diff --git a/lib/Headers/__wmmintrin_pclmul.h b/lib/Headers/__wmmintrin_pclmul.h
index e94cc2a4df909cb15242fc2bdff94ffaf58f0f29..e9c6a9f6d4152b14c0a4068c7b085209930af42f 100644
--- a/lib/Headers/__wmmintrin_pclmul.h
+++ b/lib/Headers/__wmmintrin_pclmul.h
@@ -42,12 +42,11 @@
/// A 128-bit vector of [2 x i64] containing one of the source operands.
/// \param __I
/// An immediate value specifying which 64-bit values to select from the
-/// operands.
-/// Bit 0 is used to select a value from operand \a __X, and bit 4 is used
-/// to select a value from operand \a __Y:
-/// Bit[0]=0 indicates that bits[63:0] of operand \a __X are used.
-/// Bit[0]=1 indicates that bits[127:64] of operand \a __X are used.
-/// Bit[4]=0 indicates that bits[63:0] of operand \a __Y are used.
+/// operands. Bit 0 is used to select a value from operand \a __X, and bit
+/// 4 is used to select a value from operand \a __Y: \n
+/// Bit[0]=0 indicates that bits[63:0] of operand \a __X are used. \n
+/// Bit[0]=1 indicates that bits[127:64] of operand \a __X are used. \n
+/// Bit[4]=0 indicates that bits[63:0] of operand \a __Y are used. \n
/// Bit[4]=1 indicates that bits[127:64] of operand \a __Y are used.
/// \returns The 128-bit integer vector containing the result of the carry-less
/// multiplication of the selected 64-bit values.
diff --git a/lib/Headers/bmiintrin.h b/lib/Headers/bmiintrin.h
index 650ee04e016dea662667ddb5dd61b037d2d5f7a3..488eb2dbd3d4b833865134c3f2f7263c1b995f8c 100644
--- a/lib/Headers/bmiintrin.h
+++ b/lib/Headers/bmiintrin.h
@@ -295,8 +295,8 @@ __tzcnt_u32(unsigned int __X)
///
/// \param __X
/// An unsigned 32-bit integer whose trailing zeros are to be counted.
-/// \returns An 32-bit integer containing the number of trailing zero
-/// bits in the operand.
+/// \returns An 32-bit integer containing the number of trailing zero bits in
+/// the operand.
static __inline__ int __RELAXED_FN_ATTRS
_mm_tzcnt_32(unsigned int __X)
{
@@ -532,8 +532,8 @@ __tzcnt_u64(unsigned long long __X)
///
/// \param __X
/// An unsigned 64-bit integer whose trailing zeros are to be counted.
-/// \returns An 64-bit integer containing the number of trailing zero
-/// bits in the operand.
+/// \returns An 64-bit integer containing the number of trailing zero bits in
+/// the operand.
static __inline__ long long __RELAXED_FN_ATTRS
_mm_tzcnt_64(unsigned long long __X)
{
diff --git a/lib/Headers/emmintrin.h b/lib/Headers/emmintrin.h
index 1830254109d27a710430582f06e0419dd1bdb391..1512f9f0b47bcf60a0819f8b4d06256b40b9824c 100644
--- a/lib/Headers/emmintrin.h
+++ b/lib/Headers/emmintrin.h
@@ -551,7 +551,8 @@ _mm_cmpord_pd(__m128d __a, __m128d __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCMPUNORDPD / CMPUNORDPD </c> instruction.
+/// This intrinsic corresponds to the <c> VCMPUNORDPD / CMPUNORDPD </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double].
@@ -734,10 +735,10 @@ _mm_cmple_sd(__m128d __a, __m128d __b)
return (__m128d)__builtin_ia32_cmplesd((__v2df)__a, (__v2df)__b);
}
-/// \brief Compares the lower double-precision floating-point values in each
-/// of the two 128-bit floating-point vectors of [2 x double] to determine
-/// if the value in the first parameter is greater than the corresponding
-/// value in the second parameter. The comparison yields 0h for false,
+/// \brief Compares the lower double-precision floating-point values in each of
+/// the two 128-bit floating-point vectors of [2 x double] to determine if
+/// the value in the first parameter is greater than the corresponding value
+/// in the second parameter. The comparison yields 0h for false,
/// FFFFFFFFFFFFFFFFh for true.
///
/// \headerfile <x86intrin.h>
@@ -784,9 +785,9 @@ _mm_cmpge_sd(__m128d __a, __m128d __b)
return (__m128d) { __c[0], __a[1] };
}
-/// \brief Compares the lower double-precision floating-point values in each
-/// of the two 128-bit floating-point vectors of [2 x double] to determine
-/// if the value in the first parameter is "ordered" with respect to the
+/// \brief Compares the lower double-precision floating-point values in each of
+/// the two 128-bit floating-point vectors of [2 x double] to determine if
+/// the value in the first parameter is "ordered" with respect to the
/// corresponding value in the second parameter. The comparison yields 0h for
/// false, FFFFFFFFFFFFFFFFh for true. A pair of double-precision values are
/// "ordered" with respect to each other if neither value is a NaN.
