Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -7923,6 +7923,7 @@
     }
 
     // We can't handle 8-31 immediates with native IR, use the intrinsic.
+    // Except for predicates that create constants.
     Intrinsic::ID ID;
     switch (BuiltinID) {
     default: llvm_unreachable("Unsupported intrinsic!");
@@ -7930,12 +7931,32 @@
       ID = Intrinsic::x86_sse_cmp_ps;
       break;
     case X86::BI__builtin_ia32_cmpps256:
+      // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector
+      // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0...
+      if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) {
+         Value *Constant = (CC == 0xf || CC == 0x1f) ?
+                llvm::Constant::getAllOnesValue(Builder.getInt32Ty()) :
+                llvm::Constant::getNullValue(Builder.getInt32Ty());
+         Value *Vec = Builder.CreateVectorSplat(
+                        Ops[0]->getType()->getVectorNumElements(), Constant);
+         return Builder.CreateBitCast(Vec, Ops[0]->getType());
+      }
       ID = Intrinsic::x86_avx_cmp_ps_256;
       break;
     case X86::BI__builtin_ia32_cmppd:
       ID = Intrinsic::x86_sse2_cmp_pd;
       break;
     case X86::BI__builtin_ia32_cmppd256:
+      // _CMP_TRUE_UQ, _CMP_TRUE_US produce -1,-1... vector
+      // on any input and _CMP_FALSE_OQ, _CMP_FALSE_OS produce 0, 0...
+      if (CC == 0xf || CC == 0xb || CC == 0x1b || CC == 0x1f) {
+         Value *Constant = (CC == 0xf || CC == 0x1f) ?
+                llvm::Constant::getAllOnesValue(Builder.getInt64Ty()) :
+                llvm::Constant::getNullValue(Builder.getInt64Ty());
+         Value *Vec = Builder.CreateVectorSplat(
+                        Ops[0]->getType()->getVectorNumElements(), Constant);
+         return Builder.CreateBitCast(Vec, Ops[0]->getType());
+      }
       ID = Intrinsic::x86_avx_cmp_pd_256;
       break;
     }
Index: test/CodeGen/avx-builtins.c
===================================================================
--- test/CodeGen/avx-builtins.c
+++ test/CodeGen/avx-builtins.c
@@ -1427,3 +1427,51 @@
  // CHECK: extractelement <8 x float> %{{.*}}, i32 0
  return _mm256_cvtss_f32(__a);
 }
+
+__m256 test_mm256_cmp_ps_true(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_ps_true
+ // CHECK: store <8 x float> <float 0xFFFFFFFFE0000000,
+ return _mm256_cmp_ps(a, b, _CMP_TRUE_UQ);
+}
+
+__m256 test_mm256_cmp_pd_true(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_pd_true
+ // CHECK: store <4 x double> <double 0xFFFFFFFFFFFFFFFF,
+  return _mm256_cmp_pd(a, b, _CMP_TRUE_UQ);
+}
+
+__m256 test_mm256_cmp_ps_false(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_ps_false
+ // CHECK: store <8 x float> zeroinitializer, <8 x float>* %tmp, align 32
+ return _mm256_cmp_ps(a, b, _CMP_FALSE_OQ);
+}
+
+__m256 test_mm256_cmp_pd_false(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_pd_false
+ // CHECK: store <4 x double> zeroinitializer, <4 x double>* %tmp, align 32
+  return _mm256_cmp_pd(a, b, _CMP_FALSE_OQ);
+}
+
+__m256 test_mm256_cmp_ps_strue(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_ps_strue
+ // CHECK: store <8 x float> <float 0xFFFFFFFFE0000000,
+ return _mm256_cmp_ps(a, b, _CMP_TRUE_US);
+}
+
+__m256 test_mm256_cmp_pd_strue(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_pd_strue
+ // CHECK: store <4 x double> <double 0xFFFFFFFFFFFFFFFF,
+  return _mm256_cmp_pd(a, b, _CMP_TRUE_US);
+}
+
+__m256 test_mm256_cmp_ps_sfalse(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_ps_sfalse
+ // CHECK: store <8 x float> zeroinitializer, <8 x float>* %tmp, align 32
+ return _mm256_cmp_ps(a, b, _CMP_FALSE_OS);
+}
+
+__m256 test_mm256_cmp_pd_sfalse(__m256 a, __m256 b) {
+ // CHECK-LABEL: @test_mm256_cmp_pd_sfalse
+ // CHECK: store <4 x double> zeroinitializer, <4 x double>* %tmp, align 32
+  return _mm256_cmp_pd(a, b, _CMP_FALSE_OS);
+}