summaryrefslogtreecommitdiff
path: root/test/CodeGen/avx2-builtins.c
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/avx2-builtins.c')
-rw-r--r--test/CodeGen/avx2-builtins.c52
1 files changed, 28 insertions, 24 deletions
diff --git a/test/CodeGen/avx2-builtins.c b/test/CodeGen/avx2-builtins.c
index f79f60e6db78d..b0f4b5e6b55ba 100644
--- a/test/CodeGen/avx2-builtins.c
+++ b/test/CodeGen/avx2-builtins.c
@@ -2,7 +2,7 @@
// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +avx2 -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s
-#include <x86intrin.h>
+#include <immintrin.h>
// NOTE: This should match the tests in llvm/test/CodeGen/X86/avx2-intrinsics-fast-isel.ll
@@ -141,7 +141,7 @@ __m128i test_mm_blend_epi32(__m128i a, __m128i b) {
// CHECK-LABEL: test_mm_blend_epi32
// CHECK-NOT: @llvm.x86.avx2.pblendd.128
// CHECK: shufflevector <4 x i32> %{{.*}}, <4 x i32> %{{.*}}, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
- return _mm_blend_epi32(a, b, 0x35);
+ return _mm_blend_epi32(a, b, 0x05);
}
__m256i test_mm256_blend_epi32(__m256i a, __m256i b) {
@@ -248,13 +248,13 @@ __m256i test_mm256_broadcastw_epi16(__m128i a) {
__m256i test_mm256_bslli_epi128(__m256i a) {
// CHECK-LABEL: test_mm256_bslli_epi128
- // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> %{{.*}}, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
+ // CHECK: shufflevector <32 x i8> zeroinitializer, <32 x i8> %{{.*}}, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
return _mm256_bslli_epi128(a, 3);
}
__m256i test_mm256_bsrli_epi128(__m256i a) {
// CHECK-LABEL: test_mm256_bsrli_epi128
- // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> %{{.*}}, <32 x i32> <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, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
+ // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> zeroinitializer, <32 x i32> <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, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
return _mm256_bsrli_epi128(a, 3);
}
@@ -386,21 +386,21 @@ __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> zeroinitializer, <2 x i32> <i32 0, i32 1>
+ // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <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> zeroinitializer, <2 x i32> <i32 2, i32 3>
+ // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <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> zeroinitializer, <2 x i32> <i32 0, i32 1>
- return _mm256_extracti128_si256(a, 2);
+ // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <2 x i32> <i32 0, i32 1>
+ return _mm256_extracti128_si256(a, 0);
}
__m256i test_mm256_hadd_epi16(__m256i a, __m256i b) {
@@ -612,9 +612,7 @@ __m128d test_mm_mask_i64gather_pd(__m128d a, double const *b, __m128i c, __m128d
__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: fcmp oeq <4 x double> %{{.*}}, %{{.*}}
// 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);
}
@@ -657,14 +655,14 @@ __m128 test_mm256_mask_i64gather_ps(__m128 a, float const *b, __m256i c, __m128
__m256i test0_mm256_inserti128_si256(__m256i a, __m128i b) {
// CHECK-LABEL: test0_mm256_inserti128_si256
- // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
return _mm256_inserti128_si256(a, b, 0);
}
__m256i test1_mm256_inserti128_si256(__m256i a, __m128i b) {
// CHECK-LABEL: test1_mm256_inserti128_si256
- // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
return _mm256_inserti128_si256(a, b, 1);
}
@@ -672,9 +670,9 @@ __m256i test1_mm256_inserti128_si256(__m256i a, __m128i b) {
// Immediate should be truncated to one bit.