@@ -809,16 +810,17 @@ _mm_cmpord_sd(__m128d __a, __m128d __b)
return (__m128d)__builtin_ia32_cmpordsd((__v2df)__a, (__v2df)__b);
}
-/// \brief Compares the lower double-precision floating-point values in each
-/// of the two 128-bit floating-point vectors of [2 x double] to determine
-/// if the value in the first parameter is "unordered" with respect to the
+/// \brief Compares the lower double-precision floating-point values in each of
+/// the two 128-bit floating-point vectors of [2 x double] to determine if
+/// the value in the first parameter is "unordered" with respect to the
/// corresponding value in the second parameter. The comparison yields 0h
/// for false, FFFFFFFFFFFFFFFFh for true. A pair of double-precision values
/// are "unordered" with respect to each other if one or both values are NaN.
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCMPUNORDSD / CMPUNORDSD </c> instruction.
+/// This intrinsic corresponds to the <c> VCMPUNORDSD / CMPUNORDSD </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double]. The lower double-precision value is
@@ -1115,8 +1117,8 @@ _mm_ucomieq_sd(__m128d __a, __m128d __b)
/// \brief Compares the lower double-precision floating-point values in each of
/// the two 128-bit floating-point vectors of [2 x double] to determine if
/// the value in the first parameter is less than the corresponding value in
-/// the second parameter. The comparison yields 0 for false, 1 for true.
-/// If either of the two lower double-precision values is NaN, 1 is returned.
+/// the second parameter. The comparison yields 0 for false, 1 for true. If
+/// either of the two lower double-precision values is NaN, 1 is returned.
///
/// \headerfile <x86intrin.h>
///
@@ -1414,7 +1416,8 @@ _mm_cvtss_sd(__m128d __a, __m128 __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCVTTPD2DQ / CVTTPD2DQ </c> instruction.
+/// This intrinsic corresponds to the <c> VCVTTPD2DQ / CVTTPD2DQ </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double].
@@ -1431,7 +1434,8 @@ _mm_cvttpd_epi32(__m128d __a)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCVTTSD2SI / CVTTSD2SI </c> instruction.
+/// This intrinsic corresponds to the <c> VCVTTSD2SI / CVTTSD2SI </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double]. The lower 64 bits are used in the
@@ -1559,9 +1563,9 @@ _mm_load1_pd(double const *__dp)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VMOVAPD / MOVAPD </c> instruction + needed
-/// shuffling instructions. In AVX mode, the shuffling may be combined with the
-/// \c VMOVAPD, resulting in only a \c VPERMILPD instruction.
+/// This intrinsic corresponds to the <c> VMOVAPD / MOVAPD </c> instruction +
+/// needed shuffling instructions. In AVX mode, the shuffling may be combined
+/// with the \c VMOVAPD, resulting in only a \c VPERMILPD instruction.
///
/// \param __dp
/// A 16-byte aligned pointer to an array of double-precision values to be
@@ -1624,7 +1628,7 @@ _mm_load_sd(double const *__dp)
/// This intrinsic corresponds to the <c> VMOVHPD / MOVHPD </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [63:0] are written to bits [63:0] of the result.
/// \param __dp
/// A pointer to a 64-bit memory location containing a double-precision
@@ -1651,7 +1655,7 @@ _mm_loadh_pd(__m128d __a, double const *__dp)
/// This intrinsic corresponds to the <c> VMOVLPD / MOVLPD </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [127:64] are written to bits [127:64] of the result.
/// \param __dp
/// A pointer to a 64-bit memory location containing a double-precision
@@ -2645,8 +2649,8 @@ _mm_xor_si128(__m128i __a, __m128i __b)
/// \param a
/// A 128-bit integer vector containing the source operand.
/// \param imm
-/// An immediate value specifying the number of bytes to left-shift
-/// operand \a a.
+/// An immediate value specifying the number of bytes to left-shift operand
+/// \a a.
/// \returns A 128-bit integer vector containing the left-shifted value.
#define _mm_slli_si128(a, imm) __extension__ ({ \
(__m128i)__builtin_shufflevector( \
@@ -3247,7 +3251,8 @@ _mm_cvtsd_si64(__m128d __a)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCVTTSD2SI / CVTTSD2SI </c> instruction.
