[DOXYGEN] Formatting changes for better intrinsics documentation rendering

(1) I added some \see cross-references to a few select intrinsics that are related (and have the same or similar semantics). 

(2) pmmintrin.h, smmintrin.h, xmmintrin.h have very few minor formatting changes. They make rendering of our intrinsics documentation better. 

llvm-svn: 333065

5 files changed, 43 insertions, 31 deletions

diff --git a/clang/lib/Headers/bmiintrin.h b/clang/lib/Headers/bmiintrin.h
index e995c80ab5e..d03bef442a2 100644
--- a/clang/lib/Headers/bmiintrin.h
+++ b/clang/lib/Headers/bmiintrin.h
@@ -100,6 +100,7 @@ __andn_u32(unsigned int __X, unsigned int __Y)
 ///    number of bits to be extracted.
 /// \returns An unsigned integer whose least significant bits contain the
 ///    extracted bits.
+/// \see _bextr_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __bextr_u32(unsigned int __X, unsigned int __Y)
 {
@@ -124,6 +125,7 @@ __bextr_u32(unsigned int __X, unsigned int __Y)
 ///    Bits [7:0] specify the number of bits.
 /// \returns An unsigned integer whose least significant bits contain the
 ///    extracted bits.
+/// \see __bextr_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 _bextr_u32(unsigned int __X, unsigned int __Y, unsigned int __Z)
 {
@@ -261,6 +263,7 @@ __andn_u64 (unsigned long long __X, unsigned long long __Y)
 ///    the number of bits to be extracted.
 /// \returns An unsigned 64-bit integer whose least significant bits contain the
 ///    extracted bits.
+/// \see _bextr_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __bextr_u64(unsigned long long __X, unsigned long long __Y)
 {
@@ -285,6 +288,7 @@ __bextr_u64(unsigned long long __X, unsigned long long __Y)
 ///    Bits [7:0] specify the number of bits.
 /// \returns An unsigned 64-bit integer whose least significant bits contain the
 ///    extracted bits.
+/// \see __bextr_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 _bextr_u64(unsigned long long __X, unsigned int __Y, unsigned int __Z)
 {
diff --git a/clang/lib/Headers/lzcntintrin.h b/clang/lib/Headers/lzcntintrin.h
index 152e07dfbec..558f1828f0e 100644
--- a/clang/lib/Headers/lzcntintrin.h
+++ b/clang/lib/Headers/lzcntintrin.h
@@ -57,6 +57,7 @@ __lzcnt16(unsigned short __X)
 ///    An unsigned 32-bit integer whose leading zeros are to be counted.
 /// \returns An unsigned 32-bit integer containing the number of leading zero
 ///    bits in the operand.
+/// \see _lzcnt_u32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 __lzcnt32(unsigned int __X)
 {
@@ -73,6 +74,7 @@ __lzcnt32(unsigned int __X)
 ///    An unsigned 32-bit integer whose leading zeros are to be counted.
 /// \returns An unsigned 32-bit integer containing the number of leading zero
 ///    bits in the operand.
+/// \see __lzcnt32
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 _lzcnt_u32(unsigned int __X)
 {
@@ -90,6 +92,7 @@ _lzcnt_u32(unsigned int __X)
 ///    An unsigned 64-bit integer whose leading zeros are to be counted.
 /// \returns An unsigned 64-bit integer containing the number of leading zero
 ///    bits in the operand.
+/// \see _lzcnt_u64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 __lzcnt64(unsigned long long __X)
 {
@@ -106,6 +109,7 @@ __lzcnt64(unsigned long long __X)
 ///    An unsigned 64-bit integer whose leading zeros are to be counted.
 /// \returns An unsigned 64-bit integer containing the number of leading zero
 ///    bits in the operand.
+/// \see __lzcnt64
 static __inline__ unsigned long long __DEFAULT_FN_ATTRS
 _lzcnt_u64(unsigned long long __X)
 {
diff --git a/clang/lib/Headers/pmmintrin.h b/clang/lib/Headers/pmmintrin.h
index 77101b0dc2e..fc27d7cda0a 100644
--- a/clang/lib/Headers/pmmintrin.h
+++ b/clang/lib/Headers/pmmintrin.h
@@ -229,7 +229,7 @@ _mm_hsub_pd(__m128d __a, __m128d __b)
