@cpp-linter/clang-tidy-win32-x64 12.0.1

package/lib/clang/12.0.1/include/enqcmdintrin.h

@@ -0,0 +1,63 @@
+/*===------------------ enqcmdintrin.h - enqcmd 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 <enqcmdintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __ENQCMDINTRIN_H
+#define __ENQCMDINTRIN_H
+
+/* Define the default attributes for the functions in this file */
+#define _DEFAULT_FN_ATTRS \
+  __attribute__((__always_inline__, __nodebug__, __target__("enqcmd")))
+
+/// Reads 64-byte command pointed by \a __src, formats 64-byte enqueue store
+///    data, and performs 64-byte enqueue store to memory pointed by \a __dst.
+///    This intrinsics may only be used in User mode.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsics corresponds to the <c> ENQCMD </c> instruction.
+///
+/// \param __dst
+///    Pointer to the destination of the enqueue store.
+/// \param __src
+///    Pointer to 64-byte command data.
+/// \returns If the command data is successfully written to \a __dst then 0 is
+///    returned. Otherwise 1 is returned.
+static __inline__ int _DEFAULT_FN_ATTRS
+_enqcmd (void *__dst, const void *__src)
+{
+  return __builtin_ia32_enqcmd(__dst, __src);
+}
+
+/// Reads 64-byte command pointed by \a __src, formats 64-byte enqueue store
+///    data, and performs 64-byte enqueue store to memory pointed by \a __dst
+///    This intrinsic may only be used in Privileged mode.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsics corresponds to the <c> ENQCMDS </c> instruction.
+///
+/// \param __dst
+///    Pointer to the destination of the enqueue store.
+/// \param __src
+///    Pointer to 64-byte command data.
+/// \returns If the command data is successfully written to \a __dst then 0 is
+///    returned. Otherwise 1 is returned.
+static __inline__ int _DEFAULT_FN_ATTRS
+_enqcmds (void *__dst, const void *__src)
+{
+  return __builtin_ia32_enqcmds(__dst, __src);
+}
+
+#undef _DEFAULT_FN_ATTRS
+
+#endif /* __ENQCMDINTRIN_H */

