maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[DOXYGEN] Updated instruction names corresponding to avxintrin.h intrinsics. 

Documentation for some of the avxintrin.h's intrinsics errorneously said that
non VEX-prefixed instructions could be generated. This was fixed.

I tried several different solutions to achieve pretty printing of unordered lists (nested and non-nested) in param sections in doxygen. 

llvm-svn: 287990
This commit is contained in:
Ekaterina Romanova 2016-11-26 19:38:19 +00:00
parent 3a481cf0bd
commit 4c77e8940e
1 changed files with 188 additions and 166 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

350
clang/lib/Headers/avxintrin.h
View File

@ -57,7 +57,7 @@ typedef long long __m256i __attribute__((__vector_size__(32)));
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VADDPD / ADDPD instruction. /// This intrinsic corresponds to the \c VADDPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -75,7 +75,7 @@ _mm256_add_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VADDPS / ADDPS instruction. /// This intrinsic corresponds to the \c VADDPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -93,7 +93,7 @@ _mm256_add_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VSUBPD / SUBPD instruction. /// This intrinsic corresponds to the \c VSUBPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing the minuend. /// A 256-bit vector of [4 x double] containing the minuend.
@ -111,7 +111,7 @@ _mm256_sub_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VSUBPS / SUBPS instruction. /// This intrinsic corresponds to the \c VSUBPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing the minuend. /// A 256-bit vector of [8 x float] containing the minuend.
@ -130,7 +130,7 @@ _mm256_sub_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VADDSUBPD / ADDSUBPD instruction. /// This intrinsic corresponds to the \c VADDSUBPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing the left source operand. /// A 256-bit vector of [4 x double] containing the left source operand.
@ -149,7 +149,7 @@ _mm256_addsub_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VADDSUBPS / ADDSUBPS instruction. /// This intrinsic corresponds to the \c VADDSUBPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing the left source operand. /// A 256-bit vector of [8 x float] containing the left source operand.
@ -167,7 +167,7 @@ _mm256_addsub_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VDIVPD / DIVPD instruction. /// This intrinsic corresponds to the \c VDIVPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing the dividend. /// A 256-bit vector of [4 x double] containing the dividend.
@ -185,7 +185,7 @@ _mm256_div_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VDIVPS / DIVPS instruction. /// This intrinsic corresponds to the \c VDIVPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing the dividend. /// A 256-bit vector of [8 x float] containing the dividend.
@ -204,7 +204,7 @@ _mm256_div_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMAXPD / MAXPD instruction. /// This intrinsic corresponds to the \c VMAXPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands. /// A 256-bit vector of [4 x double] containing one of the operands.
@ -223,7 +223,7 @@ _mm256_max_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMAXPS / MAXPS instruction. /// This intrinsic corresponds to the \c VMAXPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands. /// A 256-bit vector of [8 x float] containing one of the operands.
@ -242,7 +242,7 @@ _mm256_max_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMINPD / MINPD instruction. /// This intrinsic corresponds to the \c VMINPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands. /// A 256-bit vector of [4 x double] containing one of the operands.
@ -261,7 +261,7 @@ _mm256_min_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMINPS / MINPS instruction. /// This intrinsic corresponds to the \c VMINPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands. /// A 256-bit vector of [8 x float] containing one of the operands.
@ -279,7 +279,7 @@ _mm256_min_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMULPD / MULPD instruction. /// This intrinsic corresponds to the \c VMULPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the operands. /// A 256-bit vector of [4 x double] containing one of the operands.
@ -297,7 +297,7 @@ _mm256_mul_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VMULPS / MULPS instruction. /// This intrinsic corresponds to the \c VMULPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the operands. /// A 256-bit vector of [8 x float] containing one of the operands.
