npm - @cpp-linter/clang-tidy-win32-x64 - Versions diffs - 21.1.0 → 23.1.3 - Mend

@cpp-linter/clang-tidy-win32-x64 21.1.0 → 23.1.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (326) hide show

package/lib/clang/{21 → 23}/include/avx2intrin.h RENAMED Viewed

@@ -15,20 +15,19 @@
 #define __AVX2INTRIN_H
 /* Define the default attributes for the functions in this file. */
-#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
-#define __DEFAULT_FN_ATTRS256                                                  \
-  __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("avx2,no-evex512"), __min_vector_width__(256)))
-#define __DEFAULT_FN_ATTRS128                                                  \
-  __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("avx2,no-evex512"), __min_vector_width__(128)))
-#else
 #define __DEFAULT_FN_ATTRS256                                                  \
   __attribute__((__always_inline__, __nodebug__, __target__("avx2"),           \
                  __min_vector_width__(256)))
 #define __DEFAULT_FN_ATTRS128                                                  \
   __attribute__((__always_inline__, __nodebug__, __target__("avx2"),           \
                  __min_vector_width__(128)))
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS256_CONSTEXPR __DEFAULT_FN_ATTRS256 constexpr
+#define __DEFAULT_FN_ATTRS128_CONSTEXPR __DEFAULT_FN_ATTRS128 constexpr
+#else
+#define __DEFAULT_FN_ATTRS256_CONSTEXPR __DEFAULT_FN_ATTRS256
+#define __DEFAULT_FN_ATTRS128_CONSTEXPR __DEFAULT_FN_ATTRS128
 #endif
 /* SSE4 Multiple Packed Sums of Absolute Difference.  */
@@ -104,10 +103,9 @@
 /// \param __a
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_abs_epi8(__m256i __a)
-{
-    return (__m256i)__builtin_elementwise_abs((__v32qs)__a);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_abs_epi8(__m256i __a) {
+  return (__m256i)__builtin_elementwise_abs((__v32qs)__a);
 }
 /// Computes the absolute value of each signed 16-bit element in the 256-bit
@@ -121,10 +119,9 @@ _mm256_abs_epi8(__m256i __a)
 /// \param __a
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_abs_epi16(__m256i __a)
-{
-    return (__m256i)__builtin_elementwise_abs((__v16hi)__a);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_abs_epi16(__m256i __a) {
+  return (__m256i)__builtin_elementwise_abs((__v16hi)__a);
 }
 /// Computes the absolute value of each signed 32-bit element in the 256-bit
@@ -138,10 +135,9 @@ _mm256_abs_epi16(__m256i __a)
 /// \param __a
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_abs_epi32(__m256i __a)
-{
-    return (__m256i)__builtin_elementwise_abs((__v8si)__a);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_abs_epi32(__m256i __a) {
+  return (__m256i)__builtin_elementwise_abs((__v8si)__a);
 }
 /// Converts the elements of two 256-bit vectors of [16 x i16] to 8-bit
@@ -169,9 +165,8 @@ _mm256_abs_epi32(__m256i __a)
 ///    A 256-bit vector of [16 x i16] used to generate result[127:64] and
 ///    result[255:192].
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_packs_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_packs_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_packsswb256((__v16hi)__a, (__v16hi)__b);
 }
@@ -201,9 +196,8 @@ _mm256_packs_epi16(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [8 x i32] used to generate result[127:64] and
 ///    result[255:192].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_packs_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_packs_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_packssdw256((__v8si)__a, (__v8si)__b);
 }
@@ -232,9 +226,8 @@ _mm256_packs_epi32(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [16 x i16] used to generate result[127:64] and
 ///    result[255:192].
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_packus_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_packus_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_packuswb256((__v16hi)__a, (__v16hi)__b);
 }
@@ -264,9 +257,8 @@ _mm256_packus_epi16(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [8 x i32] used to generate result[127:64] and
 ///    result[255:192].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_packus_epi32(__m256i __V1, __m256i __V2)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_packus_epi32(__m256i __V1, __m256i __V2) {
   return (__m256i) __builtin_ia32_packusdw256((__v8si)__V1, (__v8si)__V2);
 }
@@ -283,9 +275,8 @@ _mm256_packus_epi32(__m256i __V1, __m256i __V2)
 /// \param __b
 ///    A 256-bit integer vector containing one of the source operands.
 /// \returns A 256-bit integer vector containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_add_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_add_epi8(__m256i __a, __m256i __b) {
   return (__m256i)((__v32qu)__a + (__v32qu)__b);
 }
@@ -302,9 +293,8 @@ _mm256_add_epi8(__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 [16 x i16] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_add_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_add_epi16(__m256i __a, __m256i __b) {
   return (__m256i)((__v16hu)__a + (__v16hu)__b);
 }
@@ -321,9 +311,8 @@ _mm256_add_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_add_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_add_epi32(__m256i __a, __m256i __b) {
   return (__m256i)((__v8su)__a + (__v8su)__b);
 }
@@ -340,9 +329,8 @@ _mm256_add_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [4 x i64] containing one of the source operands.
 /// \returns A 256-bit vector of [4 x i64] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_add_epi64(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_add_epi64(__m256i __a, __m256i __b) {
   return (__m256i)((__v4du)__a + (__v4du)__b);
 }
@@ -359,9 +347,8 @@ _mm256_add_epi64(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector containing one of the source operands.
 /// \returns A 256-bit integer vector containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_adds_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_adds_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_add_sat((__v32qs)__a, (__v32qs)__b);
 }
@@ -377,9 +364,8 @@ _mm256_adds_epi8(__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 [16 x i16] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_adds_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_adds_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_add_sat((__v16hi)__a, (__v16hi)__b);
 }
@@ -396,9 +382,8 @@ _mm256_adds_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector containing one of the source operands.
