@cpp-linter/clang-tidy-win32-x64 19.1.0 → 20.1.0

package/lib/clang/{19 → 20}/include/popcntintrin.h

@@ -11,12 +11,13 @@
 #define __POPCNTINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("popcnt")))
-
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
-#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("popcnt"))) constexpr
 #else
-#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("popcnt")))
 #endif
 
 /// Counts the number of bits in the source operand having a value of 1.
@@ -29,7 +30,7 @@
 ///    An unsigned 32-bit integer operand.
 /// \returns A 32-bit integer containing the number of bits with value 1 in the
 ///    source operand.
-static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR
+static __inline__ int __DEFAULT_FN_ATTRS
 _mm_popcnt_u32(unsigned int __A)
 {
   return __builtin_popcount(__A);
@@ -46,7 +47,7 @@ _mm_popcnt_u32(unsigned int __A)
 ///    An unsigned 64-bit integer operand.
 /// \returns A 64-bit integer containing the number of bits with value 1 in the
 ///    source operand.
-static __inline__ long long __DEFAULT_FN_ATTRS_CONSTEXPR
+static __inline__ long long __DEFAULT_FN_ATTRS
 _mm_popcnt_u64(unsigned long long __A)
 {
   return __builtin_popcountll(__A);
@@ -54,6 +55,5 @@ _mm_popcnt_u64(unsigned long long __A)
 #endif /* __x86_64__ */
 
 #undef __DEFAULT_FN_ATTRS
-#undef __DEFAULT_FN_ATTRS_CONSTEXPR
 
 #endif /* __POPCNTINTRIN_H */

package/lib/clang/{19 → 20}/include/ptrauth.h

@@ -42,6 +42,9 @@ typedef enum {
      The extra data is always 0. */
   ptrauth_key_cxx_vtable_pointer = ptrauth_key_process_independent_data,
 
+  /* The key used to sign pointers in ELF .init_array/.fini_array. */
+  ptrauth_key_init_fini_pointer = ptrauth_key_process_independent_code,
+
   /* Other pointers signed under the ABI use private ABI rules. */
 
 } ptrauth_key;
@@ -253,6 +256,9 @@ typedef __UINTPTR_TYPE__ ptrauth_generic_signature_t;
   [[clang::ptrauth_vtable_pointer(key, address_discrimination,                 \
                                   extra_discrimination)]]
 
+/* The value is ptrauth_string_discriminator("init_fini") */
+#define __ptrauth_init_fini_discriminator 0xd9d4
+
 #else
 
 #define ptrauth_strip(__value, __key)                                          \

package/lib/clang/20/include/riscv_corev_alu.h

@@ -0,0 +1,128 @@
+/*===---- riscv_corev_alu.h - CORE-V ALU intrinsics ------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __RISCV_COREV_ALU_H
+#define __RISCV_COREV_ALU_H
+
+#include <stdint.h>
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#if defined(__riscv_xcvalu)
+
+#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_abs(long a) {
+  return __builtin_abs(a);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_slet(long a, long b) {
+  return __builtin_riscv_cv_alu_slet(a, b);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_sletu(unsigned long a, unsigned long b) {
+  return __builtin_riscv_cv_alu_sletu(a, b);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_min(long a, long b) {
+  return __builtin_elementwise_min(a, b);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_minu(unsigned long a, unsigned long b) {
+  return __builtin_elementwise_min(a, b);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_max(long a, long b) {
+  return __builtin_elementwise_max(a, b);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_maxu(unsigned long a, unsigned long b) {
+  return __builtin_elementwise_max(a, b);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_exths(int16_t a) {
+  return __builtin_riscv_cv_alu_exths(a);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_exthz(uint16_t a) {
+  return __builtin_riscv_cv_alu_exthz(a);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_extbs(int8_t a) {
+  return __builtin_riscv_cv_alu_extbs(a);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_extbz(uint8_t a) {
+  return __builtin_riscv_cv_alu_extbz(a);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_clip(long a,
+                                                              unsigned long b) {
+  return __builtin_riscv_cv_alu_clip(a, b);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_clipu(unsigned long a, unsigned long b) {
+  return __builtin_riscv_cv_alu_clipu(a, b);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_addN(long a, long b,
+                                                              uint8_t shft) {
+  return __builtin_riscv_cv_alu_addN(a, b, shft);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_adduN(unsigned long a, unsigned long b, uint8_t shft) {
+  return __builtin_riscv_cv_alu_adduN(a, b, shft);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_addRN(long a, long b,
+                                                               uint8_t shft) {
+  return __builtin_riscv_cv_alu_addRN(a, b, shft);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_adduRN(unsigned long a, unsigned long b, uint8_t shft) {
+  return __builtin_riscv_cv_alu_adduRN(a, b, shft);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_subN(long a, long b,
+                                                              uint8_t shft) {
+  return __builtin_riscv_cv_alu_subN(a, b, shft);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_subuN(unsigned long a, unsigned long b, uint8_t shft) {
+  return __builtin_riscv_cv_alu_subuN(a, b, shft);
+}
+
+static __inline__ long __DEFAULT_FN_ATTRS __riscv_cv_alu_subRN(long a, long b,
+                                                               uint8_t shft) {
+  return __builtin_riscv_cv_alu_subRN(a, b, shft);
+}
+
+static __inline__ unsigned long __DEFAULT_FN_ATTRS
+__riscv_cv_alu_subuRN(unsigned long a, unsigned long b, uint8_t shft) {
+  return __builtin_riscv_cv_alu_subuRN(a, b, shft);
+}
+
+#endif // defined(__riscv_xcvalu)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif // define __RISCV_COREV_ALU_H