+/// This intrinsic corresponds to the <c> VCVTTSD2SI / CVTTSD2SI </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [2 x double]. The lower 64 bits are used in the
@@ -3296,7 +3301,8 @@ _mm_cvtps_epi32(__m128 __a)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VCVTTPS2DQ / CVTTPS2DQ </c> instruction.
+/// This intrinsic corresponds to the <c> VCVTTPS2DQ / CVTTPS2DQ </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [4 x float].
@@ -3709,7 +3715,8 @@ _mm_set1_epi8(char __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKLQDQ / PUNPCKLQDQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKLQDQ / PUNPCKLQDQ </c>
+/// instruction.
///
/// \param __q0
/// A 64-bit integral value used to initialize the lower 64 bits of the
@@ -3885,7 +3892,8 @@ _mm_storeu_si128(__m128i *__p, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VMASKMOVDQU / MASKMOVDQU </c> instruction.
+/// This intrinsic corresponds to the <c> VMASKMOVDQU / MASKMOVDQU </c>
+/// instruction.
///
/// \param __d
/// A 128-bit integer vector containing the values to be moved.
@@ -4134,14 +4142,14 @@ _mm_packus_epi16(__m128i __a, __m128i __b)
/// A 128-bit integer vector.
/// \param __imm
/// An immediate value. Bits [3:0] selects values from \a __a to be assigned
-/// to bits[15:0] of the result.
-/// 000: assign values from bits [15:0] of \a __a.
-/// 001: assign values from bits [31:16] of \a __a.
-/// 010: assign values from bits [47:32] of \a __a.
-/// 011: assign values from bits [63:48] of \a __a.
-/// 100: assign values from bits [79:64] of \a __a.
-/// 101: assign values from bits [95:80] of \a __a.
-/// 110: assign values from bits [111:96] of \a __a.
+/// to bits[15:0] of the result. \n
+/// 000: assign values from bits [15:0] of \a __a. \n
+/// 001: assign values from bits [31:16] of \a __a. \n
+/// 010: assign values from bits [47:32] of \a __a. \n
+/// 011: assign values from bits [63:48] of \a __a. \n
+/// 100: assign values from bits [79:64] of \a __a. \n
+/// 101: assign values from bits [95:80] of \a __a. \n
+/// 110: assign values from bits [111:96] of \a __a. \n
/// 111: assign values from bits [127:112] of \a __a.
/// \returns An integer, whose lower 16 bits are selected from the 128-bit
/// integer vector parameter and the remaining bits are assigned zeros.
@@ -4215,16 +4223,16 @@ _mm_movemask_epi8(__m128i __a)
/// \param imm
/// An immediate value containing an 8-bit value specifying which elements to
/// copy from a. The destinations within the 128-bit destination are assigned
-/// values as follows:
-/// Bits [1:0] are used to assign values to bits [31:0] of the result.
-/// Bits [3:2] are used to assign values to bits [63:32] of the result.
-/// Bits [5:4] are used to assign values to bits [95:64] of the result.
-/// Bits [7:6] are used to assign values to bits [127:96] of the result.
-/// Bit value assignments:
-/// 00: assign values from bits [31:0] of a.
-/// 01: assign values from bits [63:32] of a.
-/// 10: assign values from bits [95:64] of a.
-/// 11: assign values from bits [127:96] of a.
+/// values as follows: \n
+/// Bits [1:0] are used to assign values to bits [31:0] of the result. \n
+/// Bits [3:2] are used to assign values to bits [63:32] of the result. \n
+/// Bits [5:4] are used to assign values to bits [95:64] of the result. \n
+/// Bits [7:6] are used to assign values to bits [127:96] of the result. \n
+/// Bit value assignments: \n
+/// 00: assign values from bits [31:0] of \a a. \n
+/// 01: assign values from bits [63:32] of \a a. \n
+/// 10: assign values from bits [95:64] of \a a. \n
+/// 11: assign values from bits [127:96] of \a a.
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shuffle_epi32(a, imm) __extension__ ({ \
(__m128i)__builtin_shufflevector((__v4si)(__m128i)(a), \
@@ -4248,16 +4256,16 @@ _mm_movemask_epi8(__m128i __a)
/// A 128-bit integer vector of [8 x i16]. Bits [127:64] are copied to bits
/// [127:64] of the result.
/// \param imm
-/// An 8-bit immediate value specifying which elements to copy from a.
-/// Bits[1:0] are used to assign values to bits [15:0] of the result.
-/// Bits[3:2] are used to assign values to bits [31:16] of the result.
-/// Bits[5:4] are used to assign values to bits [47:32] of the result.
-/// Bits[7:6] are used to assign values to bits [63:48] of the result.
-/// Bit value assignments:
-/// 00: assign values from bits [15:0] of a.
-/// 01: assign values from bits [31:16] of a.
-/// 10: assign values from bits [47:32] of a.
