[x86] these aren't the undefs you're looking for (PR32176)

[spatel]

Summary

x86 has undef SSE/AVX intrinsics that should represent a bogus register operand. This is not the same as LLVM's undef value which can take on multiple bit patterns.

There are better solutions / follow-ups to this discussed here:
https://bugs.llvm.org/show_bug.cgi?id=32176
...but this should prevent miscompiles with a one-line code change.

[craig.topper]

Have you ran the tests all the way through to assembly and made sure we don't regress? If we do regress, I wouldn't hold up fixing this, but we should at least have bugs for what breaks.

lib/CodeGen/CGBuiltin.cpp

7384 ↗

(On Diff #91362)

Do we want to leave a TODO here to maybe do something different when we have freeze?

[spatel]

In D30834#698346, @craig.topper wrote:

Have you ran the tests all the way through to assembly and made sure we don't regress? If we do regress, I wouldn't hold up fixing this, but we should at least have bugs for what breaks.

Yes - I spot-checked several of the shuffle cases, and we always catch those even at -O0. As noted in the PR, we get those in the backend or InstCombine if optimization is on.

The AVX2 gathers regress (we have an xor for the dummy register operand), and of course the undef intrinsics themselves now have an xor. If you know where those undef intrinsics are intended to be used, I can try that too. There's no problem with the pcmpeqd example in the bug report. I'll file a new PR for the gathers once this goes in and link to PR32176.

lib/CodeGen/CGBuiltin.cpp

7384 ↗

(On Diff #91362)

Sure - I'll add that.

cfe/trunk/lib/CodeGen/CGBuiltin.cpp

case X86::BI_mm_pause: {
     return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_sse2_pause));
   }
   case X86::BI__rdtsc: {
     return Builder.CreateCall(CGM.getIntrinsic(Intrinsic::x86_rdtsc));
   }
   case X86::BI__builtin_ia32_undef128:
   case X86::BI__builtin_ia32_undef256:
   case X86::BI__builtin_ia32_undef512:
-    return UndefValue::get(ConvertType(E->getType()));
+    // The x86 definition of "undef" is not the same as the LLVM definition
+    // (PR32176). We leave optimizing away an unnecessary zero constant to the
+    // IR optimizer and backend.
+    // TODO: If we had a "freeze" IR instruction to generate a fixed undef
+    // value, we should use that here instead of a zero.
+    return llvm::Constant::getNullValue(ConvertType(E->getType()));
   case X86::BI__builtin_ia32_vec_init_v8qi:
   case X86::BI__builtin_ia32_vec_init_v4hi:
   case X86::BI__builtin_ia32_vec_init_v2si:
     return Builder.CreateBitCast(BuildVector(Ops),
                                  llvm::Type::getX86_MMXTy(getLLVMContext()));
   case X86::BI__builtin_ia32_vec_ext_v2si:
     return Builder.CreateExtractElement(Ops[0],
                                   llvm::ConstantInt::get(Ops[1]->getType(), 0));

cfe/trunk/test/CodeGen/avx-builtins.c

long long test_mm256_extract_epi64(__m256i A) {
   // CHECK-LABEL: test_mm256_extract_epi64
   // CHECK: and i32 %{{.*}}, 3
   // CHECK: extractelement <4 x i64> %{{.*}}, i32 %{{.*}}
   return _mm256_extract_epi64(A, 5);
 }
 
 __m128d test_mm256_extractf128_pd(__m256d A) {
   // CHECK-LABEL: test_mm256_extractf128_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <2 x i32> <i32 2, i32 3>
   return _mm256_extractf128_pd(A, 1);
 }
 
 __m128 test_mm256_extractf128_ps(__m256 A) {
   // CHECK-LABEL: test_mm256_extractf128_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm256_extractf128_ps(A, 1);
 }
 
 __m128i test_mm256_extractf128_si256(__m256i A) {
   // CHECK-LABEL: test_mm256_extractf128_si256
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   return _mm256_extractf128_si256(A, 1);
 }
 
 __m256d test_mm256_floor_pd(__m256d x) {
   // CHECK-LABEL: test_mm256_floor_pd
   // CHECK: call <4 x double> @llvm.x86.avx.round.pd.256(<4 x double> %{{.*}}, i32 1)
   return _mm256_floor_pd(x);
 }

 __m256 test_mm256_or_ps(__m256 A, __m256 B) {
   // CHECK-LABEL: test_mm256_or_ps
   // CHECK: or <8 x i32>
   return _mm256_or_ps(A, B);
 }
 
 __m128d test_mm_permute_pd(__m128d A) {
   // CHECK-LABEL: test_mm_permute_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <2 x i32> <i32 1, i32 0>
   return _mm_permute_pd(A, 1);
 }
 
 __m256d test_mm256_permute_pd(__m256d A) {
   // CHECK-LABEL: test_mm256_permute_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   return _mm256_permute_pd(A, 5);
 }
 
 __m128 test_mm_permute_ps(__m128 A) {
   // CHECK-LABEL: test_mm_permute_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   return _mm_permute_ps(A, 0x1b);
 }
 
 // Test case for PR12401
 __m128 test2_mm_permute_ps(__m128 a) {
   // CHECK-LABEL: test2_mm_permute_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 2, i32 3>
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <4 x i32> <i32 2, i32 1, i32 2, i32 3>
   return _mm_permute_ps(a, 0xe6);
 }
 
 __m256 test_mm256_permute_ps(__m256 A) {
   // CHECK-LABEL: test_mm256_permute_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   return _mm256_permute_ps(A, 0x1b);
 }
 
 __m256d test_mm256_permute2f128_pd(__m256d A, __m256d B) {
   // CHECK-LABEL: test_mm256_permute2f128_pd
   // CHECK: call <4 x double> @llvm.x86.avx.vperm2f128.pd.256(<4 x double> %{{.*}}, <4 x double> %{{.*}}, i8 49)
   return _mm256_permute2f128_pd(A, B, 0x31);
 }
void test_mm256_storeu_si256(__m256i* A, __m256i B) {
   // CHECk-NEXT: ret void
   _mm256_storeu_si256(A, B);
 }
 
 void test_mm256_storeu2_m128(float* A, float* B, __m256 C) {
   // CHECK-LABEL: test_mm256_storeu2_m128
   // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
   // CHECK: store <4 x float> %{{.*}}, <4 x float>* %{{.*}}, align 1{{$}}
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: store <4 x float> %{{.*}}, <4 x float>* %{{.*}}, align 1{{$}}
   _mm256_storeu2_m128(A, B, C);
 }
 
