49 ///    A 128-bit vector of [4 x float] containing one of the source operands.
52 ///    A 128-bit vector of [4 x float] containing one of the source operands.
54 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the sum
64 /// Adds two 128-bit vectors of [4 x float], and returns the results of
72 ///    A 128-bit vector of [4 x float] containing one of the source operands.
74 ///    A 128-bit vector of [4 x float] containing one of the source operands.
75 /// \returns A 128-bit vector of [4 x float] containing the sums of both
91 ///    A 128-bit vector of [4 x float] containing the minuend. The lower 32 bits
94 ///    A 128-bit vector of [4 x float] containing the subtrahend. The lower 32
96 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
107 ///    operand, both of which are 128-bit vectors of [4 x float] and returns
115 ///    A 128-bit vector of [4 x float] containing the minuend.
117 ///    A 128-bit vector of [4 x float] containing the subtrahend.
118 /// \returns A 128-bit vector of [4 x float] containing the differences between
134 ///    A 128-bit vector of [4 x float] containing one of the source operands.
137 ///    A 128-bit vector of [4 x float] containing one of the source operands.
139 /// \returns A 128-bit vector of [4 x float] containing the product of the lower
149 /// Multiplies two 128-bit vectors of [4 x float] and returns the
157 ///    A 128-bit vector of [4 x float] containing one of the source operands.
159 ///    A 128-bit vector of [4 x float] containing one of the source operands.
160 /// \returns A 128-bit vector of [4 x float] containing the products of both
176 ///    A 128-bit vector of [4 x float] containing the dividend. The lower 32
179 ///    A 128-bit vector of [4 x float] containing the divisor. The lower 32 bits
181 /// \returns A 128-bit vector of [4 x float] containing the quotients of the
191 /// Divides two 128-bit vectors of [4 x float].
198 ///    A 128-bit vector of [4 x float] containing the dividend.
200 ///    A 128-bit vector of [4 x float] containing the divisor.
201 /// \returns A 128-bit vector of [4 x float] containing the quotients of both
210 ///    of a 128-bit vector of [4 x float].
217 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
219 /// \returns A 128-bit vector of [4 x float] containing the square root of the
228 ///    of [4 x float].
235 ///    A 128-bit vector of [4 x float].
236 /// \returns A 128-bit vector of [4 x float] containing the square roots of the
245 ///    low-order bits of a 128-bit vector of [4 x float].
252 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
254 /// \returns A 128-bit vector of [4 x float] containing the approximate
263 ///    128-bit vector of [4 x float].
270 ///    A 128-bit vector of [4 x float].
271 /// \returns A 128-bit vector of [4 x float] containing the approximate
280 ///    stored in the low-order bits of a 128-bit vector of [4 x float].
287 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
289 /// \returns A 128-bit vector of [4 x float] containing the approximate
299 ///    values stored in a 128-bit vector of [4 x float].
306 ///    A 128-bit vector of [4 x float].
307 /// \returns A 128-bit vector of [4 x float] containing the approximate
317 ///    vector of [4 x float].
326 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
329 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
331 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
340 /// Compares two 128-bit vectors of [4 x float] and returns the lesser
350 ///    A 128-bit vector of [4 x float] containing one of the operands.
352 ///    A 128-bit vector of [4 x float] containing one of the operands.
353 /// \returns A 128-bit vector of [4 x float] containing the minimum values
363 ///    vector of [4 x float].
372 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
375 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
377 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
386 /// Compares two 128-bit vectors of [4 x float] and returns the greater
396 ///    A 128-bit vector of [4 x float] containing one of the operands.
398 ///    A 128-bit vector of [4 x float] containing one of the operands.
399 /// \returns A 128-bit vector of [4 x float] containing the maximum values
407 /// Performs a bitwise AND of two 128-bit vectors of [4 x float].
417 /// \returns A 128-bit vector of [4 x float] containing the bitwise AND of the
425 /// Performs a bitwise AND of two 128-bit vectors of [4 x float], using
434 ///    A 128-bit vector of [4 x float] containing the first source operand. The
437 ///    A 128-bit vector of [4 x float] containing the second source operand.
438 /// \returns A 128-bit vector of [4 x float] containing the bitwise AND of the
447 /// Performs a bitwise OR of two 128-bit vectors of [4 x float].
454 ///    A 128-bit vector of [4 x float] containing one of the source operands.
