smmintrin.h documentation fixes and updates

[dyung]

Summary

This is the result of several patches we made internally to update the documentation that we would like to have reviewed for possible submission.

The changes include:

1. Fix formatting issue due to hyphenated terms at line breaks.
2. Fix typo

These patches were made by Craig Flores

[RKSimon]

LGTM

cfe/trunk/lib/Headers/smmintrin.h

 /// \param M
 ///    An immediate integer operand. Mask bits [5:4] determine which elements
 ///    of the input vectors are used, with bit [4] corresponding to the lowest
 ///    element and bit [5] corresponding to the highest element of each of [2 x
 ///    double] vector. If a bit is set, the corresponding elements from the two
 ///    input vectors are used as an input for dot product; otherwise that input
 ///    is treated as zero. Bits [1:0] determine which elements of the result
 ///    will receive a copy of the final dot product, with bit [0] corresponding
-///    to the lowest element and bit [3] corresponding to the highest element of
+///    to the lowest element and bit [1] corresponding to the highest element of
 ///    each [2 x double] vector. If a bit is set, the dot product is returned in
 ///    the corresponding element; otherwise that element is set to zero.
 #define _mm_dp_pd(X, Y, M) __extension__ ({\
   (__m128d) __builtin_ia32_dppd((__v2df)(__m128d)(X), \
                                 (__v2df)(__m128d)(Y), (M)); })
 
 /* SSE4 Streaming Load Hint Instruction.  */
 /// \brief Loads integer values from a 128-bit aligned memory location to a

 ///    Bits [5:4] specify the bits in the result to which the selected bits
 ///    from operand \a Y are copied: \n
 ///      00: Copies the selected bits from \a Y to result bits [31:0]. \n
 ///      01: Copies the selected bits from \a Y to result bits [63:32]. \n
 ///      10: Copies the selected bits from \a Y to result bits [95:64]. \n
 ///      11: Copies the selected bits from \a Y to result bits [127:96]. \n
 ///    Bits[3:0]: If any of these bits are set, the corresponding result
 ///    element is cleared.
-/// \returns A 128-bit vector of [4 x float] containing the copied single-
-///    precision floating point elements from the operands.
+/// \returns A 128-bit vector of [4 x float] containing the copied
+///    single-precision floating point elements from the operands.
 #define _mm_insert_ps(X, Y, N) __builtin_ia32_insertps128((X), (Y), (N))
 
 /// \brief Extracts a 32-bit integer from a 128-bit vector of [4 x float] and
 ///    returns it, using the immediate value parameter \a N as a selector.
 ///
 /// \headerfile <x86intrin.h>
 ///
 /// \code