///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VADDPD / ADDPD instruction.
+/// This intrinsic corresponds to the \c VADDPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VADDPS / ADDPS instruction.
+/// This intrinsic corresponds to the \c VADDPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VSUBPD / SUBPD instruction.
+/// This intrinsic corresponds to the \c VSUBPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing the minuend.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VSUBPS / SUBPS instruction.
+/// This intrinsic corresponds to the \c VSUBPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing the minuend.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VADDSUBPD / ADDSUBPD instruction.
+/// This intrinsic corresponds to the \c VADDSUBPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing the left source operand.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VADDSUBPS / ADDSUBPS instruction.
+/// This intrinsic corresponds to the \c VADDSUBPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing the left source operand.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VDIVPD / DIVPD instruction.
+/// This intrinsic corresponds to the \c VDIVPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing the dividend.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VDIVPS / DIVPS instruction.
+/// This intrinsic corresponds to the \c VDIVPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing the dividend.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMAXPD / MAXPD instruction.
+/// This intrinsic corresponds to the \c VMAXPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMAXPS / MAXPS instruction.
+/// This intrinsic corresponds to the \c VMAXPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMINPD / MINPD instruction.
+/// This intrinsic corresponds to the \c VMINPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMINPS / MINPS instruction.
+/// This intrinsic corresponds to the \c VMINPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMULPD / MULPD instruction.
+/// This intrinsic corresponds to the \c VMULPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VMULPS / MULPS instruction.
+/// This intrinsic corresponds to the \c VMULPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VSQRTPD / SQRTPD instruction.
+/// This intrinsic corresponds to the \c VSQRTPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VSQRTPS / SQRTPS instruction.
+/// This intrinsic corresponds to the \c VSQRTPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VRSQRTPS / RSQRTPS instruction.
+/// This intrinsic corresponds to the \c VRSQRTPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VRCPPS / RCPPS instruction.
+/// This intrinsic corresponds to the \c VRCPPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
/// __m256d _mm256_round_pd(__m256d V, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction.
+/// This intrinsic corresponds to the \c VROUNDPD instruction.
///
/// \param V
/// A 256-bit vector of [4 x double].
/// \param M
-/// An integer value that specifies the rounding operation.
-/// Bits [7:4] are reserved.
-/// Bit [3] is a precision exception value:
-/// 0: A normal PE exception is used.
-/// 1: The PE field is not updated.
-/// Bit [2] is the rounding control source:
-/// 0: Use bits [1:0] of M.
-/// 1: Use the current MXCSR setting.
-/// Bits [1:0] contain the rounding control definition:
-/// 00: Nearest.
-/// 01: Downward (toward negative infinity).
-/// 10: Upward (toward positive infinity).
-/// 11: Truncated.
+/// An integer value that specifies the rounding operation. \n
+/// Bits [7:4] are reserved. \n
+/// Bit [3] is a precision exception value: \n
+/// 0: A normal PE exception is used. \n
+/// 1: The PE field is not updated. \n
+/// Bit [2] is the rounding control source: \n
+/// 0: Use bits [1:0] of M. \n
+/// 1: Use the current MXCSR setting. \n
+/// Bits [1:0] contain the rounding control definition: \n
+/// 00: Nearest. \n
+/// 01: Downward (toward negative infinity). \n
+/// 10: Upward (toward positive infinity). \n
+/// 11: Truncated.
/// \returns A 256-bit vector of [4 x double] containing the rounded values.
#define _mm256_round_pd(V, M) __extension__ ({ \
(__m256d)__builtin_ia32_roundpd256((__v4df)(__m256d)(V), (M)); })
/// __m256 _mm256_round_ps(__m256 V, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction.
+/// This intrinsic corresponds to the \c VROUNDPS instruction.
///
/// \param V
/// A 256-bit vector of [8 x float].
/// \param M
-/// An integer value that specifies the rounding operation.
-/// Bits [7:4] are reserved.
-/// Bit [3] is a precision exception value:
-/// 0: A normal PE exception is used.
-/// 1: The PE field is not updated.