package/lib/clang/{19 → 20}/include/riscv_vector.h

@@ -419,7 +419,6 @@ typedef __rvv_bfloat16m2x4_t vbfloat16m2x4_t;
 typedef __rvv_bfloat16m4_t vbfloat16m4_t;
 typedef __rvv_bfloat16m4x2_t vbfloat16m4x2_t;
 typedef __rvv_bfloat16m8_t vbfloat16m8_t;
-#define __riscv_v_intrinsic_overloading 1
 
 #ifdef __cplusplus
 }

package/lib/clang/20/include/sm4evexintrin.h

@@ -0,0 +1,32 @@
+/*===--------------- sm4evexintrin.h - SM4 EVEX intrinsics -----------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <sm4evexintrin.h> directly; include <immintrin.h> instead."
+#endif // __IMMINTRIN_H
+
+#ifndef __SM4EVEXINTRIN_H
+#define __SM4EVEXINTRIN_H
+
+#define __DEFAULT_FN_ATTRS512                                                  \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("sm4,avx10.2-512"), __min_vector_width__(512)))
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS512
+_mm512_sm4key4_epi32(__m512i __A, __m512i __B) {
+  return (__m512i)__builtin_ia32_vsm4key4512((__v16su)__A, (__v16su)__B);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS512
+_mm512_sm4rnds4_epi32(__m512i __A, __m512i __B) {
+  return (__m512i)__builtin_ia32_vsm4rnds4512((__v16su)__A, (__v16su)__B);
+}
+
+#undef __DEFAULT_FN_ATTRS512
+
+#endif // __SM4EVEXINTRIN_H

package/lib/clang/{19 → 20}/include/smmintrin.h

@@ -17,9 +17,15 @@
 #include <tmmintrin.h>
 
 /* Define the default attributes for the functions in this file. */
+#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__,                               \
                  __target__("sse4.1,no-evex512"), __min_vector_width__(128)))
+#else
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("sse4.1"),         \
+                 __min_vector_width__(128)))
+#endif
 
 /* SSE4 Rounding macros. */
 #define _MM_FROUND_TO_NEAREST_INT 0x00

package/lib/clang/{19 → 20}/include/stdalign.h

@@ -10,10 +10,6 @@
 #ifndef __STDALIGN_H
 #define __STDALIGN_H
 
-#if defined(__MVS__) && __has_include_next(<stdalign.h>)
-#include_next <stdalign.h>
-#else
-
 #if defined(__cplusplus) ||                                                    \
     (defined(__STDC_VERSION__) && __STDC_VERSION__ < 202311L)
 #ifndef __cplusplus
@@ -25,5 +21,4 @@
 #define __alignof_is_defined 1
 #endif /* __STDC_VERSION__ */
 
