) {
 ; CHECK-LABEL: zeroEqualityTest01:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    ld 5, 0(3)
-; CHECK-NEXT:    ld 6, 0(4)
+; CHECK-NEXT:    ldx 5, 0, 3
+; CHECK-NEXT:    ldx 6, 0, 4
 ; CHECK-NEXT:    cmpld 5, 6
 ; CHECK-NEXT:    bne 0, .LBB1_2
 ; CHECK-NEXT:  # %bb.1: # %loadbb1
@@ -125,7 +125,7 @@
 define signext i32 @equalityFoldOneConstant(i8* %X) {
 ; CHECK-LABEL: equalityFoldOneConstant:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    ld 4, 0(3)
+; CHECK-NEXT:    ldx 4, 0, 3
 ; CHECK-NEXT:    li 5, 1
 ; CHECK-NEXT:    sldi 5, 5, 32
 ; CHECK-NEXT:    cmpld 4, 5
diff --git a/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll b/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll
--- a/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll
+++ b/llvm/test/CodeGen/PowerPC/memcmp-mergeexpand.ll
@@ -8,8 +8,8 @@
 define zeroext i1 @opeq1(
 ; PPC64LE-LABEL: opeq1:
 ; PPC64LE:       # %bb.0: # %"entry+land.rhs.i"
-; PPC64LE-NEXT:    ld 3, 0(3)
-; PPC64LE-NEXT:    ld 4, 0(4)
+; PPC64LE-NEXT:    ldx 3, 0, 3
+; PPC64LE-NEXT:    ldx 4, 0, 4
 ; PPC64LE-NEXT:    xor 3, 3, 4
 ; PPC64LE-NEXT:    cntlzd 3, 3
 ; PPC64LE-NEXT:    rldicl 3, 3, 58, 63