Index: llvm/include/llvm/Analysis/TargetTransformInfo.h
===================================================================
--- llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -801,6 +801,9 @@
     // be done with two 4-byte compares instead of 4+2+1-byte compares. This
     // requires all loads in LoadSizes to be doable in an unaligned way.
     bool AllowOverlappingLoads = false;
+
+    // Set to true will expand by cmp+or instead of xor+or.
+    bool PreferCmpToExpand = false;
   };
   MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
                                                bool IsZeroCmp) const;
Index: llvm/lib/CodeGen/ExpandMemCmp.cpp
===================================================================
--- llvm/lib/CodeGen/ExpandMemCmp.cpp
+++ llvm/lib/CodeGen/ExpandMemCmp.cpp
@@ -80,6 +80,7 @@
   BasicBlock *EndBlock;
   PHINode *PhiRes;
   const bool IsUsedForZeroCmp;
+  const bool IsPreferCmpToExpand;
   const DataLayout &DL;
   DomTreeUpdater *DTU;
   IRBuilder<> Builder;
@@ -223,8 +224,9 @@
     const bool IsUsedForZeroCmp, const DataLayout &TheDataLayout,
     DomTreeUpdater *DTU)
     : CI(CI), Size(Size), NumLoadsPerBlockForZeroCmp(Options.NumLoadsPerBlock),
-      IsUsedForZeroCmp(IsUsedForZeroCmp), DL(TheDataLayout), DTU(DTU),
-      Builder(CI) {
+      IsUsedForZeroCmp(IsUsedForZeroCmp),
+      IsPreferCmpToExpand(Options.PreferCmpToExpand), DL(TheDataLayout),
+      DTU(DTU), Builder(CI) {
   assert(Size > 0 && "zero blocks");
   // Scale the max size down if the target can load more bytes than we need.
   llvm::ArrayRef<unsigned> LoadSizes(Options.LoadSizes);
@@ -371,7 +373,7 @@
                                             unsigned &LoadIndex) {
   assert(LoadIndex < getNumLoads() &&
          "getCompareLoadPairs() called with no remaining loads");
-  std::vector<Value *> XorList, OrList;
+  std::vector<Value *> CompareList, OrList;
   Value *Diff = nullptr;
 
   const unsigned NumLoads =
@@ -398,10 +400,14 @@
 
     if (NumLoads != 1) {
       // If we have multiple loads per block, we need to generate a composite
-      // comparison using xor+or.
-      Diff = Builder.CreateXor(Loads.Lhs, Loads.Rhs);
-      Diff = Builder.CreateZExt(Diff, MaxLoadType);
-      XorList.push_back(Diff);
+      // comparison.
+      if (IsPreferCmpToExpand) {
+        Diff = Builder.CreateICmpNE(Loads.Lhs, Loads.Rhs);
+      } else {
+        Diff = Builder.CreateXor(Loads.Lhs, Loads.Rhs);
+        Diff = Builder.CreateZExt(Diff, MaxLoadType);
+      }
+      CompareList.push_back(Diff);
     } else {
       // If there's only one load per block, we just compare the loaded values.
       Cmp = Builder.CreateICmpNE(Loads.Lhs, Loads.Rhs);
@@ -421,7 +427,7 @@
 
   if (!Cmp) {
     // Pairwise OR the XOR results.
-    OrList = pairWiseOr(XorList);
+    OrList = pairWiseOr(CompareList);
 
     // Pairwise OR the OR results until one result left.