-/// Bit [2] is the rounding control source:
-/// 0: Use bits [1:0] of M.
-/// 1: Use the current MXCSR setting.
-/// Bits [1:0] contain the rounding control definition:
-/// 00: Nearest.
-/// 01: Downward (toward negative infinity).
-/// 10: Upward (toward positive infinity).
-/// 11: Truncated.
+/// An integer value that specifies the rounding operation. \n
+/// Bits [7:4] are reserved. \n
+/// Bit [3] is a precision exception value: \n
+/// 0: A normal PE exception is used. \n
+/// 1: The PE field is not updated. \n
+/// Bit [2] is the rounding control source: \n
+/// 0: Use bits [1:0] of M. \n
+/// 1: Use the current MXCSR setting. \n
+/// Bits [1:0] contain the rounding control definition: \n
+/// 00: Nearest. \n
+/// 01: Downward (toward negative infinity). \n
+/// 10: Upward (toward positive infinity). \n
+/// 11: Truncated. \n
/// \returns A 256-bit vector of [8 x float] containing the rounded values.
#define _mm256_round_ps(V, M) __extension__ ({ \
(__m256)__builtin_ia32_roundps256((__v8sf)(__m256)(V), (M)); })
/// __m256d _mm256_ceil_pd(__m256d V);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction.
+/// This intrinsic corresponds to the \c VROUNDPD instruction.
///
/// \param V
/// A 256-bit vector of [4 x double].
/// __m256d _mm256_floor_pd(__m256d V);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction.
+/// This intrinsic corresponds to the \c VROUNDPD instruction.
///
/// \param V
/// A 256-bit vector of [4 x double].
/// __m256 _mm256_ceil_ps(__m256 V);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction.
+/// This intrinsic corresponds to the \c VROUNDPS instruction.
///
/// \param V
/// A 256-bit vector of [8 x float].
/// __m256 _mm256_floor_ps(__m256 V);
/// \endcode
///
-/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction.
+/// This intrinsic corresponds to the \c VROUNDPS instruction.
///
/// \param V
/// A 256-bit vector of [8 x float].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VANDPD / ANDPD instruction.
+/// This intrinsic corresponds to the \c VANDPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VANDPS / ANDPS instruction.
+/// This intrinsic corresponds to the \c VANDPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VANDNPD / ANDNPD instruction.
+/// This intrinsic corresponds to the \c VANDNPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing the left source operand. The
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VANDNPS / ANDNPS instruction.
+/// This intrinsic corresponds to the \c VANDNPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing the left source operand. The
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VORPD / ORPD instruction.
+/// This intrinsic corresponds to the \c VORPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VORPS / ORPS instruction.
+/// This intrinsic corresponds to the \c VORPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VXORPD / XORPD instruction.
+/// This intrinsic corresponds to the \c VXORPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VXORPS / XORPS instruction.
+/// This intrinsic corresponds to the \c VXORPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VHADDPD / HADDPD instruction.
+/// This intrinsic corresponds to the \c VHADDPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VHADDPS / HADDPS instruction.
+/// This intrinsic corresponds to the \c VHADDPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VHSUBPD / HSUBPD instruction.
+/// This intrinsic corresponds to the \c VHSUBPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VHSUBPS / HSUBPS instruction.
+/// This intrinsic corresponds to the \c VHSUBPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction.
+/// This intrinsic corresponds to the \c VPERMILPD instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double].
/// \param __c
-/// A 128-bit integer vector operand specifying how the values are to be
+/// \li A 128-bit integer vector operand specifying how the values are to be
/// copied.
-/// Bit [1]:
-/// 0: Bits [63:0] of the source are copied to bits [63:0] of the
+/// \li Bit [1]:
+/// \li 0: Bits [63:0] of the source are copied to bits [63:0] of the
/// returned vector.
-/// 1: Bits [127:64] of the source are copied to bits [63:0] of the
+/// \li 1: Bits [127:64] of the source are copied to bits [63:0] of the
/// returned vector.