 /// \returns A 256-bit integer vector containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_adds_epu8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_adds_epu8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_add_sat((__v32qu)__a, (__v32qu)__b);
 }
@@ -414,9 +399,8 @@ _mm256_adds_epu8(__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 [16 x i16] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_adds_epu16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_adds_epu16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_add_sat((__v16hu)__a, (__v16hu)__b);
 }
@@ -460,7 +444,7 @@ _mm256_adds_epu16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_and_si256(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v4du)__a & (__v4du)__b);
@@ -478,7 +462,7 @@ _mm256_and_si256(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_andnot_si256(__m256i __a, __m256i __b)
 {
   return (__m256i)(~(__v4du)__a & (__v4du)__b);
@@ -504,10 +488,9 @@ _mm256_andnot_si256(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_avg_epu8(__m256i __a, __m256i __b)
-{
-  return (__m256i)__builtin_ia32_pavgb256((__v32qi)__a, (__v32qi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_avg_epu8(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_pavgb256((__v32qu)__a, (__v32qu)__b);
 }
 /// Computes the averages of the corresponding unsigned 16-bit integers in
@@ -530,10 +513,9 @@ _mm256_avg_epu8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_avg_epu16(__m256i __a, __m256i __b)
-{
-  return (__m256i)__builtin_ia32_pavgw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_avg_epu16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_pavgw256((__v16hu)__a, (__v16hu)__b);
 }
 /// Merges 8-bit integer values from either of the two 256-bit vectors
@@ -565,9 +547,8 @@ _mm256_avg_epu16(__m256i __a, __m256i __b)
 ///    is 0, the byte is copied from \a __V1; otherwise, it is copied from
 ///    \a __V2.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_blendv_epi8(__m256i __V1, __m256i __V2, __m256i __M)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_blendv_epi8(__m256i __V1, __m256i __V2, __m256i __M) {
   return (__m256i)__builtin_ia32_pblendvb256((__v32qi)__V1, (__v32qi)__V2,
                                               (__v32qi)__M);
 }
@@ -633,7 +614,7 @@ _mm256_blendv_epi8(__m256i __V1, __m256i __V2, __m256i __M)
 /// \param __b
 ///    A 256-bit integer vector containing one of the inputs.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpeq_epi8(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v32qi)__a == (__v32qi)__b);
@@ -659,7 +640,7 @@ _mm256_cmpeq_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16] containing one of the inputs.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpeq_epi16(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v16hi)__a == (__v16hi)__b);
@@ -685,7 +666,7 @@ _mm256_cmpeq_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the inputs.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpeq_epi32(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v8si)__a == (__v8si)__b);
@@ -711,7 +692,7 @@ _mm256_cmpeq_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [4 x i64] containing one of the inputs.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpeq_epi64(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v4di)__a == (__v4di)__b);
@@ -737,7 +718,7 @@ _mm256_cmpeq_epi64(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector containing one of the inputs.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpgt_epi8(__m256i __a, __m256i __b)
 {
   /* This function always performs a signed comparison, but __v32qi is a char
@@ -765,7 +746,7 @@ _mm256_cmpgt_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16] containing one of the inputs.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpgt_epi16(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v16hi)__a > (__v16hi)__b);
@@ -791,7 +772,7 @@ _mm256_cmpgt_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the inputs.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpgt_epi32(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v8si)__a > (__v8si)__b);
@@ -817,7 +798,7 @@ _mm256_cmpgt_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [4 x i64] containing one of the inputs.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_cmpgt_epi64(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v4di)__a > (__v4di)__b);
@@ -853,10 +834,9 @@ _mm256_cmpgt_epi64(__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 [16 x i16] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hadd_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phaddw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hadd_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phaddw256((__v16hi)__a, (__v16hi)__b);
 }
 /// Horizontally adds the adjacent pairs of 32-bit integers from two 256-bit
@@ -885,10 +865,9 @@ _mm256_hadd_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hadd_epi32(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phaddd256((__v8si)__a, (__v8si)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hadd_epi32(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phaddd256((__v8si)__a, (__v8si)__b);
 }
 /// Horizontally adds the adjacent pairs of 16-bit integers from two 256-bit
@@ -920,10 +899,9 @@ _mm256_hadd_epi32(__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 [16 x i16] containing the sums.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hadds_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phaddsw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hadds_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phaddsw256((__v16hi)__a, (__v16hi)__b);
 }
 /// Horizontally subtracts adjacent pairs of 16-bit integers from two 256-bit
@@ -956,10 +934,9 @@ _mm256_hadds_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 [16 x i16] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hsub_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phsubw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hsub_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phsubw256((__v16hi)__a, (__v16hi)__b);
 }
 /// Horizontally subtracts adjacent pairs of 32-bit integers from two 256-bit
@@ -988,10 +965,9 @@ _mm256_hsub_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hsub_epi32(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phsubd256((__v8si)__a, (__v8si)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hsub_epi32(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phsubd256((__v8si)__a, (__v8si)__b);
 }
 /// Horizontally subtracts adjacent pairs of 16-bit integers from two 256-bit
@@ -1024,10 +1000,9 @@ _mm256_hsub_epi32(__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 [16 x i16] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_hsubs_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phsubsw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_hsubs_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phsubsw256((__v16hi)__a, (__v16hi)__b);
