[clang] [Headers][X86] Allow AVX512 masked shuffles to be used in constexpr (PR #162301)
via cfe-commits
cfe-commits at lists.llvm.org
Tue Oct 7 08:16:56 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang
Author: Ahmed Nour (ahmednour25689)
<details>
<summary>Changes</summary>
This PR makes AVX512 masked shuffle and broadcast intrinsics usable in constexpr
Fixes https://github.com/llvm/llvm-project/issues/162074
---
Patch is 60.24 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/162301.diff
7 Files Affected:
- (modified) clang/lib/Headers/avx512dqintrin.h (+24-36)
- (modified) clang/lib/Headers/avx512fintrin.h (+48-73)
- (modified) clang/lib/Headers/avx512vldqintrin.h (+20-30)
- (modified) clang/lib/Headers/avx512vlintrin.h (+146-215)
- (modified) clang/test/CodeGen/X86/avx512dq-builtins.c (+16)
- (modified) clang/test/CodeGen/X86/avx512f-builtins.c (+25)
- (modified) clang/test/CodeGen/X86/avx512vl-builtins.c (+70)
``````````diff
diff --git a/clang/lib/Headers/avx512dqintrin.h b/clang/lib/Headers/avx512dqintrin.h
index fb65bf933b8ad..3681ccab0b179 100644
--- a/clang/lib/Headers/avx512dqintrin.h
+++ b/clang/lib/Headers/avx512dqintrin.h
@@ -1083,17 +1083,15 @@ _mm512_broadcast_f32x2(__m128 __A) {
0, 1, 0, 1, 0, 1, 0, 1);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_f32x2 (__m512 __O, __mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_f32x2(__m512 __O, __mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x2(__A),
(__v16sf)__O);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_f32x2 (__mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_f32x2(__mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x2(__A),
(__v16sf)_mm512_setzero_ps());
@@ -1106,17 +1104,15 @@ _mm512_broadcast_f32x8(__m256 __A) {
0, 1, 2, 3, 4, 5, 6, 7);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_f32x8(__m512 __O, __mmask16 __M, __m256 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_f32x8(__m512 __O, __mmask16 __M, __m256 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x8(__A),
(__v16sf)__O);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_f32x8(__mmask16 __M, __m256 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_f32x8(__mmask16 __M, __m256 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x8(__A),
(__v16sf)_mm512_setzero_ps());
@@ -1128,17 +1124,15 @@ _mm512_broadcast_f64x2(__m128d __A) {
0, 1, 0, 1, 0, 1, 0, 1);
}
-static __inline__ __m512d __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_f64x2(__m512d __O, __mmask8 __M, __m128d __A)
-{
+static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_f64x2(__m512d __O, __mmask8 __M, __m128d __A) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__M,
(__v8df)_mm512_broadcast_f64x2(__A),
(__v8df)__O);
}
-static __inline__ __m512d __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_f64x2(__mmask8 __M, __m128d __A)
-{
+static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_f64x2(__mmask8 __M, __m128d __A) {
return (__m512d)__builtin_ia32_selectpd_512((__mmask8)__M,
(__v8df)_mm512_broadcast_f64x2(__A),
(__v8df)_mm512_setzero_pd());
@@ -1151,17 +1145,15 @@ _mm512_broadcast_i32x2(__m128i __A) {
0, 1, 0, 1, 0, 1, 0, 1);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_i32x2 (__m512i __O, __mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_i32x2(__m512i __O, __mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x2(__A),
(__v16si)__O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_i32x2 (__mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_i32x2(__mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x2(__A),
(__v16si)_mm512_setzero_si512());
@@ -1174,17 +1166,15 @@ _mm512_broadcast_i32x8(__m256i __A) {
