aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Headers
diff options
context:
space:
mode:
Diffstat (limited to 'clang/lib/Headers')
-rw-r--r--clang/lib/Headers/avx2intrin.h12
-rw-r--r--clang/lib/Headers/avx512bwintrin.h12
-rw-r--r--clang/lib/Headers/avx512vlbwintrin.h16
-rw-r--r--clang/lib/Headers/emmintrin.h4
-rw-r--r--clang/lib/Headers/mmintrin.h9
-rw-r--r--clang/lib/Headers/tmmintrin.h20
6 files changed, 36 insertions, 37 deletions
diff --git a/clang/lib/Headers/avx2intrin.h b/clang/lib/Headers/avx2intrin.h
index 31759c5..4aaca2d 100644
--- a/clang/lib/Headers/avx2intrin.h
+++ b/clang/lib/Headers/avx2intrin.h
@@ -1035,10 +1035,9 @@ _mm256_hsubs_epi16(__m256i __a, __m256i __b)
/// \param __b
/// A 256-bit vector containing one of the source operands.
/// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_maddubs_epi16(__m256i __a, __m256i __b)
-{
- return (__m256i)__builtin_ia32_pmaddubsw256((__v32qi)__a, (__v32qi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_maddubs_epi16(__m256i __a, __m256i __b) {
+ return (__m256i)__builtin_ia32_pmaddubsw256((__v32qi)__a, (__v32qi)__b);
}
/// Multiplies corresponding 16-bit elements of two 256-bit vectors of
@@ -1067,9 +1066,8 @@ _mm256_maddubs_epi16(__m256i __a, __m256i __b)
/// \param __b
/// A 256-bit vector of [16 x i16] containing one of the source operands.
/// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_madd_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_madd_epi16(__m256i __a, __m256i __b) {
return (__m256i)__builtin_ia32_pmaddwd256((__v16hi)__a, (__v16hi)__b);
}
diff --git a/clang/lib/Headers/avx512bwintrin.h b/clang/lib/Headers/avx512bwintrin.h
index c36bd81..473fe94 100644
--- a/clang/lib/Headers/avx512bwintrin.h
+++ b/clang/lib/Headers/avx512bwintrin.h
@@ -1064,12 +1064,12 @@ _mm512_maskz_mulhi_epu16(__mmask32 __U, __m512i __A, __m512i __B) {
(__v32hi)_mm512_setzero_si512());
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maddubs_epi16(__m512i __X, __m512i __Y) {
return (__m512i)__builtin_ia32_pmaddubsw512((__v64qi)__X, (__v64qi)__Y);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_maddubs_epi16(__m512i __W, __mmask32 __U, __m512i __X,
__m512i __Y) {
return (__m512i)__builtin_ia32_selectw_512((__mmask32) __U,
@@ -1077,26 +1077,26 @@ _mm512_mask_maddubs_epi16(__m512i __W, __mmask32 __U, __m512i __X,
(__v32hi)__W);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_maddubs_epi16(__mmask32 __U, __m512i __X, __m512i __Y) {
return (__m512i)__builtin_ia32_selectw_512((__mmask32) __U,
(__v32hi)_mm512_maddubs_epi16(__X, __Y),
(__v32hi)_mm512_setzero_si512());
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_madd_epi16(__m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_pmaddwd512((__v32hi)__A, (__v32hi)__B);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_mask_madd_epi16(__m512i __W, __mmask16 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__U,
(__v16si)_mm512_madd_epi16(__A, __B),
(__v16si)__W);
}
-static __inline__ __m512i __DEFAULT_FN_ATTRS512
+static __inline__ __m512i __DEFAULT_FN_ATTRS512_CONSTEXPR
_mm512_maskz_madd_epi16(__mmask16 __U, __m512i __A, __m512i __B) {
return (__m512i)__builtin_ia32_selectd_512((__mmask16)__U,
(__v16si)_mm512_madd_epi16(__A, __B),
diff --git a/clang/lib/Headers/avx512vlbwintrin.h b/clang/lib/Headers/avx512vlbwintrin.h
index 5e6daa8..81e4cbb9 100644
--- a/clang/lib/Headers/avx512vlbwintrin.h
+++ b/clang/lib/Headers/avx512vlbwintrin.h
@@ -1295,21 +1295,21 @@ _mm256_maskz_permutex2var_epi16 (__mmask16 __U, __m256i __A, __m256i __I,
(__v16hi)_mm256_setzero_si256());
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_maddubs_epi16(__m128i __W, __mmask8 __U, __m128i __X, __m128i __Y) {
return (__m128i)__builtin_ia32_selectw_128((__mmask8)__U,
(__v8hi)_mm_maddubs_epi16(__X, __Y),
(__v8hi)__W);
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_maddubs_epi16(__mmask8 __U, __m128i __X, __m128i __Y) {
return (__m128i)__builtin_ia32_selectw_128((__mmask8)__U,
(__v8hi)_mm_maddubs_epi16(__X, __Y),
(__v8hi)_mm_setzero_si128());
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_maddubs_epi16(__m256i __W, __mmask16 __U, __m256i __X,
__m256i __Y) {
return (__m256i)__builtin_ia32_selectw_256((__mmask16)__U,
@@ -1317,35 +1317,35 @@ _mm256_mask_maddubs_epi16(__m256i __W, __mmask16 __U, __m256i __X,
(__v16hi)__W);
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_maddubs_epi16(__mmask16 __U, __m256i __X, __m256i __Y) {
return (__m256i)__builtin_ia32_selectw_256((__mmask16)__U,
(__v16hi)_mm256_maddubs_epi16(__X, __Y),
(__v16hi)_mm256_setzero_si256());
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_mask_madd_epi16(__m128i __W, __mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectd_128((__mmask8)__U,
(__v4si)_mm_madd_epi16(__A, __B),
(__v4si)__W);
}
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
_mm_maskz_madd_epi16(__mmask8 __U, __m128i __A, __m128i __B) {
return (__m128i)__builtin_ia32_selectd_128((__mmask8)__U,
(__v4si)_mm_madd_epi16(__A, __B),
(__v4si)_mm_setzero_si128());
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_mask_madd_epi16(__m256i __W, __mmask8 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectd_256((__mmask8)__U,
(__v8si)_mm256_madd_epi16(__A, __B),
(__v8si)__W);
}
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
_mm256_maskz_madd_epi16(__mmask8 __U, __m256i __A, __m256i __B) {
return (__m256i)__builtin_ia32_selectd_256((__mmask8)__U,
(__v8si)_mm256_madd_epi16(__A, __B),
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index 6597e7e..454e9a2 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -2290,8 +2290,8 @@ _mm_avg_epu16(__m128i __a, __m128i __b) {
/// A 128-bit signed [8 x i16] vector.