 void test_mm256_storeu2_m128d(double* A, double* B, __m256d C) {
   // CHECK-LABEL: test_mm256_storeu2_m128d
   // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> %{{.*}}, <2 x i32> <i32 0, i32 1>
   // CHECK: store <2 x double> %{{.*}}, <2 x double>* %{{.*}}, align 1{{$}}
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: store <2 x double> %{{.*}}, <2 x double>* %{{.*}}, align 1{{$}}
   _mm256_storeu2_m128d(A, B, C);
 }
 
 void test_mm256_storeu2_m128i(__m128i* A, __m128i* B, __m256i C) {
   // CHECK-LABEL: test_mm256_storeu2_m128i
   // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <2 x i32> <i32 0, i32 1>
   // CHECK: store <2 x i64> %{{.*}}, <2 x i64>* %{{.*}}, align 1{{$}}
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: store <2 x i64> %{{.*}}, <2 x i64>* %{{.*}}, align 1{{$}}
   _mm256_storeu2_m128i(A, B, C);
 }
 
 void test_mm256_stream_pd(double* A, __m256d B) {
   // CHECK-LABEL: test_mm256_stream_pd
   // CHECK: store <4 x double> %{{.*}}, <4 x double>* %{{.*}}, align 32, !nontemporal
   _mm256_stream_pd(A, B);

 int test_mm256_testz_si256(__m256 A, __m256 B) {
   // CHECK-LABEL: test_mm256_testz_si256
   // CHECK: call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %{{.*}}, <4 x i64> %{{.*}})
   return _mm256_testz_si256(A, B);
 }
 
 __m256 test_mm256_undefined_ps() {
   // CHECK-LABEL: @test_mm256_undefined_ps
-  // CHECK: ret <8 x float> undef
+  // CHECK: ret <8 x float> zeroinitializer
   return _mm256_undefined_ps();
 }
 
 __m256d test_mm256_undefined_pd() {
   // CHECK-LABEL: @test_mm256_undefined_pd
-  // CHECK: ret <4 x double> undef
+  // CHECK: ret <4 x double> zeroinitializer
   return _mm256_undefined_pd();
 }
 
 __m256i test_mm256_undefined_si256() {
   // CHECK-LABEL: @test_mm256_undefined_si256
-  // CHECK: ret <4 x i64> undef
+  // CHECK: ret <4 x i64> zeroinitializer
   return _mm256_undefined_si256();
 }
 
 __m256d test_mm256_unpackhi_pd(__m256d A, __m256d B) {
   // CHECK-LABEL: test_mm256_unpackhi_pd
   // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   return _mm256_unpackhi_pd(A, B);
 }

cfe/trunk/test/CodeGen/avx2-builtins.c

 __m256i test_mm256_cvtepu32_epi64(__m128i a) {
   // CHECK-LABEL: test_mm256_cvtepu32_epi64
   // CHECK: zext <4 x i32> %{{.*}} to <4 x i64>
   return _mm256_cvtepu32_epi64(a);
 }
 
 __m128i test0_mm256_extracti128_si256_0(__m256i a) {
   // CHECK-LABEL: test0_mm256_extracti128_si256
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 0, i32 1>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 0, i32 1>
   return _mm256_extracti128_si256(a, 0);
 }
 
 __m128i test1_mm256_extracti128_si256_1(__m256i a) {
   // CHECK-LABEL: test1_mm256_extracti128_si256
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   return _mm256_extracti128_si256(a, 1);
 }
 
 // Immediate should be truncated to one bit.
 __m128i test2_mm256_extracti128_si256(__m256i a) {
   // CHECK-LABEL: test2_mm256_extracti128_si256
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 0, i32 1>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 0, i32 1>
   return _mm256_extracti128_si256(a, 2);
 }
 
 __m256i test_mm256_hadd_epi16(__m256i a, __m256i b) {
   // CHECK-LABEL: test_mm256_hadd_epi16
   // CHECK: call <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16> %{{.*}}, <16 x i16> %{{.*}})
   return _mm256_hadd_epi16(a, b);
 }

 __m256i test_mm256_mask_i32gather_epi32(__m256i a, int const *b, __m256i c, __m256i d) {
   // CHECK-LABEL: test_mm256_mask_i32gather_epi32
   // CHECK: call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> %{{.*}}, i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, i8 2)
   return _mm256_mask_i32gather_epi32(a, b, c, d, 2);
 }
 
 __m128i test_mm_i32gather_epi64(long long const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i32gather_epi64
-  // CHECK: call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> undef, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
+  // CHECK: call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
   return _mm_i32gather_epi64(b, c, 2);
 }
 
 __m128i test_mm_mask_i32gather_epi64(__m128i a, long long const *b, __m128i c, __m128i d) {
   // CHECK-LABEL: test_mm_mask_i32gather_epi64
   // CHECK: call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> %{{.*}}, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
   return _mm_mask_i32gather_epi64(a, b, c, d, 2);
 }
 
 __m256i test_mm256_i32gather_epi64(long long const *b, __m128i c) {
   // CHECK-LABEL: test_mm256_i32gather_epi64
-  // CHECK: call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> undef, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
+  // CHECK: call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
   return _mm256_i32gather_epi64(b, c, 2);
 }
 
 __m256i test_mm256_mask_i32gather_epi64(__m256i a, long long const *b, __m128i c, __m256i d) {
   // CHECK-LABEL: test_mm256_mask_i32gather_epi64
   // CHECK: call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> %{{.*}}, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
   return _mm256_mask_i32gather_epi64(a, b, c, d, 2);
 }
 
 __m128d test_mm_i32gather_pd(double const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i32gather_pd
   // CHECK:         [[CMP:%.*]] = fcmp oeq <2 x double>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <2 x i1> [[CMP]] to <2 x i64>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[SEXT]] to <2 x double>
-  // CHECK: call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> undef, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x double> %{{.*}}, i8 2)
+  // CHECK: call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x double> %{{.*}}, i8 2)
   return _mm_i32gather_pd(b, c, 2);
 }
 
 __m128d test_mm_mask_i32gather_pd(__m128d a, double const *b, __m128i c, __m128d d) {
   // CHECK-LABEL: test_mm_mask_i32gather_pd
   // CHECK: call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> %{{.*}}, i8* %{{.*}}, <4 x i32> %{{.*}}, <2 x double> %{{.*}}, i8 2)
   return _mm_mask_i32gather_pd(a, b, c, d, 2);
 }
 
 __m256d test_mm256_i32gather_pd(double const *b, __m128i c) {
   // CHECK-LABEL: test_mm256_i32gather_pd
   // CHECK:         [[CMP:%.*]] = fcmp oeq <4 x double>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i64>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <4 x i64> [[SEXT]] to <4 x double>
-  // CHECK: call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> undef, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x double> %{{.*}}, i8 2)
+  // CHECK: call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x double> %{{.*}}, i8 2)
   return _mm256_i32gather_pd(b, c, 2);
 }
 
