@cpp-linter/clang-tidy-linux-arm64 18.1.5 → 20.1.0

package/lib/clang/{18 → 20}/include/avxvnniint16intrin.h

@@ -15,14 +15,6 @@
 #ifndef __AVXVNNIINT16INTRIN_H
 #define __AVXVNNIINT16INTRIN_H
 
-/* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS128                                                  \
-  __attribute__((__always_inline__, __nodebug__, __target__("avxvnniint16"),   \
-                 __min_vector_width__(128)))
-#define __DEFAULT_FN_ATTRS256                                                  \
-  __attribute__((__always_inline__, __nodebug__, __target__("avxvnniint16"),   \
-                 __min_vector_width__(256)))
-
 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
 ///    signed 16-bit results. Sum these 2 results with the corresponding
@@ -53,12 +45,9 @@
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwsud_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwsud128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpwsud_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpwsud128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -90,11 +79,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwsud_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwsud_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwsud256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpwsud_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpwsud256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -127,12 +114,9 @@ _mm256_dpwsud_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwsuds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwsuds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpwsuds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpwsuds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of signed 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -165,11 +149,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwsuds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwsuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwsuds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
+#define _mm256_dpwsuds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpwsuds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding signed 16-bit integers in \a __B, producing 2 intermediate
@@ -201,12 +183,9 @@ _mm256_dpwsuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwusd_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwusd128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpwusd_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpwusd128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding signed 16-bit integers in \a __B, producing 2 intermediate
@@ -238,11 +217,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwusd_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwusd_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwusd256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpwusd_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpwusd256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding signed 16-bit integers in \a __B, producing 2 intermediate
@@ -275,12 +252,9 @@ _mm256_dpwusd_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwusds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwusds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpwusds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpwusds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding signed 16-bit integers in \a __B, producing 2 intermediate
@@ -313,11 +287,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwusds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwusds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwusds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
+#define _mm256_dpwusds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpwusds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -349,12 +321,9 @@ _mm256_dpwusds_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwuud_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwuud128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpwuud_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpwuud128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -386,11 +355,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwuud_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwuud_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwuud256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpwuud_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpwuud256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -423,12 +390,9 @@ _mm256_dpwuud_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwuuds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpwuuds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpwuuds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpwuuds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
 /// Multiply groups of 2 adjacent pairs of unsigned 16-bit integers in \a __A with
 ///    corresponding unsigned 16-bit integers in \a __B, producing 2 intermediate
@@ -461,13 +425,8 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpwuuds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpwuuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpwuuds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
-
-#undef __DEFAULT_FN_ATTRS128
-#undef __DEFAULT_FN_ATTRS256
+#define _mm256_dpwuuds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpwuuds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 #endif // __AVXVNNIINT16INTRIN_H

package/lib/clang/{18 → 20}/include/avxvnniint8intrin.h

@@ -14,14 +14,6 @@
 #ifndef __AVXVNNIINT8INTRIN_H
 #define __AVXVNNIINT8INTRIN_H
 
-/* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS256                                                  \
-  __attribute__((__always_inline__, __nodebug__, __target__("avxvnniint8"),    \
-                 __min_vector_width__(256)))
-#define __DEFAULT_FN_ATTRS128                                                  \
-  __attribute__((__always_inline__, __nodebug__, __target__("avxvnniint8"),    \
-                 __min_vector_width__(128)))
-
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding signed 8-bit integers in \a __B, producing 4 intermediate
 ///    signed 16-bit results. Sum these 4 results with the corresponding
@@ -52,12 +44,9 @@
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbssd_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbssd128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpbssd_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpbssd128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding signed 8-bit integers in \a __B, producing 4 intermediate
@@ -89,11 +78,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbssd_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbssd_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbssd256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpbssd_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpbssd256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding signed 8-bit integers in \a __B, producing 4 intermediate
@@ -126,12 +113,9 @@ _mm256_dpbssd_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbssds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbssds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpbssds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpbssds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding signed 8-bit integers in \a __B, producing 4 intermediate
@@ -164,11 +148,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbssds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbssds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbssds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
+#define _mm256_dpbssds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpbssds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -200,12 +182,9 @@ _mm256_dpbssds_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbsud_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbsud128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpbsud_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpbsud128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -237,11 +216,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbsud_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbsud_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbsud256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpbsud_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpbsud256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -274,12 +251,9 @@ _mm256_dpbsud_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbsuds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbsuds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpbsuds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpbsuds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -312,11 +286,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbsuds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbsuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbsuds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
+#define _mm256_dpbsuds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpbsuds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -348,12 +320,9 @@ _mm256_dpbsuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbuud_epi32(__m128i __W,
-                                                                 __m128i __A,
-                                                                 __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbuud128((__v4si)__W, (__v4si)__A,
-                                             (__v4si)__B);
-}
+#define _mm_dpbuud_epi32(__W, __A, __B)                                        \
+  ((__m128i)__builtin_ia32_vpdpbuud128((__v4si)(__W), (__v4si)(__A),           \
+                                       (__v4si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -385,11 +354,9 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbuud_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbuud_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbuud256((__v8si)__W, (__v8si)__A,
-                                             (__v8si)__B);
-}
+#define _mm256_dpbuud_epi32(__W, __A, __B)                                     \
+  ((__m256i)__builtin_ia32_vpdpbuud256((__v8si)(__W), (__v8si)(__A),           \
+                                       (__v8si)(__B)))
 
