r272350 - Add doxygen comments to mmintrin.h's intrinsics.

Ekaterina Romanova via cfe-commits cfe-commits at lists.llvm.org
Thu Jun 9 17:10:40 PDT 2016


Author: kromanova
Date: Thu Jun  9 19:10:40 2016
New Revision: 272350

URL: http://llvm.org/viewvc/llvm-project?rev=272350&view=rev
Log:
Add doxygen comments to mmintrin.h's intrinsics.

The doxygen comments are automatically generated based on Sony's intrinsics docu
ment.

I got an OK from Eric Christopher to commit doxygen comments without prior code
review upstream.


Modified:
    cfe/trunk/lib/Headers/mmintrin.h

Modified: cfe/trunk/lib/Headers/mmintrin.h
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Headers/mmintrin.h?rev=272350&r1=272349&r2=272350&view=diff
==============================================================================
--- cfe/trunk/lib/Headers/mmintrin.h (original)
+++ cfe/trunk/lib/Headers/mmintrin.h Thu Jun  9 19:10:40 2016
@@ -34,366 +34,1314 @@ typedef char __v8qi __attribute__((__vec
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("mmx")))
 
+/// \brief Clears the MMX state by setting the state of the x87 stack registers
+///    to empty.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c EMMS instruction.
+///
 static __inline__ void __DEFAULT_FN_ATTRS
 _mm_empty(void)
 {
     __builtin_ia32_emms();
 }
 
+/// \brief Constructs a 64-bit integer vector, setting the lower 32 bits to the
+///    value of the 32-bit integer parameter and setting the upper 32 bits to 0.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VMOVD / MOVD instruction.
+///
+/// \param __i
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector. The lower 32 bits contain the value of the
+///    parameter. The upper 32 bits are set to 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cvtsi32_si64(int __i)
 {
     return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
 }
 
+/// \brief Returns the lower 32 bits of a 64-bit integer vector as a 32-bit
+///    signed integer.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VMOVD / MOVD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector.
+/// \returns A 32-bit signed integer value containing the lower 32 bits of the
+///    parameter.
 static __inline__ int __DEFAULT_FN_ATTRS
 _mm_cvtsi64_si32(__m64 __m)
 {
     return __builtin_ia32_vec_ext_v2si((__v2si)__m, 0);
 }
 
+/// \brief Casts a 64-bit signed integer value into a 64-bit integer vector.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VMOVQ / MOVD instruction.
+///
+/// \param __i
+///    A 64-bit signed integer.
+/// \returns A 64-bit integer vector containing the same bitwise pattern as the
+///    parameter.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cvtsi64_m64(long long __i)
 {
     return (__m64)__i;
 }
 
+/// \brief Casts a 64-bit integer vector into a 64-bit signed integer value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VMOVQ / MOVD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector.
+/// \returns A 64-bit signed integer containing the same bitwise pattern as the
+///    parameter.
 static __inline__ long long __DEFAULT_FN_ATTRS
 _mm_cvtm64_si64(__m64 __m)
 {
     return (long long)__m;
 }
 