 __m256d test_mm256_mask_i32gather_pd(__m256d a, double const *b, __m128i c, __m256d d) {
   // CHECK-LABEL: test_mm256_mask_i32gather_pd
   // CHECK: call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> %{{.*}}, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x double> %{{.*}}, i8 2)
   return _mm256_mask_i32gather_pd(a, b, c, d, 2);
 }
 
 __m128 test_mm_i32gather_ps(float const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i32gather_ps
   // CHECK:         [[CMP:%.*]] = fcmp oeq <4 x float>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
-  // CHECK: call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> undef, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+  // CHECK: call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> zeroinitializer, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm_i32gather_ps(b, c, 2);
 }
 
 __m128 test_mm_mask_i32gather_ps(__m128 a, float const *b, __m128i c, __m128 d) {
   // CHECK-LABEL: test_mm_mask_i32gather_ps
   // CHECK: call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> %{{.*}}, i8* %{{.*}}, <4 x i32> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm_mask_i32gather_ps(a, b, c, d, 2);
 }
 
 __m256 test_mm256_i32gather_ps(float const *b, __m256i c) {
   // CHECK-LABEL: test_mm256_i32gather_ps
   // CHECK:         [[CMP:%.*]] = fcmp oeq <8 x float>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <8 x i32> [[SEXT]] to <8 x float>
-  // CHECK: call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x float> %{{.*}}, i8 2)
+  // CHECK: call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> zeroinitializer, i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x float> %{{.*}}, i8 2)
   return _mm256_i32gather_ps(b, c, 2);
 }
 
 __m256 test_mm256_mask_i32gather_ps(__m256 a, float const *b, __m256i c, __m256 d) {
   // CHECK-LABEL: test_mm256_mask_i32gather_ps
   // CHECK: call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %{{.*}}, i8* %{{.*}}, <8 x i32> %{{.*}}, <8 x float> %{{.*}}, i8 2)
   return _mm256_mask_i32gather_ps(a, b, c, d, 2);
 }

 __m128i test_mm256_mask_i64gather_epi32(__m128i a, int const *b, __m256i c, __m128i d) {
   // CHECK-LABEL: test_mm256_mask_i64gather_epi32
   // CHECK: call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> %{{.*}}, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i32> %{{.*}}, i8 2)
   return _mm256_mask_i64gather_epi32(a, b, c, d, 2);
 }
 
 __m128i test_mm_i64gather_epi64(long long const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i64gather_epi64
-  // CHECK: call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> undef, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
+  // CHECK: call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
   return _mm_i64gather_epi64(b, c, 2);
 }
 
 __m128i test_mm_mask_i64gather_epi64(__m128i a, long long const *b, __m128i c, __m128i d) {
   // CHECK-LABEL: test_mm_mask_i64gather_epi64
   // CHECK: call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> %{{.*}}, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, i8 2)
   return _mm_mask_i64gather_epi64(a, b, c, d, 2);
 }
 
 __m256i test_mm256_i64gather_epi64(long long const *b, __m256i c) {
   // CHECK-LABEL: test_mm256_i64gather_epi64
-  // CHECK: call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> undef, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
+  // CHECK: call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
   return _mm256_i64gather_epi64(b, c, 2);
 }
 
 __m256i test_mm256_mask_i64gather_epi64(__m256i a, long long const *b, __m256i c, __m256i d) {
   // CHECK-LABEL: test_mm256_mask_i64gather_epi64
   // CHECK: call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> %{{.*}}, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 2)
   return _mm256_mask_i64gather_epi64(a, b, c, d, 2);
 }
 
 __m128d test_mm_i64gather_pd(double const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i64gather_pd
   // CHECK:         [[CMP:%.*]] = fcmp oeq <2 x double>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <2 x i1> [[CMP]] to <2 x i64>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <2 x i64> [[SEXT]] to <2 x double>
-  // CHECK: call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> undef, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x double> %{{.*}}, i8 2)
+  // CHECK: call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x double> %{{.*}}, i8 2)
   return _mm_i64gather_pd(b, c, 2);
 }
 
 __m128d test_mm_mask_i64gather_pd(__m128d a, double const *b, __m128i c, __m128d d) {
   // CHECK-LABEL: test_mm_mask_i64gather_pd
   // CHECK: call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> %{{.*}}, i8* %{{.*}}, <2 x i64> %{{.*}}, <2 x double> %{{.*}}, i8 2)
   return _mm_mask_i64gather_pd(a, b, c, d, 2);
 }
 
 __m256d test_mm256_i64gather_pd(double const *b, __m256i c) {
   // CHECK-LABEL: test_mm256_i64gather_pd
   // CHECK:         [[CMP:%.*]] = fcmp oeq <4 x double>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i64>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <4 x i64> [[SEXT]] to <4 x double>
-  // CHECK: call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> undef, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x double> %{{.*}}, i8 2)
+  // CHECK: call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x double> %{{.*}}, i8 2)
   return _mm256_i64gather_pd(b, c, 2);
 }
 
 __m256d test_mm256_mask_i64gather_pd(__m256d a, double const *b, __m256i c, __m256d d) {
   // CHECK-LABEL: test_mm256_mask_i64gather_pd
   // CHECK: call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> %{{.*}}, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x double> %{{.*}}, i8 2)
   return _mm256_mask_i64gather_pd(a, b, c, d, 2);
 }
 
 __m128 test_mm_i64gather_ps(float const *b, __m128i c) {
   // CHECK-LABEL: test_mm_i64gather_ps
   // CHECK:         [[CMP:%.*]] = fcmp oeq <4 x float>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
-  // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> undef, i8* %{{.*}}, <2 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+  // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> zeroinitializer, i8* %{{.*}}, <2 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm_i64gather_ps(b, c, 2);
 }
 
 __m128 test_mm_mask_i64gather_ps(__m128 a, float const *b, __m128i c, __m128 d) {
   // CHECK-LABEL: test_mm_mask_i64gather_ps
   // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> %{{.*}}, i8* %{{.*}}, <2 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm_mask_i64gather_ps(a, b, c, d, 2);
 }
 
 __m128 test_mm256_i64gather_ps(float const *b, __m256i c) {
   // CHECK-LABEL: test_mm256_i64gather_ps
   // CHECK:         [[CMP:%.*]] = fcmp oeq <4 x float>
   // CHECK-NEXT:    [[SEXT:%.*]] = sext <4 x i1> [[CMP]] to <4 x i32>
   // CHECK-NEXT:    [[BC:%.*]] = bitcast <4 x i32> [[SEXT]] to <4 x float>
-  // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> undef, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
+  // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> zeroinitializer, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm256_i64gather_ps(b, c, 2);
 }
 
