(__v2df)_mm_setzero_pd(), \
(__mmask8)(U), (int)(R)); })
-static __inline __m512i
+static __inline __m512i
__DEFAULT_FN_ATTRS
_mm512_max_epi32(__m512i __A, __m512i __B)
{
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_rsqrt14_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_rsqrt14_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rsqrt14ss_mask ((__v4sf) __A,
(__v4sf) __B,
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_rsqrt14_ss (__mmask8 __U, __m128 __A, __m128 __B)
+_mm_maskz_rsqrt14_ss (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rsqrt14ss_mask ((__v4sf) __A,
(__v4sf) __B,
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_rsqrt14_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_rsqrt14_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rsqrt14sd_mask ( (__v2df) __A,
(__v2df) __B,
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_rsqrt14_sd (__mmask8 __U, __m128d __A, __m128d __B)
+_mm_maskz_rsqrt14_sd (__mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rsqrt14sd_mask ( (__v2df) __A,
(__v2df) __B,
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_rcp14_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_rcp14_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rcp14ss_mask ((__v4sf) __A,
(__v4sf) __B,
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_rcp14_ss (__mmask8 __U, __m128 __A, __m128 __B)
+_mm_maskz_rcp14_ss (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_rcp14ss_mask ((__v4sf) __A,
(__v4sf) __B,
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_rcp14_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_rcp14_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rcp14sd_mask ( (__v2df) __A,
(__v2df) __B,
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_rcp14_sd (__mmask8 __U, __m128d __A, __m128d __B)
+_mm_maskz_rcp14_sd (__mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_rcp14sd_mask ( (__v2df) __A,
(__v2df) __B,
(__v16si)(__m512i)(B), (int)(I), \
(__v16si)_mm512_setzero_si512(), \
(__mmask16)-1); })
-
+
#define _mm512_mask_alignr_epi32(W, U, A, B, imm) __extension__ ({\
(__m512i)__builtin_ia32_alignd512_mask((__v16si)(__m512i)(A), \
(__v16si)(__m512i)(B), (int)(imm), \
_mm512_cvtepi32_pd(__m256i __A)
{
return (__m512d) __builtin_ia32_cvtdq2pd512_mask ((__v8si) __A,
- (__v8df)
+ (__v8df)
_mm512_setzero_pd (),
(__mmask8) -1);
}
_mm512_cvtph_ps(__m256i __A)
{
return (__m512) __builtin_ia32_vcvtph2ps512_mask ((__v16hi) __A,
- (__v16sf)
+ (__v16sf)
_mm512_setzero_ps (),
(__mmask16) -1,
_MM_FROUND_CUR_DIRECTION);
(__mmask16) __U,
_MM_FROUND_CUR_DIRECTION);
}
-
+
#define _mm512_cvt_roundpd_epi32(A, R) __extension__ ({ \
(__m256i)__builtin_ia32_cvtpd2dq512_mask((__v8df)(__m512d)(A), \
(__v8si)_mm256_setzero_si256(), \
(__mmask16)-1, (int)(R)); })
static __inline__ __m512i __DEFAULT_FN_ATTRS
-_mm512_cvtps_epu32 ( __m512 __A)
+_mm512_cvtps_epu32 ( __m512 __A)
{
return (__m512i) __builtin_ia32_cvtps2udq512_mask ((__v16sf) __A,\
(__v16si)\
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_getexp_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_getexp_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_getexpsd128_round_mask ( (__v2df) __A,
(__v2df) __B,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_getexp_sd (__mmask8 __U, __m128d __A, __m128d __B)
+_mm_maskz_getexp_sd (__mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_getexpsd128_round_mask ( (__v2df) __A,
(__v2df) __B,
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_getexp_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_getexp_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_getexpss128_round_mask ((__v4sf) __A,
(__v4sf) __B,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_getexp_ss (__mmask8 __U, __m128 __A, __m128 __B)
+_mm_maskz_getexp_ss (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_getexpss128_round_mask ((__v4sf) __A,
(__v4sf) __B,
}
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_scalef_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_scalef_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_scalefsd_round_mask ( (__v2df) __A,
(__v2df) __B,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_scalef_sd (__mmask8 __U, __m128d __A, __m128d __B)
+_mm_maskz_scalef_sd (__mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_scalefsd_round_mask ( (__v2df) __A,
(__v2df) __B,
}
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_scalef_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_scalef_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_scalefss_round_mask ( (__v4sf) __A,
(__v4sf) __B,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_scalef_ss (__mmask8 __U, __m128 __A, __m128 __B)
+_mm_maskz_scalef_ss (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_scalefss_round_mask ( (__v4sf) __A,
(__v4sf) __B,