@ -316,7 +316,7 @@ _mm256_mul_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VSQRTPD / SQRTPD instruction. /// This intrinsic corresponds to the \c VSQRTPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -333,7 +333,7 @@ _mm256_sqrt_pd(__m256d __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VSQRTPS / SQRTPS instruction. /// This intrinsic corresponds to the \c VSQRTPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -350,7 +350,7 @@ _mm256_sqrt_ps(__m256 __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VRSQRTPS / RSQRTPS instruction. /// This intrinsic corresponds to the \c VRSQRTPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -367,7 +367,7 @@ _mm256_rsqrt_ps(__m256 __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VRCPPS / RCPPS instruction. /// This intrinsic corresponds to the \c VRCPPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -389,23 +389,23 @@ _mm256_rcp_ps(__m256 __a)
/// __m256d _mm256_round_pd(__m256d V, const int M); /// __m256d _mm256_round_pd(__m256d V, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction. /// This intrinsic corresponds to the \c VROUNDPD instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
/// \param M /// \param M
/// An integer value that specifies the rounding operation. /// An integer value that specifies the rounding operation. \n
/// Bits [7:4] are reserved. /// Bits [7:4] are reserved. \n
/// Bit [3] is a precision exception value: /// Bit [3] is a precision exception value: \n
/// 0: A normal PE exception is used. /// 0: A normal PE exception is used. \n
/// 1: The PE field is not updated. /// 1: The PE field is not updated. \n
/// Bit [2] is the rounding control source: /// Bit [2] is the rounding control source: \n
/// 0: Use bits [1:0] of M. /// 0: Use bits [1:0] of M. \n
/// 1: Use the current MXCSR setting. /// 1: Use the current MXCSR setting. \n
/// Bits [1:0] contain the rounding control definition: /// Bits [1:0] contain the rounding control definition: \n
/// 00: Nearest. /// 00: Nearest. \n
/// 01: Downward (toward negative infinity). /// 01: Downward (toward negative infinity). \n
/// 10: Upward (toward positive infinity). /// 10: Upward (toward positive infinity). \n
/// 11: Truncated. /// 11: Truncated.
/// \returns A 256-bit vector of [4 x double] containing the rounded values. /// \returns A 256-bit vector of [4 x double] containing the rounded values.
#define _mm256_round_pd(V, M) __extension__ ({ \ #define _mm256_round_pd(V, M) __extension__ ({ \
@ -421,24 +421,24 @@ _mm256_rcp_ps(__m256 __a)
/// __m256 _mm256_round_ps(__m256 V, const int M); /// __m256 _mm256_round_ps(__m256 V, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction. /// This intrinsic corresponds to the \c VROUNDPS instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
/// \param M /// \param M
/// An integer value that specifies the rounding operation. /// An integer value that specifies the rounding operation. \n
/// Bits [7:4] are reserved. /// Bits [7:4] are reserved. \n
/// Bit [3] is a precision exception value: /// Bit [3] is a precision exception value: \n
/// 0: A normal PE exception is used. /// 0: A normal PE exception is used. \n
/// 1: The PE field is not updated. /// 1: The PE field is not updated. \n
/// Bit [2] is the rounding control source: /// Bit [2] is the rounding control source: \n
/// 0: Use bits [1:0] of M. /// 0: Use bits [1:0] of M. \n
/// 1: Use the current MXCSR setting. /// 1: Use the current MXCSR setting. \n
/// Bits [1:0] contain the rounding control definition: /// Bits [1:0] contain the rounding control definition: \n
/// 00: Nearest. /// 00: Nearest. \n
/// 01: Downward (toward negative infinity). /// 01: Downward (toward negative infinity). \n
/// 10: Upward (toward positive infinity). /// 10: Upward (toward positive infinity). \n
/// 11: Truncated. /// 11: Truncated. \n
/// \returns A 256-bit vector of [8 x float] containing the rounded values. /// \returns A 256-bit vector of [8 x float] containing the rounded values.