+/// \brief Converts 16-bit signed integers from both 64-bit integer vector
+///    parameters of [4 x i16] into 8-bit signed integer values, and constructs
+///    a 64-bit integer vector of [8 x i8] as the result. Positive values
+///    greater than 0x7F are saturated to 0x7F. Negative values less than 0x80
+///    are saturated to 0x80.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PACKSSWB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16]. Each 16-bit element is treated as a
+///    16-bit signed integer and is converted to an 8-bit signed integer with
+///    saturation. Positive values greater than 0x7F are saturated to 0x7F.
+///    Negative values less than 0x80 are saturated to 0x80. The converted
+///    [4 x i8] values are written to the lower 32 bits of the result.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16]. Each 16-bit element is treated as a
+///    16-bit signed integer and is converted to an 8-bit signed integer with
+///    saturation. Positive values greater than 0x7F are saturated to 0x7F.
+///    Negative values less than 0x80 are saturated to 0x80. The converted
+///    [4 x i8] values are written to the upper 32 bits of the result.
+/// \returns A 64-bit integer vector of [8 x i8] containing the converted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_packs_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Converts 32-bit signed integers from both 64-bit integer vector
+///    parameters of [2 x i32] into 16-bit signed integer values, and constructs
+///    a 64-bit integer vector of [4 x i16] as the result. Positive values
+///    greater than 0x7FFF are saturated to 0x7FFF. Negative values less than
+///    0x8000 are saturated to 0x8000.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PACKSSDW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32]. Each 32-bit element is treated as a
+///    32-bit signed integer and is converted to a 16-bit signed integer with
+///    saturation. Positive values greater than 0x7FFF are saturated to 0x7FFF.
+///    Negative values less than 0x8000 are saturated to 0x8000. The converted
+///    [2 x i16] values are written to the lower 32 bits of the result.
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32]. Each 32-bit element is treated as a
+///    32-bit signed integer and is converted to a 16-bit signed integer with
+///    saturation. Positive values greater than 0x7FFF are saturated to 0x7FFF.
+///    Negative values less than 0x8000 are saturated to 0x8000. The converted
+///    [2 x i16] values are written to the upper 32 bits of the result.
+/// \returns A 64-bit integer vector of [4 x i16] containing the converted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_packs_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Converts 16-bit signed integers from both 64-bit integer vector
+///    parameters of [4 x i16] into 8-bit unsigned integer values, and
+///    constructs a 64-bit integer vector of [8 x i8] as the result. Values
+///    greater than 0xFF are saturated to 0xFF. Values less than 0 are saturated
+///    to 0.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PACKUSWB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16]. Each 16-bit element is treated as a
+///    16-bit signed integer and is converted to an 8-bit unsigned integer with
+///    saturation. Values greater than 0xFF are saturated to 0xFF. Values less
+///    than 0 are saturated to 0. The converted [4 x i8] values are written to
+///    the lower 32 bits of the result.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16]. Each 16-bit element is treated as a
+///    16-bit signed integer and is converted to an 8-bit unsigned integer with
+///    saturation. Values greater than 0xFF are saturated to 0xFF. Values less
+///    than 0 are saturated to 0. The converted [4 x i8] values are written to
+///    the upper 32 bits of the result.
+/// \returns A 64-bit integer vector of [8 x i8] containing the converted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_packs_pu16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Unpacks the upper 32 bits from two 64-bit integer vectors of [8 x i8]
+///    and interleaves them into a 64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKHBW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+///    Bits [39:32] are written to bits [7:0] of the result.
+///    Bits [47:40] are written to bits [23:16] of the result.
+///    Bits [55:48] are written to bits [39:32] of the result.
+///    Bits [63:56] are written to bits [55:48] of the result.
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+///    Bits [39:32] are written to bits [15:8] of the result.
+///    Bits [47:40] are written to bits [31:24] of the result.
+///    Bits [55:48] are written to bits [47:40] of the result.
+///    Bits [63:56] are written to bits [63:56] of the result.
+/// \returns A 64-bit integer vector of [8 x i8] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpackhi_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Unpacks the upper 32 bits from two 64-bit integer vectors of
+///    [4 x i16] and interleaves them into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKHWD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+///    Bits [47:32] are written to bits [15:0] of the result.
+///    Bits [63:48] are written to bits [47:32] of the result.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+///    Bits [47:32] are written to bits [31:16] of the result.
+///    Bits [63:48] are written to bits [63:48] of the result.
+/// \returns A 64-bit integer vector of [4 x i16] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpackhi_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Unpacks the upper 32 bits from two 64-bit integer vectors of
+///    [2 x i32] and interleaves them into a 64-bit integer vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKHDQ instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32]. The upper 32 bits are written to
+///    the lower 32 bits of the result.
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32]. The upper 32 bits are written to
+///    the upper 32 bits of the result.
+/// \returns A 64-bit integer vector of [2 x i32] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpackhi_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpckhdq((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Unpacks the lower 32 bits from two 64-bit integer vectors of [8 x i8]
+///    and interleaves them into a 64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKLBW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+///    Bits [7:0] are written to bits [7:0] of the result.
+///    Bits [15:8] are written to bits [23:16] of the result.
+///    Bits [23:16] are written to bits [39:32] of the result.
+///    Bits [31:24] are written to bits [55:48] of the result.
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+///    Bits [7:0] are written to bits [15:8] of the result.