(__mmask8)-1, (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_sqrt_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_sqrt_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_sqrtsd_round_mask ( (__v2df) __B,
(__v2df) __A,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_sqrt_sd (__mmask8 __U, __m128d __A, __m128d __B)
+_mm_maskz_sqrt_sd (__mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_sqrtsd_round_mask ( (__v2df) __B,
(__v2df) __A,
(__mmask8)-1, (int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_sqrt_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_sqrt_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_sqrtss_round_mask ( (__v4sf) __B,
(__v4sf) __A,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_sqrt_ss (__mmask8 __U, __m128 __A, __m128 __B)
+_mm_maskz_sqrt_ss (__mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_sqrtss_round_mask ( (__v4sf) __A,
(__v4sf) __B,
(__v8di)(__m512i)(v1), (int)(scale)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_fmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_fmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __A,
(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_fmadd_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
+_mm_maskz_fmadd_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
{
return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __A,
(__v4sf) __B,
_MM_FROUND_CUR_DIRECTION); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask3_fmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
+_mm_mask3_fmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
(__v4sf) __X,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_fmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_fmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_vfmaddss3_mask ((__v4sf) __A,
-(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_fmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
+_mm_maskz_fmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
{
return (__m128) __builtin_ia32_vfmaddss3_maskz ((__v4sf) __A,
(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask3_fmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
+_mm_mask3_fmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 ((__v4sf) __W,
(__v4sf) __X,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_fnmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_fnmadd_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_vfmaddss3_mask (-(__v4sf) __A,
(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_fnmadd_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
+_mm_maskz_fnmadd_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
{
return (__m128) __builtin_ia32_vfmaddss3_maskz (-(__v4sf) __A,
(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask3_fnmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
+_mm_mask3_fnmadd_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 (-(__v4sf) __W,
(__v4sf) __X,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask_fnmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
+_mm_mask_fnmsub_ss (__m128 __W, __mmask8 __U, __m128 __A, __m128 __B)
{
return (__m128) __builtin_ia32_vfmaddss3_mask (-(__v4sf) __A,
-(__v4sf) __B,
(int)(R)); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_maskz_fnmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
+_mm_maskz_fnmsub_ss (__mmask8 __U, __m128 __A, __m128 __B, __m128 __C)
{
return (__m128) __builtin_ia32_vfmaddss3_maskz (-(__v4sf) __A,
(__v4sf) __B,
_MM_FROUND_CUR_DIRECTION); })
static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_mask3_fnmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
+_mm_mask3_fnmsub_ss (__m128 __W, __m128 __X, __m128 __Y, __mmask8 __U)
{
return (__m128) __builtin_ia32_vfmaddss3_mask3 (-(__v4sf) __W,
(__v4sf) __X,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_fmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_fmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __A,
(__v2df) __B,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_fmadd_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
+_mm_maskz_fmadd_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
{
return (__m128d) __builtin_ia32_vfmaddsd3_maskz ( (__v2df) __A,
(__v2df) __B,
_MM_FROUND_CUR_DIRECTION); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask3_fmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
+_mm_mask3_fmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
(__v2df) __X,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_fmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_fmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask ( (__v2df) __A,
-(__v2df) __B,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_fmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
+_mm_maskz_fmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
{
return (__m128d) __builtin_ia32_vfmaddsd3_maskz ( (__v2df) __A,
(__v2df) __B,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask3_fmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