     while (OrList.size() != 1) {
@@ -429,7 +435,11 @@
     }
 
     assert(Diff && "Failed to find comparison diff");
-    Cmp = Builder.CreateICmpNE(OrList[0], ConstantInt::get(Diff->getType(), 0));
+    if (IsPreferCmpToExpand)
+      Cmp = OrList[0];
+    else
+      Cmp =
+          Builder.CreateICmpNE(OrList[0], ConstantInt::get(Diff->getType(), 0));
   }
 
   return Cmp;
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -2298,6 +2298,7 @@
     return Options;
   }
   Options.AllowOverlappingLoads = true;
+  Options.PreferCmpToExpand = true;
   Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
   Options.NumLoadsPerBlock = Options.MaxNumLoads;
   // TODO: Though vector loads usually perform well on AArch64, in some targets
Index: llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
===================================================================
--- llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
+++ llvm/test/CodeGen/AArch64/bcmp-inline-small.ll
@@ -70,18 +70,17 @@
 ; CHECKN-NEXT:    ldp x8, x9, [x0]
 ; CHECKN-NEXT:    ldp x10, x11, [x1]
 ; CHECKN-NEXT:    ldr x12, [x0, #16]
-; CHECKN-NEXT:    ldr x13, [x1, #16]
-; CHECKN-NEXT:    ldur x14, [x0, #23]
-; CHECKN-NEXT:    eor x8, x8, x10
-; CHECKN-NEXT:    ldur x15, [x1, #23]
-; CHECKN-NEXT:    eor x9, x9, x11
-; CHECKN-NEXT:    eor x10, x12, x13
-; CHECKN-NEXT:    orr x8, x8, x9
-; CHECKN-NEXT:    eor x11, x14, x15
-; CHECKN-NEXT:    orr x9, x10, x11
-; CHECKN-NEXT:    orr x8, x8, x9
-; CHECKN-NEXT:    cmp x8, #0
-; CHECKN-NEXT:    cset w0, eq
+; CHECKN-NEXT:    cmp x8, x10
+; CHECKN-NEXT:    ldr x8, [x1, #16]
+; CHECKN-NEXT:    ccmp x9, x11, #0, eq
+; CHECKN-NEXT:    ldur x9, [x0, #23]
+; CHECKN-NEXT:    ldur x10, [x1, #23]
+; CHECKN-NEXT:    cset w11, ne
+; CHECKN-NEXT:    cmp x12, x8
+; CHECKN-NEXT:    ccmp x9, x10, #0, eq
+; CHECKN-NEXT:    cset w8, ne
+; CHECKN-NEXT:    orr w8, w11, w8
+; CHECKN-NEXT:    eor w0, w8, #0x1
 ; CHECKN-NEXT:    ret
 ;
 ; CHECKS-LABEL: test_bs:
Index: llvm/test/CodeGen/AArch64/bcmp.ll
===================================================================
--- llvm/test/CodeGen/AArch64/bcmp.ll
+++ llvm/test/CodeGen/AArch64/bcmp.ll
@@ -46,10 +46,8 @@
 ; CHECK-NEXT:    ldrh w9, [x1]
 ; CHECK-NEXT:    ldrb w10, [x0, #2]
 ; CHECK-NEXT:    ldrb w11, [x1, #2]
-; CHECK-NEXT:    eor w8, w8, w9
-; CHECK-NEXT:    eor w9, w10, w11
-; CHECK-NEXT:    orr w8, w8, w9
-; CHECK-NEXT:    cmp w8, #0
+; CHECK-NEXT:    cmp w8, w9
+; CHECK-NEXT:    ccmp w10, w11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 3)
@@ -77,10 +75,8 @@
 ; CHECK-NEXT:    ldr w9, [x1]
 ; CHECK-NEXT:    ldrb w10, [x0, #4]
 ; CHECK-NEXT:    ldrb w11, [x1, #4]
-; CHECK-NEXT:    eor w8, w8, w9
-; CHECK-NEXT:    eor w9, w10, w11
-; CHECK-NEXT:    orr w8, w8, w9
-; CHECK-NEXT:    cmp w8, #0
+; CHECK-NEXT:    cmp w8, w9
+; CHECK-NEXT:    ccmp w10, w11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 5)
@@ -95,10 +91,8 @@
 ; CHECK-NEXT:    ldr w9, [x1]
 ; CHECK-NEXT:    ldrh w10, [x0, #4]
 ; CHECK-NEXT:    ldrh w11, [x1, #4]
-; CHECK-NEXT:    eor w8, w8, w9
-; CHECK-NEXT:    eor w9, w10, w11
-; CHECK-NEXT:    orr w8, w8, w9
-; CHECK-NEXT:    cmp w8, #0
+; CHECK-NEXT:    cmp w8, w9
+; CHECK-NEXT:    ccmp w10, w11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 6)