-/// 11: assign values from bits [63:48] of a.
+/// An 8-bit immediate value specifying which elements to copy from \a a. \n
+/// Bits[1:0] are used to assign values to bits [15:0] of the result. \n
+/// Bits[3:2] are used to assign values to bits [31:16] of the result. \n
+/// Bits[5:4] are used to assign values to bits [47:32] of the result. \n
+/// Bits[7:6] are used to assign values to bits [63:48] of the result. \n
+/// Bit value assignments: \n
+/// 00: assign values from bits [15:0] of \a a. \n
+/// 01: assign values from bits [31:16] of \a a. \n
+/// 10: assign values from bits [47:32] of \a a. \n
+/// 11: assign values from bits [63:48] of \a a. \n
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shufflelo_epi16(a, imm) __extension__ ({ \
(__m128i)__builtin_shufflevector((__v8hi)(__m128i)(a), \
@@ -4282,16 +4290,16 @@ _mm_movemask_epi8(__m128i __a)
/// A 128-bit integer vector of [8 x i16]. Bits [63:0] are copied to bits
/// [63:0] of the result.
/// \param imm
-/// An 8-bit immediate value specifying which elements to copy from a.
-/// Bits[1:0] are used to assign values to bits [79:64] of the result.
-/// Bits[3:2] are used to assign values to bits [95:80] of the result.
-/// Bits[5:4] are used to assign values to bits [111:96] of the result.
-/// Bits[7:6] are used to assign values to bits [127:112] of the result.
-/// Bit value assignments:
-/// 00: assign values from bits [79:64] of a.
-/// 01: assign values from bits [95:80] of a.
-/// 10: assign values from bits [111:96] of a.
-/// 11: assign values from bits [127:112] of a.
+/// An 8-bit immediate value specifying which elements to copy from \a a. \n
+/// Bits[1:0] are used to assign values to bits [79:64] of the result. \n
+/// Bits[3:2] are used to assign values to bits [95:80] of the result. \n
+/// Bits[5:4] are used to assign values to bits [111:96] of the result. \n
+/// Bits[7:6] are used to assign values to bits [127:112] of the result. \n
+/// Bit value assignments: \n
+/// 00: assign values from bits [79:64] of \a a. \n
+/// 01: assign values from bits [95:80] of \a a. \n
+/// 10: assign values from bits [111:96] of \a a. \n
+/// 11: assign values from bits [127:112] of \a a. \n
/// \returns A 128-bit integer vector containing the shuffled values.
#define _mm_shufflehi_epi16(a, imm) __extension__ ({ \
(__m128i)__builtin_shufflevector((__v8hi)(__m128i)(a), \
@@ -4307,28 +4315,29 @@ _mm_movemask_epi8(__m128i __a)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKHBW / PUNPCKHBW </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKHBW / PUNPCKHBW </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [16 x i8].
-/// Bits [71:64] are written to bits [7:0] of the result
-/// Bits [79:72] are written to bits [23:16] of the result.
-/// Bits [87:80] are written to bits [39:32] of the result.
-/// Bits [95:88] are written to bits [55:48] of the result.
-/// Bits [103:96] are written to bits [71:64] of the result.
-/// Bits [111:104] are written to bits [87:80] of the result.
-/// Bits [119:112] are written to bits [103:96] of the result.
+/// Bits [71:64] are written to bits [7:0] of the result. \n
+/// Bits [79:72] are written to bits [23:16] of the result. \n
+/// Bits [87:80] are written to bits [39:32] of the result. \n
+/// Bits [95:88] are written to bits [55:48] of the result. \n
+/// Bits [103:96] are written to bits [71:64] of the result. \n
+/// Bits [111:104] are written to bits [87:80] of the result. \n
+/// Bits [119:112] are written to bits [103:96] of the result. \n
/// Bits [127:120] are written to bits [119:112] of the result.
/// \param __b
-/// A 128-bit vector of [16 x i8].
-/// Bits [71:64] are written to bits [15:8] of the result.
-/// Bits [79:72] are written to bits [31:24] of the result.
-/// Bits [87:80] are written to bits [47:40] of the result.
-/// Bits [95:88] are written to bits [63:56] of the result.
-/// Bits [103:96] are written to bits [79:72] of the result.
-/// Bits [111:104] are written to bits [95:88] of the result.
-/// Bits [119:112] are written to bits [111:104] of the result.
-/// Bits [127:120] are written to bits [127:120] of the destination.
+/// A 128-bit vector of [16 x i8]. \n
+/// Bits [71:64] are written to bits [15:8] of the result. \n
+/// Bits [79:72] are written to bits [31:24] of the result. \n
+/// Bits [87:80] are written to bits [47:40] of the result. \n
+/// Bits [95:88] are written to bits [63:56] of the result. \n
+/// Bits [103:96] are written to bits [79:72] of the result. \n
+/// Bits [111:104] are written to bits [95:88] of the result. \n
+/// Bits [119:112] are written to bits [111:104] of the result. \n
+/// Bits [127:120] are written to bits [127:120] of the result.