456 ///    A 128-bit vector of [4 x float] containing one of the source operands.
457 /// \returns A 128-bit vector of [4 x float] containing the bitwise OR of the
466 ///    [4 x float].
473 ///    A 128-bit vector of [4 x float] containing one of the source operands.
475 ///    A 128-bit vector of [4 x float] containing one of the source operands.
476 /// \returns A 128-bit vector of [4 x float] containing the bitwise exclusive OR
488 ///    low-order bits of a vector [4 x float].
496 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
499 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
501 /// \returns A 128-bit vector of [4 x float] containing the comparison results
510 ///    128-bit vectors of [4 x float] for equality.
520 ///    A 128-bit vector of [4 x float].
522 ///    A 128-bit vector of [4 x float].
523 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
535 ///    low-order bits of a vector of [4 x float].
543 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
546 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
548 /// \returns A 128-bit vector of [4 x float] containing the comparison results
557 ///    128-bit vectors of [4 x float] to determine if the values in the first
568 ///    A 128-bit vector of [4 x float].
570 ///    A 128-bit vector of [4 x float].
571 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
583 ///    the low-order bits of a vector of [4 x float].
591 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
594 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
596 /// \returns A 128-bit vector of [4 x float] containing the comparison results
605 ///    128-bit vectors of [4 x float] to determine if the values in the first
616 ///    A 128-bit vector of [4 x float].
618 ///    A 128-bit vector of [4 x float].
619 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
631 ///    low-order bits of a vector of [4 x float].
639 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
642 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
644 /// \returns A 128-bit vector of [4 x float] containing the comparison results
651                                          4, 1, 2, 3);  in _mm_cmpgt_ss()
655 ///    128-bit vectors of [4 x float] to determine if the values in the first
666 ///    A 128-bit vector of [4 x float].
668 ///    A 128-bit vector of [4 x float].
669 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
681 ///    low-order bits of a vector of [4 x float].
689 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
692 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
694 /// \returns A 128-bit vector of [4 x float] containing the comparison results
701                                          4, 1, 2, 3);  in _mm_cmpge_ss()
705 ///    128-bit vectors of [4 x float] to determine if the values in the first
716 ///    A 128-bit vector of [4 x float].
718 ///    A 128-bit vector of [4 x float].
719 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
730 ///    low-order bits of a vector of [4 x float].
739 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
742 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
744 /// \returns A 128-bit vector of [4 x float] containing the comparison results
753 ///    128-bit vectors of [4 x float] for inequality.
764 ///    A 128-bit vector of [4 x float].
766 ///    A 128-bit vector of [4 x float].
767 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
779 ///    low-order bits of a vector of [4 x float].
788 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
791 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
793 /// \returns A 128-bit vector of [4 x float] containing the comparison results
802 ///    128-bit vectors of [4 x float] to determine if the values in the first
814 ///    A 128-bit vector of [4 x float].
816 ///    A 128-bit vector of [4 x float].
817 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
829 ///    low-order bits of a vector of [4 x float].
838 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
841 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
843 /// \returns A 128-bit vector of [4 x float] containing the comparison results
852 ///    128-bit vectors of [4 x float] to determine if the values in the first
864 ///    A 128-bit vector of [4 x float].
866 ///    A 128-bit vector of [4 x float].
867 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
879 ///    low-order bits of a vector of [4 x float].
888 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
891 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
893 /// \returns A 128-bit vector of [4 x float] containing the comparison results
900                                          4, 1, 2, 3);  in _mm_cmpngt_ss()
904 ///    128-bit vectors of [4 x float] to determine if the values in the first
916 ///    A 128-bit vector of [4 x float].
918 ///    A 128-bit vector of [4 x float].
919 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
931 ///    low-order bits of a vector of [4 x float].
940 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
943 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
945 /// \returns A 128-bit vector of [4 x float] containing the comparison results
952                                          4, 1, 2, 3);  in _mm_cmpnge_ss()
956 ///    128-bit vectors of [4 x float] to determine if the values in the first
968 ///    A 128-bit vector of [4 x float].
970 ///    A 128-bit vector of [4 x float].
971 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
992 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
995 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
997 /// \returns A 128-bit vector of [4 x float] containing the comparison results
1006 ///    128-bit vectors of [4 x float] to determine if the values in the first
1019 ///    A 128-bit vector of [4 x float].