+///    Bits [15:8] are written to bits [31:24] of the result.
+///    Bits [23:16] are written to bits [47:40] of the result.
+///    Bits [31:24] are written to bits [63:56] of the result.
+/// \returns A 64-bit integer vector of [8 x i8] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpacklo_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpcklbw((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Unpacks the lower 32 bits from two 64-bit integer vectors of
+///    [4 x i16] and interleaves them into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKLWD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+///    Bits [15:0] are written to bits [15:0] of the result.
+///    Bits [31:16] are written to bits [47:32] of the result.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+///    Bits [15:0] are written to bits [31:16] of the result.
+///    Bits [31:16] are written to bits [63:48] of the result.
+/// \returns A 64-bit integer vector of [4 x i16] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpacklo_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpcklwd((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Unpacks the lower 32 bits from two 64-bit integer vectors of
+///    [2 x i32] and interleaves them into a 64-bit integer vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PUNPCKLDQ instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32]. The lower 32 bits are written to
+///    the lower 32 bits of the result.
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32]. The lower 32 bits are written to
+///    the upper 32 bits of the result.
+/// \returns A 64-bit integer vector of [2 x i32] containing the interleaved
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_unpacklo_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_punpckldq((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Adds each 8-bit integer element of the first 64-bit integer vector
+///    of [8 x i8] to the corresponding 8-bit integer element of the second
+///    64-bit integer vector of [8 x i8]. The lower 8 bits of the results are
+///    packed into a 64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+/// \returns A 64-bit integer vector of [8 x i8] containing the sums of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_add_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Adds each 16-bit integer element of the first 64-bit integer vector
+///    of [4 x i16] to the corresponding 16-bit integer element of the second
+///    64-bit integer vector of [4 x i16]. The lower 16 bits of the results are
+///    packed into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the sums of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_add_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Adds each 32-bit integer element of the first 64-bit integer vector
+///    of [2 x i32] to the corresponding 32-bit integer element of the second
+///    64-bit integer vector of [2 x i32]. The lower 32 bits of the results are
+///    packed into a 64-bit integer vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32].
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32].
+/// \returns A 64-bit integer vector of [2 x i32] containing the sums of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_add_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddd((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Adds each 8-bit signed integer element of the first 64-bit integer
+///    vector of [8 x i8] to the corresponding 8-bit signed integer element of
+///    the second 64-bit integer vector of [8 x i8]. Positive sums greater than
+///    0x7F are saturated to 0x7F. Negative sums less than 0x80 are saturated to
+///    0x80. The results are packed into a 64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDSB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+/// \returns A 64-bit integer vector of [8 x i8] containing the saturated sums
+///    of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_adds_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddsb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Adds each 16-bit signed integer element of the first 64-bit integer
+///    vector of [4 x i16] to the corresponding 16-bit signed integer element of
+///    the second 64-bit integer vector of [4 x i16]. Positive sums greater than
+///    0x7FFF are saturated to 0x7FFF. Negative sums less than 0x8000 are
+///    saturated to 0x8000. The results are packed into a 64-bit integer vector
+///    of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDSW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the saturated sums
+///    of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_adds_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddsw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Adds each 8-bit unsigned integer element of the first 64-bit integer
+///    vector of [8 x i8] to the corresponding 8-bit unsigned integer element of
+///    the second 64-bit integer vector of [8 x i8]. Sums greater than 0xFF are
+///    saturated to 0xFF. The results are packed into a 64-bit integer vector of
+///    [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDUSB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
+///    unsigned sums of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_adds_pu8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddusb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Adds each 16-bit unsigned integer element of the first 64-bit integer
+///    vector of [4 x i16] to the corresponding 16-bit unsigned integer element
+///    of the second 64-bit integer vector of [4 x i16]. Sums greater than
+///    0xFFFF are saturated to 0xFFFF. The results are packed into a 64-bit
+///    integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PADDUSW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
+///    unsigned sums of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_adds_pu16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_paddusw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Subtracts each 8-bit integer element of the second 64-bit integer
+///    vector of [8 x i8] from the corresponding 8-bit integer element of the
+///    first 64-bit integer vector of [8 x i8]. The lower 8 bits of the results
+///    are packed into a 64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8] containing the subtrahends.
+/// \returns A 64-bit integer vector of [8 x i8] containing the differences of
+///    both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sub_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Subtracts each 16-bit integer element of the second 64-bit integer
+///    vector of [4 x i16] from the corresponding 16-bit integer element of the
+///    first 64-bit integer vector of [4 x i16]. The lower 16 bits of the
+///    results are packed into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16] containing the subtrahends.