package/lib/clang/12.0.1/include/f16cintrin.h

@@ -0,0 +1,162 @@
+/*===---- f16cintrin.h - F16C 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
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#if !defined __IMMINTRIN_H
+#error "Never use <f16cintrin.h> directly; include <immintrin.h> instead."
+#endif
+
+#ifndef __F16CINTRIN_H
+#define __F16CINTRIN_H
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS128 \
+  __attribute__((__always_inline__, __nodebug__, __target__("f16c"), __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS256 \
+  __attribute__((__always_inline__, __nodebug__, __target__("f16c"), __min_vector_width__(256)))
+
+/* NOTE: Intel documents the 128-bit versions of these as being in emmintrin.h,
+ * but that's because icc can emulate these without f16c using a library call.
+ * Since we don't do that let's leave these in f16cintrin.h.
+ */
+
+/// Converts a 16-bit half-precision float value into a 32-bit float
+///    value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTPH2PS </c> instruction.
+///
+/// \param __a
+///    A 16-bit half-precision float value.
+/// \returns The converted 32-bit float value.
+static __inline float __DEFAULT_FN_ATTRS128
+_cvtsh_ss(unsigned short __a)
+{
+  __v8hi __v = {(short)__a, 0, 0, 0, 0, 0, 0, 0};
+  __v4sf __r = __builtin_ia32_vcvtph2ps(__v);
+  return __r[0];
+}
+
+/// Converts a 32-bit single-precision float value to a 16-bit
+///    half-precision float value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// unsigned short _cvtss_sh(float a, const int imm);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCVTPS2PH </c> instruction.
+///
+/// \param a
+///    A 32-bit single-precision float value to be converted to a 16-bit
+///    half-precision float value.
+/// \param imm
+///    An immediate value controlling rounding using bits [2:0]: \n
+///    000: Nearest \n
+///    001: Down \n
+///    010: Up \n
+///    011: Truncate \n
+///    1XX: Use MXCSR.RC for rounding
+/// \returns The converted 16-bit half-precision float value.
+#define _cvtss_sh(a, imm) \
+  (unsigned short)(((__v8hi)__builtin_ia32_vcvtps2ph((__v4sf){a, 0, 0, 0}, \
+                                                     (imm)))[0])
+
+/// Converts a 128-bit vector containing 32-bit float values into a
+///    128-bit vector containing 16-bit half-precision float values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128i _mm_cvtps_ph(__m128 a, const int imm);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCVTPS2PH </c> instruction.
+///
+/// \param a
+///    A 128-bit vector containing 32-bit float values.
+/// \param imm
+///    An immediate value controlling rounding using bits [2:0]: \n
+///    000: Nearest \n
+///    001: Down \n
+///    010: Up \n
+///    011: Truncate \n
+///    1XX: Use MXCSR.RC for rounding
+/// \returns A 128-bit vector containing converted 16-bit half-precision float
+///    values. The lower 64 bits are used to store the converted 16-bit
+///    half-precision floating-point values.
+#define _mm_cvtps_ph(a, imm) \
+  (__m128i)__builtin_ia32_vcvtps2ph((__v4sf)(__m128)(a), (imm))
+
+/// Converts a 128-bit vector containing 16-bit half-precision float
+///    values into a 128-bit vector containing 32-bit float values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTPH2PS </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector containing 16-bit half-precision float values. The lower
+///    64 bits are used in the conversion.
+/// \returns A 128-bit vector of [4 x float] containing converted float values.
+static __inline __m128 __DEFAULT_FN_ATTRS128
+_mm_cvtph_ps(__m128i __a)
+{
+  return (__m128)__builtin_ia32_vcvtph2ps((__v8hi)__a);
+}
+
+/// Converts a 256-bit vector of [8 x float] into a 128-bit vector
+///    containing 16-bit half-precision float values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128i _mm256_cvtps_ph(__m256 a, const int imm);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCVTPS2PH </c> instruction.
+///
+/// \param a
+///    A 256-bit vector containing 32-bit single-precision float values to be
+///    converted to 16-bit half-precision float values.
+/// \param imm
+///    An immediate value controlling rounding using bits [2:0]: \n
+///    000: Nearest \n
+///    001: Down \n
+///    010: Up \n
+///    011: Truncate \n
+///    1XX: Use MXCSR.RC for rounding
+/// \returns A 128-bit vector containing the converted 16-bit half-precision
+///    float values.
+#define _mm256_cvtps_ph(a, imm) \
+ (__m128i)__builtin_ia32_vcvtps2ph256((__v8sf)(__m256)(a), (imm))
+
+/// Converts a 128-bit vector containing 16-bit half-precision float
+///    values into a 256-bit vector of [8 x float].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VCVTPH2PS </c> instruction.
+///
+/// \param __a
+///    A 128-bit vector containing 16-bit half-precision float values to be
+///    converted to 32-bit single-precision float values.
+/// \returns A vector of [8 x float] containing the converted 32-bit
+///    single-precision float values.
+static __inline __m256 __DEFAULT_FN_ATTRS256
+_mm256_cvtph_ps(__m128i __a)
+{
+  return (__m256)__builtin_ia32_vcvtph2ps256((__v8hi)__a);
+}
+
+#undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256
+
+#endif /* __F16CINTRIN_H */

