Index: lib/Target/X86/X86TargetTransformInfo.cpp
===================================================================
--- lib/Target/X86/X86TargetTransformInfo.cpp
+++ lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2537,8 +2537,10 @@
 }
 
 bool X86TTIImpl::enableMemCmpExpansion(unsigned &MaxLoadSize) {
-  // TODO: We can increase these based on available vector ops.
-  MaxLoadSize = ST->is64Bit() ? 8 : 4;
+  MaxLoadSize = getRegisterBitWidth(true) / 8;
+  if (MaxLoadSize == 0) {
+    MaxLoadSize = getRegisterBitWidth(false) / 8;
+  }
   return true;
 }
 
Index: test/Transforms/CodeGenPrepare/X86/memcmp.ll
===================================================================
--- test/Transforms/CodeGenPrepare/X86/memcmp.ll
+++ test/Transforms/CodeGenPrepare/X86/memcmp.ll
@@ -363,35 +363,18 @@
 ; X32-NEXT:    ret i32 [[CALL]]
 ;
 ; X64-LABEL: @cmp16(
-; X64-NEXT:  loadbb:
-; X64-NEXT:    [[TMP0:%.*]] = bitcast i8* [[X:%.*]] to i64*
-; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[Y:%.*]] to i64*
-; X64-NEXT:    [[TMP2:%.*]] = load i64, i64* [[TMP0]]
-; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
-; X64-NEXT:    [[TMP4:%.*]] = call i64 @llvm.bswap.i64(i64 [[TMP2]])
-; X64-NEXT:    [[TMP5:%.*]] = call i64 @llvm.bswap.i64(i64 [[TMP3]])
-; X64-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[TMP4]], [[TMP5]]
-; X64-NEXT:    br i1 [[TMP6]], label [[LOADBB1:%.*]], label [[RES_BLOCK:%.*]]
-; X64:       res_block:
-; X64-NEXT:    [[PHI_SRC1:%.*]] = phi i64 [ [[TMP4]], [[LOADBB:%.*]] ], [ [[TMP15:%.*]], [[LOADBB1]] ]
-; X64-NEXT:    [[PHI_SRC2:%.*]] = phi i64 [ [[TMP5]], [[LOADBB]] ], [ [[TMP16:%.*]], [[LOADBB1]] ]
-; X64-NEXT:    [[TMP7:%.*]] = icmp ult i64 [[PHI_SRC1]], [[PHI_SRC2]]
-; X64-NEXT:    [[TMP8:%.*]] = select i1 [[TMP7]], i32 -1, i32 1
-; X64-NEXT:    br label [[ENDBLOCK:%.*]]
-; X64:       loadbb1:
-; X64-NEXT:    [[TMP9:%.*]] = bitcast i8* [[X]] to i64*
-; X64-NEXT:    [[TMP10:%.*]] = bitcast i8* [[Y]] to i64*
-; X64-NEXT:    [[TMP11:%.*]] = getelementptr i64, i64* [[TMP9]], i64 1
-; X64-NEXT:    [[TMP12:%.*]] = getelementptr i64, i64* [[TMP10]], i64 1
-; X64-NEXT:    [[TMP13:%.*]] = load i64, i64* [[TMP11]]
-; X64-NEXT:    [[TMP14:%.*]] = load i64, i64* [[TMP12]]
-; X64-NEXT:    [[TMP15]] = call i64 @llvm.bswap.i64(i64 [[TMP13]])
-; X64-NEXT:    [[TMP16]] = call i64 @llvm.bswap.i64(i64 [[TMP14]])
-; X64-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[TMP15]], [[TMP16]]
-; X64-NEXT:    br i1 [[TMP17]], label [[ENDBLOCK]], label [[RES_BLOCK]]