#define _mm256_round_ps(V, M) __extension__ ({ \ #define _mm256_round_ps(V, M) __extension__ ({ \
(__m256)__builtin_ia32_roundps256((__v8sf)(__m256)(V), (M)); }) (__m256)__builtin_ia32_roundps256((__v8sf)(__m256)(V), (M)); })
@ -453,7 +453,7 @@ _mm256_rcp_ps(__m256 __a)
/// __m256d _mm256_ceil_pd(__m256d V); /// __m256d _mm256_ceil_pd(__m256d V);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction. /// This intrinsic corresponds to the \c VROUNDPD instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -470,7 +470,7 @@ _mm256_rcp_ps(__m256 __a)
/// __m256d _mm256_floor_pd(__m256d V); /// __m256d _mm256_floor_pd(__m256d V);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPD / ROUNDPD instruction. /// This intrinsic corresponds to the \c VROUNDPD instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -488,7 +488,7 @@ _mm256_rcp_ps(__m256 __a)
/// __m256 _mm256_ceil_ps(__m256 V); /// __m256 _mm256_ceil_ps(__m256 V);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction. /// This intrinsic corresponds to the \c VROUNDPS instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -505,7 +505,7 @@ _mm256_rcp_ps(__m256 __a)
/// __m256 _mm256_floor_ps(__m256 V); /// __m256 _mm256_floor_ps(__m256 V);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VROUNDPS / ROUNDPS instruction. /// This intrinsic corresponds to the \c VROUNDPS instruction.
/// ///
/// \param V /// \param V
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -517,7 +517,7 @@ _mm256_rcp_ps(__m256 __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VANDPD / ANDPD instruction. /// This intrinsic corresponds to the \c VANDPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -535,7 +535,7 @@ _mm256_and_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VANDPS / ANDPS instruction. /// This intrinsic corresponds to the \c VANDPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -554,7 +554,7 @@ _mm256_and_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VANDNPD / ANDNPD instruction. /// This intrinsic corresponds to the \c VANDNPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing the left source operand. The /// A 256-bit vector of [4 x double] containing the left source operand. The
@ -575,7 +575,7 @@ _mm256_andnot_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VANDNPS / ANDNPS instruction. /// This intrinsic corresponds to the \c VANDNPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing the left source operand. The /// A 256-bit vector of [8 x float] containing the left source operand. The
@ -595,7 +595,7 @@ _mm256_andnot_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VORPD / ORPD instruction. /// This intrinsic corresponds to the \c VORPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -613,7 +613,7 @@ _mm256_or_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VORPS / ORPS instruction. /// This intrinsic corresponds to the \c VORPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -631,7 +631,7 @@ _mm256_or_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VXORPD / XORPD instruction. /// This intrinsic corresponds to the \c VXORPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -649,7 +649,7 @@ _mm256_xor_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VXORPS / XORPS instruction. /// This intrinsic corresponds to the \c VXORPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -669,7 +669,7 @@ _mm256_xor_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VHADDPD / HADDPD instruction. /// This intrinsic corresponds to the \c VHADDPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -692,7 +692,7 @@ _mm256_hadd_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VHADDPS / HADDPS instruction. /// This intrinsic corresponds to the \c VHADDPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -715,7 +715,7 @@ _mm256_hadd_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VHSUBPD / HSUBPD instruction. /// This intrinsic corresponds to the \c VHSUBPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double] containing one of the source operands. /// A 256-bit vector of [4 x double] containing one of the source operands.
@ -738,7 +738,7 @@ _mm256_hsub_pd(__m256d __a, __m256d __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VHSUBPS / HSUBPS instruction. /// This intrinsic corresponds to the \c VHSUBPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float] containing one of the source operands. /// A 256-bit vector of [8 x float] containing one of the source operands.
@ -762,22 +762,22 @@ _mm256_hsub_ps(__m256 __a, __m256 __b)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction. /// This intrinsic corresponds to the \c VPERMILPD instruction.
/// ///
/// \param __a /// \param __a
/// A 128-bit vector of [2 x double]. /// A 128-bit vector of [2 x double].
/// \param __c /// \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. /// copied.
/// Bit [1]: /// \li Bit [1]:
/// 0: Bits [63:0] of the source are copied to bits [63:0] of the /// \li 0: Bits [63:0] of the source are copied to bits [63:0] of the
/// returned vector. /// 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. /// returned vector.