 __m128 test_mm256_mask_i64gather_ps(__m128 a, float const *b, __m256i c, __m128 d) {
   // CHECK-LABEL: test_mm256_mask_i64gather_ps
   // CHECK: call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> %{{.*}}, i8* %{{.*}}, <4 x i64> %{{.*}}, <4 x float> %{{.*}}, i8 2)
   return _mm256_mask_i64gather_ps(a, b, c, d, 2);
 }

 __m256i test_mm256_permute2x128_si256(__m256i a, __m256i b) {
   // CHECK-LABEL: test_mm256_permute2x128_si256
   // CHECK: call <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64> %{{.*}}, <4 x i64> %{{.*}}, i8 49)
   return _mm256_permute2x128_si256(a, b, 0x31);
 }
 
 __m256i test_mm256_permute4x64_epi64(__m256i a) {
   // CHECK-LABEL: test_mm256_permute4x64_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 2, i32 0>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 2, i32 0>
   return _mm256_permute4x64_epi64(a, 35);
 }
 
 __m256d test_mm256_permute4x64_pd(__m256d a) {
   // CHECK-LABEL: test_mm256_permute4x64_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
   return _mm256_permute4x64_pd(a, 25);
 }
 
 __m256i test_mm256_permutevar8x32_epi32(__m256i a, __m256i b) {
   // CHECK-LABEL: test_mm256_permutevar8x32_epi32
   // CHECK: call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %{{.*}}, <8 x i32> %{{.*}})
   return _mm256_permutevar8x32_epi32(a, b);
 }

cfe/trunk/test/CodeGen/avx512bw-builtins.c

 __m512i test_mm512_movm_epi16(__mmask32 __A) {
   // CHECK-LABEL: @test_mm512_movm_epi16
   // CHECK: @llvm.x86.avx512.cvtmask2w.512
   return _mm512_movm_epi16(__A); 
 }
 
 __m512i test_mm512_broadcastb_epi8(__m128i __A) {
   // CHECK-LABEL: @test_mm512_broadcastb_epi8
-  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> undef, <64 x i32> zeroinitializer
+  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> zeroinitializer, <64 x i32> zeroinitializer
   return _mm512_broadcastb_epi8(__A);
 }
 
 __m512i test_mm512_mask_broadcastb_epi8(__m512i __O, __mmask64 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastb_epi8
-  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> undef, <64 x i32> zeroinitializer
+  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> zeroinitializer, <64 x i32> zeroinitializer
   // CHECK: select <64 x i1> %{{.*}}, <64 x i8> %{{.*}}, <64 x i8> %{{.*}}
   return _mm512_mask_broadcastb_epi8(__O, __M, __A);
 }
 
 __m512i test_mm512_maskz_broadcastb_epi8(__mmask64 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastb_epi8
-  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> undef, <64 x i32> zeroinitializer
+  // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> zeroinitializer, <64 x i32> zeroinitializer
   // CHECK: select <64 x i1> %{{.*}}, <64 x i8> %{{.*}}, <64 x i8> %{{.*}}
   return _mm512_maskz_broadcastb_epi8(__M, __A);
 }
 
 __m512i test_mm512_broadcastw_epi16(__m128i __A) {
   // CHECK-LABEL: @test_mm512_broadcastw_epi16
-  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <32 x i32> zeroinitializer
+  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> zeroinitializer, <32 x i32> zeroinitializer
   return _mm512_broadcastw_epi16(__A);
 }
 
 __m512i test_mm512_mask_broadcastw_epi16(__m512i __O, __mmask32 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastw_epi16
-  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <32 x i32> zeroinitializer
+  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> zeroinitializer, <32 x i32> zeroinitializer
   // CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
   return _mm512_mask_broadcastw_epi16(__O, __M, __A);
 }
 
 __m512i test_mm512_maskz_broadcastw_epi16(__mmask32 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastw_epi16
-  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> undef, <32 x i32> zeroinitializer
+  // CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> zeroinitializer, <32 x i32> zeroinitializer
   // CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
   return _mm512_maskz_broadcastw_epi16(__M, __A);
 }
 
 __m512i test_mm512_mask_set1_epi16(__m512i __O, __mmask32 __M, short __A) {
   // CHECK-LABEL: @test_mm512_mask_set1_epi16
   // CHECK: @llvm.x86.avx512.mask.pbroadcast.w.gpr.512
   return _mm512_mask_set1_epi16(__O, __M, __A); 

cfe/trunk/test/CodeGen/avx512dq-builtins.c

__m512i test_mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i const* __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcast_i64x2
   // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_maskz_broadcast_i64x2(__M, _mm_loadu_si128(__A)); 
 }
 
 __m256 test_mm512_extractf32x8_ps(__m512 __A) {
   // CHECK-LABEL: @test_mm512_extractf32x8_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   return _mm512_extractf32x8_ps(__A, 1); 
 }
 
 __m256 test_mm512_mask_extractf32x8_ps(__m256 __W, __mmask8 __U, __m512 __A) {
   // CHECK-LABEL: @test_mm512_mask_extractf32x8_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   // CHECK: select <8 x i1> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}}
   return _mm512_mask_extractf32x8_ps(__W, __U, __A, 1); 
 }
 
 __m256 test_mm512_maskz_extractf32x8_ps(__mmask8 __U, __m512 __A) {
   // CHECK-LABEL: @test_mm512_maskz_extractf32x8_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   // CHECK: select <8 x i1> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}}
   return _mm512_maskz_extractf32x8_ps(__U, __A, 1); 
 }
 
 __m128d test_mm512_extractf64x2_pd(__m512d __A) {
   // CHECK-LABEL: @test_mm512_extractf64x2_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <2 x i32> <i32 6, i32 7>
   return _mm512_extractf64x2_pd(__A, 3); 
 }
 
 __m128d test_mm512_mask_extractf64x2_pd(__m128d __W, __mmask8 __U, __m512d __A) {
   // CHECK-LABEL: @test_mm512_mask_extractf64x2_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <2 x i32> <i32 6, i32 7>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm512_mask_extractf64x2_pd(__W, __U, __A, 3); 
 }
 
 __m128d test_mm512_maskz_extractf64x2_pd(__mmask8 __U, __m512d __A) {
   // CHECK-LABEL: @test_mm512_maskz_extractf64x2_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <2 x i32> <i32 6, i32 7>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm512_maskz_extractf64x2_pd(__U, __A, 3); 
 }
 