 }
 /// Multiplies each unsigned byte from the 256-bit integer vector in \a __a
@@ -1054,10 +1029,9 @@ _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
@@ -1086,9 +1060,8 @@ _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);
 }
@@ -1105,9 +1078,8 @@ _mm256_madd_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v32qs)__a, (__v32qs)__b);
 }
@@ -1124,9 +1096,8 @@ _mm256_max_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v16hi)__a, (__v16hi)__b);
 }
@@ -1143,9 +1114,8 @@ _mm256_max_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v8si)__a, (__v8si)__b);
 }
@@ -1162,9 +1132,8 @@ _mm256_max_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epu8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epu8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v32qu)__a, (__v32qu)__b);
 }
@@ -1181,9 +1150,8 @@ _mm256_max_epu8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epu16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epu16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v16hu)__a, (__v16hu)__b);
 }
@@ -1200,9 +1168,8 @@ _mm256_max_epu16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_max_epu32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_max_epu32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_max((__v8su)__a, (__v8su)__b);
 }
@@ -1219,9 +1186,8 @@ _mm256_max_epu32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v32qs)__a, (__v32qs)__b);
 }
@@ -1238,9 +1204,8 @@ _mm256_min_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v16hi)__a, (__v16hi)__b);
 }
@@ -1257,9 +1222,8 @@ _mm256_min_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v8si)__a, (__v8si)__b);
 }
@@ -1276,9 +1240,8 @@ _mm256_min_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epu8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epu8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v32qu)__a, (__v32qu)__b);
 }
@@ -1295,9 +1258,8 @@ _mm256_min_epu8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epu16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epu16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v16hu)__a, (__v16hu)__b);
 }
@@ -1314,9 +1276,8 @@ _mm256_min_epu16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_min_epu32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_min_epu32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_min((__v8su)__a, (__v8su)__b);
 }
@@ -1337,9 +1298,8 @@ _mm256_min_epu32(__m256i __a, __m256i __b)
 /// \param __a
 ///    A 256-bit integer vector containing the source bytes.
 /// \returns The 32-bit integer mask.
-static __inline__ int __DEFAULT_FN_ATTRS256
-_mm256_movemask_epi8(__m256i __a)
-{
+static __inline__ int __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_movemask_epi8(__m256i __a) {
   return __builtin_ia32_pmovmskb256((__v32qi)__a);
 }
@@ -1363,9 +1323,8 @@ _mm256_movemask_epi8(__m256i __a)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [16 x i16] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi8_epi16(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi8_epi16(__m128i __V) {
   /* This function always performs a signed extension, but __v16qi is a char
      which may be signed or unsigned, so use __v16qs. */
   return (__m256i)__builtin_convertvector((__v16qs)__V, __v16hi);
@@ -1391,9 +1350,8 @@ _mm256_cvtepi8_epi16(__m128i __V)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [8 x i32] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi8_epi32(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi8_epi32(__m128i __V) {
   /* This function always performs a signed extension, but __v16qi is a char
      which may be signed or unsigned, so use __v16qs. */
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v16qs)__V, (__v16qs)__V, 0, 1, 2, 3, 4, 5, 6, 7), __v8si);
@@ -1418,9 +1376,8 @@ _mm256_cvtepi8_epi32(__m128i __V)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi8_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi8_epi64(__m128i __V) {
   /* This function always performs a signed extension, but __v16qi is a char
      which may be signed or unsigned, so use __v16qs. */
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v16qs)__V, (__v16qs)__V, 0, 1, 2, 3), __v4di);
@@ -1446,9 +1403,8 @@ _mm256_cvtepi8_epi64(__m128i __V)
 ///    A 128-bit vector of [8 x i16] containing the source values.
 /// \returns A 256-bit vector of [8 x i32] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi16_epi32(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi16_epi32(__m128i __V) {
   return (__m256i)__builtin_convertvector((__v8hi)__V, __v8si);
 }
@@ -1471,9 +1427,8 @@ _mm256_cvtepi16_epi32(__m128i __V)
 ///    A 128-bit vector of [8 x i16] containing the source values.
 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi16_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi16_epi64(__m128i __V) {
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v8hi)__V, (__v8hi)__V, 0, 1, 2, 3), __v4di);
 }
@@ -1496,9 +1451,8 @@ _mm256_cvtepi16_epi64(__m128i __V)
 ///    A 128-bit vector of [4 x i32] containing the source values.
 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepi32_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepi32_epi64(__m128i __V) {
   return (__m256i)__builtin_convertvector((__v4si)__V, __v4di);
 }
@@ -1522,9 +1476,8 @@ _mm256_cvtepi32_epi64(__m128i __V)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [16 x i16] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu8_epi16(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu8_epi16(__m128i __V) {
   return (__m256i)__builtin_convertvector((__v16qu)__V, __v16hi);
 }
@@ -1548,9 +1501,8 @@ _mm256_cvtepu8_epi16(__m128i __V)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [8 x i32] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu8_epi32(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu8_epi32(__m128i __V) {
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v16qu)__V, (__v16qu)__V, 0, 1, 2, 3, 4, 5, 6, 7), __v8si);
 }
@@ -1573,9 +1525,8 @@ _mm256_cvtepu8_epi32(__m128i __V)
 ///    A 128-bit integer vector containing the source bytes.
 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu8_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu8_epi64(__m128i __V) {
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v16qu)__V, (__v16qu)__V, 0, 1, 2, 3), __v4di);
 }
@@ -1599,9 +1550,8 @@ _mm256_cvtepu8_epi64(__m128i __V)
 ///    A 128-bit vector of [8 x i16] containing the source values.
 /// \returns A 256-bit vector of [8 x i32] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu16_epi32(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu16_epi32(__m128i __V) {
   return (__m256i)__builtin_convertvector((__v8hu)__V, __v8si);
 }
@@ -1624,9 +1574,8 @@ _mm256_cvtepu16_epi32(__m128i __V)
 ///    A 128-bit vector of [8 x i16] containing the source values.