/// Bit [65]: /// \li Bit [65]:
/// 0: Bits [63:0] of the source are copied to bits [127:64] of the /// \li 0: Bits [63:0] of the source are copied to bits [127:64] of the
/// returned vector. /// 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. /// returned vector.
/// \returns A 128-bit vector of [2 x double] containing the copied values. /// \returns A 128-bit vector of [2 x double] containing the copied values.
static __inline __m128d __DEFAULT_FN_ATTRS static __inline __m128d __DEFAULT_FN_ATTRS
@ -791,32 +791,32 @@ _mm_permutevar_pd(__m128d __a, __m128i __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction. /// This intrinsic corresponds to the \c VPERMILPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
/// \param __c /// \param __c
/// A 256-bit integer vector operand specifying how the values are to be /// A 256-bit integer vector operand specifying how the values are to be
/// copied. /// copied. \n
/// Bit [1]: /// Bit [1]: \n
/// 0: Bits [63:0] of the source are copied to bits [63:0] of the /// \li 0: Bits [63:0] of the source are copied to bits [63:0] of the
/// returned vector. /// 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. /// returned vector.
/// Bit [65]: /// Bit [65]: \n
/// 0: Bits [63:0] of the source are copied to bits [127:64] of the /// \li 0: Bits [63:0] of the source are copied to bits [127:64] of the
/// returned vector. /// 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. /// returned vector.
/// Bit [129]: /// Bit [129]: \n
/// 0: Bits [191:128] of the source are copied to bits [191:128] of the /// \li 0: Bits [191:128] of the source are copied to bits [191:128] of the
/// returned vector. /// 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. /// returned vector.
/// Bit [193]: /// Bit [193]: \n
/// 0: Bits [191:128] of the source are copied to bits [255:192] of the /// \li 0: Bits [191:128] of the source are copied to bits [255:192] of the
/// returned vector. /// 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. /// returned vector.
/// \returns A 256-bit vector of [4 x double] containing the copied values. /// \returns A 256-bit vector of [4 x double] containing the copied values.
static __inline __m256d __DEFAULT_FN_ATTRS static __inline __m256d __DEFAULT_FN_ATTRS
@ -830,49 +830,66 @@ _mm256_permutevar_pd(__m256d __a, __m256i __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction. /// This intrinsic corresponds to the \c VPERMILPS instruction.
/// ///
/// \param __a /// \param __a
/// A 128-bit vector of [4 x float]. /// A 128-bit vector of [4 x float].
/// \param __c /// \param __c
/// A 128-bit integer vector operand specifying how the values are to be /// <ul>
/// <li> A 128-bit integer vector operand specifying how the values are to be
/// copied. /// copied.
/// Bits [1:0]: /// </li>
/// 00: Bits [31:0] of the source are copied to bits [31:0] of the /// <li> Bits [1:0]:
/// returned vector. /// <ul>
/// 01: Bits [63:32] of the source are copied to bits [31:0] of the /// <li> 00: Bits [31:0] of the source are copied to bits [31:0] of the
/// returned vector. /// returned vector. </li>
/// 10: Bits [95:64] of the source are copied to bits [31:0] of the /// <li> 01: Bits [63:32] of the source are copied to bits [31:0] of the
/// returned vector. /// returned vector. </li>
/// 11: Bits [127:96] of the source are copied to bits [31:0] of the /// <li> 10: Bits [95:64] of the source are copied to bits [31:0] of the
/// returned vector. /// returned vector. </li>
/// Bits [33:32]: /// <li> 11: Bits [127:96] of the source are copied to bits [31:0] of the
/// 00: Bits [31:0] of the source are copied to bits [63:32] of the /// returned vector. </li>
/// returned vector. /// </ul>
/// 01: Bits [63:32] of the source are copied to bits [63:32] of the /// </li>
/// returned vector. /// <li> Bits [33:32]:
/// 10: Bits [95:64] of the source are copied to bits [63:32] of the /// <ul>
/// returned vector. /// <li> 00: Bits [31:0] of the source are copied to bits [63:32] of the
/// 11: Bits [127:96] of the source are copied to bits [63:32] of the /// returned vector. </li>
