Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -8060,6 +8060,29 @@
   return CGF.Builder.CreateSelect(Mask, Op0, Op1);
 }
 
+static Value *EmitX86MaskedCompareResult(CodeGenFunction &CGF, Value *Cmp,
+                                         unsigned NumElts, Value *MaskIn) {
+  if (MaskIn) {
+    const auto *C = dyn_cast<Constant>(MaskIn);
+    if (!C || !C->isAllOnesValue())
+      Cmp = CGF.Builder.CreateAnd(Cmp, getMaskVecValue(CGF, MaskIn, NumElts));
+  }
+
+  if (NumElts < 8) {
+    uint32_t Indices[8];
+    for (unsigned i = 0; i != NumElts; ++i)
+      Indices[i] = i;
+    for (unsigned i = NumElts; i != 8; ++i)
+      Indices[i] = i % NumElts + NumElts;
+    Cmp = CGF.Builder.CreateShuffleVector(
+        Cmp, llvm::Constant::getNullValue(Cmp->getType()), Indices);
+  }
+
+  return CGF.Builder.CreateBitCast(Cmp,
+                                   IntegerType::get(CGF.getLLVMContext(),
+                                                    std::max(NumElts, 8U)));
+}
+
 static Value *EmitX86MaskedCompare(CodeGenFunction &CGF, unsigned CC,
                                    bool Signed, ArrayRef<Value *> Ops) {
   assert((Ops.size() == 2 || Ops.size() == 4) &&
@@ -8087,24 +8110,11 @@
     Cmp = CGF.Builder.CreateICmp(Pred, Ops[0], Ops[1]);
   }
 
-  if (Ops.size() == 4) {
-    const auto *C = dyn_cast<Constant>(Ops[3]);
-    if (!C || !C->isAllOnesValue())
-      Cmp = CGF.Builder.CreateAnd(Cmp, getMaskVecValue(CGF, Ops[3], NumElts));
-  }
+  Value *MaskIn = nullptr;
+  if (Ops.size() == 4)
+    MaskIn = Ops[3];
 
-  if (NumElts < 8) {
-    uint32_t Indices[8];
-    for (unsigned i = 0; i != NumElts; ++i)
-      Indices[i] = i;
-    for (unsigned i = NumElts; i != 8; ++i)
-      Indices[i] = i % NumElts + NumElts;
-    Cmp = CGF.Builder.CreateShuffleVector(
-        Cmp, llvm::Constant::getNullValue(Cmp->getType()), Indices);
-  }
-  return CGF.Builder.CreateBitCast(Cmp,
-                                   IntegerType::get(CGF.getLLVMContext(),
-                                                    std::max(NumElts, 8U)));
+  return EmitX86MaskedCompareResult(CGF, Cmp, NumElts, MaskIn);
 }
 
 static Value *EmitX86ConvertToMask(CodeGenFunction &CGF, Value *In) {
@@ -8882,6 +8892,43 @@
     return Builder.CreateExtractValue(Call, 1);
   }
 
+  case X86::BI__builtin_ia32_cmpps128_mask:
+  case X86::BI__builtin_ia32_cmpps256_mask:
+  case X86::BI__builtin_ia32_cmpps512_mask:
+  case X86::BI__builtin_ia32_cmppd128_mask:
+  case X86::BI__builtin_ia32_cmppd256_mask:
+  case X86::BI__builtin_ia32_cmppd512_mask: {
+    unsigned NumElts = Ops[0]->getType()->getVectorNumElements();
+    Value *MaskIn = Ops[3];
+    Ops.erase(&Ops[3]);
+
+    Intrinsic::ID ID;
+    switch (BuiltinID) {
+    default: llvm_unreachable("Unsupported intrinsic!");
+    case X86::BI__builtin_ia32_cmpps128_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_ps_128;
+      break;
+    case X86::BI__builtin_ia32_cmpps256_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_ps_256;
+      break;
+    case X86::BI__builtin_ia32_cmpps512_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_ps_512;
+      break;
+    case X86::BI__builtin_ia32_cmppd128_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_pd_128;
+      break;
+    case X86::BI__builtin_ia32_cmppd256_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_pd_256;
+      break;
+    case X86::BI__builtin_ia32_cmppd512_mask:
+      ID = Intrinsic::x86_avx512_mask_cmp_pd_512;
+      break;
+    }
+
+    Value *Cmp = Builder.CreateCall(CGM.getIntrinsic(ID), Ops);
+    return EmitX86MaskedCompareResult(*this, Cmp, NumElts, MaskIn);
+  }
+
   // SSE packed comparison intrinsics
   case X86::BI__builtin_ia32_cmpeqps:
   case X86::BI__builtin_ia32_cmpeqpd:
Index: test/CodeGen/avx512f-builtins.c
===================================================================
--- test/CodeGen/avx512f-builtins.c
+++ test/CodeGen/avx512f-builtins.c
@@ -1001,49 +1001,53 @@
 