+_mm_mask3_fmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 ((__v2df) __W,
(__v2df) __X,
(__mmask8)(U), (int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_fnmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_fnmadd_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask ( -(__v2df) __A,
(__v2df) __B,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_fnmadd_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
+_mm_maskz_fnmadd_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
{
return (__m128d) __builtin_ia32_vfmaddsd3_maskz ( -(__v2df) __A,
(__v2df) __B,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask3_fnmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
+_mm_mask3_fnmadd_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 (-(__v2df) __W,
(__v2df) __X,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask_fnmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
+_mm_mask_fnmsub_sd (__m128d __W, __mmask8 __U, __m128d __A, __m128d __B)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask ( -(__v2df) __A,
-(__v2df) __B,
(int)(R)); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_maskz_fnmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
+_mm_maskz_fnmsub_sd (__mmask8 __U, __m128d __A, __m128d __B, __m128d __C)
{
return (__m128d) __builtin_ia32_vfmaddsd3_maskz ( -(__v2df) __A,
(__v2df) __B,
_MM_FROUND_CUR_DIRECTION); })
static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_mask3_fnmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
+_mm_mask3_fnmsub_sd (__m128d __W, __m128d __X, __m128d __Y, __mmask8 __U)
{
return (__m128d) __builtin_ia32_vfmaddsd3_mask3 (-(__v2df) (__W),
(__v2df) __X,
#define _mm512_setr_epi32(e0,e1,e2,e3,e4,e5,e6,e7, \
e8,e9,e10,e11,e12,e13,e14,e15) \
_mm512_set_epi32(e15,e14,e13,e12,e11,e10,e9,e8,e7,e6,e5,e4,e3,e2,e1,e0)
-
+
static __inline__ __m512i __DEFAULT_FN_ATTRS
_mm512_set_epi64 (long long __A, long long __B, long long __C,
long long __D, long long __E, long long __F,
__attribute__((__always_inline__, __nodebug__, __target__("sse3")))
/// \brief Loads data from an unaligned memory location to elements in a 128-bit
-/// vector. If the address of the data is not 16-byte aligned, the
-/// instruction may read two adjacent aligned blocks of memory to retrieve
-/// the requested data.
+/// vector. If the address of the data is not 16-byte aligned, the
+/// instruction may read two adjacent aligned blocks of memory to retrieve
+/// the requested data.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VHADDPS instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x float] containing one of the source operands.
-/// The horizontal sums of the values are stored in the lower bits of the
+/// A 128-bit vector of [4 x float] containing one of the source operands.
+/// The horizontal sums of the values are stored in the lower bits of the
/// destination.
/// \param __b
-/// A 128-bit vector of [4 x float] containing one of the source operands.
-/// The horizontal sums of the values are stored in the upper bits of the
+/// A 128-bit vector of [4 x float] containing one of the source operands.
+/// The horizontal sums of the values are stored in the upper bits of the
/// destination.
-/// \returns A 128-bit vector of [4 x float] containing the horizontal sums of
+/// \returns A 128-bit vector of [4 x float] containing the horizontal sums of
/// both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_hadd_ps(__m128 __a, __m128 __b)
/// This intrinsic corresponds to the \c VHSUBPS instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x float] containing one of the source operands.
-/// The horizontal differences between the values are stored in the lower
+/// A 128-bit vector of [4 x float] containing one of the source operands.
+/// The horizontal differences between the values are stored in the lower
/// bits of the destination.
/// \param __b
-/// A 128-bit vector of [4 x float] containing one of the source operands.
-/// The horizontal differences between the values are stored in the upper
+/// A 128-bit vector of [4 x float] containing one of the source operands.
+/// The horizontal differences between the values are stored in the upper
/// bits of the destination.
-/// \returns A 128-bit vector of [4 x float] containing the horizontal
+/// \returns A 128-bit vector of [4 x float] containing the horizontal
/// differences of both operands.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_hsub_ps(__m128 __a, __m128 __b)
/// A 128-bit vector of [2 x double] containing the left source operand.
/// \param __b
/// A 128-bit vector of [2 x double] containing the right source operand.
-/// \returns A 128-bit vector of [2 x double] containing the alternating sums
+/// \returns A 128-bit vector of [2 x double] containing the alternating sums
/// and differences of both operands.
