aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Headers/mmintrin.h
diff options
context:
space:
mode:
Diffstat (limited to 'clang/lib/Headers/mmintrin.h')
-rw-r--r--clang/lib/Headers/mmintrin.h168
1 files changed, 68 insertions, 100 deletions
diff --git a/clang/lib/Headers/mmintrin.h b/clang/lib/Headers/mmintrin.h
index 3961b79..4ed95c5 100644
--- a/clang/lib/Headers/mmintrin.h
+++ b/clang/lib/Headers/mmintrin.h
@@ -242,11 +242,10 @@ _mm_packs_pu16(__m64 __m1, __m64 __m2)
/// Bits [63:56] are written to bits [63:56] of the result.
/// \returns A 64-bit integer vector of [8 x i8] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpackhi_pi8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2,
- 4, 12, 5, 13, 6, 14, 7, 15);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpackhi_pi8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2, 4, 12, 5,
+ 13, 6, 14, 7, 15);
}
/// Unpacks the upper 32 bits from two 64-bit integer vectors of
@@ -266,11 +265,9 @@ _mm_unpackhi_pi8(__m64 __m1, __m64 __m2)
/// Bits [63:48] are written to bits [63:48] of the result.
/// \returns A 64-bit integer vector of [4 x i16] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpackhi_pi16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2,
- 2, 6, 3, 7);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpackhi_pi16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2, 2, 6, 3, 7);
}
/// Unpacks the upper 32 bits from two 64-bit integer vectors of
@@ -288,10 +285,9 @@ _mm_unpackhi_pi16(__m64 __m1, __m64 __m2)
/// the upper 32 bits of the result.
/// \returns A 64-bit integer vector of [2 x i32] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpackhi_pi32(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 1, 3);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpackhi_pi32(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 1, 3);
}
/// Unpacks the lower 32 bits from two 64-bit integer vectors of [8 x i8]
@@ -315,11 +311,10 @@ _mm_unpackhi_pi32(__m64 __m1, __m64 __m2)
/// Bits [31:24] are written to bits [63:56] of the result.
/// \returns A 64-bit integer vector of [8 x i8] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpacklo_pi8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2,
- 0, 8, 1, 9, 2, 10, 3, 11);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpacklo_pi8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v8qi)__m1, (__v8qi)__m2, 0, 8, 1, 9,
+ 2, 10, 3, 11);
}
/// Unpacks the lower 32 bits from two 64-bit integer vectors of
@@ -339,11 +334,9 @@ _mm_unpacklo_pi8(__m64 __m1, __m64 __m2)
/// Bits [31:16] are written to bits [63:48] of the result.
/// \returns A 64-bit integer vector of [4 x i16] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpacklo_pi16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2,
- 0, 4, 1, 5);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpacklo_pi16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v4hi)__m1, (__v4hi)__m2, 0, 4, 1, 5);
}
/// Unpacks the lower 32 bits from two 64-bit integer vectors of
@@ -361,10 +354,9 @@ _mm_unpacklo_pi16(__m64 __m1, __m64 __m2)
/// the upper 32 bits of the result.
/// \returns A 64-bit integer vector of [2 x i32] containing the interleaved
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_unpacklo_pi32(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 0, 2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_unpacklo_pi32(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_shufflevector((__v2si)__m1, (__v2si)__m2, 0, 2);
}
/// Adds each 8-bit integer element of the first 64-bit integer vector
@@ -448,10 +440,9 @@ _mm_add_pi32(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [8 x i8].
/// \returns A 64-bit integer vector of [8 x i8] containing the saturated sums
/// of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_adds_pi8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_add_sat((__v8qs)__m1, (__v8qs)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_adds_pi8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_add_sat((__v8qs)__m1, (__v8qs)__m2);
}
/// Adds, with saturation, each 16-bit signed integer element of the first
@@ -472,10 +463,9 @@ _mm_adds_pi8(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [4 x i16].
/// \returns A 64-bit integer vector of [4 x i16] containing the saturated sums
/// of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_adds_pi16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_add_sat((__v4hi)__m1, (__v4hi)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_adds_pi16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_add_sat((__v4hi)__m1, (__v4hi)__m2);
}
/// Adds, with saturation, each 8-bit unsigned integer element of the first
@@ -495,10 +485,9 @@ _mm_adds_pi16(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [8 x i8].
/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
/// unsigned sums of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_adds_pu8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_add_sat((__v8qu)__m1, (__v8qu)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_adds_pu8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_add_sat((__v8qu)__m1, (__v8qu)__m2);
}
/// Adds, with saturation, each 16-bit unsigned integer element of the first
@@ -518,10 +507,9 @@ _mm_adds_pu8(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [4 x i16].
/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
/// unsigned sums of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_adds_pu16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_add_sat((__v4hu)__m1, (__v4hu)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_adds_pu16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_add_sat((__v4hu)__m1, (__v4hu)__m2);
}
/// Subtracts each 8-bit integer element of the second 64-bit integer
@@ -605,10 +593,9 @@ _mm_sub_pi32(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [8 x i8] containing the subtrahends.