 __m256i test_mm512_extracti32x8_epi32(__m512i __A) {
   // CHECK-LABEL: @test_mm512_extracti32x8_epi32
   // CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   return _mm512_extracti32x8_epi32(__A, 1); 
__m256i test_mm512_maskz_extracti32x8_epi32(__mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_maskz_extracti32x8_epi32
   // CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   // CHECK: select <8 x i1> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}
   return _mm512_maskz_extracti32x8_epi32(__U, __A, 1); 
 }
 
 __m128i test_mm512_extracti64x2_epi64(__m512i __A) {
   // CHECK-LABEL: @test_mm512_extracti64x2_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <2 x i32> <i32 6, i32 7>
   return _mm512_extracti64x2_epi64(__A, 3); 
 }
 
 __m128i test_mm512_mask_extracti64x2_epi64(__m128i __W, __mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_mask_extracti64x2_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <2 x i32> <i32 6, i32 7>
   // CHECK: select <2 x i1> %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}
   return _mm512_mask_extracti64x2_epi64(__W, __U, __A, 3); 
 }
 
 __m128i test_mm512_maskz_extracti64x2_epi64(__mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_maskz_extracti64x2_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <2 x i32> <i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <2 x i32> <i32 6, i32 7>
   // CHECK: select <2 x i1> %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}
   return _mm512_maskz_extracti64x2_epi64(__U, __A, 3); 
 }
 
 __m512 test_mm512_insertf32x8(__m512 __A, __m256 __B) {
   // CHECK-LABEL: @test_mm512_insertf32x8
   // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
   return _mm512_insertf32x8(__A, __B, 1); 

cfe/trunk/test/CodeGen/avx512f-builtins.c

__mmask8 test_mm512_mask_cmpunord_ps_mask(__mmask8 k, __m512 a, __m512 b) {
   // CHECK-LABEL: @test_mm512_mask_cmpunord_ps_mask
   // CHECK: @llvm.x86.avx512.mask.cmp.ps.512
   return _mm512_mask_cmpunord_ps_mask(k, a, b);
 }
 
 __m256d test_mm512_extractf64x4_pd(__m512d a)
 {
   // CHECK-LABEL: @test_mm512_extractf64x4_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm512_extractf64x4_pd(a, 1);
 }
 
 __m256d test_mm512_mask_extractf64x4_pd(__m256d  __W,__mmask8  __U,__m512d __A){
   // CHECK-LABEL:@test_mm512_mask_extractf64x4_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm512_mask_extractf64x4_pd( __W, __U, __A, 1);
 }
 
 __m256d test_mm512_maskz_extractf64x4_pd(__mmask8  __U,__m512d __A){
   // CHECK-LABEL:@test_mm512_maskz_extractf64x4_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm512_maskz_extractf64x4_pd( __U, __A, 1);
 }
 
 __m128 test_mm512_extractf32x4_ps(__m512 a)
 {
   // CHECK-LABEL: @test_mm512_extractf32x4_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm512_extractf32x4_ps(a, 1);
 }
 
 __m128 test_mm512_mask_extractf32x4_ps(__m128 __W, __mmask8  __U,__m512d __A){
   // CHECK-LABEL:@test_mm512_mask_extractf32x4_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
   return _mm512_mask_extractf32x4_ps( __W, __U, __A, 1);
 }
 
 __m128 test_mm512_maskz_extractf32x4_ps( __mmask8  __U,__m512d __A){
   // CHECK-LABEL:@test_mm512_maskz_extractf32x4_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
  return _mm512_maskz_extractf32x4_ps(  __U, __A, 1);
 }
 
 __mmask16 test_mm512_cmpeq_epu32_mask(__m512i __a, __m512i __b) {
   // CHECK-LABEL: @test_mm512_cmpeq_epu32_mask
   // CHECK: icmp eq <16 x i32> %{{.*}}, %{{.*}}
   return (__mmask16)_mm512_cmpeq_epu32_mask(__a, __b);

 __m128d test_mm_maskz_min_sd(__mmask8 __U, __m128d __A, __m128d __B) {
   // CHECK-LABEL: @test_mm_maskz_min_sd
   // CHECK: @llvm.x86.avx512.mask.min.sd.round
   return _mm_maskz_min_sd(__U,__A,__B); 
 }
 
 __m512 test_mm512_undefined() {
   // CHECK-LABEL: @test_mm512_undefined
-  // CHECK: ret <16 x float> undef
+  // CHECK: ret <16 x float> zeroinitializer
   return _mm512_undefined();
 }
 
 __m512 test_mm512_undefined_ps() {
   // CHECK-LABEL: @test_mm512_undefined_ps
-  // CHECK: ret <16 x float> undef
+  // CHECK: ret <16 x float> zeroinitializer
   return _mm512_undefined_ps();
 }
 
 __m512d test_mm512_undefined_pd() {
   // CHECK-LABEL: @test_mm512_undefined_pd
-  // CHECK: ret <8 x double> undef
+  // CHECK: ret <8 x double> zeroinitializer
   return _mm512_undefined_pd();
 }
 
 __m512i test_mm512_undefined_epi32() {
   // CHECK-LABEL: @test_mm512_undefined_epi32
-  // CHECK: ret <8 x i64> undef
+  // CHECK: ret <8 x i64> zeroinitializer
   return _mm512_undefined_epi32();
 }
 
 __m512i test_mm512_cvtepi8_epi32(__m128i __A) {
   // CHECK-LABEL: @test_mm512_cvtepi8_epi32
   // CHECK: sext <16 x i8> %{{.*}} to <16 x i32>
   return _mm512_cvtepi8_epi32(__A); 
 }

 __m512i test_mm512_mask2_permutex2var_epi64(__m512i __A, __m512i __I, __mmask8 __U, __m512i __B) {
   // CHECK-LABEL: @test_mm512_mask2_permutex2var_epi64
   // CHECK: @llvm.x86.avx512.mask.vpermi2var.q.512
   return _mm512_mask2_permutex2var_epi64(__A, __I, __U, __B); 
 }
 
 __m512d test_mm512_permute_pd(__m512d __X) {
   // CHECK-LABEL: @test_mm512_permute_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   return _mm512_permute_pd(__X, 2);
 }
 
 __m512d test_mm512_mask_permute_pd(__m512d __W, __mmask8 __U, __m512d __X) {
   // CHECK-LABEL: @test_mm512_mask_permute_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_mask_permute_pd(__W, __U, __X, 2);
 }
 
 __m512d test_mm512_maskz_permute_pd(__mmask8 __U, __m512d __X) {
   // CHECK-LABEL: @test_mm512_maskz_permute_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_maskz_permute_pd(__U, __X, 2);
 }
 
