aboutsummaryrefslogtreecommitdiff
path: root/clang/test/CodeGen/X86
diff options
context:
space:
mode:
Diffstat (limited to 'clang/test/CodeGen/X86')
-rw-r--r--clang/test/CodeGen/X86/avx2-builtins.c2
-rw-r--r--clang/test/CodeGen/X86/avx512bw-builtins.c11
-rw-r--r--clang/test/CodeGen/X86/avx512fp16-builtins.c4
-rw-r--r--clang/test/CodeGen/X86/avx512vlbw-builtins.c8
-rw-r--r--clang/test/CodeGen/X86/avx512vlfp16-builtins.c2
-rw-r--r--clang/test/CodeGen/X86/mmx-builtins.c2
-rw-r--r--clang/test/CodeGen/X86/sse2-builtins.c1
-rw-r--r--clang/test/CodeGen/X86/ssse3-builtins.c1
8 files changed, 31 insertions, 0 deletions
diff --git a/clang/test/CodeGen/X86/avx2-builtins.c b/clang/test/CodeGen/X86/avx2-builtins.c
index 4299b18..55f18f9 100644
--- a/clang/test/CodeGen/X86/avx2-builtins.c
+++ b/clang/test/CodeGen/X86/avx2-builtins.c
@@ -810,12 +810,14 @@ __m256i test_mm256_madd_epi16(__m256i a, __m256i b) {
// CHECK: call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %{{.*}}, <16 x i16> %{{.*}})
return _mm256_madd_epi16(a, b);
}
+TEST_CONSTEXPR(match_v8si(_mm256_madd_epi16((__m256i)(__v16hi){1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, (__m256i)(__v16hi){10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160}), 50, 250, 610, 1130, 1810, 2650, 3650, 4810));
__m256i test_mm256_maddubs_epi16(__m256i a, __m256i b) {
// CHECK-LABEL: test_mm256_maddubs_epi16
// CHECK: call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %{{.*}}, <32 x i8> %{{.*}})
return _mm256_maddubs_epi16(a, b);
}
+TEST_CONSTEXPR(match_v16hi(_mm256_maddubs_epi16((__m256i)(__v32qi){1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7,8}, (__m256i)(__v32qs){2, 3, 4, 5, 6, 7, 8, 9, 1, 2, 3, 4, 5, 6, 7, 8, -1, -1, -2, -2, -3, -3, -4, -4, -5, -5, -6, -6, -7, -7, -8, -8}), 5, 18, 39, 68, 15, 42, 77, 120, -3, -14, -33, -60, -15, -42, -77, -120));
__m128i test_mm_maskload_epi32(int const *a, __m128i m) {
// CHECK-LABEL: test_mm_maskload_epi32
diff --git a/clang/test/CodeGen/X86/avx512bw-builtins.c b/clang/test/CodeGen/X86/avx512bw-builtins.c
index bd19363..af1c904 100644
--- a/clang/test/CodeGen/X86/avx512bw-builtins.c
+++ b/clang/test/CodeGen/X86/avx512bw-builtins.c
@@ -1650,35 +1650,46 @@ __m512i test_mm512_maddubs_epi16(__m512i __X, __m512i __Y) {
// CHECK: @llvm.x86.avx512.pmaddubs.w.512
return _mm512_maddubs_epi16(__X,__Y);
}
+TEST_CONSTEXPR(match_v32hi(_mm512_maddubs_epi16((__m512i)(__v64qi){2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3}, (__m512i)(__v64qs){5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5}), -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5));
+
__m512i test_mm512_mask_maddubs_epi16(__m512i __W, __mmask32 __U, __m512i __X, __m512i __Y) {
// CHECK-LABEL: test_mm512_mask_maddubs_epi16
// CHECK: @llvm.x86.avx512.pmaddubs.w.512
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_mask_maddubs_epi16(__W,__U,__X,__Y);
}
+TEST_CONSTEXPR(match_v32hi(_mm512_mask_maddubs_epi16((__m512i)(__v32hi){-1, -2, -3, -4, -5, -6, -7, -8, -9, -10, -11, -12, -13, -14, -15, -16, -17, -18, -19, -20, -21, -22, -23, -24, -25, -26, -27, -28, -29, -30, -31, -32}, 0x0000FFFF, (__m512i)(__v64qi){2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3}, (__m512i)(__v64qs){5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5}), -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -17, -18, -19, -20, -21, -22, -23, -24, -25, -26, -27, -28, -29, -30, -31, -32));