/// \returns A 128-bit vector of [16 x i8] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_unpackhi_epi8(__m128i __a, __m128i __b)
@@ -4341,19 +4350,20 @@ _mm_unpackhi_epi8(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKHWD / PUNPCKHWD </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKHWD / PUNPCKHWD </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [8 x i16].
-/// Bits [79:64] are written to bits [15:0] of the result.
-/// Bits [95:80] are written to bits [47:32] of the result.
-/// Bits [111:96] are written to bits [79:64] of the result.
+/// Bits [79:64] are written to bits [15:0] of the result. \n
+/// Bits [95:80] are written to bits [47:32] of the result. \n
+/// Bits [111:96] are written to bits [79:64] of the result. \n
/// Bits [127:112] are written to bits [111:96] of the result.
/// \param __b
/// A 128-bit vector of [8 x i16].
-/// Bits [79:64] are written to bits [31:16] of the result.
-/// Bits [95:80] are written to bits [63:48] of the result.
-/// Bits [111:96] are written to bits [95:80] of the result.
+/// Bits [79:64] are written to bits [31:16] of the result. \n
+/// Bits [95:80] are written to bits [63:48] of the result. \n
+/// Bits [111:96] are written to bits [95:80] of the result. \n
/// Bits [127:112] are written to bits [127:112] of the result.
/// \returns A 128-bit vector of [8 x i16] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4367,15 +4377,16 @@ _mm_unpackhi_epi16(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKHDQ / PUNPCKHDQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKHDQ / PUNPCKHDQ </c>
+/// instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x i32].
-/// Bits [95:64] are written to bits [31:0] of the destination.
+/// A 128-bit vector of [4 x i32]. \n
+/// Bits [95:64] are written to bits [31:0] of the destination. \n
/// Bits [127:96] are written to bits [95:64] of the destination.
/// \param __b
-/// A 128-bit vector of [4 x i32].
-/// Bits [95:64] are written to bits [64:32] of the destination.
+/// A 128-bit vector of [4 x i32]. \n
+/// Bits [95:64] are written to bits [64:32] of the destination. \n
/// Bits [127:96] are written to bits [127:96] of the destination.
/// \returns A 128-bit vector of [4 x i32] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4389,13 +4400,14 @@ _mm_unpackhi_epi32(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKHQDQ / PUNPCKHQDQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKHQDQ / PUNPCKHQDQ </c>
+/// instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x i64].
+/// A 128-bit vector of [2 x i64]. \n
/// Bits [127:64] are written to bits [63:0] of the destination.
/// \param __b
-/// A 128-bit vector of [2 x i64].
+/// A 128-bit vector of [2 x i64]. \n
/// Bits [127:64] are written to bits [127:64] of the destination.
/// \returns A 128-bit vector of [2 x i64] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4409,27 +4421,28 @@ _mm_unpackhi_epi64(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKLBW / PUNPCKLBW </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKLBW / PUNPCKLBW </c>
+/// instruction.
///
/// \param __a
-/// A 128-bit vector of [16 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.
-/// Bits [39:32] are written to bits [71:64] of the result.
-/// Bits [47:40] are written to bits [87:80] of the result.
-/// Bits [55:48] are written to bits [103:96] of the result.
-/// Bits [63:56] are written to bits [119:112] of the destination.
+/// A 128-bit vector of [16 x i8]. \n
+/// Bits [7:0] are written to bits [7:0] of the result. \n
+/// Bits [15:8] are written to bits [23:16] of the result. \n
+/// Bits [23:16] are written to bits [39:32] of the result. \n
+/// Bits [31:24] are written to bits [55:48] of the result. \n
+/// Bits [39:32] are written to bits [71:64] of the result. \n
+/// Bits [47:40] are written to bits [87:80] of the result. \n
+/// Bits [55:48] are written to bits [103:96] of the result. \n
+/// Bits [63:56] are written to bits [119:112] of the result.
/// \param __b
/// A 128-bit vector of [16 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.
-/// Bits [39:32] are written to bits [79:72] of the result.
-/// Bits [47:40] are written to bits [95:88] of the result.
-/// Bits [55:48] are written to bits [111:104] of the result.