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_addsub_pd(__m128d __a, __m128d __b)
return __builtin_ia32_addsubpd((__v2df)__a, (__v2df)__b);
}
-/// \brief Horizontally adds the pairs of values contained in two 128-bit
+/// \brief Horizontally adds the pairs of values contained in two 128-bit
/// vectors of [2 x double].
///
/// \headerfile <x86intrin.h>
/// This intrinsic corresponds to the \c VHADDPD instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double] containing one of the source operands.
-/// The horizontal sum of the values is stored in the lower bits of the
+/// A 128-bit vector of [2 x double] containing one of the source operands.
+/// The horizontal sum of the values is stored in the lower bits of the
/// destination.
/// \param __b
-/// A 128-bit vector of [2 x double] containing one of the source operands.
-/// The horizontal sum of the values is stored in the upper bits of the
+/// A 128-bit vector of [2 x double] containing one of the source operands.
+/// The horizontal sum of the values is stored in the upper bits of the
/// destination.
/// \returns A 128-bit vector of [2 x double] containing the horizontal sums of
/// both operands.
/// This intrinsic corresponds to the \c VHSUBPD instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double] containing one of the source operands.
+/// A 128-bit vector of [2 x double] containing one of the source operands.
/// The horizontal difference of the values is stored in the lower bits of
/// the destination.
/// \param __b
-/// A 128-bit vector of [2 x double] containing one of the source operands.
+/// A 128-bit vector of [2 x double] containing one of the source operands.
/// The horizontal difference of the values is stored in the upper bits of
/// the destination.
-/// \returns A 128-bit vector of [2 x double] containing the horizontal
+/// \returns A 128-bit vector of [2 x double] containing the horizontal
/// differences of both operands.
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_hsub_pd(__m128d __a, __m128d __b)
///
/// \headerfile <x86intrin.h>
///
-/// \code
+/// \code
/// __m128d _mm_loaddup_pd(double const * dp);
-/// \endcode
+/// \endcode
///
/// This intrinsic corresponds to the \c VMOVDDUP instruction.
///
/// \param dp
/// A pointer to a double-precision value to be moved and duplicated.
-/// \returns A 128-bit vector of [2 x double] containing the moved and
+/// \returns A 128-bit vector of [2 x double] containing the moved and
/// duplicated values.
#define _mm_loaddup_pd(dp) _mm_load1_pd(dp)
-/// \brief Moves and duplicates the double-precision value in the lower bits of
+/// \brief Moves and duplicates the double-precision value in the lower bits of
/// a 128-bit vector of [2 x double] to double-precision values stored in a
/// 128-bit vector of [2 x double].
///
/// This intrinsic corresponds to the \c VMOVDDUP instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double]. Bits [63:0] are written to bits
+/// A 128-bit vector of [2 x double]. Bits [63:0] are written to bits
/// [127:64] and [63:0] of the destination.
-/// \returns A 128-bit vector of [2 x double] containing the moved and
+/// \returns A 128-bit vector of [2 x double] containing the moved and
/// duplicated values.
static __inline__ __m128d __DEFAULT_FN_ATTRS
_mm_movedup_pd(__m128d __a)
#define _MM_GET_DENORMALS_ZERO_MODE() (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)
#define _MM_SET_DENORMALS_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x)))
-/// \brief Establishes a linear address memory range to be monitored and puts
-/// the processor in the monitor event pending state. Data stored in the
+/// \brief Establishes a linear address memory range to be monitored and puts
+/// the processor in the monitor event pending state. Data stored in the
/// monitored address range causes the processor to exit the pending state.
///
/// \headerfile <x86intrin.h>
/// This intrinsic corresponds to the \c MONITOR instruction.
///
/// \param __p
-/// The memory range to be monitored. The size of the range is determined by
+/// The memory range to be monitored. The size of the range is determined by
/// CPUID function 0000_0005h.
/// \param __extensions
/// Optional extensions for the monitoring state.
/// This intrinsic corresponds to the \c MWAIT instruction.
///
/// \param __extensions
-/// Optional extensions for the monitoring state, which may vary by
+/// Optional extensions for the monitoring state, which may vary by
/// processor.
/// \param __hints
/// Optional hints for the monitoring state, which may vary by processor.