+
__m512i test_mm512_maskz_maddubs_epi16(__mmask32 __U, __m512i __X, __m512i __Y) {
// CHECK-LABEL: test_mm512_maskz_maddubs_epi16
// CHECK: @llvm.x86.avx512.pmaddubs.w.512
// CHECK: select <32 x i1> %{{.*}}, <32 x i16> %{{.*}}, <32 x i16> %{{.*}}
return _mm512_maskz_maddubs_epi16(__U,__X,__Y);
}
+TEST_CONSTEXPR(match_v32hi(_mm512_maskz_maddubs_epi16(0x0000FFFF, (__m512i)(__v64qi){2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3}, (__m512i)(__v64qs){5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5, 5, -5}), -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, -5, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0));
+
__m512i test_mm512_madd_epi16(__m512i __A, __m512i __B) {
// CHECK-LABEL: test_mm512_madd_epi16
// CHECK: @llvm.x86.avx512.pmaddw.d.512
return _mm512_madd_epi16(__A,__B);
}
+TEST_CONSTEXPR(match_v16si(_mm512_madd_epi16((__m512i)(__v32hi){1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4}, (__m512i)(__v32hi){1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8}), 3, 7, 22, 30, 9, 21, 44, 60, 3, 7, 22, 30, 9, 21, 44, 60));
+
__m512i test_mm512_mask_madd_epi16(__m512i __W, __mmask16 __U, __m512i __A, __m512i __B) {
// CHECK-LABEL: test_mm512_mask_madd_epi16
// CHECK: @llvm.x86.avx512.pmaddw.d.512
// CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
return _mm512_mask_madd_epi16(__W,__U,__A,__B);
}
+TEST_CONSTEXPR(match_v16si(_mm512_mask_madd_epi16((__m512i)(__v16si){100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500, 1600}, 0xF0F0, (__m512i)(__v32hi){1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4}, (__m512i)(__v32hi){1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8}), 100, 200, 300, 400, 9, 21, 44, 60, 900, 1000, 1100, 1200, 9, 21, 44, 60));
+
__m512i test_mm512_maskz_madd_epi16(__mmask16 __U, __m512i __A, __m512i __B) {
// CHECK-LABEL: test_mm512_maskz_madd_epi16
// CHECK: @llvm.x86.avx512.pmaddw.d.512
// CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}}
return _mm512_maskz_madd_epi16(__U,__A,__B);
}
+TEST_CONSTEXPR(match_v16si(_mm512_maskz_madd_epi16(0xF0F0, (__m512i)(__v32hi){1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4}, (__m512i)(__v32hi){1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7, 8}), 0, 0, 0, 0, 9, 21, 44, 60, 0, 0, 0, 0, 9, 21, 44, 60));
__m256i test_mm512_cvtsepi16_epi8(__m512i __A) {
// CHECK-LABEL: test_mm512_cvtsepi16_epi8
diff --git a/clang/test/CodeGen/X86/avx512fp16-builtins.c b/clang/test/CodeGen/X86/avx512fp16-builtins.c
index dbf89b3..2befff0 100644
--- a/clang/test/CodeGen/X86/avx512fp16-builtins.c
+++ b/clang/test/CodeGen/X86/avx512fp16-builtins.c
@@ -117,6 +117,7 @@ __m512h test_mm512_set1_pch(_Float16 _Complex h) {
// CHECK: bitcast <16 x float>{{.*}} to <32 x half>
return _mm512_set1_pch(h);
}
+TEST_CONSTEXPR(match_m512h(_mm512_set1_pch(1.0), 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0));
__m512h test_mm512_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
_Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8,
@@ -340,18 +341,21 @@ __m128h test_mm256_castph256_ph128(__m256h __a) {
// CHECK: shufflevector <16 x half> %{{.*}}, <16 x half> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return _mm256_castph256_ph128(__a);
}