@@ -138,15 +132,12 @@
 define i1 @bcmp9(ptr %a, ptr %b) {
 ; CHECK-LABEL: bcmp9:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ldrb w9, [x0, #8]
-; CHECK-NEXT:    ldrb w10, [x1, #8]
 ; CHECK-NEXT:    ldr x8, [x0]
-; CHECK-NEXT:    ldr x11, [x1]
-; CHECK-NEXT:    eor w9, w9, w10
-; CHECK-NEXT:    and x9, x9, #0xff
-; CHECK-NEXT:    eor x8, x8, x11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    ldr x9, [x1]
+; CHECK-NEXT:    ldrb w10, [x0, #8]
+; CHECK-NEXT:    ldrb w11, [x1, #8]
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    ccmp x10, x11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 9)
@@ -157,15 +148,12 @@
 define i1 @bcmp10(ptr %a, ptr %b) {
 ; CHECK-LABEL: bcmp10:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ldrh w9, [x0, #8]
-; CHECK-NEXT:    ldrh w10, [x1, #8]
 ; CHECK-NEXT:    ldr x8, [x0]
-; CHECK-NEXT:    ldr x11, [x1]
-; CHECK-NEXT:    eor w9, w9, w10
-; CHECK-NEXT:    and x9, x9, #0xffff
-; CHECK-NEXT:    eor x8, x8, x11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    ldr x9, [x1]
+; CHECK-NEXT:    ldrh w10, [x0, #8]
+; CHECK-NEXT:    ldrh w11, [x1, #8]
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    ccmp x10, x11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 10)
@@ -196,10 +184,8 @@
 ; CHECK-NEXT:    ldr x9, [x1]
 ; CHECK-NEXT:    ldr w10, [x0, #8]
 ; CHECK-NEXT:    ldr w11, [x1, #8]
-; CHECK-NEXT:    eor x8, x8, x9
-; CHECK-NEXT:    eor w9, w10, w11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    ccmp x10, x11, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 12)
@@ -274,14 +260,11 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldp x8, x9, [x0]
 ; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldr w12, [x0, #16]
-; CHECK-NEXT:    ldr w13, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    eor w10, w12, w13
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    orr x8, x8, x10
-; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldr w8, [x0, #16]
+; CHECK-NEXT:    ldr w10, [x1, #16]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ccmp x8, x10, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 20)
@@ -294,14 +277,11 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldp x8, x9, [x0]
 ; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldr x12, [x0, #16]
-; CHECK-NEXT:    ldr x13, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    eor x10, x12, x13
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    orr x8, x8, x10
-; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldr x8, [x0, #16]
+; CHECK-NEXT:    ldr x10, [x1, #16]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ccmp x8, x10, #0, eq
 ; CHECK-NEXT:    cset w0, eq
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 24)
@@ -315,18 +295,17 @@
 ; CHECK-NEXT:    ldp x8, x9, [x0]
 ; CHECK-NEXT:    ldp x10, x11, [x1]
 ; CHECK-NEXT:    ldr x12, [x0, #16]
-; CHECK-NEXT:    ldr x13, [x1, #16]
-; CHECK-NEXT:    ldr w14, [x0, #24]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    ldr w15, [x1, #24]
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    eor x10, x12, x13
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    eor w11, w14, w15
-; CHECK-NEXT:    orr x9, x10, x11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    cmp x8, #0