+/// \returns A 64-bit integer vector of [4 x i16] containing the differences of
+///    both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sub_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Subtracts each 32-bit integer element of the second 64-bit integer
+///    vector of [2 x i32] from the corresponding 32-bit integer element of the
+///    first 64-bit integer vector of [2 x i32]. The lower 32 bits of the
+///    results are packed into a 64-bit integer vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32] containing the subtrahends.
+/// \returns A 64-bit integer vector of [2 x i32] containing the differences of
+///    both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sub_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubd((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Subtracts each 8-bit signed integer element of the second 64-bit
+///    integer vector of [8 x i8] from the corresponding 8-bit signed integer
+///    element of the first 64-bit integer vector of [8 x i8]. Positive results
+///    greater than 0x7F are saturated to 0x7F. Negative results less than 0x80
+///    are saturated to 0x80. The results are packed into a 64-bit integer
+///    vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBSB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8] containing the subtrahends.
+/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
+///    differences of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_subs_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubsb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Subtracts each 16-bit signed integer element of the second 64-bit
+///    integer vector of [4 x i16] from the corresponding 16-bit signed integer
+///    element of the first 64-bit integer vector of [4 x i16]. Positive results
+///    greater than 0x7FFF are saturated to 0x7FFF. Negative results less than
+///    0x8000 are saturated to 0x8000. The results are packed into a 64-bit
+///    integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBSW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16] containing the subtrahends.
+/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
+///    differences of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_subs_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubsw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Subtracts each 8-bit unsigned integer element of the second 64-bit
+///    integer vector of [8 x i8] from the corresponding 8-bit unsigned integer
+///    element of the first 64-bit integer vector of [8 x i8]. If an element of
+///    the first vector is less than the corresponding element of the second
+///    vector, the result is saturated to 0. The results are packed into a
+///    64-bit integer vector of [8 x i8].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBUSB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8] containing the subtrahends.
+/// \returns A 64-bit integer vector of [8 x i8] containing the saturated
+///    differences of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_subs_pu8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubusb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Subtracts each 16-bit unsigned integer element of the second 64-bit
+///    integer vector of [4 x i16] from the corresponding 16-bit unsigned
+///    integer element of the first 64-bit integer vector of [4 x i16]. If an
+///    element of the first vector is less than the corresponding element of the
+///    second vector, the result is saturated to 0. The results are packed into
+///    a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSUBUSW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16] containing the minuends.
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16] containing the subtrahends.
+/// \returns A 64-bit integer vector of [4 x i16] containing the saturated
+///    differences of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_subs_pu16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_psubusw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Multiplies each 16-bit signed integer element of the first 64-bit
+///    integer vector of [4 x i16] by the corresponding 16-bit signed integer
+///    element of the second 64-bit integer vector of [4 x i16] and get four
+///    32-bit products. Adds adjacent pairs of products to get two 32-bit sums.
+///    The lower 32 bits of these two sums are packed into a 64-bit integer
+///    vector of [2 x i32]. For example, bits [15:0] of both parameters are
+///    multiplied, bits [31:16] of both parameters are multiplied, and the sum
+///    of both results is written to bits [31:0] of the result.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PMADDWD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [2 x i32] containing the sums of
+///    products of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_madd_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pmaddwd((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Multiplies each 16-bit signed integer element of the first 64-bit
+///    integer vector of [4 x i16] by the corresponding 16-bit signed integer
+///    element of the second 64-bit integer vector of [4 x i16]. Packs the upper
+///    16 bits of the 32-bit products into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PMULHW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the upper 16 bits
+///    of the products of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_mulhi_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pmulhw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Multiplies each 16-bit signed integer element of the first 64-bit
+///    integer vector of [4 x i16] by the corresponding 16-bit signed integer
+///    element of the second 64-bit integer vector of [4 x i16]. Packs the lower
+///    16 bits of the 32-bit products into a 64-bit integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PMULLW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the lower 16 bits
+///    of the products of both parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_mullo_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pmullw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Left-shifts each 16-bit signed integer element of the first
+///    parameter, which is a 64-bit integer vector of [4 x i16], by the number
+///    of bits specified by the second parameter, which is a 64-bit integer. The
+///    lower 16 bits of the results are packed into a 64-bit integer vector of
+///    [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [4 x i16] containing the left-shifted
+///    values. If __count is greater or equal to 16, the result is set to all 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sll_pi16(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psllw((__v4hi)__m, __count);
 }
 