0, 1, 2, 3, 4, 5, 6, 7);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_i32x8(__m512i __O, __mmask16 __M, __m256i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_i32x8(__m512i __O, __mmask16 __M, __m256i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x8(__A),
(__v16si)__O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_i32x8(__mmask16 __M, __m256i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_i32x8(__mmask16 __M, __m256i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x8(__A),
(__v16si)_mm512_setzero_si512());
@@ -1196,17 +1186,15 @@ _mm512_broadcast_i64x2(__m128i __A) {
0, 1, 0, 1, 0, 1, 0, 1);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_i64x2(__m512i __O, __mmask8 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_i64x2(__m512i __O, __mmask8 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectq_512((__mmask8)__M,
(__v8di)_mm512_broadcast_i64x2(__A),
(__v8di)__O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectq_512((__mmask8)__M,
(__v8di)_mm512_broadcast_i64x2(__A),
(__v8di)_mm512_setzero_si512());
diff --git a/clang/lib/Headers/avx512fintrin.h b/clang/lib/Headers/avx512fintrin.h
index 80e58425cdd71..8401647ef9da5 100644
--- a/clang/lib/Headers/avx512fintrin.h
+++ b/clang/lib/Headers/avx512fintrin.h
@@ -225,17 +225,15 @@ _mm512_broadcastd_epi32(__m128i __A) {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcastd_epi32 (__m512i __O, __mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcastd_epi32(__m512i __O, __mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512(__M,
(__v16si) _mm512_broadcastd_epi32(__A),
(__v16si) __O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcastd_epi32 (__mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcastd_epi32(__mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512(__M,
(__v16si) _mm512_broadcastd_epi32(__A),
(__v16si) _mm512_setzero_si512());
@@ -247,18 +245,15 @@ _mm512_broadcastq_epi64(__m128i __A) {
0, 0, 0, 0, 0, 0, 0, 0);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcastq_epi64 (__m512i __O, __mmask8 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcastq_epi64(__m512i __O, __mmask8 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectq_512(__M,
(__v8di) _mm512_broadcastq_epi64(__A),
(__v8di) __O);
-
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcastq_epi64 (__mmask8 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcastq_epi64(__mmask8 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectq_512(__M,
(__v8di) _mm512_broadcastq_epi64(__A),
(__v8di) _mm512_setzero_si512());
@@ -321,9 +316,8 @@ _mm512_set1_epi32(int __s)
__s, __s, __s, __s, __s, __s, __s, __s };
}
-static __inline __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_set1_epi32(__mmask16 __M, int __A)
-{
+static __inline __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_set1_epi32(__mmask16 __M, int __A) {
return (__m512i)__builtin_ia32_selectd_512(__M,
(__v16si)_mm512_set1_epi32(__A),
(__v16si)_mm512_setzero_si512());
@@ -335,9 +329,8 @@ _mm512_set1_epi64(long long __d)
return __extension__(__m512i)(__v8di){ __d, __d, __d, __d, __d, __d, __d, __d };
}
-static __inline __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_set1_epi64(__mmask8 __M, long long __A)
-{
+static __inline __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_set1_epi64(__mmask8 __M, long long __A) {
return (__m512i)__builtin_ia32_selectq_512(__M,
(__v8di)_mm512_set1_epi64(__A),
(__v8di)_mm512_setzero_si512());
@@ -6552,17 +6545,15 @@ _mm512_broadcast_f32x4(__m128 __A) {
0, 1, 2, 3, 0, 1, 2, 3);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_f32x4(__m512 __O, __mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_f32x4(__m512 __O, __mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x4(__A),