-#endif /* __MVS__ */
 #endif /* __STDALIGN_H */

package/lib/clang/{19 → 20}/include/tbmintrin.h

@@ -15,63 +15,60 @@
 #define __TBMINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("tbm")))
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("tbm"))) constexpr
+#else
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("tbm")))
+#endif
 
 #define __bextri_u32(a, b) \
   ((unsigned int)__builtin_ia32_bextri_u32((unsigned int)(a), \
                                            (unsigned int)(b)))
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blcfill_u32(unsigned int __a)
-{
+__blcfill_u32(unsigned int __a) {
   return __a & (__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blci_u32(unsigned int __a)
-{
+__blci_u32(unsigned int __a) {
   return __a | ~(__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blcic_u32(unsigned int __a)
-{
+__blcic_u32(unsigned int __a) {
   return ~__a & (__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blcmsk_u32(unsigned int __a)
-{
+__blcmsk_u32(unsigned int __a) {
   return __a ^ (__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blcs_u32(unsigned int __a)
-{
+__blcs_u32(unsigned int __a) {
   return __a | (__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blsfill_u32(unsigned int __a)
-{
+__blsfill_u32(unsigned int __a) {
   return __a | (__a - 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__blsic_u32(unsigned int __a)
-{
+__blsic_u32(unsigned int __a) {
   return ~__a | (__a - 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__t1mskc_u32(unsigned int __a)
-{
+__t1mskc_u32(unsigned int __a) {
   return ~__a | (__a + 1);
 }
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
-__tzmsk_u32(unsigned int __a)
-{
+__tzmsk_u32(unsigned int __a) {
   return ~__a & (__a - 1);
 }
 
@@ -81,56 +78,47 @@ __tzmsk_u32(unsigned int __a)
                                                  (unsigned long long)(b)))
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blcfill_u64(unsigned long long __a)
-{
+__blcfill_u64(unsigned long long __a) {
   return __a & (__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blci_u64(unsigned long long __a)
-{
+__blci_u64(unsigned long long __a) {
   return __a | ~(__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blcic_u64(unsigned long long __a)
-{
+__blcic_u64(unsigned long long __a) {
   return ~__a & (__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blcmsk_u64(unsigned long long __a)
-{
+__blcmsk_u64(unsigned long long __a) {
   return __a ^ (__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blcs_u64(unsigned long long __a)
-{
+__blcs_u64(unsigned long long __a) {
   return __a | (__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blsfill_u64(unsigned long long __a)
-{
+__blsfill_u64(unsigned long long __a) {
   return __a | (__a - 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__blsic_u64(unsigned long long __a)
-{
+__blsic_u64(unsigned long long __a) {
   return ~__a | (__a - 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__t1mskc_u64(unsigned long long __a)
-{
+__t1mskc_u64(unsigned long long __a) {
   return ~__a | (__a + 1);
 }
 
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
-__tzmsk_u64(unsigned long long __a)
-{
+__tzmsk_u64(unsigned long long __a) {
   return ~__a & (__a - 1);
 }
 #endif

package/lib/clang/{19 → 20}/include/tmmintrin.h

@@ -17,13 +17,21 @@
 #include <pmmintrin.h>
 
 /* Define the default attributes for the functions in this file. */
+#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("ssse3,no-evex512"), __min_vector_width__(64)))
-#define __DEFAULT_FN_ATTRS_MMX                                                 \
-  __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("mmx,ssse3,no-evex512"),                           \
-                 __min_vector_width__(64)))
+                 __target__("ssse3,no-evex512"), __min_vector_width__(128)))
+#else
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("ssse3"),          \
+                 __min_vector_width__(128)))
+#endif
+
+#define __trunc64(x)                                                           \
+  (__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0)
+#define __anyext128(x)                                                         \
+  (__m128i) __builtin_shufflevector((__v2si)(x), __extension__(__v2si){}, 0,   \
+                                    1, -1, -1)
 