+/// \brief Left-shifts each 16-bit signed integer element of a 64-bit integer
+///    vector of [4 x i16] by the number of bits specified by a 32-bit integer.
+///    The lower 16 bits of the results are packed into a 64-bit integer vector
+///    of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [4 x i16] containing the left-shifted
+///    values. If __count is greater or equal to 16, the result is set to all 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_slli_pi16(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psllwi((__v4hi)__m, __count);
 }
 
+/// \brief Left-shifts each 32-bit signed integer element of the first
+///    parameter, which is a 64-bit integer vector of [2 x i32], by the number
+///    of bits specified by the second parameter, which is a 64-bit integer. The
+///    lower 32 bits of the results are packed into a 64-bit integer vector of
+///    [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [2 x i32] containing the left-shifted
+///    values. If __count is greater or equal to 32, the result is set to all 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sll_pi32(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_pslld((__v2si)__m, __count);
 }
 
+/// \brief Left-shifts each 32-bit signed integer element of a 64-bit integer
+///    vector of [2 x i32] by the number of bits specified by a 32-bit integer.
+///    The lower 32 bits of the results are packed into a 64-bit integer vector
+///    of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [2 x i32] containing the left-shifted
+///    values. If __count is greater or equal to 32, the result is set to all 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_slli_pi32(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_pslldi((__v2si)__m, __count);
 }
 
+/// \brief Left-shifts the first 64-bit integer parameter by the number of bits
+///    specified by the second 64-bit integer parameter. The lower 64 bits of
+///    result are returned.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLQ instruction.
+///
+/// \param __m
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector containing the left-shifted value. If
+///     __count is greater or equal to 64, the result is set to 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sll_si64(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psllq((__v1di)__m, __count);
 }
 
+/// \brief Left-shifts the first parameter, which is a 64-bit integer, by the
+///    number of bits specified by the second parameter, which is a 32-bit
+///    integer. The lower 64 bits of result are returned.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSLLQ instruction.
+///
+/// \param __m
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector containing the left-shifted value. If
+///     __count is greater or equal to 64, the result is set to 0.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_slli_si64(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psllqi((__v1di)__m, __count);
 }
 
+/// \brief Right-shifts each 16-bit integer element of the first parameter,
+///    which is a 64-bit integer vector of [4 x i16], by the number of bits
+///    specified by the second parameter, which is a 64-bit integer. High-order
+///    bits are filled with the sign bit of the initial value of each 16-bit
+///    element. The 16-bit results are packed into a 64-bit integer vector of
+///    [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRAW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sra_pi16(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psraw((__v4hi)__m, __count);
 }
 
+/// \brief Right-shifts each 16-bit integer element of a 64-bit integer vector
+///    of [4 x i16] by the number of bits specified by a 32-bit integer.
+///    High-order bits are filled with the sign bit of the initial value of each
+///    16-bit element. The 16-bit results are packed into a 64-bit integer
+///    vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRAW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srai_pi16(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psrawi((__v4hi)__m, __count);
 }
 
+/// \brief Right-shifts each 32-bit integer element of the first parameter,
+///    which is a 64-bit integer vector of [2 x i32], by the number of bits
+///    specified by the second parameter, which is a 64-bit integer. High-order
+///    bits are filled with the sign bit of the initial value of each 32-bit
+///    element. The 32-bit results are packed into a 64-bit integer vector of
+///    [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRAD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_sra_pi32(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psrad((__v2si)__m, __count);
 }
 
+/// \brief Right-shifts each 32-bit integer element of a 64-bit integer vector
+///    of [2 x i32] by the number of bits specified by a 32-bit integer.
+///    High-order bits are filled with the sign bit of the initial value of each
+///    32-bit element. The 32-bit results are packed into a 64-bit integer
+///    vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRAD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srai_pi32(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psradi((__v2si)__m, __count);
 }
 
+/// \brief Right-shifts each 16-bit integer element of the first parameter,
+///    which is a 64-bit integer vector of [4 x i16], by the number of bits
+///    specified by the second parameter, which is a 64-bit integer. High-order
+///    bits are cleared. The 16-bit results are packed into a 64-bit integer
+///    vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srl_pi16(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psrlw((__v4hi)__m, __count);
 }
 