-/// Bit [65]:
-/// 0: Bits [63:0] of the source are copied to bits [127:64] of the
+/// \li Bit [65]:
+/// \li 0: Bits [63:0] of the source are copied to bits [127:64] of the
/// returned vector.
-/// 1: Bits [127:64] of the source are copied to bits [127:64] of the
+/// \li 1: Bits [127:64] of the source are copied to bits [127:64] of the
/// returned vector.
/// \returns A 128-bit vector of [2 x double] containing the copied values.
static __inline __m128d __DEFAULT_FN_ATTRS
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction.
+/// This intrinsic corresponds to the \c VPERMILPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double].
/// \param __c
/// A 256-bit integer vector operand specifying how the values are to be
-/// copied.
-/// Bit [1]:
-/// 0: Bits [63:0] of the source are copied to bits [63:0] of the
+/// copied. \n
+/// Bit [1]: \n
+/// \li 0: Bits [63:0] of the source are copied to bits [63:0] of the
/// returned vector.
-/// 1: Bits [127:64] of the source are copied to bits [63:0] of the
+/// \li 1: Bits [127:64] of the source are copied to bits [63:0] of the
/// returned vector.
-/// Bit [65]:
-/// 0: Bits [63:0] of the source are copied to bits [127:64] of the
+/// Bit [65]: \n
+/// \li 0: Bits [63:0] of the source are copied to bits [127:64] of the
/// returned vector.
-/// 1: Bits [127:64] of the source are copied to bits [127:64] of the
+/// \li 1: Bits [127:64] of the source are copied to bits [127:64] of the
/// returned vector.
-/// Bit [129]:
-/// 0: Bits [191:128] of the source are copied to bits [191:128] of the
+/// Bit [129]: \n
+/// \li 0: Bits [191:128] of the source are copied to bits [191:128] of the
/// returned vector.
-/// 1: Bits [255:192] of the source are copied to bits [191:128] of the
+/// \li 1: Bits [255:192] of the source are copied to bits [191:128] of the
/// returned vector.
-/// Bit [193]:
-/// 0: Bits [191:128] of the source are copied to bits [255:192] of the
+/// Bit [193]: \n
+/// \li 0: Bits [191:128] of the source are copied to bits [255:192] of the
/// returned vector.
-/// 1: Bits [255:192] of the source are copied to bits [255:192] of the
+/// \li 1: Bits [255:192] of the source are copied to bits [255:192] of the
/// returned vector.
/// \returns A 256-bit vector of [4 x double] containing the copied values.
static __inline __m256d __DEFAULT_FN_ATTRS
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction.
+/// This intrinsic corresponds to the \c VPERMILPS instruction.
///
/// \param __a
/// A 128-bit vector of [4 x float].
/// \param __c
-/// A 128-bit integer vector operand specifying how the values are to be
-/// copied.
-/// Bits [1:0]:
-/// 00: Bits [31:0] of the source are copied to bits [31:0] of the
-/// returned vector.
-/// 01: Bits [63:32] of the source are copied to bits [31:0] of the
-/// returned vector.
-/// 10: Bits [95:64] of the source are copied to bits [31:0] of the
-/// returned vector.
-/// 11: Bits [127:96] of the source are copied to bits [31:0] of the
-/// returned vector.
-/// Bits [33:32]:
-/// 00: Bits [31:0] of the source are copied to bits [63:32] of the
-/// returned vector.
-/// 01: Bits [63:32] of the source are copied to bits [63:32] of the
-/// returned vector.
-/// 10: Bits [95:64] of the source are copied to bits [63:32] of the
-/// returned vector.
-/// 11: Bits [127:96] of the source are copied to bits [63:32] of the
-/// returned vector.
-/// Bits [65:64]:
-/// 00: Bits [31:0] of the source are copied to bits [95:64] of the
-/// returned vector.
-/// 01: Bits [63:32] of the source are copied to bits [95:64] of the
-/// returned vector.
-/// 10: Bits [95:64] of the source are copied to bits [95:64] of the
-/// returned vector.
