maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

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

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.

Differential Revision: https://reviews.llvm.org/D30834

llvm-svn: 297588
This commit is contained in:
Sanjay Patel 2017-03-12 19:15:10 +00:00
parent c9d4cb2f42
commit e795daa55e
10 changed files with 115 additions and 110 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
clang/lib/CodeGen/CGBuiltin.cpp
View File

@ -7381,7 +7381,12 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
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:

28
clang/test/CodeGen/avx-builtins.c
View File

@ -346,19 +346,19 @@ long long test_mm256_extract_epi64(__m256i A) {
__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);
}
@ -647,32 +647,32 @@ __m256 test_mm256_or_ps(__m256 A, __m256 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);
}
@ -1177,7 +1177,7 @@ 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);
}
@ -1186,7 +1186,7 @@ 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);
}
@ -1195,7 +1195,7 @@ 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);
}
@ -1322,19 +1322,19 @@ int test_mm256_testz_si256(__m256 A, __m256 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();
}

34
clang/test/CodeGen/avx2-builtins.c
View File

@ -368,20 +368,20 @@ __m256i test_mm256_cvtepu32_epi64(__m128i 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);
}
@ -447,7 +447,7 @@ __m256i test_mm256_mask_i32gather_epi32(__m256i a, int const *b, __m256i c, __m2
__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);
}
@ -459,7 +459,7 @@ __m128i test_mm_mask_i32gather_epi64(__m128i a, long long const *b, __m128i c, _
__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);
}
@ -474,7 +474,7 @@ __m128d test_mm_i32gather_pd(double const *b, __m128i c) {
// 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);
}
@ -489,7 +489,7 @@ __m256d test_mm256_i32gather_pd(double const *b, __m128i c) {
// 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);
}
@ -504,7 +504,7 @@ __m128 test_mm_i32gather_ps(float const *b, __m128i c) {
// 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);
}
@ -519,7 +519,7 @@ __m256 test_mm256_i32gather_ps(float const *b, __m256i c) {
// 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);
}
@ -555,7 +555,7 @@ __m128i test_mm256_mask_i64gather_epi32(__m128i a, int const *b, __m256i c, __m1
__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);
}
@ -567,7 +567,7 @@ __m128i test_mm_mask_i64gather_epi64(__m128i a, long long const *b, __m128i c, _
__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);
}
@ -582,7 +582,7 @@ __m128d test_mm_i64gather_pd(double const *b, __m128i c) {
// 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);
}
@ -597,7 +597,7 @@ __m256d test_mm256_i64gather_pd(double const *b, __m256i c) {
// 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);
}
@ -612,7 +612,7 @@ __m128 test_mm_i64gather_ps(float const *b, __m128i c) {
// 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);
}
@ -627,7 +627,7 @@ __m128 test_mm256_i64gather_ps(float const *b, __m256i c) {
// 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);
}
@ -895,13 +895,13 @@ __m256i test_mm256_permute2x128_si256(__m256i a, __m256i b) {
__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);
}

12
clang/test/CodeGen/avx512bw-builtins.c
View File

@ -1555,40 +1555,40 @@ __m512i test_mm512_movm_epi16(__mmask32 __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);
}

18
clang/test/CodeGen/avx512dq-builtins.c
View File

@ -1063,40 +1063,40 @@ __m512i test_mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i const* __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);
}
@ -1123,20 +1123,20 @@ __m256i test_mm512_maskz_extracti32x8_epi32(__mmask8 __U, __m512i __A) {
__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);
}

74
clang/test/CodeGen/avx512f-builtins.c
View File

@ -1241,20 +1241,20 @@ __mmask8 test_mm512_mask_cmpunord_ps_mask(__mmask8 k, __m512 a, __m512 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);
}
@ -1262,20 +1262,20 @@ __m256d test_mm512_maskz_extractf64x4_pd(__mmask8 __U,__m512d __A){
__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);
}
@ -2458,25 +2458,25 @@ __m128d test_mm_maskz_min_sd(__mmask8 __U, __m128d __A, __m128d __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();
}
@ -3714,40 +3714,40 @@ __m512i test_mm512_mask2_permutex2var_epi64(__m512i __A, __m512i __I, __mmask8 _
__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);
}
@ -4729,80 +4729,80 @@ __m512i test_mm512_maskz_broadcast_i64x4(__mmask8 __M, __m256i const* __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);
}
@ -5189,20 +5189,20 @@ __m128i test_mm512_maskz_extracti32x4_epi32(__mmask8 __U, __m512i __A) {
__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);
}
@ -6085,40 +6085,40 @@ __m128d test_mm_mask3_fnmsub_round_sd(__m128d __W, __m128d __X, __m128d __Y, __m
__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);
}

34
clang/test/CodeGen/avx512vl-builtins.c
View File

@ -5008,56 +5008,56 @@ __m256 test_mm256_maskz_rcp14_ps(__mmask8 __U, __m256 __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);
}
@ -6592,20 +6592,20 @@ void test_mm256_mask_cvtepi64_storeu_epi16(void * __P, __mmask8 __M, __m256i __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);
}
@ -6840,40 +6840,40 @@ __m256i test_mm256_mask_i32gather_epi32(__m256i __v1_old, __mmask8 __mask, __m25
__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);
}

12
clang/test/CodeGen/avx512vldq-builtins.c
View File

@ -996,40 +996,40 @@ __m256i test_mm256_maskz_broadcast_i64x2(__mmask8 __M, __m128i const* __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);
}

2
clang/test/CodeGen/sse-builtins.c
View File

@ -802,7 +802,7 @@ int test_mm_ucomineq_ss(__m128 A, __m128 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();
}

4
clang/test/CodeGen/sse2-builtins.c
View File

@ -1455,13 +1455,13 @@ int test_mm_ucomineq_sd(__m128d A, __m128d 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();
}