+TEST_CONSTEXPR(match_m128h(_mm256_castph256_ph128((__m256h){-1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0, 8.0, -9.0, 10.0, -11.0, 12.0, -13.0, 14.0, -15.0, -16.0}), -1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0, 8.0));
__m128h test_mm512_castph512_ph128(__m512h __a) {
// CHECK-LABEL: test_mm512_castph512_ph128
// CHECK: shufflevector <32 x half> %{{.*}}, <32 x half> %{{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return _mm512_castph512_ph128(__a);
}
+TEST_CONSTEXPR(match_m128h(_mm512_castph512_ph128((__m512h){0.0, -1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0, 8.0, -9.0, 10.0, -11.0, 12.0, -13.0, 14.0, -15.0, -16.0, -17.0, 18.0, -19.0, 20.0, -21.0, 22.0, -23.0, 24.0, -25.0, 26.0, -27.0, 28.0, -29.0, 30.0, -31.0}), 0.0, -1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0));
__m256h test_mm512_castph512_ph256(__m512h __a) {
// CHECK-LABEL: test_mm512_castph512_ph256
// CHECK: shufflevector <32 x half> %{{.*}}, <32 x half> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
return _mm512_castph512_ph256(__a);
}
+TEST_CONSTEXPR(match_m256h(_mm512_castph512_ph256((__m512h){-1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0, 8.0, -9.0, 10.0, -11.0, 12.0, -13.0, 14.0, -15.0, -16.0, -17.0, 18.0, -19.0, 20.0, -21.0, 22.0, -23.0, 24.0, -25.0, 26.0, -27.0, 28.0, -29.0, 30.0, -31.0, 32.0}), -1.0, 2.0, -3.0, 4.0, -5.0, 6.0, -7.0, 8.0, -9.0, 10.0, -11.0, 12.0, -13.0, 14.0, -15.0, -16.0));
__m256h test_mm256_castph128_ph256(__m128h __a) {
// CHECK-LABEL: test_mm256_castph128_ph256
diff --git a/clang/test/CodeGen/X86/avx512vlbw-builtins.c b/clang/test/CodeGen/X86/avx512vlbw-builtins.c
index 1fe1ec0..c0e46de 100644
--- a/clang/test/CodeGen/X86/avx512vlbw-builtins.c
+++ b/clang/test/CodeGen/X86/avx512vlbw-builtins.c
@@ -1865,6 +1865,7 @@ __m128i test_mm_mask_maddubs_epi16(__m128i __W, __mmask8 __U, __m128i __X, __m12
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_mask_maddubs_epi16(__W, __U, __X, __Y);
}
+TEST_CONSTEXPR(match_v8hi(_mm_mask_maddubs_epi16((__m128i)(__v8hi){1, 2, 3, 4, 5, 6, 7, 8}, 0x0F, (__m128i)(__v16qi){1, 1, 2, 2, 3, 3, 4, 4, 1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v16qs){2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -2, -2, -3, -3, -4, -4}), 5, 18, 39, 68, 5, 6, 7, 8));
__m128i test_mm_maskz_maddubs_epi16(__mmask8 __U, __m128i __X, __m128i __Y) {
// CHECK-LABEL: test_mm_maskz_maddubs_epi16
@@ -1872,6 +1873,7 @@ __m128i test_mm_maskz_maddubs_epi16(__mmask8 __U, __m128i __X, __m128i __Y) {
// CHECK: select <8 x i1> %{{.*}}, <8 x i16> %{{.*}}, <8 x i16> %{{.*}}
return _mm_maskz_maddubs_epi16(__U, __X, __Y);
}
+TEST_CONSTEXPR(match_v8hi(_mm_maskz_maddubs_epi16(0x0F, (__m128i)(__v16qi){1, 1, 2, 2, 3, 3, 4, 4, 1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v16qs){2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -2, -2, -3, -3, -4, -4}), 5, 18, 39, 68, 0, 0, 0, 0));
__m256i test_mm256_mask_maddubs_epi16(__m256i __W, __mmask16 __U, __m256i __X, __m256i __Y) {
// CHECK-LABEL: test_mm256_mask_maddubs_epi16
@@ -1879,6 +1881,7 @@ __m256i test_mm256_mask_maddubs_epi16(__m256i __W, __mmask16 __U, __m256i __X, _
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_mask_maddubs_epi16(__W, __U, __X, __Y);
}