-; CHECK-NEXT:    cset w0, eq
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldr x8, [x1, #16]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ldr w9, [x0, #24]
+; CHECK-NEXT:    ldr w10, [x1, #24]
+; CHECK-NEXT:    cset w11, ne
+; CHECK-NEXT:    cmp x12, x8
+; CHECK-NEXT:    ccmp x9, x10, #0, eq
+; CHECK-NEXT:    cset w8, ne
+; CHECK-NEXT:    orr w8, w11, w8
+; CHECK-NEXT:    eor w0, w8, #0x1
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 28)
   %r = icmp eq i32 %cr, 0
@@ -336,24 +315,22 @@
 define i1 @bcmp33(ptr %a, ptr %b) {
 ; CHECK-LABEL: bcmp33:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ldp x8, x9, [x0]
-; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldp x12, x13, [x0, #16]
-; CHECK-NEXT:    ldp x14, x15, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    ldrb w16, [x0, #32]
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    ldrb w17, [x1, #32]
-; CHECK-NEXT:    eor x10, x12, x14
-; CHECK-NEXT:    eor x11, x13, x15
-; CHECK-NEXT:    eor w12, w16, w17
-; CHECK-NEXT:    orr x9, x10, x11
-; CHECK-NEXT:    and x10, x12, #0xff
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    orr x8, x8, x10
-; CHECK-NEXT:    cmp x8, #0
-; CHECK-NEXT:    cset w0, eq
+; CHECK-NEXT:    ldrb w8, [x0, #32]
+; CHECK-NEXT:    ldrb w9, [x1, #32]
+; CHECK-NEXT:    ldp x10, x11, [x0]
+; CHECK-NEXT:    ldp x12, x13, [x1]
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    cset w8, eq
+; CHECK-NEXT:    cmp x10, x12
+; CHECK-NEXT:    ldp x9, x10, [x0, #16]
+; CHECK-NEXT:    ccmp x11, x13, #0, eq
+; CHECK-NEXT:    ldp x11, x12, [x1, #16]
+; CHECK-NEXT:    cset w13, ne
+; CHECK-NEXT:    cmp x9, x11
+; CHECK-NEXT:    ccmp x10, x12, #0, eq
+; CHECK-NEXT:    cset w9, ne
+; CHECK-NEXT:    orr w9, w13, w9
+; CHECK-NEXT:    bic w0, w8, w9
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 33)
   %r = icmp eq i32 %cr, 0
@@ -363,23 +340,22 @@
 define i1 @bcmp38(ptr %a, ptr %b) {
 ; CHECK-LABEL: bcmp38:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    ldp x8, x9, [x0]
-; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldp x12, x13, [x0, #16]
-; CHECK-NEXT:    ldp x14, x15, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    ldur x10, [x0, #30]
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    ldur x11, [x1, #30]
-; CHECK-NEXT:    eor x12, x12, x14
-; CHECK-NEXT:    eor x13, x13, x15
-; CHECK-NEXT:    orr x9, x12, x13
-; CHECK-NEXT:    eor x10, x10, x11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    orr x8, x8, x10
-; CHECK-NEXT:    cmp x8, #0
-; CHECK-NEXT:    cset w0, eq
+; CHECK-NEXT:    ldur x8, [x0, #30]
+; CHECK-NEXT:    ldur x9, [x1, #30]
+; CHECK-NEXT:    ldp x10, x11, [x0]
+; CHECK-NEXT:    ldp x12, x13, [x1]
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    cset w8, eq
+; CHECK-NEXT:    cmp x10, x12
+; CHECK-NEXT:    ldp x9, x10, [x0, #16]
+; CHECK-NEXT:    ccmp x11, x13, #0, eq
+; CHECK-NEXT:    ldp x11, x12, [x1, #16]
+; CHECK-NEXT:    cset w13, ne
+; CHECK-NEXT:    cmp x9, x11
+; CHECK-NEXT:    ccmp x10, x12, #0, eq
+; CHECK-NEXT:    cset w9, ne
+; CHECK-NEXT:    orr w9, w13, w9
+; CHECK-NEXT:    bic w0, w8, w9
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 38)
   %r = icmp eq i32 %cr, 0
@@ -391,25 +367,24 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldp x8, x9, [x0]
 ; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldp x12, x13, [x0, #16]
-; CHECK-NEXT:    ldp x14, x15, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    ldr x16, [x0, #32]
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    ldr x17, [x1, #32]
-; CHECK-NEXT:    ldur x18, [x0, #37]
-; CHECK-NEXT:    eor x10, x12, x14
-; CHECK-NEXT:    ldur x0, [x1, #37]
-; CHECK-NEXT:    eor x11, x13, x15
-; CHECK-NEXT:    eor x12, x16, x17
-; CHECK-NEXT:    orr x9, x10, x11
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    eor x13, x18, x0
-; CHECK-NEXT:    orr x10, x12, x13
-; CHECK-NEXT:    orr x8, x8, x10
-; CHECK-NEXT:    cmp x8, #0
-; CHECK-NEXT:    cset w0, eq
+; CHECK-NEXT:    ldr x12, [x0, #32]
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldp x8, x10, [x0, #16]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ldp x9, x11, [x1, #16]
+; CHECK-NEXT:    cset w13, ne
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    ldr x8, [x1, #32]
+; CHECK-NEXT:    ccmp x10, x11, #0, eq
+; CHECK-NEXT:    ldur x9, [x0, #37]
+; CHECK-NEXT:    ldur x10, [x1, #37]
+; CHECK-NEXT:    cset w11, ne
+; CHECK-NEXT:    cmp x12, x8
+; CHECK-NEXT:    ccmp x9, x10, #0, eq
+; CHECK-NEXT:    orr w9, w13, w11
+; CHECK-NEXT:    cset w8, ne
+; CHECK-NEXT:    orr w8, w9, w8
+; CHECK-NEXT:    eor w0, w8, #0x1
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 45)
   %r = icmp eq i32 %cr, 0
@@ -421,29 +396,28 @@
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    ldp x8, x9, [x0]
 ; CHECK-NEXT:    ldp x10, x11, [x1]
-; CHECK-NEXT:    ldp x12, x13, [x0, #16]
-; CHECK-NEXT:    ldp x14, x15, [x1, #16]
-; CHECK-NEXT:    eor x8, x8, x10
-; CHECK-NEXT:    eor x9, x9, x11
-; CHECK-NEXT:    ldp x16, x17, [x0, #32]
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    ldp x18, x2, [x1, #32]
-; CHECK-NEXT:    eor x12, x12, x14
-; CHECK-NEXT:    eor x13, x13, x15
-; CHECK-NEXT:    ldp x3, x0, [x0, #48]
-; CHECK-NEXT:    orr x9, x12, x13
-; CHECK-NEXT:    ldp x10, x11, [x1, #48]
-; CHECK-NEXT:    eor x14, x16, x18
-; CHECK-NEXT:    eor x15, x17, x2
-; CHECK-NEXT:    orr x12, x14, x15
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    eor x10, x3, x10
-; CHECK-NEXT:    eor x11, x0, x11
-; CHECK-NEXT:    orr x10, x10, x11
-; CHECK-NEXT:    orr x9, x12, x10
-; CHECK-NEXT:    orr x8, x8, x9
-; CHECK-NEXT:    cmp x8, #0
-; CHECK-NEXT:    cset w0, eq
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldp x8, x10, [x0, #16]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ldp x9, x11, [x1, #16]
+; CHECK-NEXT:    cset w12, ne
+; CHECK-NEXT:    cmp x8, x9
+; CHECK-NEXT:    ldp x8, x9, [x0, #32]
+; CHECK-NEXT:    ccmp x10, x11, #0, eq
+; CHECK-NEXT:    ldp x10, x11, [x1, #32]
+; CHECK-NEXT:    cset w13, ne
+; CHECK-NEXT:    cmp x8, x10
+; CHECK-NEXT:    ldp x14, x8, [x0, #48]
+; CHECK-NEXT:    ccmp x9, x11, #0, eq
+; CHECK-NEXT:    ldp x9, x10, [x1, #48]
+; CHECK-NEXT:    cset w11, ne
+; CHECK-NEXT:    cmp x14, x9
+; CHECK-NEXT:    orr w9, w12, w13
+; CHECK-NEXT:    ccmp x8, x10, #0, eq
+; CHECK-NEXT:    cset w8, ne
+; CHECK-NEXT:    orr w8, w11, w8
+; CHECK-NEXT:    orr w8, w9, w8
+; CHECK-NEXT:    eor w0, w8, #0x1
 ; CHECK-NEXT:    ret
   %cr = call i32 @bcmp(ptr %a, ptr %b, i64 64)
   %r = icmp eq i32 %cr, 0