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
@@ -740,7 +740,7 @@
 static bool expandMemCmp(CallInst *CI, const TargetTransformInfo *TTI,
                          const TargetLowering *TLI, const DataLayout *DL,
                          ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI,
-                         DomTreeUpdater *DTU) {
+                         DomTreeUpdater *DTU, const bool IsBCmp) {
   NumMemCmpCalls++;
 
   // Early exit from expansion if -Oz.
@@ -760,7 +760,8 @@
   }
   // TTI call to check if target would like to expand memcmp. Also, get the
   // available load sizes.
-  const bool IsUsedForZeroCmp = isOnlyUsedInZeroEqualityComparison(CI);
+  const bool IsUsedForZeroCmp =
+      IsBCmp || isOnlyUsedInZeroEqualityComparison(CI);
   bool OptForSize = CI->getFunction()->hasOptSize() ||
                     llvm::shouldOptimizeForSize(CI->getParent(), PSI, BFI);
   auto Options = TTI->enableMemCmpExpansion(OptForSize,
@@ -864,7 +865,7 @@
     LibFunc Func;
     if (TLI->getLibFunc(*CI, Func) &&
         (Func == LibFunc_memcmp || Func == LibFunc_bcmp) &&
-        expandMemCmp(CI, TTI, TL, &DL, PSI, BFI, DTU)) {
+        expandMemCmp(CI, TTI, TL, &DL, PSI, BFI, DTU, Func == LibFunc_bcmp)) {
       return true;
     }
   }
diff --git a/llvm/test/Transforms/ExpandMemCmp/X86/bcmp.ll b/llvm/test/Transforms/ExpandMemCmp/X86/bcmp.ll
--- a/llvm/test/Transforms/ExpandMemCmp/X86/bcmp.ll
+++ b/llvm/test/Transforms/ExpandMemCmp/X86/bcmp.ll
@@ -9,14 +9,9 @@
 ; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i64*
 ; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]], align 1
 ; X64-NEXT:    [[TMP4:%.*]] = load i64, i64* [[TMP2]], align 1
-; X64-NEXT:    [[TMP5:%.*]] = call i64 @llvm.bswap.i64(i64 [[TMP3]])
-; X64-NEXT:    [[TMP6:%.*]] = call i64 @llvm.bswap.i64(i64 [[TMP4]])
-; X64-NEXT:    [[TMP7:%.*]] = icmp ugt i64 [[TMP5]], [[TMP6]]
-; X64-NEXT:    [[TMP8:%.*]] = icmp ult i64 [[TMP5]], [[TMP6]]
-; X64-NEXT:    [[TMP9:%.*]] = zext i1 [[TMP7]] to i32
-; X64-NEXT:    [[TMP10:%.*]] = zext i1 [[TMP8]] to i32
-; X64-NEXT:    [[TMP11:%.*]] = sub i32 [[TMP9]], [[TMP10]]
-; X64-NEXT:    ret i32 [[TMP11]]
+; X64-NEXT:    [[TMP5:%.*]] = icmp ne i64 [[TMP3]], [[TMP4]]
+; X64-NEXT:    [[TMP6:%.*]] = zext i1 [[TMP5]] to i32
+; X64-NEXT:    ret i32 [[TMP6]]
 ;
   %call = tail call i32 @bcmp(i8* %x, i8* %y, i64 8)
   ret i32 %call