-; X64:       endblock:
-; X64-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ [[TMP8]], [[RES_BLOCK]] ]
-; X64-NEXT:    ret i32 [[PHI_RES]]
+; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i128*
+; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i128*
+; X64-NEXT:    [[TMP3:%.*]] = load i128, i128* [[TMP1]]
+; X64-NEXT:    [[TMP4:%.*]] = load i128, i128* [[TMP2]]
+; X64-NEXT:    [[TMP5:%.*]] = call i128 @llvm.bswap.i128(i128 [[TMP3]])
+; X64-NEXT:    [[TMP6:%.*]] = call i128 @llvm.bswap.i128(i128 [[TMP4]])
+; X64-NEXT:    [[TMP7:%.*]] = icmp ugt i128 [[TMP5]], [[TMP6]]
+; X64-NEXT:    [[TMP8:%.*]] = icmp ult i128 [[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]]
 ;
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16)
   ret i32 %call
@@ -753,27 +736,13 @@
 ; X32-NEXT:    ret i32 [[CONV]]
 ;
 ; X64-LABEL: @cmp_eq16(
-; X64-NEXT:  loadbb:
-; X64-NEXT:    [[TMP0:%.*]] = bitcast i8* [[X:%.*]] to i64*
-; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[Y:%.*]] to i64*
-; X64-NEXT:    [[TMP2:%.*]] = load i64, i64* [[TMP0]]
-; X64-NEXT:    [[TMP3:%.*]] = load i64, i64* [[TMP1]]
-; X64-NEXT:    [[TMP4:%.*]] = icmp ne i64 [[TMP2]], [[TMP3]]
-; X64-NEXT:    br i1 [[TMP4]], label [[RES_BLOCK:%.*]], label [[LOADBB1:%.*]]
-; X64:       res_block:
-; X64-NEXT:    br label [[ENDBLOCK:%.*]]
-; X64:       loadbb1:
-; X64-NEXT:    [[TMP5:%.*]] = bitcast i8* [[X]] to i64*
-; X64-NEXT:    [[TMP6:%.*]] = bitcast i8* [[Y]] to i64*
-; X64-NEXT:    [[TMP7:%.*]] = getelementptr i64, i64* [[TMP5]], i64 1
-; X64-NEXT:    [[TMP8:%.*]] = getelementptr i64, i64* [[TMP6]], i64 1
-; X64-NEXT:    [[TMP9:%.*]] = load i64, i64* [[TMP7]]
-; X64-NEXT:    [[TMP10:%.*]] = load i64, i64* [[TMP8]]
-; X64-NEXT:    [[TMP11:%.*]] = icmp ne i64 [[TMP9]], [[TMP10]]
-; X64-NEXT:    br i1 [[TMP11]], label [[RES_BLOCK]], label [[ENDBLOCK]]
-; X64:       endblock:
-; X64-NEXT:    [[PHI_RES:%.*]] = phi i32 [ 0, [[LOADBB1]] ], [ 1, [[RES_BLOCK]] ]
-; X64-NEXT:    [[CMP:%.*]] = icmp eq i32 [[PHI_RES]], 0
+; X64-NEXT:    [[TMP1:%.*]] = bitcast i8* [[X:%.*]] to i128*
+; X64-NEXT:    [[TMP2:%.*]] = bitcast i8* [[Y:%.*]] to i128*
+; X64-NEXT:    [[TMP3:%.*]] = load i128, i128* [[TMP1]]
+; X64-NEXT:    [[TMP4:%.*]] = load i128, i128* [[TMP2]]
+; X64-NEXT:    [[TMP5:%.*]] = icmp ne i128 [[TMP3]], [[TMP4]]
+; X64-NEXT:    [[TMP6:%.*]] = zext i1 [[TMP5]] to i32
+; X64-NEXT:    [[CMP:%.*]] = icmp eq i32 [[TMP6]], 0
 ; X64-NEXT:    [[CONV:%.*]] = zext i1 [[CMP]] to i32
 ; X64-NEXT:    ret i32 [[CONV]]
 ;