 __m512 test_mm512_permute_ps(__m512 __X) {
   // CHECK-LABEL: @test_mm512_permute_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
   return _mm512_permute_ps(__X, 2);
 }
 
 __m512 test_mm512_mask_permute_ps(__m512 __W, __mmask16 __U, __m512 __X) {
   // CHECK-LABEL: @test_mm512_mask_permute_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
   // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}}
   return _mm512_mask_permute_ps(__W, __U, __X, 2);
 }
 
 __m512 test_mm512_maskz_permute_ps(__mmask16 __U, __m512 __X) {
   // CHECK-LABEL: @test_mm512_maskz_permute_ps
-  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> undef, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
+  // CHECK: shufflevector <16 x float> %{{.*}}, <16 x float> zeroinitializer, <16 x i32> <i32 2, i32 0, i32 0, i32 0, i32 6, i32 4, i32 4, i32 4, i32 10, i32 8, i32 8, i32 8, i32 14, i32 12, i32 12, i32 12>
   // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}}
   return _mm512_maskz_permute_ps(__U, __X, 2);
 }
 
 __m512d test_mm512_permutevar_pd(__m512d __A, __m512i __C) {
   // CHECK-LABEL: @test_mm512_permutevar_pd
   // CHECK: @llvm.x86.avx512.vpermilvar.pd.512
   return _mm512_permutevar_pd(__A, __C); 
__m512i test_mm512_maskz_broadcast_i64x4(__mmask8 __M, __m256i const* __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcast_i64x4
   // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_maskz_broadcast_i64x4(__M, _mm256_loadu_si256(__A)); 
 }
 
 __m512d test_mm512_broadcastsd_pd(__m128d __A) {
   // CHECK-LABEL: @test_mm512_broadcastsd_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <8 x i32> zeroinitializer
   return _mm512_broadcastsd_pd(__A);
 }
 
 __m512d test_mm512_mask_broadcastsd_pd(__m512d __O, __mmask8 __M, __m128d __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastsd_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <8 x i32> zeroinitializer
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_mask_broadcastsd_pd(__O, __M, __A);
 }
 
 __m512d test_mm512_maskz_broadcastsd_pd(__mmask8 __M, __m128d __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastsd_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <8 x i32> zeroinitializer
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_maskz_broadcastsd_pd(__M, __A);
 }
 
 __m512 test_mm512_broadcastss_ps(__m128 __A) {
   // CHECK-LABEL: @test_mm512_broadcastss_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <16 x i32> zeroinitializer
   return _mm512_broadcastss_ps(__A);
 }
 
 __m512 test_mm512_mask_broadcastss_ps(__m512 __O, __mmask16 __M, __m128 __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastss_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <16 x i32> zeroinitializer
   // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}}
   return _mm512_mask_broadcastss_ps(__O, __M, __A);
 }
 
 __m512 test_mm512_maskz_broadcastss_ps(__mmask16 __M, __m128 __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastss_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <16 x i32> zeroinitializer
   // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}}
   return _mm512_maskz_broadcastss_ps(__M, __A);
 }
 
 __m512i test_mm512_broadcastd_epi32(__m128i __A) {
   // CHECK-LABEL: @test_mm512_broadcastd_epi32
-  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> zeroinitializer, <16 x i32> zeroinitializer
   return _mm512_broadcastd_epi32(__A);
 }
 
 __m512i test_mm512_mask_broadcastd_epi32(__m512i __O, __mmask16 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastd_epi32
-  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> zeroinitializer, <16 x i32> zeroinitializer
   // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
   return _mm512_mask_broadcastd_epi32(__O, __M, __A);
 }
 
 __m512i test_mm512_maskz_broadcastd_epi32(__mmask16 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastd_epi32
-  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> undef, <16 x i32> zeroinitializer
+  // CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> zeroinitializer, <16 x i32> zeroinitializer
   // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
   return _mm512_maskz_broadcastd_epi32(__M, __A);
 }
 
 __m512i test_mm512_broadcastq_epi64(__m128i __A) {
   // CHECK-LABEL: @test_mm512_broadcastq_epi64
-  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> zeroinitializer, <8 x i32> zeroinitializer
   return _mm512_broadcastq_epi64(__A);
 }
 
 __m512i test_mm512_mask_broadcastq_epi64(__m512i __O, __mmask8 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_mask_broadcastq_epi64
-  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> zeroinitializer, <8 x i32> zeroinitializer
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_mask_broadcastq_epi64(__O, __M, __A);
 }
 
 __m512i test_mm512_maskz_broadcastq_epi64(__mmask8 __M, __m128i __A) {
   // CHECK-LABEL: @test_mm512_maskz_broadcastq_epi64
-  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <8 x i32> zeroinitializer
+  // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> zeroinitializer, <8 x i32> zeroinitializer
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_maskz_broadcastq_epi64(__M, __A);
 }
 
 __m128i test_mm512_cvtsepi32_epi8(__m512i __A) {
   // CHECK-LABEL: @test_mm512_cvtsepi32_epi8
   // CHECK: @llvm.x86.avx512.mask.pmovs.db.512
   return _mm512_cvtsepi32_epi8(__A); 
__m128i test_mm512_maskz_extracti32x4_epi32(__mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_maskz_extracti32x4_epi32
   // CHECK: shufflevector <16 x i32> %{{.*}}, <16 x i32> %{{.*}}, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}
   return _mm512_maskz_extracti32x4_epi32(__U, __A, 3); 
 }
 
 __m256i test_mm512_extracti64x4_epi64(__m512i __A) {
   // CHECK-LABEL: @test_mm512_extracti64x4_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm512_extracti64x4_epi64(__A, 1); 
 }
 
 __m256i test_mm512_mask_extracti64x4_epi64(__m256i __W, __mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_mask_extracti64x4_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}
   return _mm512_mask_extracti64x4_epi64(__W, __U, __A, 1); 
 }
 
 __m256i test_mm512_maskz_extracti64x4_epi64(__mmask8 __U, __m512i __A) {
   // CHECK-LABEL: @test_mm512_maskz_extracti64x4_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}
   return _mm512_maskz_extracti64x4_epi64(__U, __A, 1); 
 }
 
 __m512d test_mm512_insertf64x4(__m512d __A, __m256d __B) {
   // CHECK-LABEL: @test_mm512_insertf64x4
   // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
   return _mm512_insertf64x4(__A, __B, 1);

 __m128d test_mm_mask3_fnmsub_round_sd(__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U){
   // CHECK-LABEL: @test_mm_mask3_fnmsub_round_sd
   // CHECK: @llvm.x86.avx512.mask3.vfnmsub.sd
   return _mm_mask3_fnmsub_round_sd(__W, __X, __Y, __U, _MM_FROUND_CUR_DIRECTION);
 }
 