 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu16_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu16_epi64(__m128i __V) {
   return (__m256i)__builtin_convertvector(__builtin_shufflevector((__v8hu)__V, (__v8hu)__V, 0, 1, 2, 3), __v4di);
 }
@@ -1649,9 +1598,8 @@ _mm256_cvtepu16_epi64(__m128i __V)
 ///    A 128-bit vector of [4 x i32] containing the source values.
 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
 ///    values.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_cvtepu32_epi64(__m128i __V)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_cvtepu32_epi64(__m128i __V) {
   return (__m256i)__builtin_convertvector((__v4su)__V, __v4di);
 }
@@ -1675,9 +1623,8 @@ _mm256_cvtepu32_epi64(__m128i __V)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [4 x i64] containing the products.
-static __inline__  __m256i __DEFAULT_FN_ATTRS256
-_mm256_mul_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mul_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_pmuldq256((__v8si)__a, (__v8si)__b);
 }
@@ -1702,9 +1649,8 @@ _mm256_mul_epi32(__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 [16 x i16] containing the rounded products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mulhrs_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mulhrs_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_pmulhrsw256((__v16hi)__a, (__v16hi)__b);
 }
@@ -1721,10 +1667,9 @@ _mm256_mulhrs_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 [16 x i16] containing the products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mulhi_epu16(__m256i __a, __m256i __b)
-{
-  return (__m256i)__builtin_ia32_pmulhuw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mulhi_epu16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_pmulhuw256((__v16hu)__a, (__v16hu)__b);
 }
 /// Multiplies signed 16-bit integer elements of two 256-bit vectors of
@@ -1740,7 +1685,7 @@ _mm256_mulhi_epu16(__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 [16 x i16] containing the products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_mulhi_epi16(__m256i __a, __m256i __b)
 {
   return (__m256i)__builtin_ia32_pmulhw256((__v16hi)__a, (__v16hi)__b);
@@ -1759,7 +1704,7 @@ _mm256_mulhi_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 [16 x i16] containing the products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_mullo_epi16(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v16hu)__a * (__v16hu)__b);
@@ -1778,9 +1723,8 @@ _mm256_mullo_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the products.
-static __inline__  __m256i __DEFAULT_FN_ATTRS256
-_mm256_mullo_epi32 (__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mullo_epi32(__m256i __a, __m256i __b) {
   return (__m256i)((__v8su)__a * (__v8su)__b);
 }
@@ -1804,9 +1748,8 @@ _mm256_mullo_epi32 (__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [4 x i64] containing the products.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_mul_epu32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_mul_epu32(__m256i __a, __m256i __b) {
   return __builtin_ia32_pmuludq256((__v8si)__a, (__v8si)__b);
 }
@@ -1822,7 +1765,7 @@ _mm256_mul_epu32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_or_si256(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v4du)__a | (__v4du)__b);
@@ -1867,10 +1810,9 @@ _mm256_or_si256(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sad_epu8(__m256i __a, __m256i __b)
-{
-  return __builtin_ia32_psadbw256((__v32qi)__a, (__v32qi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sad_epu8(__m256i __a, __m256i __b) {
+  return __builtin_ia32_psadbw256((__v32qu)__a, (__v32qu)__b);
 }
 /// Shuffles 8-bit integers in the 256-bit integer vector \a __a according
@@ -1906,9 +1848,8 @@ _mm256_sad_epu8(__m256i __a, __m256i __b)
 ///    control byte specify the index (within the same 128-bit half) of \a __a
 ///    to copy to the result byte.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_shuffle_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_shuffle_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_pshufb256((__v32qi)__a, (__v32qi)__b);
 }
@@ -2033,10 +1974,9 @@ _mm256_shuffle_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector].
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sign_epi8(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_psignb256((__v32qi)__a, (__v32qi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sign_epi8(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_psignb256((__v32qi)__a, (__v32qi)__b);
 }
 /// Sets each element of the result to the corresponding element of the
@@ -2054,10 +1994,9 @@ _mm256_sign_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16].
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sign_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_psignw256((__v16hi)__a, (__v16hi)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sign_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_psignw256((__v16hi)__a, (__v16hi)__b);
 }
 /// Sets each element of the result to the corresponding element of the
@@ -2075,10 +2014,9 @@ _mm256_sign_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32].
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sign_epi32(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_psignd256((__v8si)__a, (__v8si)__b);
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sign_epi32(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_psignd256((__v8si)__a, (__v8si)__b);
 }
 /// Shifts each 128-bit half of the 256-bit integer vector \a a left by
@@ -2098,8 +2036,9 @@ _mm256_sign_epi32(__m256i __a, __m256i __b)
 /// \param imm
 ///     An unsigned immediate value specifying the shift count (in bytes).
 /// \returns A 256-bit integer vector containing the result.
-#define _mm256_slli_si256(a, imm) \
-  ((__m256i)__builtin_ia32_pslldqi256_byteshift((__v4di)(__m256i)(a), (int)(imm)))
+#define _mm256_slli_si256(a, imm)                                              \
+  ((__m256i)__builtin_ia32_pslldqi256_byteshift((__v32qi)(__m256i)(a),         \
+                                                (int)(imm)))
 /// Shifts each 128-bit half of the 256-bit integer vector \a a left by
 ///    \a imm bytes, shifting in zero bytes, and returns the result. If \a imm
@@ -2118,8 +2057,9 @@ _mm256_sign_epi32(__m256i __a, __m256i __b)
 /// \param imm
 ///    An unsigned immediate value specifying the shift count (in bytes).
 /// \returns A 256-bit integer vector containing the result.