-/// 11: Bits [127:96] of the source are copied to bits [95:64] of the
-/// returned vector.
-/// Bits [97:96]:
-/// 00: Bits [31:0] of the source are copied to bits [127:96] of the
-/// returned vector.
-/// 01: Bits [63:32] of the source are copied to bits [127:96] of the
-/// returned vector.
-/// 10: Bits [95:64] of the source are copied to bits [127:96] of the
-/// returned vector.
-/// 11: Bits [127:96] of the source are copied to bits [127:96] of the
-/// returned vector.
+/// <ul>
+/// <li> A 128-bit integer vector operand specifying how the values are to be
+/// copied.
+/// </li>
+/// <li> Bits [1:0]:
+/// <ul>
+/// <li> 00: Bits [31:0] of the source are copied to bits [31:0] of the
+/// returned vector. </li>
+/// <li> 01: Bits [63:32] of the source are copied to bits [31:0] of the
+/// returned vector. </li>
+/// <li> 10: Bits [95:64] of the source are copied to bits [31:0] of the
+/// returned vector. </li>
+/// <li> 11: Bits [127:96] of the source are copied to bits [31:0] of the
+/// returned vector. </li>
+/// </ul>
+/// </li>
+/// <li> Bits [33:32]:
+/// <ul>
+/// <li> 00: Bits [31:0] of the source are copied to bits [63:32] of the
+/// returned vector. </li>
+/// <li> 01: Bits [63:32] of the source are copied to bits [63:32] of the
+/// returned vector. </li>
+/// <li> 10: Bits [95:64] of the source are copied to bits [63:32] of the
+/// returned vector. </li>
+/// <li> 11: Bits [127:96] of the source are copied to bits [63:32] of the
+/// returned vector. </li>
+/// </ul>
+/// </li>
+/// <li> Bits [65:64]:
+/// <ul>
+/// <li> 00: Bits [31:0] of the source are copied to bits [95:64] of the
+/// returned vector. </li>
+/// <li> 01: Bits [63:32] of the source are copied to bits [95:64] of the
+/// returned vector. </li>
+/// <li> 10: Bits [95:64] of the source are copied to bits [95:64] of the
+/// returned vector. </li>
+/// <li> 11: Bits [127:96] of the source are copied to bits [95:64] of the
+/// returned vector. </li>
+/// </ul>
+/// </li>
+/// <li> Bits [97:96]:
+/// <ul>
+/// <li> 00: Bits [31:0] of the source are copied to bits [127:96] of the
+/// returned vector. </li>
+/// <li> 01: Bits [63:32] of the source are copied to bits [127:96] of the
+/// returned vector. </li>
+/// <li> 10: Bits [95:64] of the source are copied to bits [127:96] of the
+/// returned vector. </li>
+/// <li> 11: Bits [127:96] of the source are copied to bits [127:96] of the
+/// returned vector. </li>
+/// <li> 11: Bits [127:96] of the source are copied to bits [95:64] of the
+/// returned vector. </li>
+/// </ul>
+/// </li>
+/// </ul>
/// \returns A 128-bit vector of [4 x float] containing the copied values.
static __inline __m128 __DEFAULT_FN_ATTRS
_mm_permutevar_ps(__m128 __a, __m128i __c)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction.
+/// This intrinsic corresponds to the \c VPERMILPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
/// __m128d _mm_permute_pd(__m128d A, const int C);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction.
+/// This intrinsic corresponds to the \c VPERMILPD instruction.
///
/// \param A
/// A 128-bit vector of [2 x double].
/// \param C
+/// \parblock
/// An immediate integer operand specifying how the values are to be copied.
/// Bit [0]:
/// 0: Bits [63:0] of the source are copied to bits [63:0] of the
/// returned vector.
/// 1: Bits [127:64] of the source are copied to bits [127:64] of the
/// returned vector.
+/// \endparblock
/// \returns A 128-bit vector of [2 x double] containing the copied values.
#define _mm_permute_pd(A, C) __extension__ ({ \
(__m128d)__builtin_shufflevector((__v2df)(__m128d)(A), \
/// __m256d _mm256_permute_pd(__m256d A, const int C);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction.