+/// Bits [7:0] are written to bits [15:8] of the result. \n
+/// Bits [15:8] are written to bits [31:24] of the result. \n
+/// Bits [23:16] are written to bits [47:40] of the result. \n
+/// Bits [31:24] are written to bits [63:56] of the result. \n
+/// Bits [39:32] are written to bits [79:72] of the result. \n
+/// Bits [47:40] are written to bits [95:88] of the result. \n
+/// Bits [55:48] are written to bits [111:104] of the result. \n
/// Bits [63:56] are written to bits [127:120] of the result.
/// \returns A 128-bit vector of [16 x i8] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4444,19 +4457,20 @@ _mm_unpacklo_epi8(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKLWD / PUNPCKLWD </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKLWD / PUNPCKLWD </c>
+/// instruction.
///
/// \param __a
/// A 128-bit vector of [8 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.
-/// Bits [47:32] are written to bits [79:64] of the result.
+/// Bits [15:0] are written to bits [15:0] of the result. \n
+/// Bits [31:16] are written to bits [47:32] of the result. \n
+/// Bits [47:32] are written to bits [79:64] of the result. \n
/// Bits [63:48] are written to bits [111:96] of the result.
/// \param __b
/// A 128-bit vector of [8 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.
-/// Bits [47:32] are written to bits [95:80] of the result.
+/// Bits [15:0] are written to bits [31:16] of the result. \n
+/// Bits [31:16] are written to bits [63:48] of the result. \n
+/// Bits [47:32] are written to bits [95:80] of the result. \n
/// Bits [63:48] are written to bits [127:112] of the result.
/// \returns A 128-bit vector of [8 x i16] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4470,15 +4484,16 @@ _mm_unpacklo_epi16(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKLDQ / PUNPCKLDQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKLDQ / PUNPCKLDQ </c>
+/// instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x i32].
-/// Bits [31:0] are written to bits [31:0] of the destination.
+/// A 128-bit vector of [4 x i32]. \n
+/// Bits [31:0] are written to bits [31:0] of the destination. \n
/// Bits [63:32] are written to bits [95:64] of the destination.
/// \param __b
-/// A 128-bit vector of [4 x i32].
-/// Bits [31:0] are written to bits [64:32] of the destination.
+/// A 128-bit vector of [4 x i32]. \n
+/// Bits [31:0] are written to bits [64:32] of the destination. \n
/// Bits [63:32] are written to bits [127:96] of the destination.
/// \returns A 128-bit vector of [4 x i32] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -4492,14 +4507,15 @@ _mm_unpacklo_epi32(__m128i __a, __m128i __b)
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPUNPCKLQDQ / PUNPCKLQDQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPUNPCKLQDQ / PUNPCKLQDQ </c>
+/// instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x i64].
-/// Bits [63:0] are written to bits [63:0] of the destination.
+/// A 128-bit vector of [2 x i64]. \n
+/// Bits [63:0] are written to bits [63:0] of the destination. \n
/// \param __b
-/// A 128-bit vector of [2 x i64].
-/// Bits [63:0] are written to bits [127:64] of the destination.
+/// A 128-bit vector of [2 x i64]. \n
+/// Bits [63:0] are written to bits [127:64] of the destination. \n
/// \returns A 128-bit vector of [2 x i64] containing the interleaved values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_unpacklo_epi64(__m128i __a, __m128i __b)
@@ -4568,10 +4584,10 @@ _mm_move_epi64(__m128i __a)
/// This intrinsic corresponds to the <c> VUNPCKHPD / UNPCKHPD </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [127:64] are written to bits [63:0] of the destination.
/// \param __b
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [127:64] are written to bits [127:64] of the destination.
/// \returns A 128-bit vector of [2 x double] containing the interleaved values.
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -4589,10 +4605,10 @@ _mm_unpackhi_pd(__m128d __a, __m128d __b)
/// This intrinsic corresponds to the <c> VUNPCKLPD / UNPCKLPD </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [63:0] are written to bits [63:0] of the destination.
/// \param __b
-/// A 128-bit vector of [2 x double].
+/// A 128-bit vector of [2 x double]. \n
/// Bits [63:0] are written to bits [127:64] of the destination.
/// \returns A 128-bit vector of [2 x double] containing the interleaved values.
static __inline__ __m128d __DEFAULT_FN_ATTRS
@@ -4639,11 +4655,11 @@ _mm_movemask_pd(__m128d __a)
/// A 128-bit vector of [2 x double].
/// \param i
/// An 8-bit immediate value. The least significant two bits specify which
-/// elements to copy from a and b:
-/// Bit[0] = 0: lower element of a copied to lower element of result.
-/// Bit[0] = 1: upper element of a copied to lower element of result.
-/// Bit[1] = 0: lower element of \a b copied to upper element of result.
-/// Bit[1] = 1: upper element of \a b copied to upper element of result.