 /// \headerfile <x86intrin.h>
 ///
 /// \code
-/// __m128d _mm_loaddup_pd(double const * dp);
+/// __m128d _mm_loaddup_pd(double const *dp);
 /// \endcode
 ///
 /// This intrinsic corresponds to the <c> VMOVDDUP </c> instruction.
diff --git a/clang/lib/Headers/smmintrin.h b/clang/lib/Headers/smmintrin.h
index 99e50bab679..645af418b58 100644
--- a/clang/lib/Headers/smmintrin.h
+++ b/clang/lib/Headers/smmintrin.h
@@ -493,7 +493,7 @@ _mm_blendv_ps (__m128 __V1, __m128 __V2, __m128 __M)
 /// \param __V2
 ///    A 128-bit vector of [16 x i8].
 /// \param __M
-///    A 128-bit vector operand, with mask bits 127, 119, 111 ... 7 specifying
+///    A 128-bit vector operand, with mask bits 127, 119, 111...7 specifying
 ///    how the values are to be copied. The position of the mask bit corresponds
 ///    to the most significant bit of a copied value. When a mask bit is 0, the
 ///    corresponding 8-bit element in operand \a __V1 is copied to the same
@@ -1277,8 +1277,8 @@ _mm_cvtepi8_epi16(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVSXBD / PMOVSXBD </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [16 x i8]. The lower four 8-bit elements are sign-
-///    extended to 32-bit values.
+///    A 128-bit vector of [16 x i8]. The lower four 8-bit elements are
+///    sign-extended to 32-bit values.
 /// \returns A 128-bit vector of [4 x i32] containing the sign-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi8_epi32(__m128i __V)
@@ -1298,8 +1298,8 @@ _mm_cvtepi8_epi32(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVSXBQ / PMOVSXBQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [16 x i8]. The lower two 8-bit elements are sign-
-///    extended to 64-bit values.
+///    A 128-bit vector of [16 x i8]. The lower two 8-bit elements are
+///    sign-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the sign-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi8_epi64(__m128i __V)
@@ -1319,8 +1319,8 @@ _mm_cvtepi8_epi64(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVSXWD / PMOVSXWD </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [8 x i16]. The lower four 16-bit elements are sign-
-///    extended to 32-bit values.
+///    A 128-bit vector of [8 x i16]. The lower four 16-bit elements are
+///    sign-extended to 32-bit values.
 /// \returns A 128-bit vector of [4 x i32] containing the sign-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi16_epi32(__m128i __V)
@@ -1338,8 +1338,8 @@ _mm_cvtepi16_epi32(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVSXWQ / PMOVSXWQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [8 x i16]. The lower two 16-bit elements are sign-
-///    extended to 64-bit values.
+///    A 128-bit vector of [8 x i16]. The lower two 16-bit elements are
+///     sign-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the sign-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi16_epi64(__m128i __V)
@@ -1357,8 +1357,8 @@ _mm_cvtepi16_epi64(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVSXDQ / PMOVSXDQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [4 x i32]. The lower two 32-bit elements are sign-
-///    extended to 64-bit values.
+///    A 128-bit vector of [4 x i32]. The lower two 32-bit elements are
+///    sign-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the sign-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi32_epi64(__m128i __V)
@@ -1377,8 +1377,8 @@ _mm_cvtepi32_epi64(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXBW / PMOVZXBW </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [16 x i8]. The lower eight 8-bit elements are zero-
-///    extended to 16-bit values.
+///    A 128-bit vector of [16 x i8]. The lower eight 8-bit elements are
+///    zero-extended to 16-bit values.