 /// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
@@ -422,14 +389,10 @@ _mm256_dpbuud_epi32(__m256i __W, __m256i __A, __m256i __B) {
 /// ENDFOR
 /// dst[MAX:128] := 0
 /// \endcode
-static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbuuds_epi32(__m128i __W,
-                                                                  __m128i __A,
-                                                                  __m128i __B) {
-  return (__m128i)__builtin_ia32_vpdpbuuds128((__v4si)__W, (__v4si)__A,
-                                              (__v4si)__B);
-}
+#define _mm_dpbuuds_epi32(__W, __A, __B)                                       \
+  ((__m128i)__builtin_ia32_vpdpbuuds128((__v4si)(__W), (__v4si)(__A),          \
+                                        (__v4si)(__B)))
 
-/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
 ///    corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
 ///    signed 16-bit results. Sum these 4 results with the corresponding
 ///    32-bit integer in \a __W with signed saturation, and store the packed
@@ -460,12 +423,8 @@ static __inline__ __m128i __DEFAULT_FN_ATTRS128 _mm_dpbuuds_epi32(__m128i __W,
 /// ENDFOR
 /// dst[MAX:256] := 0
 /// \endcode
-static __inline__ __m256i __DEFAULT_FN_ATTRS256
-_mm256_dpbuuds_epi32(__m256i __W, __m256i __A, __m256i __B) {
-  return (__m256i)__builtin_ia32_vpdpbuuds256((__v8si)__W, (__v8si)__A,
-                                              (__v8si)__B);
-}
-#undef __DEFAULT_FN_ATTRS128
-#undef __DEFAULT_FN_ATTRS256
+#define _mm256_dpbuuds_epi32(__W, __A, __B)                                    \
+  ((__m256i)__builtin_ia32_vpdpbuuds256((__v8si)(__W), (__v8si)(__A),          \
+                                        (__v8si)(__B)))
 
 #endif // __AVXVNNIINT8INTRIN_H

package/lib/clang/{18 → 20}/include/bmi2intrin.h

@@ -15,7 +15,13 @@
 #define __BMI2INTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("bmi2")))
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("bmi2"))) constexpr
+#else
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("bmi2")))
+#endif
 
 /// Copies the unsigned 32-bit integer \a __X and zeroes the upper bits
 ///    starting at bit number \a __Y.
@@ -38,8 +44,7 @@
 ///    The lower 8 bits specify the bit number of the lowest bit to zero.
 /// \returns The partially zeroed 32-bit value.
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_bzhi_u32(unsigned int __X, unsigned int __Y)
-{
+_bzhi_u32(unsigned int __X, unsigned int __Y) {
   return __builtin_ia32_bzhi_si(__X, __Y);
 }
 
@@ -68,8 +73,7 @@ _bzhi_u32(unsigned int __X, unsigned int __Y)
 ///    The 32-bit mask specifying where to deposit source bits.
 /// \returns The 32-bit result.
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_pdep_u32(unsigned int __X, unsigned int __Y)
-{
+_pdep_u32(unsigned int __X, unsigned int __Y) {
   return __builtin_ia32_pdep_si(__X, __Y);
 }
 
@@ -98,8 +102,7 @@ _pdep_u32(unsigned int __X, unsigned int __Y)
 ///    The 32-bit mask specifying which source bits to extract.
 /// \returns The 32-bit result.
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_pext_u32(unsigned int __X, unsigned int __Y)
-{
+_pext_u32(unsigned int __X, unsigned int __Y) {
   return __builtin_ia32_pext_si(__X, __Y);
 }
 
@@ -124,8 +127,7 @@ _pext_u32(unsigned int __X, unsigned int __Y)
 ///    A pointer to memory for storing the upper half of the product.
 /// \returns The lower half of the product.
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-_mulx_u32(unsigned int __X, unsigned int __Y, unsigned int *__P)
-{
+_mulx_u32(unsigned int __X, unsigned int __Y, unsigned int *__P) {
   unsigned long long __res = (unsigned long long) __X * __Y;
   *__P = (unsigned int)(__res >> 32);
   return (unsigned int)__res;
@@ -154,8 +156,7 @@ _mulx_u32(unsigned int __X, unsigned int __Y, unsigned int *__P)
 ///    The lower 8 bits specify the bit number of the lowest bit to zero.
 /// \returns The partially zeroed 64-bit value.
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-_bzhi_u64(unsigned long long __X, unsigned long long __Y)
-{
+_bzhi_u64(unsigned long long __X, unsigned long long __Y) {
   return __builtin_ia32_bzhi_di(__X, __Y);
 }
 
@@ -184,8 +185,7 @@ _bzhi_u64(unsigned long long __X, unsigned long long __Y)
 ///    The 64-bit mask specifying where to deposit source bits.
 /// \returns The 64-bit result.
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-_pdep_u64(unsigned long long __X, unsigned long long __Y)
-{
+_pdep_u64(unsigned long long __X, unsigned long long __Y) {
   return __builtin_ia32_pdep_di(__X, __Y);
 }
 
@@ -214,8 +214,7 @@ _pdep_u64(unsigned long long __X, unsigned long long __Y)
 ///    The 64-bit mask specifying which source bits to extract.
 /// \returns The 64-bit result.
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-_pext_u64(unsigned long long __X, unsigned long long __Y)
-{
+_pext_u64(unsigned long long __X, unsigned long long __Y) {
   return __builtin_ia32_pext_di(__X, __Y);
 }
 
@@ -241,8 +240,7 @@ _pext_u64(unsigned long long __X, unsigned long long __Y)
 /// \returns The lower half of the product.
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 _mulx_u64 (unsigned long long __X, unsigned long long __Y,
-	   unsigned long long *__P)
-{
+           unsigned long long *__P) {
   unsigned __int128 __res = (unsigned __int128) __X * __Y;
   *__P = (unsigned long long) (__res >> 64);
   return (unsigned long long) __res;