+/// \brief Right-shifts each 16-bit integer element of a 64-bit integer vector
+///    of [4 x i16] by the number of bits specified by a 32-bit integer.
+///    High-order bits are cleared. The 16-bit results are packed into a 64-bit
+///    integer vector of [4 x i16].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLW instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [4 x i16].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [4 x i16] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srli_pi16(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psrlwi((__v4hi)__m, __count);
 }
 
+/// \brief Right-shifts each 32-bit integer element of the first parameter,
+///    which is a 64-bit integer vector of [2 x i32], by the number of bits
+///    specified by the second parameter, which is a 64-bit integer. High-order
+///    bits are cleared. The 32-bit results are packed into a 64-bit integer
+///    vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srl_pi32(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psrld((__v2si)__m, __count);
 }
 
+/// \brief Right-shifts each 32-bit integer element of a 64-bit integer vector
+///    of [2 x i32] by the number of bits specified by a 32-bit integer.
+///    High-order bits are cleared. The 32-bit results are packed into a 64-bit
+///    integer vector of [2 x i32].
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLD instruction.
+///
+/// \param __m
+///    A 64-bit integer vector of [2 x i32].
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector of [2 x i32] containing the right-shifted
+///    values.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srli_pi32(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psrldi((__v2si)__m, __count);
 }
 
+/// \brief Right-shifts the first 64-bit integer parameter by the number of bits
+///    specified by the second 64-bit integer parameter. High-order bits are
+///    cleared.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLQ instruction.
+///
+/// \param __m
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \param __count
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \returns A 64-bit integer vector containing the right-shifted value.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srl_si64(__m64 __m, __m64 __count)
 {
     return (__m64)__builtin_ia32_psrlq((__v1di)__m, __count);
 }
 
+/// \brief Right-shifts the first parameter, which is a 64-bit integer, by the
+///    number of bits specified by the second parameter, which is a 32-bit
+///    integer. High-order bits are cleared.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PSRLQ instruction.
+///
+/// \param __m
+///    A 64-bit integer vector interpreted as a single 64-bit integer.
+/// \param __count
+///    A 32-bit integer value.
+/// \returns A 64-bit integer vector containing the right-shifted value.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_srli_si64(__m64 __m, int __count)
 {
     return (__m64)__builtin_ia32_psrlqi((__v1di)__m, __count);
 }
 
+/// \brief Performs a bitwise AND of two 64-bit integer vectors.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PAND instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector.
+/// \param __m2
+///    A 64-bit integer vector.
+/// \returns A 64-bit integer vector containing the bitwise AND of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_and_si64(__m64 __m1, __m64 __m2)
 {
     return __builtin_ia32_pand((__v1di)__m1, (__v1di)__m2);
 }
 
+/// \brief Performs a bitwise NOT of the first 64-bit integer vector, and then
+///    performs a bitwise AND of the intermediate result and the second 64-bit
+///    integer vector.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PANDN instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector. The one's complement of this parameter is used
+///    in the bitwise AND.
+/// \param __m2
+///    A 64-bit integer vector.
+/// \returns A 64-bit integer vector containing the bitwise AND of the second
+///    parameter and the one's complement of the first parameter.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_andnot_si64(__m64 __m1, __m64 __m2)
 {
     return __builtin_ia32_pandn((__v1di)__m1, (__v1di)__m2);
 }
 
+/// \brief Performs a bitwise OR of two 64-bit integer vectors.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c POR instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector.
+/// \param __m2
+///    A 64-bit integer vector.
+/// \returns A 64-bit integer vector containing the bitwise OR of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_or_si64(__m64 __m1, __m64 __m2)
 {
     return __builtin_ia32_por((__v1di)__m1, (__v1di)__m2);
 }
 
+/// \brief Performs a bitwise exclusive OR of two 64-bit integer vectors.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PXOR instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector.
+/// \param __m2
+///    A 64-bit integer vector.
+/// \returns A 64-bit integer vector containing the bitwise exclusive OR of both
+///    parameters.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_xor_si64(__m64 __m1, __m64 __m2)
 {
     return __builtin_ia32_pxor((__v1di)__m1, (__v1di)__m2);
 }
 