+/// elements to copy from a and b: \n
+/// Bit[0] = 0: lower element of a copied to lower element of result. \n
+/// Bit[0] = 1: upper element of a copied to lower element of result. \n
+/// Bit[1] = 0: lower element of \a b copied to upper element of result. \n
+/// Bit[1] = 1: upper element of \a b copied to upper element of result. \n
/// \returns A 128-bit vector of [2 x double] containing the shuffled values.
#define _mm_shuffle_pd(a, b, i) __extension__ ({ \
(__m128d)__builtin_shufflevector((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \
diff --git a/lib/Headers/f16cintrin.h b/lib/Headers/f16cintrin.h
index fbfc1860f9f98148408766c3e45968e8b88bfe5b..180712ffc680c92b974a4619ecfc7679bace074a 100644
--- a/lib/Headers/f16cintrin.h
+++ b/lib/Headers/f16cintrin.h
@@ -65,11 +65,11 @@ _cvtsh_ss(unsigned short __a)
/// A 32-bit single-precision float value to be converted to a 16-bit
/// half-precision float value.
/// \param imm
-/// An immediate value controlling rounding using bits [2:0]:
-/// 000: Nearest
-/// 001: Down
-/// 010: Up
-/// 011: Truncate
+/// An immediate value controlling rounding using bits [2:0]: \n
+/// 000: Nearest \n
+/// 001: Down \n
+/// 010: Up \n
+/// 011: Truncate \n
/// 1XX: Use MXCSR.RC for rounding
/// \returns The converted 16-bit half-precision float value.
#define _cvtss_sh(a, imm) \
@@ -90,11 +90,11 @@ _cvtsh_ss(unsigned short __a)
/// \param a
/// A 128-bit vector containing 32-bit float values.
/// \param imm
-/// An immediate value controlling rounding using bits [2:0]:
-/// 000: Nearest
-/// 001: Down
-/// 010: Up
-/// 011: Truncate
+/// An immediate value controlling rounding using bits [2:0]: \n
+/// 000: Nearest \n
+/// 001: Down \n
+/// 010: Up \n
+/// 011: Truncate \n
/// 1XX: Use MXCSR.RC for rounding
/// \returns A 128-bit vector containing converted 16-bit half-precision float
/// values. The lower 64 bits are used to store the converted 16-bit
diff --git a/lib/Headers/immintrin.h b/lib/Headers/immintrin.h
index 0bdc921c788a8bad424bc24b0989d011708acf78..7f91d49fbcec0126cf9dd3a7862a62be33fd7977 100644
--- a/lib/Headers/immintrin.h
+++ b/lib/Headers/immintrin.h
@@ -84,11 +84,11 @@
/// A 256-bit vector containing 32-bit single-precision float values to be
/// converted to 16-bit half-precision float values.
/// \param imm
-/// An immediate value controlling rounding using bits [2:0]:
-/// 000: Nearest
-/// 001: Down
-/// 010: Up
-/// 011: Truncate
+/// An immediate value controlling rounding using bits [2:0]: \n
+/// 000: Nearest \n
+/// 001: Down \n
+/// 010: Up \n
+/// 011: Truncate \n
/// 1XX: Use MXCSR.RC for rounding
/// \returns A 128-bit vector containing the converted 16-bit half-precision
/// float values.
diff --git a/lib/Headers/mmintrin.h b/lib/Headers/mmintrin.h
index 55db470de391c471d972a6fb084a6b960cbdf8d5..e0c277a65a33cfa923d73280a00dc07e4d624a67 100644
--- a/lib/Headers/mmintrin.h
+++ b/lib/Headers/mmintrin.h
@@ -211,16 +211,16 @@ _mm_packs_pu16(__m64 __m1, __m64 __m2)
/// This intrinsic corresponds to the <c> PUNPCKHBW </c> 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.
+/// A 64-bit integer vector of [8 x i8]. \n
+/// Bits [39:32] are written to bits [7:0] of the result. \n
+/// Bits [47:40] are written to bits [23:16] of the result. \n
+/// Bits [55:48] are written to bits [39:32] of the result. \n
/// 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 [39:32] are written to bits [15:8] of the result. \n
+/// Bits [47:40] are written to bits [31:24] of the result. \n
+/// Bits [55:48] are written to bits [47:40] of the result. \n
/// 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.
@@ -239,11 +239,11 @@ _mm_unpackhi_pi8(__m64 __m1, __m64 __m2)
///
/// \param __m1
/// A 64-bit integer vector of [4 x i16].
-/// Bits [47:32] are written to bits [15:0] of the result.
+/// Bits [47:32] are written to bits [15:0] of the result. \n
/// 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 [47:32] are written to bits [31:16] of the result. \n
/// 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.