/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
/// differences of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_subs_pi8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_sub_sat((__v8qs)__m1, (__v8qs)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_subs_pi8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_sub_sat((__v8qs)__m1, (__v8qs)__m2);
}
/// Subtracts, with saturation, each 16-bit signed integer element of the
@@ -629,10 +616,9 @@ _mm_subs_pi8(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [4 x i16] containing the subtrahends.
/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
/// differences of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_subs_pi16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_sub_sat((__v4hi)__m1, (__v4hi)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_subs_pi16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_sub_sat((__v4hi)__m1, (__v4hi)__m2);
}
/// Subtracts each 8-bit unsigned integer element of the second 64-bit
@@ -653,10 +639,9 @@ _mm_subs_pi16(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [8 x i8] containing the subtrahends.
/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
/// differences of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_subs_pu8(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_sub_sat((__v8qu)__m1, (__v8qu)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_subs_pu8(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_sub_sat((__v8qu)__m1, (__v8qu)__m2);
}
/// Subtracts each 16-bit unsigned integer element of the second 64-bit
@@ -677,10 +662,9 @@ _mm_subs_pu8(__m64 __m1, __m64 __m2)
/// A 64-bit integer vector of [4 x i16] containing the subtrahends.
/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
/// differences of both parameters.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_subs_pu16(__m64 __m1, __m64 __m2)
-{
- return (__m64)__builtin_elementwise_sub_sat((__v4hu)__m1, (__v4hu)__m2);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_subs_pu16(__m64 __m1, __m64 __m2) {
+ return (__m64)__builtin_elementwise_sub_sat((__v4hu)__m1, (__v4hu)__m2);
}
/// Multiplies each 16-bit signed integer element of the first 64-bit
@@ -794,11 +778,9 @@ _mm_sll_pi16(__m64 __m, __m64 __count)
/// \returns A 64-bit integer vector of [4 x i16] containing the left-shifted
/// values. If \a __count is greater or equal to 16, the result is set to all
/// 0.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_slli_pi16(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psllwi128((__v8hi)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_slli_pi16(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psllwi128((__v8hi)__zext128(__m), __count));
}
/// Left-shifts each 32-bit signed integer element of the first
@@ -841,11 +823,9 @@ _mm_sll_pi32(__m64 __m, __m64 __count)
/// \returns A 64-bit integer vector of [2 x i32] containing the left-shifted
/// values. If \a __count is greater or equal to 32, the result is set to all
/// 0.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_slli_pi32(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_pslldi128((__v4si)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_slli_pi32(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_pslldi128((__v4si)__zext128(__m), __count));
}
/// Left-shifts the first 64-bit integer parameter by the number of bits
@@ -883,11 +863,9 @@ _mm_sll_si64(__m64 __m, __m64 __count)
/// A 32-bit integer value.
/// \returns A 64-bit integer vector containing the left-shifted value. If
/// \a __count is greater or equal to 64, the result is set to 0.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_slli_si64(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psllqi128((__v2di)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_slli_si64(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psllqi128((__v2di)__zext128(__m), __count));
}
/// Right-shifts each 16-bit integer element of the first parameter,
@@ -932,11 +910,9 @@ _mm_sra_pi16(__m64 __m, __m64 __count)
/// A 32-bit integer value.
/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_srai_pi16(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psrawi128((__v8hi)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_srai_pi16(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psrawi128((__v8hi)__zext128(__m), __count));
}
/// Right-shifts each 32-bit integer element of the first parameter,
@@ -981,11 +957,9 @@ _mm_sra_pi32(__m64 __m, __m64 __count)
/// A 32-bit integer value.
/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_srai_pi32(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psradi128((__v4si)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_srai_pi32(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psradi128((__v4si)__zext128(__m), __count));
}
/// Right-shifts each 16-bit integer element of the first parameter,
@@ -1028,11 +1002,9 @@ _mm_srl_pi16(__m64 __m, __m64 __count)
/// A 32-bit integer value.
/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_srli_pi16(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psrlwi128((__v8hi)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_srli_pi16(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psrlwi128((__v8hi)__zext128(__m), __count));
}
/// Right-shifts each 32-bit integer element of the first parameter,
@@ -1075,11 +1047,9 @@ _mm_srl_pi32(__m64 __m, __m64 __count)
/// A 32-bit integer value.
/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
/// values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_srli_pi32(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psrldi128((__v4si)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_srli_pi32(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psrldi128((__v4si)__zext128(__m), __count));
}
/// Right-shifts the first 64-bit integer parameter by the number of bits
@@ -1118,11 +1088,9 @@ _mm_srl_si64(__m64 __m, __m64 __count)
/// \param __count
/// A 32-bit integer value.
/// \returns A 64-bit integer vector containing the right-shifted value.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_srli_si64(__m64 __m, int __count)
-{
- return __trunc64(__builtin_ia32_psrlqi128((__v2di)__anyext128(__m),
- __count));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_srli_si64(__m64 __m, int __count) {
+ return __trunc64(__builtin_ia32_psrlqi128((__v2di)__zext128(__m), __count));
}
/// Performs a bitwise AND of two 64-bit integer vectors.
generated by cgit v1.1 at 2025-08-31 21:22:44 +0000