+/// \brief Compares the 8-bit integer elements of two 64-bit integer vectors of
+///    [8 x i8] to determine if the element of the first vector is equal to the
+///    corresponding element of the second vector. The comparison yields 0 for
+///    false, 0xFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPEQB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+/// \returns A 64-bit integer vector of [8 x i8] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpeq_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpeqb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Compares the 16-bit integer elements of two 64-bit integer vectors of
+///    [4 x i16] to determine if the element of the first vector is equal to the
+///    corresponding element of the second vector. The comparison yields 0 for
+///    false, 0xFFFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPEQW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpeq_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpeqw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Compares the 32-bit integer elements of two 64-bit integer vectors of
+///    [2 x i32] to determine if the element of the first vector is equal to the
+///    corresponding element of the second vector. The comparison yields 0 for
+///    false, 0xFFFFFFFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPEQD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32].
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32].
+/// \returns A 64-bit integer vector of [2 x i32] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpeq_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpeqd((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Compares the 8-bit integer elements of two 64-bit integer vectors of
+///    [8 x i8] to determine if the element of the first vector is greater than
+///    the corresponding element of the second vector. The comparison yields 0
+///    for false, 0xFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPGTB instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [8 x i8].
+/// \param __m2
+///    A 64-bit integer vector of [8 x i8].
+/// \returns A 64-bit integer vector of [8 x i8] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpgt_pi8(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpgtb((__v8qi)__m1, (__v8qi)__m2);
 }
 
+/// \brief Compares the 16-bit integer elements of two 64-bit integer vectors of
+///    [4 x i16] to determine if the element of the first vector is greater than
+///    the corresponding element of the second vector. The comparison yields 0
+///    for false, 0xFFFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPGTW instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [4 x i16].
+/// \param __m2
+///    A 64-bit integer vector of [4 x i16].
+/// \returns A 64-bit integer vector of [4 x i16] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpgt_pi16(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpgtw((__v4hi)__m1, (__v4hi)__m2);
 }
 
+/// \brief Compares the 32-bit integer elements of two 64-bit integer vectors of
+///    [2 x i32] to determine if the element of the first vector is greater than
+///    the corresponding element of the second vector. The comparison yields 0
+///    for false, 0xFFFFFFFF for true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c PCMPGTD instruction.
+///
+/// \param __m1
+///    A 64-bit integer vector of [2 x i32].
+/// \param __m2
+///    A 64-bit integer vector of [2 x i32].
+/// \returns A 64-bit integer vector of [2 x i32] containing the comparison
+///    results.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_cmpgt_pi32(__m64 __m1, __m64 __m2)
 {
     return (__m64)__builtin_ia32_pcmpgtd((__v2si)__m1, (__v2si)__m2);
 }
 
+/// \brief Constructs a 64-bit integer vector initialized to zero.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the the \c VXORPS / XORPS instruction.
+///
+/// \returns An initialized 64-bit integer vector with all elements set to zero.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_setzero_si64(void)
 {
     return (__m64){ 0LL };
 }
 
+/// \brief Constructs a 64-bit integer vector initialized with the specified
+///    32-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __i1
+///    A 32-bit integer value used to initialize the upper 32 bits of the
+///    result.
+/// \param __i0
+///    A 32-bit integer value used to initialize the lower 32 bits of the
+///    result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set_pi32(int __i1, int __i0)
 {
     return (__m64)__builtin_ia32_vec_init_v2si(__i0, __i1);
 }
 
+/// \brief Constructs a 64-bit integer vector initialized with the specified
+///    16-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __s3
+///    A 16-bit integer value used to initialize bits [63:48] of the result.
+/// \param __s2
+///    A 16-bit integer value used to initialize bits [47:32] of the result.
+/// \param __s1
+///    A 16-bit integer value used to initialize bits [31:16] of the result.
+/// \param __s0
+///    A 16-bit integer value used to initialize bits [15:0] of the result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set_pi16(short __s3, short __s2, short __s1, short __s0)
 {
     return (__m64)__builtin_ia32_vec_init_v4hi(__s0, __s1, __s2, __s3);
 }
 
+/// \brief Constructs a 64-bit integer vector initialized with the specified
+///    8-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __b7
+///    An 8-bit integer value used to initialize bits [63:56] of the result.
+/// \param __b6
+///    An 8-bit integer value used to initialize bits [55:48] of the result.
+/// \param __b5
+///    An 8-bit integer value used to initialize bits [47:40] of the result.
+/// \param __b4
+///    An 8-bit integer value used to initialize bits [39:32] of the result.
+/// \param __b3
+///    An 8-bit integer value used to initialize bits [31:24] of the result.
+/// \param __b2
+///    An 8-bit integer value used to initialize bits [23:16] of the result.
+/// \param __b1
+///    An 8-bit integer value used to initialize bits [15:8] of the result.
+/// \param __b0
+///    An 8-bit integer value used to initialize bits [7:0] of the result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set_pi8(char __b7, char __b6, char __b5, char __b4, char __b3, char __b2,
             char __b1, char __b0)
@@ -402,36 +1350,129 @@ _mm_set_pi8(char __b7, char __b6, char _
                                                __b4, __b5, __b6, __b7);
 }
 