 /// Computes the absolute value of each of the packed 8-bit signed
 ///    integers in the source operand and stores the 8-bit unsigned integer
@@ -37,10 +45,10 @@
 ///    A 64-bit vector of [8 x i8].
 /// \returns A 64-bit integer vector containing the absolute values of the
 ///    elements in the operand.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_abs_pi8(__m64 __a)
 {
-    return (__m64)__builtin_ia32_pabsb((__v8qi)__a);
+  return (__m64)__builtin_elementwise_abs((__v8qs)__a);
 }
 
 /// Computes the absolute value of each of the packed 8-bit signed
@@ -73,10 +81,10 @@ _mm_abs_epi8(__m128i __a)
 ///    A 64-bit vector of [4 x i16].
 /// \returns A 64-bit integer vector containing the absolute values of the
 ///    elements in the operand.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_abs_pi16(__m64 __a)
 {
-    return (__m64)__builtin_ia32_pabsw((__v4hi)__a);
+    return (__m64)__builtin_elementwise_abs((__v4hi)__a);
 }
 
 /// Computes the absolute value of each of the packed 16-bit signed
@@ -109,10 +117,10 @@ _mm_abs_epi16(__m128i __a)
 ///    A 64-bit vector of [2 x i32].
 /// \returns A 64-bit integer vector containing the absolute values of the
 ///    elements in the operand.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_abs_pi32(__m64 __a)
 {
-    return (__m64)__builtin_ia32_pabsd((__v2si)__a);
+    return (__m64)__builtin_elementwise_abs((__v2si)__a);
 }
 
 /// Computes the absolute value of each of the packed 32-bit signed
@@ -177,7 +185,10 @@ _mm_abs_epi32(__m128i __a)
 /// \returns A 64-bit integer vector containing the concatenated right-shifted
 ///    value.
 #define _mm_alignr_pi8(a, b, n) \
-  ((__m64)__builtin_ia32_palignr((__v8qi)(__m64)(a), (__v8qi)(__m64)(b), (n)))
+  ((__m64)__builtin_shufflevector(                                       \
+       __builtin_ia32_psrldqi128_byteshift(                              \
+           __builtin_shufflevector((__v1di)(a), (__v1di)(b), 1, 0),      \
+           (n)), __extension__ (__v2di){}, 0))
 
 /// Horizontally adds the adjacent pairs of values contained in 2 packed
 ///    128-bit vectors of [8 x i16].
@@ -242,10 +253,11 @@ _mm_hadd_epi32(__m128i __a, __m128i __b)
 ///    destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal sums of both
 ///    operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hadd_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phaddw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_phaddw128(
+        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Horizontally adds the adjacent pairs of values contained in 2 packed
@@ -265,10 +277,11 @@ _mm_hadd_pi16(__m64 __a, __m64 __b)
 ///    destination.
 /// \returns A 64-bit vector of [2 x i32] containing the horizontal sums of both
 ///    operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hadd_pi32(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phaddd((__v2si)__a, (__v2si)__b);
+    return __trunc64(__builtin_ia32_phaddd128(
+        (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
 }
 
 /// Horizontally adds, with saturation, the adjacent pairs of values contained
@@ -317,10 +330,11 @@ _mm_hadds_epi16(__m128i __a, __m128i __b)
 ///    destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
 ///    sums of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hadds_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phaddsw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_phaddsw128(
+        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Horizontally subtracts the adjacent pairs of values contained in 2
@@ -386,10 +400,11 @@ _mm_hsub_epi32(__m128i __a, __m128i __b)
 ///    the destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal differences
 ///    of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hsub_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phsubw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_phsubw128(
+        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Horizontally subtracts the adjacent pairs of values contained in 2
@@ -409,10 +424,11 @@ _mm_hsub_pi16(__m64 __a, __m64 __b)
 ///    the destination.
 /// \returns A 64-bit vector of [2 x i32] containing the horizontal differences
 ///    of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hsub_pi32(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phsubd((__v2si)__a, (__v2si)__b);
+    return __trunc64(__builtin_ia32_phsubd128(
+        (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
 }
 