/// returned vector. /// <li> 01: Bits [63:32] of the source are copied to bits [63:32] of the
/// Bits [65:64]: /// returned vector. </li>
/// 00: Bits [31:0] of the source are copied to bits [95:64] of the /// <li> 10: Bits [95:64] of the source are copied to bits [63:32] of the
/// returned vector. /// returned vector. </li>
/// 01: Bits [63:32] of the source are copied to bits [95:64] of the /// <li> 11: Bits [127:96] of the source are copied to bits [63:32] of the
/// returned vector. /// returned vector. </li>
/// 10: Bits [95:64] of the source are copied to bits [95:64] of the /// </ul>
/// returned vector. /// </li>
/// 11: Bits [127:96] of the source are copied to bits [95:64] of the /// <li> Bits [65:64]:
/// returned vector. /// <ul>
/// Bits [97:96]: /// <li> 00: Bits [31:0] of the source are copied to bits [95:64] of the
/// 00: Bits [31:0] of the source are copied to bits [127:96] of the /// returned vector. </li>
/// returned vector. /// <li> 01: Bits [63:32] of the source are copied to bits [95:64] of the
/// 01: Bits [63:32] of the source are copied to bits [127:96] of the /// returned vector. </li>
/// returned vector. /// <li> 10: Bits [95:64] of the source are copied to bits [95:64] of the
/// 10: Bits [95:64] of the source are copied to bits [127:96] of the /// returned vector. </li>
/// returned vector. /// <li> 11: Bits [127:96] of the source are copied to bits [95:64] of the
/// 11: Bits [127:96] of the source are copied to bits [127:96] of the /// returned vector. </li>
/// returned vector. /// </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. /// \returns A 128-bit vector of [4 x float] containing the copied values.
static __inline __m128 __DEFAULT_FN_ATTRS static __inline __m128 __DEFAULT_FN_ATTRS
_mm_permutevar_ps(__m128 __a, __m128i __c) _mm_permutevar_ps(__m128 __a, __m128i __c)
@ -885,7 +902,7 @@ _mm_permutevar_ps(__m128 __a, __m128i __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction. /// This intrinsic corresponds to the \c VPERMILPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -980,11 +997,12 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m128d _mm_permute_pd(__m128d A, const int C); /// __m128d _mm_permute_pd(__m128d A, const int C);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction. /// This intrinsic corresponds to the \c VPERMILPD instruction.
/// ///
/// \param A /// \param A
/// A 128-bit vector of [2 x double]. /// A 128-bit vector of [2 x double].
/// \param C /// \param C
/// \parblock
/// An immediate integer operand specifying how the values are to be copied. /// An immediate integer operand specifying how the values are to be copied.
/// Bit [0]: /// Bit [0]:
/// 0: Bits [63:0] of the source are copied to bits [63:0] of the /// 0: Bits [63:0] of the source are copied to bits [63:0] of the
@ -996,6 +1014,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// returned vector. /// returned vector.
/// 1: Bits [127:64] of the source are copied to bits [127:64] of the /// 1: Bits [127:64] of the source are copied to bits [127:64] of the
/// returned vector. /// returned vector.
/// \endparblock
/// \returns A 128-bit vector of [2 x double] containing the copied values. /// \returns A 128-bit vector of [2 x double] containing the copied values.
#define _mm_permute_pd(A, C) __extension__ ({ \ #define _mm_permute_pd(A, C) __extension__ ({ \
(__m128d)__builtin_shufflevector((__v2df)(__m128d)(A), \ (__m128d)__builtin_shufflevector((__v2df)(__m128d)(A), \
@ -1011,7 +1030,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256d _mm256_permute_pd(__m256d A, const int C); /// __m256d _mm256_permute_pd(__m256d A, const int C);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERMILPD / PERMILPD instruction. /// This intrinsic corresponds to the \c VPERMILPD instruction.
/// ///
/// \param A /// \param A
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1055,7 +1074,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m128 _mm_permute_ps(__m128 A, const int C); /// __m128 _mm_permute_ps(__m128 A, const int C);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction. /// This intrinsic corresponds to the \c VPERMILPS instruction.