(__v16sf)__O);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_f32x4(__mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_f32x4(__mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__M,
(__v16sf)_mm512_broadcast_f32x4(__A),
(__v16sf)_mm512_setzero_ps());
@@ -6597,17 +6588,15 @@ _mm512_broadcast_i32x4(__m128i __A) {
0, 1, 2, 3, 0, 1, 2, 3);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcast_i32x4(__m512i __O, __mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcast_i32x4(__m512i __O, __mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x4(__A),
(__v16si)__O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcast_i32x4(__mmask16 __M, __m128i __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcast_i32x4(__mmask16 __M, __m128i __A) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__M,
(__v16si)_mm512_broadcast_i32x4(__A),
(__v16si)_mm512_setzero_si512());
@@ -6635,33 +6624,29 @@ _mm512_maskz_broadcast_i64x4(__mmask8 __M, __m256i __A)
(__v8di)_mm512_setzero_si512());
}
-static __inline__ __m512d __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcastsd_pd (__m512d __O, __mmask8 __M, __m128d __A)
-{
+static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcastsd_pd(__m512d __O, __mmask8 __M, __m128d __A) {
return (__m512d)__builtin_ia32_selectpd_512(__M,
(__v8df) _mm512_broadcastsd_pd(__A),
(__v8df) __O);
}
-static __inline__ __m512d __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcastsd_pd (__mmask8 __M, __m128d __A)
-{
+static __inline__ __m512d __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcastsd_pd(__mmask8 __M, __m128d __A) {
return (__m512d)__builtin_ia32_selectpd_512(__M,
(__v8df) _mm512_broadcastsd_pd(__A),
(__v8df) _mm512_setzero_pd());
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_broadcastss_ps (__m512 __O, __mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_broadcastss_ps(__m512 __O, __mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512(__M,
(__v16sf) _mm512_broadcastss_ps(__A),
(__v16sf) __O);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_broadcastss_ps (__mmask16 __M, __m128 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_broadcastss_ps(__mmask16 __M, __m128 __A) {
return (__m512)__builtin_ia32_selectps_512(__M,
(__v16sf) _mm512_broadcastss_ps(__A),
(__v16sf) _mm512_setzero_ps());
@@ -8381,17 +8366,15 @@ _mm512_movehdup_ps (__m512 __A)
1, 1, 3, 3, 5, 5, 7, 7, 9, 9, 11, 11, 13, 13, 15, 15);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_movehdup_ps (__m512 __W, __mmask16 __U, __m512 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_movehdup_ps(__m512 __W, __mmask16 __U, __m512 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_movehdup_ps(__A),
(__v16sf)__W);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_movehdup_ps (__mmask16 __U, __m512 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_movehdup_ps(__mmask16 __U, __m512 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_movehdup_ps(__A),
(__v16sf)_mm512_setzero_ps());
@@ -8404,44 +8387,38 @@ _mm512_moveldup_ps (__m512 __A)
0, 0, 2, 2, 4, 4, 6, 6, 8, 8, 10, 10, 12, 12, 14, 14);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_mask_moveldup_ps (__m512 __W, __mmask16 __U, __m512 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_moveldup_ps(__m512 __W, __mmask16 __U, __m512 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_moveldup_ps(__A),
(__v16sf)__W);
}
-static __inline__ __m512 __DEFAULT_FN_ATTRS512
-_mm512_maskz_moveldup_ps (__mmask16 __U, __m512 __A)
-{
+static __inline__ __m512 __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_maskz_moveldup_ps(__mmask16 __U, __m512 __A) {
return (__m512)__builtin_ia32_selectps_512((__mmask16)__U,
(__v16sf)_mm512_moveldup_ps(__A),