-#define _mm256_bslli_epi128(a, imm) \
-  ((__m256i)__builtin_ia32_pslldqi256_byteshift((__v4di)(__m256i)(a), (int)(imm)))
+#define _mm256_bslli_epi128(a, imm)                                            \
+  ((__m256i)__builtin_ia32_pslldqi256_byteshift((__v32qi)(__m256i)(a),         \
+                                                (int)(imm)))
 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
 ///    left by \a __count bits, shifting in zero bits, and returns the result.
@@ -2134,9 +2074,8 @@ _mm256_sign_epi32(__m256i __a, __m256i __b)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_slli_epi16(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_slli_epi16(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_psllwi256((__v16hi)__a, __count);
 }
@@ -2155,9 +2094,8 @@ _mm256_slli_epi16(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sll_epi16(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sll_epi16(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_psllw256((__v16hi)__a, (__v8hi)__count);
 }
@@ -2174,9 +2112,8 @@ _mm256_sll_epi16(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_slli_epi32(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_slli_epi32(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_pslldi256((__v8si)__a, __count);
 }
@@ -2195,9 +2132,8 @@ _mm256_slli_epi32(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sll_epi32(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sll_epi32(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_pslld256((__v8si)__a, (__v4si)__count);
 }
@@ -2214,9 +2150,8 @@ _mm256_sll_epi32(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_slli_epi64(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_slli_epi64(__m256i __a, int __count) {
   return __builtin_ia32_psllqi256((__v4di)__a, __count);
 }
@@ -2235,9 +2170,8 @@ _mm256_slli_epi64(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sll_epi64(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sll_epi64(__m256i __a, __m128i __count) {
   return __builtin_ia32_psllq256((__v4di)__a, __count);
 }
@@ -2255,9 +2189,8 @@ _mm256_sll_epi64(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srai_epi16(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srai_epi16(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_psrawi256((__v16hi)__a, __count);
 }
@@ -2277,9 +2210,8 @@ _mm256_srai_epi16(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sra_epi16(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sra_epi16(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_psraw256((__v16hi)__a, (__v8hi)__count);
 }
@@ -2297,9 +2229,8 @@ _mm256_sra_epi16(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srai_epi32(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srai_epi32(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_psradi256((__v8si)__a, __count);
 }
@@ -2319,9 +2250,8 @@ _mm256_srai_epi32(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sra_epi32(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sra_epi32(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_psrad256((__v8si)__a, (__v4si)__count);
 }
@@ -2342,8 +2272,9 @@ _mm256_sra_epi32(__m256i __a, __m128i __count)
 /// \param imm
 ///    An unsigned immediate value specifying the shift count (in bytes).
 /// \returns A 256-bit integer vector containing the result.
-#define _mm256_srli_si256(a, imm) \
-  ((__m256i)__builtin_ia32_psrldqi256_byteshift((__m256i)(a), (int)(imm)))
+#define _mm256_srli_si256(a, imm)                                              \
+  ((__m256i)__builtin_ia32_psrldqi256_byteshift((__v32qi)(__m256i)(a),         \
+                                                (int)(imm)))
 /// Shifts each 128-bit half of the 256-bit integer vector in \a a right by
 ///    \a imm bytes, shifting in zero bytes, and returns the result. If
@@ -2362,8 +2293,9 @@ _mm256_sra_epi32(__m256i __a, __m128i __count)
 /// \param imm
 ///     An unsigned immediate value specifying the shift count (in bytes).
 /// \returns A 256-bit integer vector containing the result.
-#define _mm256_bsrli_epi128(a, imm) \
-  ((__m256i)__builtin_ia32_psrldqi256_byteshift((__m256i)(a), (int)(imm)))
+#define _mm256_bsrli_epi128(a, imm)                                            \
+  ((__m256i)__builtin_ia32_psrldqi256_byteshift((__v32qi)(__m256i)(a),         \
+                                                (int)(imm)))
 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
 ///    right by \a __count bits, shifting in zero bits, and returns the result.
@@ -2378,9 +2310,8 @@ _mm256_sra_epi32(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srli_epi16(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srli_epi16(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_psrlwi256((__v16hi)__a, __count);
 }
@@ -2399,9 +2330,8 @@ _mm256_srli_epi16(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srl_epi16(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srl_epi16(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_psrlw256((__v16hi)__a, (__v8hi)__count);
 }
@@ -2418,9 +2348,8 @@ _mm256_srl_epi16(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srli_epi32(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srli_epi32(__m256i __a, int __count) {
   return (__m256i)__builtin_ia32_psrldi256((__v8si)__a, __count);
 }
@@ -2439,9 +2368,8 @@ _mm256_srli_epi32(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srl_epi32(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srl_epi32(__m256i __a, __m128i __count) {
   return (__m256i)__builtin_ia32_psrld256((__v8si)__a, (__v4si)__count);
 }
@@ -2458,9 +2386,8 @@ _mm256_srl_epi32(__m256i __a, __m128i __count)
 /// \param __count
 ///    An unsigned integer value specifying the shift count (in bits).
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srli_epi64(__m256i __a, int __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srli_epi64(__m256i __a, int __count) {
   return __builtin_ia32_psrlqi256((__v4di)__a, __count);
 }
@@ -2479,9 +2406,8 @@ _mm256_srli_epi64(__m256i __a, int __count)
 ///    A 128-bit vector of [2 x i64] whose lower element gives the unsigned
 ///    shift count (in bits). The upper element is ignored.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_srl_epi64(__m256i __a, __m128i __count)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_srl_epi64(__m256i __a, __m128i __count) {
   return __builtin_ia32_psrlq256((__v4di)__a, __count);
 }
@@ -2506,9 +2432,8 @@ _mm256_srl_epi64(__m256i __a, __m128i __count)
 /// \param __b
 ///    A 256-bit integer vector containing the subtrahends.