 __mmask16 test_mm512_cmp_round_ps_mask(__m512 a, __m512 b) {
   // CHECK-LABEL: @test_mm512_cmp_round_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: call <16 x i1> @llvm.x86.avx512.mask.cmp.ps.512
   return _mm512_cmp_round_ps_mask(a, b, 0, _MM_FROUND_CUR_DIRECTION);
 }
 
 __mmask16 test_mm512_mask_cmp_round_ps_mask(__mmask16 m, __m512 a, __m512 b) {
   // CHECK-LABEL: @test_mm512_mask_cmp_round_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: [[CMP:%.*]] = call <16 x i1> @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: and <16 x i1> [[CMP]], {{.*}}
   return _mm512_mask_cmp_round_ps_mask(m, a, b, 0, _MM_FROUND_CUR_DIRECTION);
 }
 
 __mmask16 test_mm512_cmp_ps_mask(__m512 a, __m512 b) {
   // CHECK-LABEL: @test_mm512_cmp_ps_mask
-  // CHECKn: @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: call <16 x i1> @llvm.x86.avx512.mask.cmp.ps.512
   return _mm512_cmp_ps_mask(a, b, 0);
 }
 
 __mmask16 test_mm512_mask_cmp_ps_mask(__mmask16 m, __m512 a, __m512 b) {
   // CHECK-LABEL: @test_mm512_mask_cmp_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: [[CMP:%.*]] = call <16 x i1> @llvm.x86.avx512.mask.cmp.ps.512
+  // CHECK: and <16 x i1> [[CMP]], {{.*}}
   return _mm512_mask_cmp_ps_mask(m, a, b, 0);
 }
 
 __mmask8 test_mm512_cmp_round_pd_mask(__m512d a, __m512d b) {
   // CHECK-LABEL: @test_mm512_cmp_round_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: call <8 x i1> @llvm.x86.avx512.mask.cmp.pd.512
   return _mm512_cmp_round_pd_mask(a, b, 0, _MM_FROUND_CUR_DIRECTION);
 }
 
 __mmask8 test_mm512_mask_cmp_round_pd_mask(__mmask8 m, __m512d a, __m512d b) {
   // CHECK-LABEL: @test_mm512_mask_cmp_round_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: [[CMP:%.*]] = call <8 x i1> @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: and <8 x i1> [[CMP]], {{.*}}
   return _mm512_mask_cmp_round_pd_mask(m, a, b, 0, _MM_FROUND_CUR_DIRECTION);
 }
 
 __mmask8 test_mm512_cmp_pd_mask(__m512d a, __m512d b) {
   // CHECK-LABEL: @test_mm512_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: call <8 x i1> @llvm.x86.avx512.mask.cmp.pd.512
   return _mm512_cmp_pd_mask(a, b, 0);
 }
 
