Index: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -629,6 +629,10 @@
 
   MaxStoresPerMemmoveOptSize = MaxStoresPerMemmove = 4;
 
+  MaxLoadsPerMemcmpOptSize = 4;
+  MaxLoadsPerMemcmp = Subtarget->requiresStrictAlign()
+                      ? MaxLoadsPerMemcmpOptSize : 8;
+
   setStackPointerRegisterToSaveRestore(AArch64::SP);
 
   setSchedulingPreference(Sched::Hybrid);
Index: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -130,6 +130,9 @@
   int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                          const Instruction *I = nullptr);
 
+  TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
+                                                    bool IsZeroCmp) const;
+
   int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
                       unsigned AddressSpace, const Instruction *I = nullptr);
 
Index: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -618,6 +618,19 @@
   return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, I);
 }
 
+AArch64TTIImpl::TTI::MemCmpExpansionOptions
+AArch64TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
+  TTI::MemCmpExpansionOptions Options;
+  Options.AllowOverlappingLoads = !ST->requiresStrictAlign();
+  Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
+  Options.NumLoadsPerBlock = Options.MaxNumLoads;
+  // TODO: Though vector loads usually perform well on AArch64, in some targets
+  // they may wake up the FP unit, which raises the power consumption.  Perhaps
+  // they could be used with no holds barred (-O3).
+  Options.LoadSizes = {8, 4, 2, 1};
+  return Options;
+}
+
 int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
                                     unsigned Alignment, unsigned AddressSpace,
                                     const Instruction *I) {
Index: llvm/trunk/test/CodeGen/AArch64/bcmp-inline-small.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/bcmp-inline-small.ll
+++ llvm/trunk/test/CodeGen/AArch64/bcmp-inline-small.ll
@@ -0,0 +1,44 @@
+; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu                     | FileCheck %s --check-prefixes=CHECK,CHECKN
+; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu -mattr=strict-align | FileCheck %s --check-prefixes=CHECK,CHECKS
+
+declare i32 @bcmp(i8*, i8*, i64) nounwind readonly
+declare i32 @memcmp(i8*, i8*, i64) nounwind readonly
+
+define i1 @bcmp_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-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
+}
+
+define i1 @bcmp_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:
+; CHECKN-NOT:  bl memcmp
+; CHECKN:      ldp  x
+; CHECKN-NEXT: ldp  x
+; CHECKN-NEXT: ldr  x
+; CHECKN-NEXT: ldr  x
+; CHECKN-NEXT: ldur x
+; CHECKN-NEXT: ldur x
+; CHECKS:      bl memcmp
+}