 __m512d test_mm512_permutex_pd(__m512d __X) {
   // CHECK-LABEL: @test_mm512_permutex_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   return _mm512_permutex_pd(__X, 0);
 }
 
 __m512d test_mm512_mask_permutex_pd(__m512d __W, __mmask8 __U, __m512d __X) {
   // CHECK-LABEL: @test_mm512_mask_permutex_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_mask_permutex_pd(__W, __U, __X, 0);
 }
 
 __m512d test_mm512_maskz_permutex_pd(__mmask8 __U, __m512d __X) {
   // CHECK-LABEL: @test_mm512_maskz_permutex_pd
-  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x double> %{{.*}}, <8 x double> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}}
   return _mm512_maskz_permutex_pd(__U, __X, 0);
 }
 
 __m512i test_mm512_permutex_epi64(__m512i __X) {
   // CHECK-LABEL: @test_mm512_permutex_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   return _mm512_permutex_epi64(__X, 0);
 }
 
 __m512i test_mm512_mask_permutex_epi64(__m512i __W, __mmask8 __M, __m512i __X) {
   // CHECK-LABEL: @test_mm512_mask_permutex_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_mask_permutex_epi64(__W, __M, __X, 0);
 }
 
 __m512i test_mm512_maskz_permutex_epi64(__mmask8 __M, __m512i __X) {
   // CHECK-LABEL: @test_mm512_maskz_permutex_epi64
-  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
+  // CHECK: shufflevector <8 x i64> %{{.*}}, <8 x i64> zeroinitializer, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}}
   return _mm512_maskz_permutex_epi64(__M, __X, 0);
 }
 
 __m512d test_mm512_permutexvar_pd(__m512i __X, __m512d __Y) {
   // CHECK-LABEL: @test_mm512_permutexvar_pd
   // CHECK: @llvm.x86.avx512.mask.permvar.df.512
   return _mm512_permutexvar_pd(__X, __Y); 

cfe/trunk/test/CodeGen/avx512vl-builtins.c

 __m256 test_mm256_maskz_rcp14_ps(__mmask8 __U, __m256 __A) {
   // CHECK-LABEL: @test_mm256_maskz_rcp14_ps
   // CHECK: @llvm.x86.avx512.rcp14.ps.256
   return _mm256_maskz_rcp14_ps(__U, __A); 
 }
 
 __m128d test_mm_mask_permute_pd(__m128d __W, __mmask8 __U, __m128d __X) {
   // CHECK-LABEL: @test_mm_mask_permute_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <2 x i32> <i32 1, i32 0>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm_mask_permute_pd(__W, __U, __X, 1); 
 }
 
 __m128d test_mm_maskz_permute_pd(__mmask8 __U, __m128d __X) {
   // CHECK-LABEL: @test_mm_maskz_permute_pd
-  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> undef, <2 x i32> <i32 1, i32 0>
+  // CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> zeroinitializer, <2 x i32> <i32 1, i32 0>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm_maskz_permute_pd(__U, __X, 1); 
 }
 
 __m256d test_mm256_mask_permute_pd(__m256d __W, __mmask8 __U, __m256d __X) {
   // CHECK-LABEL: @test_mm256_mask_permute_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm256_mask_permute_pd(__W, __U, __X, 5); 
 }
 
 __m256d test_mm256_maskz_permute_pd(__mmask8 __U, __m256d __X) {
   // CHECK-LABEL: @test_mm256_maskz_permute_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm256_maskz_permute_pd(__U, __X, 5); 
 }
 
 __m128 test_mm_mask_permute_ps(__m128 __W, __mmask8 __U, __m128 __X) {
   // CHECK-LABEL: @test_mm_mask_permute_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
   return _mm_mask_permute_ps(__W, __U, __X, 0x1b); 
 }
 
 __m128 test_mm_maskz_permute_ps(__mmask8 __U, __m128 __X) {
   // CHECK-LABEL: @test_mm_maskz_permute_ps
-  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> zeroinitializer, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
   return _mm_maskz_permute_ps(__U, __X, 0x1b); 
 }
 
 __m256 test_mm256_mask_permute_ps(__m256 __W, __mmask8 __U, __m256 __X) {
   // CHECK-LABEL: @test_mm256_mask_permute_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}}
   return _mm256_mask_permute_ps(__W, __U, __X, 0x1b); 
 }
 
 __m256 test_mm256_maskz_permute_ps(__mmask8 __U, __m256 __X) {
   // CHECK-LABEL: @test_mm256_maskz_permute_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   // CHECK: select <8 x i1> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}}
   return _mm256_maskz_permute_ps(__U, __X, 0x1b); 
 }
 
 __m128d test_mm_mask_permutevar_pd(__m128d __W, __mmask8 __U, __m128d __A, __m128i __C) {
   // CHECK-LABEL: @test_mm_mask_permutevar_pd
   // CHECK: @llvm.x86.avx.vpermilvar.pd
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}

 void test_mm256_mask_cvtepi64_storeu_epi16(void * __P, __mmask8 __M, __m256i __A) {
   // CHECK-LABEL: @test_mm256_mask_cvtepi64_storeu_epi16
   // CHECK: @llvm.x86.avx512.mask.pmov.qw.mem.256
   return _mm256_mask_cvtepi64_storeu_epi16(__P, __M, __A); 
 }
 
 __m128 test_mm256_extractf32x4_ps(__m256 __A) {
   // CHECK-LABEL: @test_mm256_extractf32x4_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm256_extractf32x4_ps(__A, 1); 
 }
 
 __m128 test_mm256_mask_extractf32x4_ps(__m128 __W, __mmask8 __U, __m256 __A) {
   // CHECK-LABEL: @test_mm256_mask_extractf32x4_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
   return _mm256_mask_extractf32x4_ps(__W, __U, __A, 1); 
 }
 
 __m128 test_mm256_maskz_extractf32x4_ps(__mmask8 __U, __m256 __A) {
   // CHECK-LABEL: @test_mm256_maskz_extractf32x4_ps
-  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+  // CHECK: shufflevector <8 x float> %{{.*}}, <8 x float> zeroinitializer, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   // CHECK: select <4 x i1> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}}
   return _mm256_maskz_extractf32x4_ps(__U, __A, 1); 
 }
 
 __m128i test_mm256_extracti32x4_epi32(__m256i __A) {
   // CHECK-LABEL: @test_mm256_extracti32x4_epi32
   // CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   return _mm256_extracti32x4_epi32(__A, 1); 