+/// This intrinsic corresponds to the \c VPERMILPD instruction.
///
/// \param A
/// A 256-bit vector of [4 x double].
/// __m128 _mm_permute_ps(__m128 A, const int C);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction.
+/// This intrinsic corresponds to the \c VPERMILPS instruction.
///
/// \param A
/// A 128-bit vector of [4 x float].
/// __m256 _mm256_permute_ps(__m256 A, const int C);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction.
+/// This intrinsic corresponds to the \c VPERMILPS instruction.
///
/// \param A
/// A 256-bit vector of [8 x float].
/// __m256d _mm256_permute2f128_pd(__m256d V1, __m256d V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction.
+/// This intrinsic corresponds to the \c VPERM2F128 instruction.
///
/// \param V1
/// A 256-bit vector of [4 x double].
/// __m256 _mm256_permute2f128_ps(__m256 V1, __m256 V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction.
+/// This intrinsic corresponds to the \c VPERM2F128 instruction.
///
/// \param V1
/// A 256-bit vector of [8 x float].
/// __m256i _mm256_permute2f128_si256(__m256i V1, __m256i V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction.
+/// This intrinsic corresponds to the \c VPERM2F128 instruction.
///
/// \param V1
/// A 256-bit integer vector.
/// __m256d _mm256_blend_pd(__m256d V1, __m256d V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VBLENDPD / BLENDPD instruction.
+/// This intrinsic corresponds to the \c VBLENDPD instruction.
///
/// \param V1
/// A 256-bit vector of [4 x double].
/// __m256 _mm256_blend_ps(__m256 V1, __m256 V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VBLENDPS / BLENDPS instruction.
+/// This intrinsic corresponds to the \c VBLENDPS instruction.
///
/// \param V1
/// A 256-bit vector of [8 x float].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VBLENDVPD / BLENDVPD instruction.
+/// This intrinsic corresponds to the \c VBLENDVPD instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double].
/// to the most significant bit of a copied value. When a mask bit is 0, the
/// corresponding 64-bit element in operand __a is copied to the same
/// position in the destination. When a mask bit is 1, the corresponding
-/// 64-bit element in operand __b is copied to the same position in the
+/// 64-bit element in operand \a __b is copied to the same position in the
/// destination.
/// \returns A 256-bit vector of [4 x double] containing the copied values.
static __inline __m256d __DEFAULT_FN_ATTRS
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VBLENDVPS / BLENDVPS instruction.
+/// This intrinsic corresponds to the \c VBLENDVPS instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
/// __m256 _mm256_dp_ps(__m256 V1, __m256 V2, const int M);
/// \endcode
///
-/// This intrinsic corresponds to the \c VDPPS / DPPS instruction.
+/// This intrinsic corresponds to the \c VDPPS instruction.
///
/// \param V1
/// A vector of [8 x float] values, treated as two [4 x float] vectors.
/// __m256 _mm256_shuffle_ps(__m256 a, __m256 b, const int mask);
/// \endcode
///
-/// This intrinsic corresponds to the \c VSHUFPS / SHUFPS instruction.
+/// This intrinsic corresponds to the \c VSHUFPS instruction.
///
/// \param a
/// A 256-bit vector of [8 x float]. The four selected elements in this
/// destination, according to the bits specified in the immediate operand.
/// \param mask
/// An immediate value containing an 8-bit value specifying which elements to
-/// copy from a and b. Bits [3:0] specify the values copied from operand a.
+/// copy from a and b.
+/// Bits [3:0] specify the values copied from operand a.
/// Bits [7:4] specify the values copied from operand b.
/// The destinations within the 256-bit destination are assigned values as
/// follows, according to the bit value assignments described below:
/// __m256d _mm256_shuffle_pd(__m256d a, __m256d b, const int mask);
/// \endcode
///
-/// This intrinsic corresponds to the \c VSHUFPD / SHUFPD instruction.
+/// This intrinsic corresponds to the \c VSHUFPD instruction.