/// ///
/// \param A /// \param A
/// A 128-bit vector of [4 x float]. /// A 128-bit vector of [4 x float].
@ -1113,7 +1132,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256 _mm256_permute_ps(__m256 A, const int C); /// __m256 _mm256_permute_ps(__m256 A, const int C);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERMILPS / PERMILPS instruction. /// This intrinsic corresponds to the \c VPERMILPS instruction.
/// ///
/// \param A /// \param A
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -1213,7 +1232,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256d _mm256_permute2f128_pd(__m256d V1, __m256d V2, const int M); /// __m256d _mm256_permute2f128_pd(__m256d V1, __m256d V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction. /// This intrinsic corresponds to the \c VPERM2F128 instruction.
/// ///
/// \param V1 /// \param V1
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1254,7 +1273,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256 _mm256_permute2f128_ps(__m256 V1, __m256 V2, const int M); /// __m256 _mm256_permute2f128_ps(__m256 V1, __m256 V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction. /// This intrinsic corresponds to the \c VPERM2F128 instruction.
/// ///
/// \param V1 /// \param V1
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -1295,7 +1314,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256i _mm256_permute2f128_si256(__m256i V1, __m256i V2, const int M); /// __m256i _mm256_permute2f128_si256(__m256i V1, __m256i V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VPERM2F128 / PERM2F128 instruction. /// This intrinsic corresponds to the \c VPERM2F128 instruction.
/// ///
/// \param V1 /// \param V1
/// A 256-bit integer vector. /// A 256-bit integer vector.
@ -1337,7 +1356,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256d _mm256_blend_pd(__m256d V1, __m256d V2, const int M); /// __m256d _mm256_blend_pd(__m256d V1, __m256d V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VBLENDPD / BLENDPD instruction. /// This intrinsic corresponds to the \c VBLENDPD instruction.
/// ///
/// \param V1 /// \param V1
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1369,7 +1388,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// __m256 _mm256_blend_ps(__m256 V1, __m256 V2, const int M); /// __m256 _mm256_blend_ps(__m256 V1, __m256 V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VBLENDPS / BLENDPS instruction. /// This intrinsic corresponds to the \c VBLENDPS instruction.
/// ///
/// \param V1 /// \param V1
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -1401,7 +1420,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VBLENDVPD / BLENDVPD instruction. /// This intrinsic corresponds to the \c VBLENDVPD instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1413,7 +1432,7 @@ _mm256_permutevar_ps(__m256 __a, __m256i __c)
/// to the most significant bit of a copied value. When a mask bit is 0, the /// 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 /// corresponding 64-bit element in operand __a is copied to the same
/// position in the destination. When a mask bit is 1, the corresponding /// 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. /// destination.
/// \returns A 256-bit vector of [4 x double] containing the copied values. /// \returns A 256-bit vector of [4 x double] containing the copied values.
static __inline __m256d __DEFAULT_FN_ATTRS static __inline __m256d __DEFAULT_FN_ATTRS
@ -1429,7 +1448,7 @@ _mm256_blendv_pd(__m256d __a, __m256d __b, __m256d __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VBLENDVPS / BLENDVPS instruction. /// This intrinsic corresponds to the \c VBLENDVPS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -1468,7 +1487,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m256 _mm256_dp_ps(__m256 V1, __m256 V2, const int M); /// __m256 _mm256_dp_ps(__m256 V1, __m256 V2, const int M);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VDPPS / DPPS instruction. /// This intrinsic corresponds to the \c VDPPS instruction.
/// ///
/// \param V1 /// \param V1
/// A vector of [8 x float] values, treated as two [4 x float] vectors. /// A vector of [8 x float] values, treated as two [4 x float] vectors.
@ -1510,7 +1529,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m256 _mm256_shuffle_ps(__m256 a, __m256 b, const int mask); /// __m256 _mm256_shuffle_ps(__m256 a, __m256 b, const int mask);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VSHUFPS / SHUFPS instruction. /// This intrinsic corresponds to the \c VSHUFPS instruction.