+/// \brief Constructs a 64-bit integer vector of [2 x i32], with each of the
+///    32-bit integer vector elements set to the specified 32-bit integer
+///    value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VPSHUFD / PSHUFD instruction.
+///
+/// \param __i
+///    A 32-bit integer value used to initialize each vector element of the
+///    result.
+/// \returns An initialized 64-bit integer vector of [2 x i32].
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set1_pi32(int __i)
 {
     return _mm_set_pi32(__i, __i);
 }
 
+/// \brief Constructs a 64-bit integer vector of [4 x i16], with each of the
+///    16-bit integer vector elements set to the specified 16-bit integer
+///    value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VPSHUFLW / PSHUFLW instruction.
+///
+/// \param __w
+///    A 16-bit integer value used to initialize each vector element of the
+///    result.
+/// \returns An initialized 64-bit integer vector of [4 x i16].
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set1_pi16(short __w)
 {
     return _mm_set_pi16(__w, __w, __w, __w);
 }
 
+/// \brief Constructs a 64-bit integer vector of [8 x i8], with each of the
+///    8-bit integer vector elements set to the specified 8-bit integer value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the \c VPUNPCKLBW + VPSHUFLW / \c PUNPCKLBW +
+///    PSHUFLW instruction.
+///
+/// \param __b
+///    An 8-bit integer value used to initialize each vector element of the
+///    result.
+/// \returns An initialized 64-bit integer vector of [8 x i8].
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_set1_pi8(char __b)
 {
     return _mm_set_pi8(__b, __b, __b, __b, __b, __b, __b, __b);
 }
 
+/// \brief Constructs a 64-bit integer vector, initialized in reverse order with
+///    the specified 32-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __i0
+///    A 32-bit integer value used to initialize the lower 32 bits of the
+///    result.
+/// \param __i1
+///    A 32-bit integer value used to initialize the upper 32 bits of the
+///    result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_setr_pi32(int __i0, int __i1)
 {
     return _mm_set_pi32(__i1, __i0);
 }
 
+/// \brief Constructs a 64-bit integer vector, initialized in reverse order with
+///    the specified 16-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __w0
+///    A 16-bit integer value used to initialize bits [15:0] of the result.
+/// \param __w1
+///    A 16-bit integer value used to initialize bits [31:16] of the result.
+/// \param __w2
+///    A 16-bit integer value used to initialize bits [47:32] of the result.
+/// \param __w3
+///    A 16-bit integer value used to initialize bits [63:48] of the result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_setr_pi16(short __w0, short __w1, short __w2, short __w3)
 {
     return _mm_set_pi16(__w3, __w2, __w1, __w0);
 }
 
+/// \brief Constructs a 64-bit integer vector, initialized in reverse order with
+///    the specified 8-bit integer values.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic is a utility function and does not correspond to a specific
+///    instruction.
+///
+/// \param __b0
+///    An 8-bit integer value used to initialize bits [7:0] of the result.
+/// \param __b1
+///    An 8-bit integer value used to initialize bits [15:8] of the result.
+/// \param __b2
+///    An 8-bit integer value used to initialize bits [23:16] of the result.
+/// \param __b3
+///    An 8-bit integer value used to initialize bits [31:24] of the result.
+/// \param __b4
+///    An 8-bit integer value used to initialize bits [39:32] of the result.
+/// \param __b5
+///    An 8-bit integer value used to initialize bits [47:40] of the result.
+/// \param __b6
+///    An 8-bit integer value used to initialize bits [55:48] of the result.
+/// \param __b7
+///    An 8-bit integer value used to initialize bits [63:56] of the result.
+/// \returns An initialized 64-bit integer vector.
 static __inline__ __m64 __DEFAULT_FN_ATTRS
 _mm_setr_pi8(char __b0, char __b1, char __b2, char __b3, char __b4, char __b5,
              char __b6, char __b7)




More information about the cfe-commits mailing list