 __m256i test_mm256_mask_i32gather_epi32(__m256i __v1_old, __mmask8 __mask, __m256i __index, void const *__addr) {
   // CHECK-LABEL: @test_mm256_mask_i32gather_epi32
   // CHECK: @llvm.x86.avx512.gather3siv8.si
   return _mm256_mmask_i32gather_epi32(__v1_old, __mask, __index, __addr, 2); 
 }
 
 __m256d test_mm256_permutex_pd(__m256d __X) {
   // CHECK-LABEL: @test_mm256_permutex_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
   return _mm256_permutex_pd(__X, 3);
 }
 
 __m256d test_mm256_mask_permutex_pd(__m256d __W, __mmask8 __U, __m256d __X) {
   // CHECK-LABEL: @test_mm256_mask_permutex_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm256_mask_permutex_pd(__W, __U, __X, 1);
 }
 
 __m256d test_mm256_maskz_permutex_pd(__mmask8 __U, __m256d __X) {
   // CHECK-LABEL: @test_mm256_maskz_permutex_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}}
   return _mm256_maskz_permutex_pd(__U, __X, 1);
 }
 
 __m256i test_mm256_permutex_epi64(__m256i __X) {
   // CHECK-LABEL: @test_mm256_permutex_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
   return _mm256_permutex_epi64(__X, 3);
 }
 
 __m256i test_mm256_mask_permutex_epi64(__m256i __W, __mmask8 __M, __m256i __X) {
   // CHECK-LABEL: @test_mm256_mask_permutex_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}
   return _mm256_mask_permutex_epi64(__W, __M, __X, 3);
 }
 
 __m256i test_mm256_maskz_permutex_epi64(__mmask8 __M, __m256i __X) {
   // CHECK-LABEL: @test_mm256_maskz_permutex_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 0, i32 0>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}
   return _mm256_maskz_permutex_epi64(__M, __X, 3);
 }
 
 __m256d test_mm256_permutexvar_pd(__m256i __X, __m256d __Y) {
   // CHECK-LABEL: @test_mm256_permutexvar_pd
   // CHECK: @llvm.x86.avx512.mask.permvar.df.256
   return _mm256_permutexvar_pd(__X, __Y);

cfe/trunk/test/CodeGen/avx512vldq-builtins.c

__m256i test_mm256_maskz_broadcast_i64x2(__mmask8 __M, __m128i const* __A) {
   // CHECK-LABEL: @test_mm256_maskz_broadcast_i64x2
   // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
   // CHECK: select <4 x i1> %{{.*}}, <4 x i64> %{{.*}}, <4 x i64> %{{.*}}
   return _mm256_maskz_broadcast_i64x2(__M, _mm_loadu_si128(__A)); 
 }
 
 __m128d test_mm256_extractf64x2_pd(__m256d __A) {
   // CHECK-LABEL: @test_mm256_extractf64x2_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <2 x i32> <i32 2, i32 3>
   return _mm256_extractf64x2_pd(__A, 1); 
 }
 
 __m128d test_mm256_mask_extractf64x2_pd(__m128d __W, __mmask8 __U, __m256d __A) {
   // CHECK-LABEL: @test_mm256_mask_extractf64x2_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm256_mask_extractf64x2_pd(__W, __U, __A, 1); 
 }
 
 __m128d test_mm256_maskz_extractf64x2_pd(__mmask8 __U, __m256d __A) {
   // CHECK-LABEL: @test_mm256_maskz_extractf64x2_pd
-  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: select <2 x i1> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}}
   return _mm256_maskz_extractf64x2_pd(__U, __A, 1); 
 }
 
 __m128i test_mm256_extracti64x2_epi64(__m256i __A) {
   // CHECK-LABEL: @test_mm256_extracti64x2_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   return _mm256_extracti64x2_epi64(__A, 1); 
 }
 
 __m128i test_mm256_mask_extracti64x2_epi64(__m128i __W, __mmask8 __U, __m256i __A) {
   // CHECK-LABEL: @test_mm256_mask_extracti64x2_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: select <2 x i1> %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}
   return _mm256_mask_extracti64x2_epi64(__W, __U, __A, 1); 
 }
 
 __m128i test_mm256_maskz_extracti64x2_epi64(__mmask8 __U, __m256i __A) {
   // CHECK-LABEL: @test_mm256_maskz_extracti64x2_epi64
-  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 2, i32 3>
+  // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> zeroinitializer, <2 x i32> <i32 2, i32 3>
   // CHECK: select <2 x i1> %{{.*}}, <2 x i64> %{{.*}}, <2 x i64> %{{.*}}
   return _mm256_maskz_extracti64x2_epi64(__U, __A, 1); 
 }
 
 __m256d test_mm256_insertf64x2(__m256d __A, __m128d __B) {
   // CHECK-LABEL: @test_mm256_insertf64x2
   // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
   return _mm256_insertf64x2(__A, __B, 1); 

cfe/trunk/test/CodeGen/sse-builtins.c

 int test_mm_ucomineq_ss(__m128 A, __m128 B) {
   // CHECK-LABEL: test_mm_ucomineq_ss
   // CHECK: call i32 @llvm.x86.sse.ucomineq.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}})
   return _mm_ucomineq_ss(A, B);
 }
 
 __m128 test_mm_undefined_ps() {
   // CHECK-LABEL: @test_mm_undefined_ps
-  // CHECK: ret <4 x float> undef
+  // CHECK: ret <4 x float> zeroinitializer
   return _mm_undefined_ps();
 }
 
 __m128 test_mm_unpackhi_ps(__m128 A, __m128 B) {
   // CHECK-LABEL: test_mm_unpackhi_ps
   // CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
   return _mm_unpackhi_ps(A, B);
 }

cfe/trunk/test/CodeGen/sse2-builtins.c

 int test_mm_ucomineq_sd(__m128d A, __m128d B) {
   // CHECK-LABEL: test_mm_ucomineq_sd
   // CHECK: call i32 @llvm.x86.sse2.ucomineq.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}})
   return _mm_ucomineq_sd(A, B);
 }
 
 __m128d test_mm_undefined_pd() {
   // CHECK-LABEL: @test_mm_undefined_pd
-  // CHECK: ret <2 x double> undef
+  // CHECK: ret <2 x double> zeroinitializer
   return _mm_undefined_pd();
 }
 
 __m128i test_mm_undefined_si128() {
   // CHECK-LABEL: @test_mm_undefined_si128
-  // CHECK: ret <2 x i64> undef
+  // CHECK: ret <2 x i64> zeroinitializer
   return _mm_undefined_si128();
 }
 
 __m128i test_mm_unpackhi_epi8(__m128i A, __m128i B) {
   // CHECK-LABEL: test_mm_unpackhi_epi8
   // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> %{{.*}}, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
   return _mm_unpackhi_epi8(A, B);
 }