(__v16sf)_mm512_setzero_ps());
}
-static __inline__ __m128 __DEFAULT_FN_ATTRS128
-_mm_mask_move_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_mask_move_ss(__m128 __W, __mmask8 __U, __m128 __A, __m128 __B) {
return __builtin_ia32_selectss_128(__U, _mm_move_ss(__A, __B), __W);
}
-static __inline__ __m128 __DEFAULT_FN_ATTRS128
-_mm_maskz_move_ss (__mmask8 __U, __m128 __A, __m128 __B)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_maskz_move_ss(__mmask8 __U, __m128 __A, __m128 __B) {
return __builtin_ia32_selectss_128(__U, _mm_move_ss(__A, __B),
_mm_setzero_ps());
}
-static __inline__ __m128d __DEFAULT_FN_ATTRS128
-_mm_mask_move_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_mask_move_sd(__m128d __W, __mmask8 __U, __m128d __A, __m128d __B) {
return __builtin_ia32_selectsd_128(__U, _mm_move_sd(__A, __B), __W);
}
-static __inline__ __m128d __DEFAULT_FN_ATTRS128
-_mm_maskz_move_sd (__mmask8 __U, __m128d __A, __m128d __B)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_maskz_move_sd(__mmask8 __U, __m128d __A, __m128d __B) {
return __builtin_ia32_selectsd_128(__U, _mm_move_sd(__A, __B),
_mm_setzero_pd());
}
@@ -8884,17 +8861,15 @@ _mm_cvtu64_ss (__m128 __A, unsigned long long __B)
}
#endif
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_set1_epi32 (__m512i __O, __mmask16 __M, int __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_set1_epi32(__m512i __O, __mmask16 __M, int __A) {
return (__m512i) __builtin_ia32_selectd_512(__M,
(__v16si) _mm512_set1_epi32(__A),
(__v16si) __O);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
-_mm512_mask_set1_epi64 (__m512i __O, __mmask8 __M, long long __A)
-{
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
+_mm512_mask_set1_epi64(__m512i __O, __mmask8 __M, long long __A) {
return (__m512i) __builtin_ia32_selectq_512(__M,
(__v8di) _mm512_set1_epi64(__A),
(__v8di) __O);
diff --git a/clang/lib/Headers/avx512vldqintrin.h b/clang/lib/Headers/avx512vldqintrin.h
index 68bd52e43981a..ee7974e924afe 100644
--- a/clang/lib/Headers/avx512vldqintrin.h
+++ b/clang/lib/Headers/avx512vldqintrin.h
@@ -968,17 +968,15 @@ _mm256_broadcast_f32x2(__m128 __A) {
0, 1, 0, 1, 0, 1, 0, 1);
}
-static __inline__ __m256 __DEFAULT_FN_ATTRS256
-_mm256_mask_broadcast_f32x2 (__m256 __O, __mmask8 __M, __m128 __A)
-{
+static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mask_broadcast_f32x2(__m256 __O, __mmask8 __M, __m128 __A) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__M,
(__v8sf)_mm256_broadcast_f32x2(__A),
(__v8sf)__O);
}
-static __inline__ __m256 __DEFAULT_FN_ATTRS256
-_mm256_maskz_broadcast_f32x2 (__mmask8 __M, __m128 __A)
-{
+static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_maskz_broadcast_f32x2(__mmask8 __M, __m128 __A) {
return (__m256)__builtin_ia32_selectps_256((__mmask8)__M,
(__v8sf)_mm256_broadcast_f32x2(__A),
(__v8sf)_mm256_setzero_ps());
@@ -990,17 +988,15 @@ _mm256_broadcast_f64x2(__m128d __A) {
0, 1, 0, 1);
}
-static __inline__ __m256d __DEFAULT_FN_ATTRS256
-_mm256_mask_broadcast_f64x2(__m256d __O, __mmask8 __M, __m128d __A)
-{
+static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mask_broadcast_f64x2(__m256d __O, __mmask8 __M, __m128d __A) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__M,
(__v4df)_mm256_broadcast_f64x2(__A),
(__v4df)__O);
}
-static __inline__ __m256d __DEFAULT_FN_ATTRS256
-_mm256_maskz_broadcast_f64x2 (__mmask8 __M, __m128d __A)
-{
+static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_maskz_broadcast_f64x2(__mmask8 __M, __m128d __A) {
return (__m256d)__builtin_ia32_selectpd_256((__mmask8)__M,
(__v4df)_mm256_broadcast_f64x2(__A),
...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/162301
More information about the cfe-commits
mailing list