 /// \returns A 256-bit integer vector containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sub_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sub_epi8(__m256i __a, __m256i __b) {
   return (__m256i)((__v32qu)__a - (__v32qu)__b);
 }
@@ -2533,9 +2458,8 @@ _mm256_sub_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16] containing the subtrahends.
 /// \returns A 256-bit vector of [16 x i16] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sub_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sub_epi16(__m256i __a, __m256i __b) {
   return (__m256i)((__v16hu)__a - (__v16hu)__b);
 }
@@ -2559,9 +2483,8 @@ _mm256_sub_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [8 x i32] containing the subtrahends.
 /// \returns A 256-bit vector of [8 x i32] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sub_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sub_epi32(__m256i __a, __m256i __b) {
   return (__m256i)((__v8su)__a - (__v8su)__b);
 }
@@ -2585,9 +2508,8 @@ _mm256_sub_epi32(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [4 x i64] containing the subtrahends.
 /// \returns A 256-bit vector of [4 x i64] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_sub_epi64(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_sub_epi64(__m256i __a, __m256i __b) {
   return (__m256i)((__v4du)__a - (__v4du)__b);
 }
@@ -2611,9 +2533,8 @@ _mm256_sub_epi64(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector containing the subtrahends.
 /// \returns A 256-bit integer vector containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_subs_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_subs_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_sub_sat((__v32qs)__a, (__v32qs)__b);
 }
@@ -2637,9 +2558,8 @@ _mm256_subs_epi8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16] containing the subtrahends.
 /// \returns A 256-bit vector of [16 x i16] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_subs_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_subs_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_sub_sat((__v16hi)__a, (__v16hi)__b);
 }
@@ -2664,9 +2584,8 @@ _mm256_subs_epi16(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector containing the subtrahends.
 /// \returns A 256-bit integer vector containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_subs_epu8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_subs_epu8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_sub_sat((__v32qu)__a, (__v32qu)__b);
 }
@@ -2690,9 +2609,8 @@ _mm256_subs_epu8(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit vector of [16 x i16] containing the subtrahends.
 /// \returns A 256-bit vector of [16 x i16] containing the differences.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_subs_epu16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_subs_epu16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_elementwise_sub_sat((__v16hu)__a, (__v16hu)__b);
 }
@@ -2724,9 +2642,8 @@ _mm256_subs_epu16(__m256i __a, __m256i __b)
 ///    A 256-bit integer vector used as the source for the odd-numbered bytes
 ///    of the result.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpackhi_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpackhi_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v32qi)__a, (__v32qi)__b, 8, 32+8, 9, 32+9, 10, 32+10, 11, 32+11, 12, 32+12, 13, 32+13, 14, 32+14, 15, 32+15, 24, 32+24, 25, 32+25, 26, 32+26, 27, 32+27, 28, 32+28, 29, 32+29, 30, 32+30, 31, 32+31);
 }
@@ -2759,9 +2676,8 @@ _mm256_unpackhi_epi8(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [16 x i16] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpackhi_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpackhi_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v16hi)__a, (__v16hi)__b, 4, 16+4, 5, 16+5, 6, 16+6, 7, 16+7, 12, 16+12, 13, 16+13, 14, 16+14, 15, 16+15);
 }
@@ -2793,9 +2709,8 @@ _mm256_unpackhi_epi16(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [8 x i32] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpackhi_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpackhi_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v8si)__a, (__v8si)__b, 2, 8+2, 3, 8+3, 6, 8+6, 7, 8+7);
 }
@@ -2823,9 +2738,8 @@ _mm256_unpackhi_epi32(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [4 x i64] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpackhi_epi64(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpackhi_epi64(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v4di)__a, (__v4di)__b, 1, 4+1, 3, 4+3);
 }
@@ -2857,9 +2771,8 @@ _mm256_unpackhi_epi64(__m256i __a, __m256i __b)
 ///    A 256-bit integer vector used as the source for the odd-numbered bytes
 ///    of the result.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpacklo_epi8(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpacklo_epi8(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v32qi)__a, (__v32qi)__b, 0, 32+0, 1, 32+1, 2, 32+2, 3, 32+3, 4, 32+4, 5, 32+5, 6, 32+6, 7, 32+7, 16, 32+16, 17, 32+17, 18, 32+18, 19, 32+19, 20, 32+20, 21, 32+21, 22, 32+22, 23, 32+23);
 }
@@ -2892,9 +2805,8 @@ _mm256_unpacklo_epi8(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [16 x i16] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpacklo_epi16(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpacklo_epi16(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v16hi)__a, (__v16hi)__b, 0, 16+0, 1, 16+1, 2, 16+2, 3, 16+3, 8, 16+8, 9, 16+9, 10, 16+10, 11, 16+11);
 }
@@ -2926,9 +2838,8 @@ _mm256_unpacklo_epi16(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [8 x i32] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpacklo_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpacklo_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v8si)__a, (__v8si)__b, 0, 8+0, 1, 8+1, 4, 8+4, 5, 8+5);
 }
@@ -2956,9 +2867,8 @@ _mm256_unpacklo_epi32(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [4 x i64] used as the source for the odd-numbered
 ///    elements of the result.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_unpacklo_epi64(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_unpacklo_epi64(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_shufflevector((__v4di)__a, (__v4di)__b, 0, 4+0, 2, 4+2);
 }
@@ -2974,7 +2884,7 @@ _mm256_unpacklo_epi64(__m256i __a, __m256i __b)
 /// \param __b
 ///    A 256-bit integer vector.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_xor_si256(__m256i __a, __m256i __b)
 {
   return (__m256i)((__v4du)__a ^ (__v4du)__b);
@@ -3009,9 +2919,8 @@ _mm256_stream_load_si256(const void *__V)
 /// \param __X
 ///    A 128-bit vector of [4 x float] whose low element will be broadcast.