 /// \returns A 128-bit vector of [8 x i16] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu8_epi16(__m128i __V)
@@ -1396,8 +1396,8 @@ _mm_cvtepu8_epi16(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXBD / PMOVZXBD </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [16 x i8]. The lower four 8-bit elements are zero-
-///    extended to 32-bit values.
+///    A 128-bit vector of [16 x i8]. The lower four 8-bit elements are
+///    zero-extended to 32-bit values.
 /// \returns A 128-bit vector of [4 x i32] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu8_epi32(__m128i __V)
@@ -1415,8 +1415,8 @@ _mm_cvtepu8_epi32(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXBQ / PMOVZXBQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [16 x i8]. The lower two 8-bit elements are zero-
-///    extended to 64-bit values.
+///    A 128-bit vector of [16 x i8]. The lower two 8-bit elements are
+///    zero-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu8_epi64(__m128i __V)
@@ -1434,8 +1434,8 @@ _mm_cvtepu8_epi64(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXWD / PMOVZXWD </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [8 x i16]. The lower four 16-bit elements are zero-
-///    extended to 32-bit values.
+///    A 128-bit vector of [8 x i16]. The lower four 16-bit elements are
+///    zero-extended to 32-bit values.
 /// \returns A 128-bit vector of [4 x i32] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu16_epi32(__m128i __V)
@@ -1453,8 +1453,8 @@ _mm_cvtepu16_epi32(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXWQ / PMOVZXWQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [8 x i16]. The lower two 16-bit elements are zero-
-///    extended to 64-bit values.
+///    A 128-bit vector of [8 x i16]. The lower two 16-bit elements are
+///    zero-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu16_epi64(__m128i __V)
@@ -1472,8 +1472,8 @@ _mm_cvtepu16_epi64(__m128i __V)
 /// This intrinsic corresponds to the <c> VPMOVZXDQ / PMOVZXDQ </c> instruction.
 ///
 /// \param __V
-///    A 128-bit vector of [4 x i32]. The lower two 32-bit elements are zero-
-///    extended to 64-bit values.
+///    A 128-bit vector of [4 x i32]. The lower two 32-bit elements are
+///    zero-extended to 64-bit values.
 /// \returns A 128-bit vector of [2 x i64] containing the zero-extended values.
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepu32_epi64(__m128i __V)
@@ -1534,14 +1534,14 @@ _mm_packus_epi32(__m128i __V1, __m128i __V2)
 ///    \code
 ///    // M2 represents bit 2 of the immediate operand
 ///    // M10 represents bits [1:0] of the immediate operand
-///    i = M2 * 4
-///    j = M10 * 4
+///    i = M2 * 4;
+///    j = M10 * 4;
 ///    for (k = 0; k < 8; k = k + 1) {
-///      d0 = abs(X[i + k + 0] - Y[j + 0])
-///      d1 = abs(X[i + k + 1] - Y[j + 1])
-///      d2 = abs(X[i + k + 2] - Y[j + 2])
-///      d3 = abs(X[i + k + 3] - Y[j + 3])
-///      r[k] = d0 + d1 + d2 + d3
+///      d0 = abs(X[i + k + 0] - Y[j + 0]);
+///      d1 = abs(X[i + k + 1] - Y[j + 1]);
+///      d2 = abs(X[i + k + 2] - Y[j + 2]);
+///      d3 = abs(X[i + k + 3] - Y[j + 3]);
+///      r[k] = d0 + d1 + d2 + d3;
 ///    }
 ///    \endcode
 /// \returns A 128-bit integer vector containing the sums of the sets of
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 9590e475109..0103a997dda 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2495,10 +2495,14 @@ extern "C" {
 ///
 ///    For example, the following expression checks if an overflow exception has
 ///    occurred:
+///    \code
 ///      ( _mm_getcsr() & _MM_EXCEPT_OVERFLOW )
+///    \endcode
 ///
 ///    The following expression gets the current rounding mode:
+///    \code
 ///      _MM_GET_ROUNDING_MODE()
+///    \endcode
 ///
 /// \headerfile <x86intrin.h>
 ///