 __mmask8 test_mm512_mask_cmp_pd_mask(__mmask8 m, __m512d a, __m512d b) {
   // CHECK-LABEL: @test_mm512_mask_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: [[CMP:%.*]] = call <8 x i1> @llvm.x86.avx512.mask.cmp.pd.512
+  // CHECK: and <8 x i1> [[CMP]], {{.*}}
   return _mm512_mask_cmp_pd_mask(m, a, b, 0);
 }
 
Index: test/CodeGen/avx512vl-builtins.c
===================================================================
--- test/CodeGen/avx512vl-builtins.c
+++ test/CodeGen/avx512vl-builtins.c
@@ -1049,49 +1049,53 @@
 
 __mmask8 test_mm256_cmp_ps_mask(__m256 __A, __m256 __B) {
   // CHECK-LABEL: @test_mm256_cmp_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.256
+  // CHECK: call <8 x i1> @llvm.x86.avx512.mask.cmp.ps.256
   return (__mmask8)_mm256_cmp_ps_mask(__A, __B, 0);
 }
 
 __mmask8 test_mm256_mask_cmp_ps_mask(__mmask8 m, __m256 __A, __m256 __B) {
   // CHECK-LABEL: @test_mm256_mask_cmp_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.256
+  // CHECK: [[CMP:%.*]] = call <8 x i1> @llvm.x86.avx512.mask.cmp.ps.256
+  // CHECK: and <8 x i1> [[CMP]], {{.*}}
   return _mm256_mask_cmp_ps_mask(m, __A, __B, 0);
 }
 
 __mmask8 test_mm_cmp_ps_mask(__m128 __A, __m128 __B) {
   // CHECK-LABEL: @test_mm_cmp_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.128
+  // CHECK: call <4 x i1> @llvm.x86.avx512.mask.cmp.ps.128
   return (__mmask8)_mm_cmp_ps_mask(__A, __B, 0);
 }
 
 __mmask8 test_mm_mask_cmp_ps_mask(__mmask8 m, __m128 __A, __m128 __B) {
   // CHECK-LABEL: @test_mm_mask_cmp_ps_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.ps.128
+  // CHECK: [[CMP:%.*]] = call <4 x i1> @llvm.x86.avx512.mask.cmp.ps.128
+  // CHECK: and <4 x i1> [[CMP]], {{.*}}
   return _mm_mask_cmp_ps_mask(m, __A, __B, 0);
 }
 
 __mmask8 test_mm256_cmp_pd_mask(__m256d __A, __m256d __B) {
   // CHECK-LABEL: @test_mm256_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.256
+  // CHECK: call <4 x i1> @llvm.x86.avx512.mask.cmp.pd.256
   return (__mmask8)_mm256_cmp_pd_mask(__A, __B, 0);
 }
 
 __mmask8 test_mm256_mask_cmp_pd_mask(__mmask8 m, __m256d __A, __m256d __B) {
   // CHECK-LABEL: @test_mm256_mask_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.256
+  // CHECK: [[CMP:%.*]] = call <4 x i1> @llvm.x86.avx512.mask.cmp.pd.256
+  // CHECK: and <4 x i1> [[CMP]], {{.*}}
   return _mm256_mask_cmp_pd_mask(m, __A, __B, 0);
 }
 
 __mmask8 test_mm_cmp_pd_mask(__m128d __A, __m128d __B) {
   // CHECK-LABEL: @test_mm_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.128
+  // CHECK: call <2 x i1> @llvm.x86.avx512.mask.cmp.pd.128
   return (__mmask8)_mm_cmp_pd_mask(__A, __B, 0);
 }
 
 __mmask8 test_mm_mask_cmp_pd_mask(__mmask8 m, __m128d __A, __m128d __B) {
   // CHECK-LABEL: @test_mm_mask_cmp_pd_mask
-  // CHECK: @llvm.x86.avx512.mask.cmp.pd.128
+  // CHECK: [[CMP:%.*]] = call <2 x i1> @llvm.x86.avx512.mask.cmp.pd.128
+  // CHECK: and <2 x i1> [[CMP]], {{.*}}
   return _mm_mask_cmp_pd_mask(m, __A, __B, 0);
 }