/// \returns A 128-bit signed [4 x i32] vector containing the sums of products
/// of both parameters.
-static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_madd_epi16(__m128i __a,
- __m128i __b) {
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_madd_epi16(__m128i __a, __m128i __b) {
return (__m128i)__builtin_ia32_pmaddwd128((__v8hi)__a, (__v8hi)__b);
}
diff --git a/clang/lib/Headers/mmintrin.h b/clang/lib/Headers/mmintrin.h
index 5f61753..aca78e6 100644
--- a/clang/lib/Headers/mmintrin.h
+++ b/clang/lib/Headers/mmintrin.h
@@ -679,11 +679,10 @@ _mm_subs_pu16(__m64 __m1, __m64 __m2) {
/// A 64-bit integer vector of [4 x i16].
/// \returns A 64-bit integer vector of [2 x i32] containing the sums of
/// products of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_madd_pi16(__m64 __m1, __m64 __m2)
-{
- return __trunc64(__builtin_ia32_pmaddwd128((__v8hi)__anyext128(__m1),
- (__v8hi)__anyext128(__m2)));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_madd_pi16(__m64 __m1, __m64 __m2) {
+ return __trunc64(__builtin_ia32_pmaddwd128((__v8hi)__zext128(__m1),
+ (__v8hi)__zext128(__m2)));
}
/// Multiplies each 16-bit signed integer element of the first 64-bit
diff --git a/clang/lib/Headers/tmmintrin.h b/clang/lib/Headers/tmmintrin.h
index d40f0c5..3fc9f98 100644
--- a/clang/lib/Headers/tmmintrin.h
+++ b/clang/lib/Headers/tmmintrin.h
@@ -23,6 +23,9 @@
#define __trunc64(x) \
(__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0)
+#define __zext128(x) \
+ (__m128i) __builtin_shufflevector((__v2si)(x), __extension__(__v2si){}, 0, \
+ 1, 2, 3)
#define __anyext128(x) \
(__m128i) __builtin_shufflevector((__v2si)(x), __extension__(__v2si){}, 0, \
1, -1, -1)
@@ -504,10 +507,9 @@ _mm_hsubs_pi16(__m64 __a, __m64 __b)
/// \a R5 := (\a __a10 * \a __b10) + (\a __a11 * \a __b11) \n
/// \a R6 := (\a __a12 * \a __b12) + (\a __a13 * \a __b13) \n
/// \a R7 := (\a __a14 * \a __b14) + (\a __a15 * \a __b15)
-static __inline__ __m128i __DEFAULT_FN_ATTRS
-_mm_maddubs_epi16(__m128i __a, __m128i __b)
-{
- return (__m128i)__builtin_ia32_pmaddubsw128((__v16qi)__a, (__v16qi)__b);
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_maddubs_epi16(__m128i __a, __m128i __b) {
+ return (__m128i)__builtin_ia32_pmaddubsw128((__v16qi)__a, (__v16qi)__b);
}
/// Multiplies corresponding pairs of packed 8-bit unsigned integer
@@ -534,11 +536,10 @@ _mm_maddubs_epi16(__m128i __a, __m128i __b)
/// \a R1 := (\a __a2 * \a __b2) + (\a __a3 * \a __b3) \n
/// \a R2 := (\a __a4 * \a __b4) + (\a __a5 * \a __b5) \n
/// \a R3 := (\a __a6 * \a __b6) + (\a __a7 * \a __b7)
-static __inline__ __m64 __DEFAULT_FN_ATTRS
-_mm_maddubs_pi16(__m64 __a, __m64 __b)
-{
- return __trunc64(__builtin_ia32_pmaddubsw128((__v16qi)__anyext128(__a),
- (__v16qi)__anyext128(__b)));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_maddubs_pi16(__m64 __a, __m64 __b) {
+ return __trunc64(__builtin_ia32_pmaddubsw128((__v16qi)__zext128(__a),
+ (__v16qi)__zext128(__b)));
}
/// Multiplies packed 16-bit signed integer values, truncates the 32-bit
@@ -796,6 +797,7 @@ _mm_sign_pi32(__m64 __a, __m64 __b)
}
#undef __anyext128
+#undef __zext128
#undef __trunc64
#undef __DEFAULT_FN_ATTRS
#undef __DEFAULT_FN_ATTRS_CONSTEXPR
generated by cgit v1.1 at 2025-10-09 03:09:28 +0000