 /// \returns A 128-bit vector of [4 x float] containing the result.
-static __inline__ __m128 __DEFAULT_FN_ATTRS128
-_mm_broadcastss_ps(__m128 __X)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastss_ps(__m128 __X) {
   return (__m128)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0);
 }
@@ -3026,9 +2935,8 @@ _mm_broadcastss_ps(__m128 __X)
 /// \param __a
 ///    A 128-bit vector of [2 x double] whose low element will be broadcast.
 /// \returns A 128-bit vector of [2 x double] containing the result.
-static __inline__ __m128d __DEFAULT_FN_ATTRS128
-_mm_broadcastsd_pd(__m128d __a)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastsd_pd(__m128d __a) {
   return __builtin_shufflevector((__v2df)__a, (__v2df)__a, 0, 0);
 }
@@ -3043,9 +2951,8 @@ _mm_broadcastsd_pd(__m128d __a)
 /// \param __X
 ///    A 128-bit vector of [4 x float] whose low element will be broadcast.
 /// \returns A 256-bit vector of [8 x float] containing the result.
-static __inline__ __m256 __DEFAULT_FN_ATTRS256
-_mm256_broadcastss_ps(__m128 __X)
-{
+static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastss_ps(__m128 __X) {
   return (__m256)__builtin_shufflevector((__v4sf)__X, (__v4sf)__X, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3060,9 +2967,8 @@ _mm256_broadcastss_ps(__m128 __X)
 /// \param __X
 ///    A 128-bit vector of [2 x double] whose low element will be broadcast.
 /// \returns A 256-bit vector of [4 x double] containing the result.
-static __inline__ __m256d __DEFAULT_FN_ATTRS256
-_mm256_broadcastsd_pd(__m128d __X)
-{
+static __inline__ __m256d __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastsd_pd(__m128d __X) {
   return (__m256d)__builtin_shufflevector((__v2df)__X, (__v2df)__X, 0, 0, 0, 0);
 }
@@ -3076,9 +2982,8 @@ _mm256_broadcastsd_pd(__m128d __X)
 /// \param __X
 ///    A 128-bit integer vector to be broadcast.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_broadcastsi128_si256(__m128i __X)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastsi128_si256(__m128i __X) {
   return (__m256i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 1, 0, 1);
 }
@@ -3152,7 +3057,7 @@ _mm256_broadcastsi128_si256(__m128i __X)
 ///    An immediate 8-bit integer operand, with bits [7:0] specifying the
 ///    source for each element of the result. The position of the mask bit
 ///    corresponds to the index of a copied value. When a mask bit is 0, the
-///    element is copied from \a V1; otherwise, it is is copied from \a V2.
+///    element is copied from \a V1; otherwise, it is copied from \a V2.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
 #define _mm256_blend_epi32(V1, V2, M) \
   ((__m256i)__builtin_ia32_pblendd256((__v8si)(__m256i)(V1), \
@@ -3168,9 +3073,8 @@ _mm256_broadcastsi128_si256(__m128i __X)
 /// \param __X
 ///    A 128-bit integer vector whose low byte will be broadcast.
 /// \returns A 256-bit integer vector containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_broadcastb_epi8(__m128i __X)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastb_epi8(__m128i __X) {
   return (__m256i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3184,9 +3088,8 @@ _mm256_broadcastb_epi8(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [8 x i16] whose low element will be broadcast.
 /// \returns A 256-bit vector of [16 x i16] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_broadcastw_epi16(__m128i __X)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastw_epi16(__m128i __X) {
   return (__m256i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3200,9 +3103,8 @@ _mm256_broadcastw_epi16(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [4 x i32] whose low element will be broadcast.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_broadcastd_epi32(__m128i __X)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastd_epi32(__m128i __X) {
   return (__m256i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3216,9 +3118,8 @@ _mm256_broadcastd_epi32(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [2 x i64] whose low element will be broadcast.
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_broadcastq_epi64(__m128i __X)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_broadcastq_epi64(__m128i __X) {
   return (__m256i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 0, 0, 0);
 }
@@ -3232,9 +3133,8 @@ _mm256_broadcastq_epi64(__m128i __X)
 /// \param __X
 ///    A 128-bit integer vector whose low byte will be broadcast.
 /// \returns A 128-bit integer vector containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
-_mm_broadcastb_epi8(__m128i __X)
-{
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastb_epi8(__m128i __X) {
   return (__m128i)__builtin_shufflevector((__v16qi)__X, (__v16qi)__X, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3248,9 +3148,8 @@ _mm_broadcastb_epi8(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [8 x i16] whose low element will be broadcast.
 /// \returns A 128-bit vector of [8 x i16] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
-_mm_broadcastw_epi16(__m128i __X)
-{
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastw_epi16(__m128i __X) {
   return (__m128i)__builtin_shufflevector((__v8hi)__X, (__v8hi)__X, 0, 0, 0, 0, 0, 0, 0, 0);
 }
@@ -3264,9 +3163,8 @@ _mm_broadcastw_epi16(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [4 x i32] whose low element will be broadcast.
 /// \returns A 128-bit vector of [4 x i32] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
-_mm_broadcastd_epi32(__m128i __X)
-{
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastd_epi32(__m128i __X) {
   return (__m128i)__builtin_shufflevector((__v4si)__X, (__v4si)__X, 0, 0, 0, 0);
 }
@@ -3280,9 +3178,8 @@ _mm_broadcastd_epi32(__m128i __X)
 /// \param __X
 ///    A 128-bit vector of [2 x i64] whose low element will be broadcast.