 /// Horizontally subtracts, with saturation, the adjacent pairs of values
@@ -461,10 +477,11 @@ _mm_hsubs_epi16(__m128i __a, __m128i __b)
 ///    the destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
 ///    differences of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_hsubs_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_phsubsw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_phsubsw128(
+        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Multiplies corresponding pairs of packed 8-bit unsigned integer
@@ -525,10 +542,11 @@ _mm_maddubs_epi16(__m128i __a, __m128i __b)
 ///    \a R1 := (\a __a2 * \a __b2) + (\a __a3 * \a __b3) \n
 ///    \a R2 := (\a __a4 * \a __b4) + (\a __a5 * \a __b5) \n
 ///    \a R3 := (\a __a6 * \a __b6) + (\a __a7 * \a __b7)
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_maddubs_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_pmaddubsw((__v8qi)__a, (__v8qi)__b);
+    return __trunc64(__builtin_ia32_pmaddubsw128((__v16qi)__anyext128(__a),
+                                                 (__v16qi)__anyext128(__b)));
 }
 
 /// Multiplies packed 16-bit signed integer values, truncates the 32-bit
@@ -565,10 +583,11 @@ _mm_mulhrs_epi16(__m128i __a, __m128i __b)
 ///    A 64-bit vector of [4 x i16] containing one of the source operands.
 /// \returns A 64-bit vector of [4 x i16] containing the rounded and scaled
 ///    products of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_mulhrs_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_pmulhrsw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_pmulhrsw128((__v8hi)__anyext128(__a),
+                                                (__v8hi)__anyext128(__b)));
 }
 
 /// Copies the 8-bit integers from a 128-bit integer vector to the
@@ -614,12 +633,15 @@ _mm_shuffle_epi8(__m128i __a, __m128i __b)
 ///    1: Clear the corresponding byte in the destination. \n
 ///    0: Copy the selected source byte to the corresponding byte in the
 ///    destination. \n
-///    Bits [3:0] select the source byte to be copied.
+///    Bits [2:0] select the source byte to be copied.
 /// \returns A 64-bit integer vector containing the copied or cleared values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_shuffle_pi8(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_pshufb((__v8qi)__a, (__v8qi)__b);
+    return __trunc64(__builtin_ia32_pshufb128(
+        (__v16qi)__builtin_shufflevector(
+            (__v2si)(__a), __extension__ (__v2si){}, 0, 1, 0, 1),
+        (__v16qi)__anyext128(__b)));
 }
 
 /// For each 8-bit integer in the first source operand, perform one of
@@ -720,10 +742,11 @@ _mm_sign_epi32(__m128i __a, __m128i __b)
 ///    A 64-bit integer vector containing control bytes corresponding to
 ///    positions in the destination.
 /// \returns A 64-bit integer vector containing the resultant values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sign_pi8(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_psignb((__v8qi)__a, (__v8qi)__b);
+    return __trunc64(__builtin_ia32_psignb128((__v16qi)__anyext128(__a),
+                                              (__v16qi)__anyext128(__b)));
 }
 
 /// For each 16-bit integer in the first source operand, perform one of
@@ -746,10 +769,11 @@ _mm_sign_pi8(__m64 __a, __m64 __b)
 ///    A 64-bit integer vector containing control words corresponding to
 ///    positions in the destination.
 /// \returns A 64-bit integer vector containing the resultant values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sign_pi16(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_psignw((__v4hi)__a, (__v4hi)__b);
+    return __trunc64(__builtin_ia32_psignw128((__v8hi)__anyext128(__a),
+                                              (__v8hi)__anyext128(__b)));
 }
 
 /// For each 32-bit integer in the first source operand, perform one of
@@ -772,13 +796,15 @@ _mm_sign_pi16(__m64 __a, __m64 __b)
 ///    A 64-bit integer vector containing two control doublewords corresponding
 ///    to positions in the destination.
 /// \returns A 64-bit integer vector containing the resultant values.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
+static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sign_pi32(__m64 __a, __m64 __b)
 {
-    return (__m64)__builtin_ia32_psignd((__v2si)__a, (__v2si)__b);
+    return __trunc64(__builtin_ia32_psignd128((__v4si)__anyext128(__a),
+                                              (__v4si)__anyext128(__b)));
 }
 
+#undef __anyext128
+#undef __trunc64
 #undef __DEFAULT_FN_ATTRS
-#undef __DEFAULT_FN_ATTRS_MMX
 
 #endif /* __TMMINTRIN_H */