package/lib/clang/12.0.1/include/float.h

@@ -0,0 +1,152 @@
+/*===---- float.h - Characteristics of floating point types ----------------===
+ *
+ * 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 __CLANG_FLOAT_H
+#define __CLANG_FLOAT_H
+
+/* If we're on MinGW, fall back to the system's float.h, which might have
+ * additional definitions provided for Windows.
+ * For more details see http://msdn.microsoft.com/en-us/library/y0ybw9fy.aspx
+ *
+ * Also fall back on Darwin to allow additional definitions and
+ * implementation-defined values.
+ */
+#if (defined(__APPLE__) || (defined(__MINGW32__) || defined(_MSC_VER))) && \
+    __STDC_HOSTED__ && __has_include_next(<float.h>)
+
+/* Prior to Apple's 10.7 SDK, float.h SDK header used to apply an extra level
+ * of #include_next<float.h> to keep Metrowerks compilers happy. Avoid this
+ * extra indirection.
+ */
+#ifdef __APPLE__
+#define _FLOAT_H_
+#endif
+
+#  include_next <float.h>
+
+/* Undefine anything that we'll be redefining below. */
+#  undef FLT_EVAL_METHOD
+#  undef FLT_ROUNDS
+#  undef FLT_RADIX
+#  undef FLT_MANT_DIG
+#  undef DBL_MANT_DIG
+#  undef LDBL_MANT_DIG
+#  if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__) || __cplusplus >= 201103L
+#    undef DECIMAL_DIG
+#  endif
+#  undef FLT_DIG
+#  undef DBL_DIG
+#  undef LDBL_DIG
+#  undef FLT_MIN_EXP
+#  undef DBL_MIN_EXP
+#  undef LDBL_MIN_EXP
+#  undef FLT_MIN_10_EXP
+#  undef DBL_MIN_10_EXP
+#  undef LDBL_MIN_10_EXP
+#  undef FLT_MAX_EXP
+#  undef DBL_MAX_EXP
+#  undef LDBL_MAX_EXP
+#  undef FLT_MAX_10_EXP
+#  undef DBL_MAX_10_EXP
+#  undef LDBL_MAX_10_EXP
+#  undef FLT_MAX
+#  undef DBL_MAX
+#  undef LDBL_MAX
+#  undef FLT_EPSILON
+#  undef DBL_EPSILON
+#  undef LDBL_EPSILON
+#  undef FLT_MIN
+#  undef DBL_MIN
+#  undef LDBL_MIN
+#  if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__) || __cplusplus >= 201703L
+#    undef FLT_TRUE_MIN
+#    undef DBL_TRUE_MIN
+#    undef LDBL_TRUE_MIN
+#    undef FLT_DECIMAL_DIG
+#    undef DBL_DECIMAL_DIG
+#    undef LDBL_DECIMAL_DIG
+#    undef FLT_HAS_SUBNORM
+#    undef DBL_HAS_SUBNORM
+#    undef LDBL_HAS_SUBNORM
+#  endif
+#endif
+
+/* Characteristics of floating point types, C99 5.2.4.2.2 */
+
+#define FLT_EVAL_METHOD __FLT_EVAL_METHOD__
+#define FLT_ROUNDS (__builtin_flt_rounds())
+#define FLT_RADIX __FLT_RADIX__
+
+#define FLT_MANT_DIG __FLT_MANT_DIG__
+#define DBL_MANT_DIG __DBL_MANT_DIG__
+#define LDBL_MANT_DIG __LDBL_MANT_DIG__
+
+#if __STDC_VERSION__ >= 199901L || !defined(__STRICT_ANSI__) || __cplusplus >= 201103L
+#  define DECIMAL_DIG __DECIMAL_DIG__
+#endif
+
+#define FLT_DIG __FLT_DIG__
+#define DBL_DIG __DBL_DIG__
+#define LDBL_DIG __LDBL_DIG__
+
+#define FLT_MIN_EXP __FLT_MIN_EXP__
+#define DBL_MIN_EXP __DBL_MIN_EXP__
+#define LDBL_MIN_EXP __LDBL_MIN_EXP__
+
+#define FLT_MIN_10_EXP __FLT_MIN_10_EXP__
+#define DBL_MIN_10_EXP __DBL_MIN_10_EXP__
+#define LDBL_MIN_10_EXP __LDBL_MIN_10_EXP__
+
+#define FLT_MAX_EXP __FLT_MAX_EXP__
+#define DBL_MAX_EXP __DBL_MAX_EXP__
+#define LDBL_MAX_EXP __LDBL_MAX_EXP__
+
+#define FLT_MAX_10_EXP __FLT_MAX_10_EXP__
+#define DBL_MAX_10_EXP __DBL_MAX_10_EXP__
+#define LDBL_MAX_10_EXP __LDBL_MAX_10_EXP__
+
+#define FLT_MAX __FLT_MAX__
+#define DBL_MAX __DBL_MAX__
+#define LDBL_MAX __LDBL_MAX__
+
+#define FLT_EPSILON __FLT_EPSILON__
+#define DBL_EPSILON __DBL_EPSILON__
+#define LDBL_EPSILON __LDBL_EPSILON__
+
+#define FLT_MIN __FLT_MIN__
+#define DBL_MIN __DBL_MIN__
+#define LDBL_MIN __LDBL_MIN__
+
+#if __STDC_VERSION__ >= 201112L || !defined(__STRICT_ANSI__) || __cplusplus >= 201703L
+#  define FLT_TRUE_MIN __FLT_DENORM_MIN__
+#  define DBL_TRUE_MIN __DBL_DENORM_MIN__
+#  define LDBL_TRUE_MIN __LDBL_DENORM_MIN__
+#  define FLT_DECIMAL_DIG __FLT_DECIMAL_DIG__
+#  define DBL_DECIMAL_DIG __DBL_DECIMAL_DIG__
+#  define LDBL_DECIMAL_DIG __LDBL_DECIMAL_DIG__
+#  define FLT_HAS_SUBNORM __FLT_HAS_DENORM__
+#  define DBL_HAS_SUBNORM __DBL_HAS_DENORM__
+#  define LDBL_HAS_SUBNORM __LDBL_HAS_DENORM__
+#endif
+
+#ifdef __STDC_WANT_IEC_60559_TYPES_EXT__
+#  define FLT16_MANT_DIG    __FLT16_MANT_DIG__
+#  define FLT16_DECIMAL_DIG __FLT16_DECIMAL_DIG__
+#  define FLT16_DIG         __FLT16_DIG__
+#  define FLT16_MIN_EXP     __FLT16_MIN_EXP__
+#  define FLT16_MIN_10_EXP  __FLT16_MIN_10_EXP__
+#  define FLT16_MAX_EXP     __FLT16_MAX_EXP__
+#  define FLT16_MAX_10_EXP  __FLT16_MAX_10_EXP__
+#  define FLT16_MAX         __FLT16_MAX__
+#  define FLT16_EPSILON     __FLT16_EPSILON__
+#  define FLT16_MIN         __FLT16_MIN__
+#  define FLT16_TRUE_MIN    __FLT16_TRUE_MIN__
+#endif /* __STDC_WANT_IEC_60559_TYPES_EXT__ */
+
+#endif /* __CLANG_FLOAT_H */