 /// \returns A 128-bit vector of [2 x i64] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
-_mm_broadcastq_epi64(__m128i __X)
-{
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
+_mm_broadcastq_epi64(__m128i __X) {
   return (__m128i)__builtin_shufflevector((__v2di)__X, (__v2di)__X, 0, 0);
 }
@@ -3308,9 +3205,8 @@ _mm_broadcastq_epi64(__m128i __X)
 ///    A 256-bit vector of [8 x i32] containing indexes of values to use from
 ///    \a __a.
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_permutevar8x32_epi32(__m256i __a, __m256i __b)
-{
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_permutevar8x32_epi32(__m256i __a, __m256i __b) {
   return (__m256i)__builtin_ia32_permvarsi256((__v8si)__a, (__v8si)__b);
 }
@@ -3366,9 +3262,8 @@ _mm256_permutevar8x32_epi32(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [8 x i32] containing indexes of values to use from
 ///    \a __a.
 /// \returns A 256-bit vector of [8 x float] containing the result.
-static __inline__ __m256 __DEFAULT_FN_ATTRS256
-_mm256_permutevar8x32_ps(__m256 __a, __m256i __b)
-{
+static __inline__ __m256 __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_permutevar8x32_ps(__m256 __a, __m256i __b) {
   return (__m256)__builtin_ia32_permvarsf256((__v8sf)__a, (__v8si)__b);
 }
@@ -3756,7 +3651,7 @@ _mm_maskstore_epi64(long long *__X, __m128i __M, __m128i __Y)
 ///    A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_sllv_epi32(__m256i __X, __m256i __Y)
 {
   return (__m256i)__builtin_ia32_psllv8si((__v8si)__X, (__v8si)__Y);
@@ -3778,7 +3673,7 @@ _mm256_sllv_epi32(__m256i __X, __m256i __Y)
 ///    A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 128-bit vector of [4 x i32] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
 _mm_sllv_epi32(__m128i __X, __m128i __Y)
 {
   return (__m128i)__builtin_ia32_psllv4si((__v4si)__X, (__v4si)__Y);
@@ -3800,7 +3695,7 @@ _mm_sllv_epi32(__m128i __X, __m128i __Y)
 ///    A 256-bit vector of [4 x i64] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_sllv_epi64(__m256i __X, __m256i __Y)
 {
   return (__m256i)__builtin_ia32_psllv4di((__v4di)__X, (__v4di)__Y);
@@ -3822,7 +3717,7 @@ _mm256_sllv_epi64(__m256i __X, __m256i __Y)
 ///    A 128-bit vector of [2 x i64] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 128-bit vector of [2 x i64] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
 _mm_sllv_epi64(__m128i __X, __m128i __Y)
 {
   return (__m128i)__builtin_ia32_psllv2di((__v2di)__X, (__v2di)__Y);
@@ -3845,7 +3740,7 @@ _mm_sllv_epi64(__m128i __X, __m128i __Y)
 ///    A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_srav_epi32(__m256i __X, __m256i __Y)
 {
   return (__m256i)__builtin_ia32_psrav8si((__v8si)__X, (__v8si)__Y);
@@ -3868,7 +3763,7 @@ _mm256_srav_epi32(__m256i __X, __m256i __Y)
 ///    A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 128-bit vector of [4 x i32] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
 _mm_srav_epi32(__m128i __X, __m128i __Y)
 {
   return (__m128i)__builtin_ia32_psrav4si((__v4si)__X, (__v4si)__Y);
@@ -3890,7 +3785,7 @@ _mm_srav_epi32(__m128i __X, __m128i __Y)
 ///    A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 256-bit vector of [8 x i32] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_srlv_epi32(__m256i __X, __m256i __Y)
 {
   return (__m256i)__builtin_ia32_psrlv8si((__v8si)__X, (__v8si)__Y);
@@ -3912,7 +3807,7 @@ _mm256_srlv_epi32(__m256i __X, __m256i __Y)
 ///    A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 128-bit vector of [4 x i32] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
 _mm_srlv_epi32(__m128i __X, __m128i __Y)
 {
   return (__m128i)__builtin_ia32_psrlv4si((__v4si)__X, (__v4si)__Y);
@@ -3934,7 +3829,7 @@ _mm_srlv_epi32(__m128i __X, __m128i __Y)
 ///    A 256-bit vector of [4 x i64] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 256-bit vector of [4 x i64] containing the result.
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
+static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
 _mm256_srlv_epi64(__m256i __X, __m256i __Y)
 {
   return (__m256i)__builtin_ia32_psrlv4di((__v4di)__X, (__v4di)__Y);
@@ -3956,7 +3851,7 @@ _mm256_srlv_epi64(__m256i __X, __m256i __Y)
 ///    A 128-bit vector of [2 x i64] containing the unsigned shift counts (in
 ///    bits).
 /// \returns A 128-bit vector of [2 x i64] containing the result.
-static __inline__ __m128i __DEFAULT_FN_ATTRS128
+static __inline__ __m128i __DEFAULT_FN_ATTRS128_CONSTEXPR
 _mm_srlv_epi64(__m128i __X, __m128i __Y)
 {
   return (__m128i)__builtin_ia32_psrlv2di((__v2di)__X, (__v2di)__Y);
@@ -5289,5 +5184,7 @@ _mm_srlv_epi64(__m128i __X, __m128i __Y)
 #undef __DEFAULT_FN_ATTRS256
 #undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256_CONSTEXPR
+#undef __DEFAULT_FN_ATTRS128_CONSTEXPR
 #endif /* __AVX2INTRIN_H */