__m256i test2_mm256_inserti128_si256(__m256i a, __m128i b) {
// CHECK-LABEL: test2_mm256_inserti128_si256
- // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> %{{.*}}, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ // CHECK: shufflevector <2 x i64> %{{.*}}, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> %{{.*}}, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
- return _mm256_inserti128_si256(a, b, 2);
+ return _mm256_inserti128_si256(a, b, 0);
}
__m256i test_mm256_madd_epi16(__m256i a, __m256i b) {
@@ -835,13 +833,19 @@ __m256i test_mm256_mpsadbw_epu8(__m256i x, __m256i y) {
__m256i test_mm256_mul_epi32(__m256i a, __m256i b) {
// CHECK-LABEL: test_mm256_mul_epi32
- // CHECK: call <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32> %{{.*}}, <8 x i32> %{{.*}})
+ // CHECK: shl <4 x i64> %{{.*}}, <i64 32, i64 32, i64 32, i64 32>
+ // CHECK: ashr <4 x i64> %{{.*}}, <i64 32, i64 32, i64 32, i64 32>
+ // CHECK: shl <4 x i64> %{{.*}}, <i64 32, i64 32, i64 32, i64 32>
+ // CHECK: ashr <4 x i64> %{{.*}}, <i64 32, i64 32, i64 32, i64 32>
+ // CHECK: mul <4 x i64> %{{.*}}, %{{.*}}
return _mm256_mul_epi32(a, b);
}
__m256i test_mm256_mul_epu32(__m256i a, __m256i b) {
// CHECK-LABEL: test_mm256_mul_epu32
- // CHECK: call <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32> %{{.*}}, <8 x i32> %{{.*}})
+ // CHECK: and <4 x i64> %{{.*}}, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
+ // CHECK: and <4 x i64> %{{.*}}, <i64 4294967295, i64 4294967295, i64 4294967295, i64 4294967295>
+ // CHECK: mul <4 x i64> %{{.*}}, %{{.*}}
return _mm256_mul_epu32(a, b);
}
@@ -913,13 +917,13 @@ __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> zeroinitializer, <4 x i32> <i32 3, i32 0, i32 2, i32 0>
+ // CHECK: shufflevector <4 x i64> %{{.*}}, <4 x i64> undef, <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> zeroinitializer, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
+ // CHECK: shufflevector <4 x double> %{{.*}}, <4 x double> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
return _mm256_permute4x64_pd(a, 25);
}
@@ -949,19 +953,19 @@ __m256i test_mm256_shuffle_epi8(__m256i a, __m256i b) {
__m256i test_mm256_shuffle_epi32(__m256i a) {
// CHECK-LABEL: test_mm256_shuffle_epi32
- // CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> %{{.*}}, <8 x i32> <i32 3, i32 3, i32 0, i32 0, i32 7, i32 7, i32 4, i32 4>
+ // CHECK: shufflevector <8 x i32> %{{.*}}, <8 x i32> undef, <8 x i32> <i32 3, i32 3, i32 0, i32 0, i32 7, i32 7, i32 4, i32 4>
return _mm256_shuffle_epi32(a, 15);
}
__m256i test_mm256_shufflehi_epi16(__m256i a) {
// CHECK-LABEL: test_mm256_shufflehi_epi16
- // CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 6, i32 5, i32 8, i32 9, i32 10, i32 11, i32 15, i32 14, i32 14, i32 13>
+ // CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 6, i32 5, i32 8, i32 9, i32 10, i32 11, i32 15, i32 14, i32 14, i32 13>
return _mm256_shufflehi_epi16(a, 107);
}
__m256i test_mm256_shufflelo_epi16(__m256i a) {
// CHECK-LABEL: test_mm256_shufflelo_epi16
- // CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> %{{.*}}, <16 x i32> <i32 3, i32 0, i32 1, i32 1, i32 4, i32 5, i32 6, i32 7, i32 11, i32 8, i32 9, i32 9, i32 12, i32 13, i32 14, i32 15>
+ // CHECK: shufflevector <16 x i16> %{{.*}}, <16 x i16> undef, <16 x i32> <i32 3, i32 0, i32 1, i32 1, i32 4, i32 5, i32 6, i32 7, i32 11, i32 8, i32 9, i32 9, i32 12, i32 13, i32 14, i32 15>
return _mm256_shufflelo_epi16(a, 83);
}
@@ -1003,7 +1007,7 @@ __m256i test_mm256_slli_epi64(__m256i a) {
__m256i test_mm256_slli_si256(__m256i a) {
// CHECK-LABEL: test_mm256_slli_si256
- // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> %{{.*}}, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
+ // CHECK: shufflevector <32 x i8> zeroinitializer, <32 x i8> %{{.*}}, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
return _mm256_slli_si256(a, 3);
}
@@ -1105,7 +1109,7 @@ __m256i test_mm256_srli_epi64(__m256i a) {
__m256i test_mm256_srli_si256(__m256i a) {
// CHECK-LABEL: test_mm256_srli_si256
- // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> %{{.*}}, <32 x i32> <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, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
+ // CHECK: shufflevector <32 x i8> %{{.*}}, <32 x i8> zeroinitializer, <32 x i32> <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, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
return _mm256_srli_si256(a, 3);
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-01 19:35:06 +0000