+TEST_CONSTEXPR(match_v16hi(_mm256_mask_maddubs_epi16((__m256i)(__v16hi){-1, -2, -3, -4, -5, -6, -7, -8, -9, -10, -11, -12, -13, -14, -15, -16}, 0x00FF, (__m256i)(__v32qi){1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7,8}, (__m256i)(__v32qs){2, 3, 4, 5, 6, 7, 8, 9, 1, 2, 3, 4, 5, 6, 7, 8, -1, -1, -2, -2, -3, -3, -4, -4, -5, -5, -6, -6, -7, -7, -8, -8}), 5, 18, 39, 68, 15, 42, 77, 120, -9, -10, -11, -12, -13, -14, -15, -16));
__m256i test_mm256_maskz_maddubs_epi16(__mmask16 __U, __m256i __X, __m256i __Y) {
// CHECK-LABEL: test_mm256_maskz_maddubs_epi16
@@ -1886,6 +1889,7 @@ __m256i test_mm256_maskz_maddubs_epi16(__mmask16 __U, __m256i __X, __m256i __Y)
// CHECK: select <16 x i1> %{{.*}}, <16 x i16> %{{.*}}, <16 x i16> %{{.*}}
return _mm256_maskz_maddubs_epi16(__U, __X, __Y);
}
+TEST_CONSTEXPR(match_v16hi(_mm256_maskz_maddubs_epi16(0x00FF, (__m256i)(__v32qi){1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 1, 2, 3, 4, 5, 6, 7, 8, 1, 2, 3, 4, 5, 6, 7,8}, (__m256i)(__v32qs){2, 3, 4, 5, 6, 7, 8, 9, 1, 2, 3, 4, 5, 6, 7, 8, -1, -1, -2, -2, -3, -3, -4, -4, -5, -5, -6, -6, -7, -7, -8, -8}), 5, 18, 39, 68, 15, 42, 77, 120, 0, 0, 0, 0, 0, 0, 0, 0));
__m128i test_mm_mask_madd_epi16(__m128i __W, __mmask8 __U, __m128i __A, __m128i __B) {
// CHECK-LABEL: test_mm_mask_madd_epi16
@@ -1893,6 +1897,7 @@ __m128i test_mm_mask_madd_epi16(__m128i __W, __mmask8 __U, __m128i __A, __m128i
// CHECK: select <4 x i1> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}
return _mm_mask_madd_epi16(__W, __U, __A, __B);
}
+TEST_CONSTEXPR(match_v4si(_mm_mask_madd_epi16((__m128i)(__v4si){1, 2, 3, 4}, 0x3, (__m128i)(__v8hi){1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v8hi){9, 10, 11, 12, 13, 14, 15, 16}), 29, 81, 3, 4));
__m128i test_mm_maskz_madd_epi16(__mmask8 __U, __m128i __A, __m128i __B) {
// CHECK-LABEL: test_mm_maskz_madd_epi16
@@ -1900,6 +1905,7 @@ __m128i test_mm_maskz_madd_epi16(__mmask8 __U, __m128i __A, __m128i __B) {
// CHECK: select <4 x i1> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> %{{.*}}
return _mm_maskz_madd_epi16(__U, __A, __B);
}
+TEST_CONSTEXPR(match_v4si(_mm_maskz_madd_epi16(0x3, (__m128i)(__v8hi){1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v8hi){9, 10, 11, 12, 13, 14, 15, 16}), 29, 81, 0, 0));
__m256i test_mm256_mask_madd_epi16(__m256i __W, __mmask8 __U, __m256i __A, __m256i __B) {
// CHECK-LABEL: test_mm256_mask_madd_epi16
@@ -1907,6 +1913,7 @@ __m256i test_mm256_mask_madd_epi16(__m256i __W, __mmask8 __U, __m256i __A, __m25
// CHECK: select <8 x i1> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}
return _mm256_mask_madd_epi16(__W, __U, __A, __B);
}
+TEST_CONSTEXPR(match_v8si(_mm256_mask_madd_epi16((__m256i)(__v8si){1, 2, 3, 4, 5, 6, 7, 8}, 0x0F, (__m256i)(__v16hi){1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, (__m256i)(__v16hi){10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160}), 50, 250, 610, 1130, 5, 6, 7, 8));
__m256i test_mm256_maskz_madd_epi16(__mmask8 __U, __m256i __A, __m256i __B) {
// CHECK-LABEL: test_mm256_maskz_madd_epi16
@@ -1914,6 +1921,7 @@ __m256i test_mm256_maskz_madd_epi16(__mmask8 __U, __m256i __A, __m256i __B) {
// CHECK: select <8 x i1> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> %{{.*}}
return _mm256_maskz_madd_epi16(__U, __A, __B);
}
+TEST_CONSTEXPR(match_v8si(_mm256_maskz_madd_epi16(0x0F, (__m256i)(__v16hi){1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, (__m256i)(__v16hi){10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150, 160}), 50, 250, 610, 1130, 0, 0, 0, 0));