package/lib/clang/12.0.1/include/fma4intrin.h

@@ -0,0 +1,218 @@
+/*===---- fma4intrin.h - FMA4 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 __X86INTRIN_H
+#error "Never use <fma4intrin.h> directly; include <x86intrin.h> instead."
+#endif
+
+#ifndef __FMA4INTRIN_H
+#define __FMA4INTRIN_H
+
+#include <pmmintrin.h>
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS128 __attribute__((__always_inline__, __nodebug__, __target__("fma4"), __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS256 __attribute__((__always_inline__, __nodebug__, __target__("fma4"), __min_vector_width__(256)))
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_macc_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddps((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_macc_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddpd((__v2df)__A, (__v2df)__B, (__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_macc_ss(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_macc_sd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B, (__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_msub_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddps((__v4sf)__A, (__v4sf)__B, -(__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_msub_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddpd((__v2df)__A, (__v2df)__B, -(__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_msub_ss(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddss((__v4sf)__A, (__v4sf)__B, -(__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_msub_sd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsd((__v2df)__A, (__v2df)__B, -(__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_nmacc_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddps(-(__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_nmacc_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddpd(-(__v2df)__A, (__v2df)__B, (__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_nmacc_ss(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddss(-(__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_nmacc_sd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsd(-(__v2df)__A, (__v2df)__B, (__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_nmsub_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddps(-(__v4sf)__A, (__v4sf)__B, -(__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_nmsub_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddpd(-(__v2df)__A, (__v2df)__B, -(__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_nmsub_ss(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddss(-(__v4sf)__A, (__v4sf)__B, -(__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_nmsub_sd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsd(-(__v2df)__A, (__v2df)__B, -(__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_maddsub_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddsubps((__v4sf)__A, (__v4sf)__B, (__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_maddsub_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsubpd((__v2df)__A, (__v2df)__B, (__v2df)__C);
+}
+
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_msubadd_ps(__m128 __A, __m128 __B, __m128 __C)
+{
+  return (__m128)__builtin_ia32_vfmaddsubps((__v4sf)__A, (__v4sf)__B, -(__v4sf)__C);
+}
+
+static __inline__ __m128d __DEFAULT_FN_ATTRS128
+_mm_msubadd_pd(__m128d __A, __m128d __B, __m128d __C)
+{
+  return (__m128d)__builtin_ia32_vfmaddsubpd((__v2df)__A, (__v2df)__B, -(__v2df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_macc_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddps256((__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_macc_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddpd256((__v4df)__A, (__v4df)__B, (__v4df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_msub_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddps256((__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_msub_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddpd256((__v4df)__A, (__v4df)__B, -(__v4df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_nmacc_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddps256(-(__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_nmacc_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddpd256(-(__v4df)__A, (__v4df)__B, (__v4df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_nmsub_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddps256(-(__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_nmsub_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddpd256(-(__v4df)__A, (__v4df)__B, -(__v4df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_maddsub_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddsubps256((__v8sf)__A, (__v8sf)__B, (__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_maddsub_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddsubpd256((__v4df)__A, (__v4df)__B, (__v4df)__C);
+}
+
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_msubadd_ps(__m256 __A, __m256 __B, __m256 __C)
+{
+  return (__m256)__builtin_ia32_vfmaddsubps256((__v8sf)__A, (__v8sf)__B, -(__v8sf)__C);
+}
+
+static __inline__ __m256d __DEFAULT_FN_ATTRS256
+_mm256_msubadd_pd(__m256d __A, __m256d __B, __m256d __C)
+{
+  return (__m256d)__builtin_ia32_vfmaddsubpd256((__v4df)__A, (__v4df)__B, -(__v4df)__C);
+}
+
+#undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256
+
+#endif /* __FMA4INTRIN_H */