/// ///
/// \param a /// \param a
/// A 256-bit vector of [8 x float]. The four selected elements in this /// A 256-bit vector of [8 x float]. The four selected elements in this
@ -1522,7 +1541,8 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// destination, according to the bits specified in the immediate operand. /// destination, according to the bits specified in the immediate operand.
/// \param mask /// \param mask
/// An immediate value containing an 8-bit value specifying which elements to /// 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. /// Bits [7:4] specify the values copied from operand b.
/// The destinations within the 256-bit destination are assigned values as /// The destinations within the 256-bit destination are assigned values as
/// follows, according to the bit value assignments described below: /// follows, according to the bit value assignments described below:
@ -1567,7 +1587,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m256d _mm256_shuffle_pd(__m256d a, __m256d b, const int mask); /// __m256d _mm256_shuffle_pd(__m256d a, __m256d b, const int mask);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VSHUFPD / SHUFPD instruction. /// This intrinsic corresponds to the \c VSHUFPD instruction.
/// ///
/// \param a /// \param a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1647,25 +1667,35 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c); /// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPPD / CMPPD instruction. /// This intrinsic corresponds to the \c VCMPPD instruction.
/// ///
/// \param a /// \param a
/// A 128-bit vector of [2 x double]. /// A 128-bit vector of [2 x double].
/// \param b /// \param b
/// A 128-bit vector of [2 x double]. /// A 128-bit vector of [2 x double].
/// \param c /// \param c
/// \parblock
/// An immediate integer operand, with bits [4:0] specifying which comparison /// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use: /// operation to use:
///
/// 00h, 08h, 10h, 18h: Equal /// 00h, 08h, 10h, 18h: Equal
///
/// 01h, 09h, 11h, 19h: Less than /// 01h, 09h, 11h, 19h: Less than
///
/// 02h, 0Ah, 12h, 1Ah: Less than or equal / Greater than or equal (swapped /// 02h, 0Ah, 12h, 1Ah: Less than or equal / Greater than or equal (swapped
/// operands) /// operands)
///
/// 03h, 0Bh, 13h, 1Bh: Unordered /// 03h, 0Bh, 13h, 1Bh: Unordered
///
/// 04h, 0Ch, 14h, 1Ch: Not equal /// 04h, 0Ch, 14h, 1Ch: Not equal
///
/// 05h, 0Dh, 15h, 1Dh: Not less than / Not greater than (swapped operands) /// 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 /// 06h, 0Eh, 16h, 1Eh: Not less than or equal / Not greater than or equal
/// (swapped operands) /// (swapped operands)
///
/// 07h, 0Fh, 17h, 1Fh: Ordered /// 07h, 0Fh, 17h, 1Fh: Ordered
/// \endparblock
/// \returns A 128-bit vector of [2 x double] containing the comparison results. /// \returns A 128-bit vector of [2 x double] containing the comparison results.
#define _mm_cmp_pd(a, b, c) __extension__ ({ \ #define _mm_cmp_pd(a, b, c) __extension__ ({ \
(__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \ (__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \
@ -1683,7 +1713,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c); /// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPPS / CMPPS instruction. /// This intrinsic corresponds to the \c VCMPPS instruction.
/// ///
/// \param a /// \param a
/// A 128-bit vector of [4 x float]. /// A 128-bit vector of [4 x float].
@ -1719,7 +1749,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m256d _mm256_cmp_pd(__m256d a, __m256d b, const int c); /// __m256d _mm256_cmp_pd(__m256d a, __m256d b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPPD / CMPPD instruction. /// This intrinsic corresponds to the \c VCMPPD instruction.
/// ///
/// \param a /// \param a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -1755,7 +1785,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m256 _mm256_cmp_ps(__m256 a, __m256 b, const int c); /// __m256 _mm256_cmp_ps(__m256 a, __m256 b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPPS / CMPPS instruction. /// This intrinsic corresponds to the \c VCMPPS instruction.
/// ///
/// \param a /// \param a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].
@ -1790,7 +1820,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c); /// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPSD / CMPSD instruction. /// This intrinsic corresponds to the \c VCMPSD instruction.