__m128i test_mm_cvtsepi16_epi8(__m128i __A) {
// CHECK-LABEL: test_mm_cvtsepi16_epi8
diff --git a/clang/test/CodeGen/X86/avx512vlfp16-builtins.c b/clang/test/CodeGen/X86/avx512vlfp16-builtins.c
index f1865aa..68d0984 100644
--- a/clang/test/CodeGen/X86/avx512vlfp16-builtins.c
+++ b/clang/test/CodeGen/X86/avx512vlfp16-builtins.c
@@ -17,12 +17,14 @@ _Float16 test_mm_cvtsh_h(__m128h __A) {
// CHECK: extractelement <8 x half> %{{.*}}, i32 0
return _mm_cvtsh_h(__A);
}
+TEST_CONSTEXPR(_mm_cvtsh_h((__m128h){-8.0, 7.0, -6.0, 5.0, -4.0, 3.0, -2.0, 1.0}) == -8.0);
_Float16 test_mm256_cvtsh_h(__m256h __A) {
// CHECK-LABEL: test_mm256_cvtsh_h
// CHECK: extractelement <16 x half> %{{.*}}, i32 0
return _mm256_cvtsh_h(__A);
}
+TEST_CONSTEXPR(_mm256_cvtsh_h((__m256h){-32.0, 31.0, -30.0, 29.0, -28.0, 27.0, -26.0, 25.0, -24.0, 23.0, -22.0, 21.0, -20.0, 19.0, -18.0, 17.0}) == -32.0);
__m128h test_mm_set_sh(_Float16 __h) {
// CHECK-LABEL: test_mm_set_sh
diff --git a/clang/test/CodeGen/X86/mmx-builtins.c b/clang/test/CodeGen/X86/mmx-builtins.c
index a4494b69..2b45b92 100644
--- a/clang/test/CodeGen/X86/mmx-builtins.c
+++ b/clang/test/CodeGen/X86/mmx-builtins.c
@@ -355,12 +355,14 @@ __m64 test_mm_madd_pi16(__m64 a, __m64 b) {
// CHECK: call <4 x i32> @llvm.x86.sse2.pmadd.wd(
return _mm_madd_pi16(a, b);
}
+TEST_CONSTEXPR(match_v2si(_mm_madd_pi16((__m64)(__v4hi){+1, -2, +3, -4}, (__m64)(__v4hi){-10, +8, +6, -4}), -26, 34));
__m64 test_mm_maddubs_pi16(__m64 a, __m64 b) {
// CHECK-LABEL: test_mm_maddubs_pi16
// CHECK: call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(
return _mm_maddubs_pi16(a, b);
}
+TEST_CONSTEXPR(match_v4hi(_mm_maddubs_pi16((__m64)(__v8qi){16, 17, 18, 19, 20, 21, 22, 23}, (__m64)(__v8qi){1, 2, 3, 4, 5, 0, 7, 8}), 50, 130, 100, 338));
void test_mm_maskmove_si64(__m64 d, __m64 n, char *p) {
// CHECK-LABEL: test_mm_maskmove_si64
diff --git a/clang/test/CodeGen/X86/sse2-builtins.c b/clang/test/CodeGen/X86/sse2-builtins.c
index 8428fd6..ade7ef3 100644
--- a/clang/test/CodeGen/X86/sse2-builtins.c
+++ b/clang/test/CodeGen/X86/sse2-builtins.c
@@ -852,6 +852,7 @@ __m128i test_mm_madd_epi16(__m128i A, __m128i B) {
// CHECK: call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %{{.*}}, <8 x i16> %{{.*}})
return _mm_madd_epi16(A, B);
}
+TEST_CONSTEXPR(match_v4si(_mm_madd_epi16((__m128i)(__v8hi){1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v8hi){9, 10, 11, 12, 13, 14, 15, 16}), 29, 81, 149, 233));
void test_mm_maskmoveu_si128(__m128i A, __m128i B, char* C) {
// CHECK-LABEL: test_mm_maskmoveu_si128
diff --git a/clang/test/CodeGen/X86/ssse3-builtins.c b/clang/test/CodeGen/X86/ssse3-builtins.c
index 56ff73f0..5885768 100644
--- a/clang/test/CodeGen/X86/ssse3-builtins.c
+++ b/clang/test/CodeGen/X86/ssse3-builtins.c
@@ -96,6 +96,7 @@ __m128i test_mm_maddubs_epi16(__m128i a, __m128i b) {
// CHECK: call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %{{.*}}, <16 x i8> %{{.*}})
return _mm_maddubs_epi16(a, b);
}
+TEST_CONSTEXPR(match_v8hi(_mm_maddubs_epi16((__m128i)(__v16qi){1, 1, 2, 2, 3, 3, 4, 4, 1, 2, 3, 4, 5, 6, 7, 8}, (__m128i)(__v16qs){2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -2, -2, -3, -3, -4, -4}), 5, 18, 39, 68, -3, -14, -33, -60));
__m128i test_mm_mulhrs_epi16(__m128i a, __m128i b) {
// CHECK-LABEL: test_mm_mulhrs_epi16
generated by cgit v1.1 at 2025-10-08 18:59:41 +0000