@@ -283,15 +283,15 @@ _mm_unpackhi_pi32(__m64 __m1, __m64 __m2)
///
/// \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 [7:0] are written to bits [7:0] of the result. \n
+/// Bits [15:8] are written to bits [23:16] of the result. \n
+/// Bits [23:16] are written to bits [39:32] of the result. \n
/// 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 [7:0] are written to bits [15:8] of the result. \n
+/// Bits [15:8] are written to bits [31:24] of the result. \n
+/// Bits [23:16] are written to bits [47:40] of the result. \n
/// 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.
@@ -310,11 +310,11 @@ _mm_unpacklo_pi8(__m64 __m1, __m64 __m2)
///
/// \param __m1
/// A 64-bit integer vector of [4 x i16].
-/// Bits [15:0] are written to bits [15:0] of the result.
+/// Bits [15:0] are written to bits [15:0] of the result. \n
/// 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 [15:0] are written to bits [31:16] of the result. \n
/// 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.
diff --git a/lib/Headers/pmmintrin.h b/lib/Headers/pmmintrin.h
index 5f201fb53bd10e7a6a9d065079c598d4eb495aec..d4f6487af179cc1fd96a4e32ff8b4526c4b0f3ad 100644
--- a/lib/Headers/pmmintrin.h
+++ b/lib/Headers/pmmintrin.h
@@ -115,18 +115,18 @@ _mm_hsub_ps(__m128 __a, __m128 __b)
/// \brief Moves and duplicates high-order (odd-indexed) values from a 128-bit
/// vector of [4 x float] to float values stored in a 128-bit vector of
-/// [4 x float].
-/// Bits [127:96] of the source are written to bits [127:96] and [95:64] of
-/// the destination.
-/// Bits [63:32] of the source are written to bits [63:32] and [31:0] of the
-/// destination.
+/// [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSHDUP </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x float].
+/// A 128-bit vector of [4 x float]. \n
+/// Bits [127:96] of the source are written to bits [127:96] and [95:64] of
+/// the destination. \n
+/// Bits [63:32] of the source are written to bits [63:32] and [31:0] of the
+/// destination.
/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
/// values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
@@ -135,20 +135,19 @@ _mm_movehdup_ps(__m128 __a)
return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 1, 1, 3, 3);
}
-/// \brief Duplicates low-order (even-indexed) values from a 128-bit
-/// vector of [4 x float] to float values stored in a 128-bit vector of
-/// [4 x float].
-/// Bits [95:64] of the source are written to bits [127:96] and [95:64] of
-/// the destination.
-/// Bits [31:0] of the source are written to bits [63:32] and [31:0] of the
-/// destination.
+/// \brief Duplicates low-order (even-indexed) values from a 128-bit vector of
+/// [4 x float] to float values stored in a 128-bit vector of [4 x float].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VMOVSLDUP </c> instruction.
///
/// \param __a
-/// A 128-bit vector of [4 x float].
+/// A 128-bit vector of [4 x float] \n
+/// Bits [95:64] of the source are written to bits [127:96] and [95:64] of
+/// the destination. \n
+/// Bits [31:0] of the source are written to bits [63:32] and [31:0] of the
+/// destination.
/// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
/// values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
diff --git a/lib/Headers/tmmintrin.h b/lib/Headers/tmmintrin.h
index 6a8e5c1bb4ec10b1576b3825202eac687a7934d4..80664043a06fb841dd3802b73327ff620e2385d3 100644
--- a/lib/Headers/tmmintrin.h
+++ b/lib/Headers/tmmintrin.h
@@ -580,11 +580,11 @@ _mm_mulhrs_pi16(__m64 __a, __m64 __b)
/// \param __b
/// A 128-bit integer vector containing control bytes corresponding to
/// positions in the destination:
-/// Bit 7:
-/// 1: Clear the corresponding byte in the destination.
+/// Bit 7: \n
+/// 1: Clear the corresponding byte in the destination. \n
/// 0: Copy the selected source byte to the corresponding byte in the
-/// destination.
-/// Bits [6:4] Reserved.
+/// destination. \n
+/// Bits [6:4] Reserved. \n
/// Bits [3:0] select the source byte to be copied.
/// \returns A 128-bit integer vector containing the copied or cleared values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
@@ -606,10 +606,10 @@ _mm_shuffle_epi8(__m128i __a, __m128i __b)
/// \param __b
/// A 64-bit integer vector containing control bytes corresponding to
/// positions in the destination:
-/// Bit 7:
-/// 1: Clear the corresponding byte in the destination.
+/// Bit 7: \n
+/// 1: Clear the corresponding byte in the destination. \n
/// 0: Copy the selected source byte to the corresponding byte in the
-/// destination.
+/// destination. \n
/// Bits [3:0] select the source byte to be copied.
/// \returns A 64-bit integer vector containing the copied or cleared values.
static __inline__ __m64 __DEFAULT_FN_ATTRS