/// ///
/// \param a /// \param a
/// A 128-bit vector of [2 x double]. /// A 128-bit vector of [2 x double].
@ -1825,7 +1855,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c); /// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c);
/// \endcode /// \endcode
/// ///
/// This intrinsic corresponds to the \c VCMPSS / CMPSS instruction. /// This intrinsic corresponds to the \c VCMPSS instruction.
/// ///
/// \param a /// \param a
/// A 128-bit vector of [4 x float]. /// A 128-bit vector of [4 x float].
@ -1854,8 +1884,7 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE / /// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
/// EXTRACTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x i32]. /// A 256-bit vector of [8 x i32].
@ -1876,8 +1905,7 @@ _mm256_extract_epi32(__m256i __a, const int __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE / /// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
/// EXTRACTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit integer vector of [16 x i16]. /// A 256-bit integer vector of [16 x i16].
@ -1898,8 +1926,7 @@ _mm256_extract_epi16(__m256i __a, const int __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE / /// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
/// EXTRACTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit integer vector of [32 x i8]. /// A 256-bit integer vector of [32 x i8].
@ -1921,8 +1948,7 @@ _mm256_extract_epi8(__m256i __a, const int __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE / /// This intrinsic corresponds to the \c VEXTRACTF128+COMPOSITE instruction.
/// EXTRACTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit integer vector of [4 x i64]. /// A 256-bit integer vector of [4 x i64].
@ -1945,8 +1971,7 @@ _mm256_extract_epi64(__m256i __a, const int __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE / /// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
/// INSERTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A vector of [8 x i32] to be used by the insert operation. /// A vector of [8 x i32] to be used by the insert operation.
@ -1972,8 +1997,7 @@ _mm256_insert_epi32(__m256i __a, int __b, int const __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE / /// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
/// INSERTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A vector of [16 x i16] to be used by the insert operation. /// A vector of [16 x i16] to be used by the insert operation.
@ -1998,8 +2022,7 @@ _mm256_insert_epi16(__m256i __a, int __b, int const __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE / /// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
/// INSERTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A vector of [32 x i8] to be used by the insert operation. /// A vector of [32 x i8] to be used by the insert operation.
@ -2025,8 +2048,7 @@ _mm256_insert_epi8(__m256i __a, int __b, int const __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE / /// This intrinsic corresponds to the \c VINSERTF128+COMPOSITE instruction.
/// INSERTF128+COMPOSITE instruction.
/// ///
/// \param __a /// \param __a
/// A vector of [4 x i64] to be used by the insert operation. /// A vector of [4 x i64] to be used by the insert operation.
@ -2051,7 +2073,7 @@ _mm256_insert_epi64(__m256i __a, long long __b, int const __imm)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VCVTDQ2PD / CVTDQ2PD instruction. /// This intrinsic corresponds to the \c VCVTDQ2PD instruction.
/// ///
/// \param __a /// \param __a
/// A 128-bit integer vector of [4 x i32]. /// A 128-bit integer vector of [4 x i32].
@ -2066,7 +2088,7 @@ _mm256_cvtepi32_pd(__m128i __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VCVTDQ2PS / CVTDQ2PS instruction. /// This intrinsic corresponds to the \c VCVTDQ2PS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit integer vector. /// A 256-bit integer vector.
@ -2082,7 +2104,7 @@ _mm256_cvtepi32_ps(__m256i __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VCVTPD2PS / CVTPD2PS instruction. /// This intrinsic corresponds to the \c VCVTPD2PS instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [4 x double]. /// A 256-bit vector of [4 x double].
@ -2097,7 +2119,7 @@ _mm256_cvtpd_ps(__m256d __a)
/// ///
/// \headerfile <x86intrin.h> /// \headerfile <x86intrin.h>
/// ///
/// This intrinsic corresponds to the \c VCVTPS2DQ / CVTPS2DQ instruction. /// This intrinsic corresponds to the \c VCVTPS2DQ instruction.
/// ///
/// \param __a /// \param __a
/// A 256-bit vector of [8 x float]. /// A 256-bit vector of [8 x float].