///
/// \param a
/// A 256-bit vector of [4 x double].
/// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPPD / CMPPD instruction.
+/// This intrinsic corresponds to the \c VCMPPD instruction.
///
/// \param a
/// A 128-bit vector of [2 x double].
/// \param b
/// A 128-bit vector of [2 x double].
/// \param c
+/// \parblock
/// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use:
+///
/// 00h, 08h, 10h, 18h: Equal
+///
/// 01h, 09h, 11h, 19h: Less than
+///
/// 02h, 0Ah, 12h, 1Ah: Less than or equal / Greater than or equal (swapped
/// operands)
+///
/// 03h, 0Bh, 13h, 1Bh: Unordered
+///
/// 04h, 0Ch, 14h, 1Ch: Not equal
+///
/// 05h, 0Dh, 15h, 1Dh: Not less than / Not greater than (swapped operands)
+///
/// 06h, 0Eh, 16h, 1Eh: Not less than or equal / Not greater than or equal
/// (swapped operands)
+///
/// 07h, 0Fh, 17h, 1Fh: Ordered
+/// \endparblock
/// \returns A 128-bit vector of [2 x double] containing the comparison results.
#define _mm_cmp_pd(a, b, c) __extension__ ({ \
(__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \
/// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPPS / CMPPS instruction.
+/// This intrinsic corresponds to the \c VCMPPS instruction.
///
/// \param a
/// A 128-bit vector of [4 x float].
/// __m256d _mm256_cmp_pd(__m256d a, __m256d b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPPD / CMPPD instruction.
+/// This intrinsic corresponds to the \c VCMPPD instruction.
///
/// \param a
/// A 256-bit vector of [4 x double].
/// __m256 _mm256_cmp_ps(__m256 a, __m256 b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPPS / CMPPS instruction.
+/// This intrinsic corresponds to the \c VCMPPS instruction.
///
/// \param a
/// A 256-bit vector of [8 x float].
/// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPSD / CMPSD instruction.
+/// This intrinsic corresponds to the \c VCMPSD instruction.
///
/// \param a
/// A 128-bit vector of [2 x double].
/// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the \c VCMPSS / CMPSS instruction.
+/// This intrinsic corresponds to the \c VCMPSS instruction.
///
/// \param a
/// A 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE /
-/// EXTRACTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
///
/// \param __a
/// A 256-bit vector of [8 x i32].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE /
-/// EXTRACTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
///
/// \param __a
/// A 256-bit integer vector of [16 x i16].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE /
-/// EXTRACTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
///
/// \param __a
/// A 256-bit integer vector of [32 x i8].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE /
-/// EXTRACTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
///
/// \param __a
/// A 256-bit integer vector of [4 x i64].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE /
-/// INSERTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
///
/// \param __a
/// A vector of [8 x i32] to be used by the insert operation.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE /
-/// INSERTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
///
/// \param __a
/// A vector of [16 x i16] to be used by the insert operation.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE /
-/// INSERTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
///
/// \param __a
/// A vector of [32 x i8] to be used by the insert operation.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE /
-/// INSERTF128+COMPOSITE instruction.
+/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
///
/// \param __a
/// A vector of [4 x i64] to be used by the insert operation.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VCVTDQ2PD / CVTDQ2PD instruction.
+/// This intrinsic corresponds to the \c VCVTDQ2PD instruction.
///
/// \param __a
/// A 128-bit integer vector of [4 x i32].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VCVTDQ2PS / CVTDQ2PS instruction.
+/// This intrinsic corresponds to the \c VCVTDQ2PS instruction.
///
/// \param __a
/// A 256-bit integer vector.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VCVTPD2PS / CVTPD2PS instruction.
+/// This intrinsic corresponds to the \c VCVTPD2PS instruction.
///
/// \param __a
/// A 256-bit vector of [4 x double].
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the \c VCVTPS2DQ / CVTPS2DQ instruction.
+/// This intrinsic corresponds to the \c VCVTPS2DQ instruction.
///
/// \param __a
/// A 256-bit vector of [8 x float].
projects / clang / commitdiff