1021 ///    A 128-bit vector of [4 x float].
1022 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
1043 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
1046 ///    A 128-bit vector of [4 x float] containing one of the operands. The lower
1048 /// \returns A 128-bit vector of [4 x float] containing the comparison results
1057 ///    128-bit vectors of [4 x float] to determine if the values in the first
1070 ///    A 128-bit vector of [4 x float].
1072 ///    A 128-bit vector of [4 x float].
1073 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
1092 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1095 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1117 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1120 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1141 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1144 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1165 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1168 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1189 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1192 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1213 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1216 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1236 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1239 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1260 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1263 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1284 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1287 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1308 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1311 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1332 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1335 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1355 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1358 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1368 ///    [4 x float] into a 32-bit integer.
1380 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1390 ///    [4 x float] into a 32-bit integer.
1402 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1414 ///    [4 x float] into a 64-bit integer.
1426 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1438 ///    [4 x float] into a 64-bit vector of [2 x i32].
1449 ///    A 128-bit vector of [4 x float].
1458 ///    [4 x float] into a 64-bit vector of [2 x i32].
1469 ///    A 128-bit vector of [4 x float].
1477 /// Converts the lower (first) element of a vector of [4 x float] into a signed
1490 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1499 /// Converts the lower (first) element of a vector of [4 x float] into a signed
1512 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1522 /// Converts the lower (first) element of a vector of [4 x float] into a signed
1535 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1545 /// Converts the lower (first) two elements of a 128-bit vector of [4 x float]
1547 ///    returned in a 64-bit vector of [2 x i32].
1559 ///    A 128-bit vector of [4 x float].
1567 /// Converts the lower (first) two elements of a 128-bit vector of [4 x float]
1569 ///    returned in a 64-bit vector of [2 x i32].
1580 ///    A 128-bit vector of [4 x float].
1598 ///    A 128-bit vector of [4 x float].
1601 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
1621 ///    A 128-bit vector of [4 x float].
1624 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
1645 ///    A 128-bit vector of [4 x float].
1648 /// \returns A 128-bit vector of [4 x float] whose lower 32 bits contain the
1660 /// Converts two elements of a 64-bit vector of [2 x i32] into two
1670 ///    A 128-bit vector of [4 x float].
1672 ///    A 64-bit vector of [2 x i32]. The elements in this vector are converted
1674 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
1683 /// Converts two elements of a 64-bit vector of [2 x i32] into two
1693 ///    A 128-bit vector of [4 x float].
1695 ///    A 64-bit vector of [2 x i32]. The elements in this vector are converted
1697 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
1707 ///    [4 x float].
1714 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1724 ///     high-order bits of a 128-bit vector of [4 x float]. The low-order bits
1732 ///    A 128-bit vector of [4 x float]. Bits [63:0] are written to bits [63:0]
1737 /// \returns A 128-bit vector of [4 x float] containing the moved values.
1747   return __builtin_shufflevector(__a, __bb, 0, 1, 4, 5);  in _mm_loadh_pi()
1751 ///    low-order bits of a 128-bit vector of [4 x float]. The high-order bits
1759 ///    A 128-bit vector of [4 x float]. Bits [127:64] are written to bits
1764 /// \returns A 128-bit vector of [4 x float] containing the moved values.
1774   return __builtin_shufflevector(__a, __bb, 4, 5, 2, 3);  in _mm_loadl_pi()
1777 /// Constructs a 128-bit floating-point vector of [4 x float]. The lower
1789 /// \returns An initialized 128-bit floating-point vector of [4 x float]. The
1803 ///    elements of a 128-bit vector of [4 x float].
1812 /// \returns A 128-bit vector of [4 x float] containing the loaded and
1826 /// Loads a 128-bit floating-point vector of [4 x float] from an aligned
1836 /// \returns A 128-bit vector of [4 x float] containing the loaded values.
1843 /// Loads a 128-bit floating-point vector of [4 x float] from an
1853 /// \returns A 128-bit vector of [4 x float] containing the loaded values.
1864 ///    memory location to 32-bit elements in a 128-bit vector of [4 x float].
1874 /// \returns A 128-bit vector of [4 x float] containing the moved values, loaded
1883 /// Create a 128-bit vector of [4 x float] with undefined values.
1889 /// \returns A 128-bit vector of [4 x float] containing undefined values.
1896 /// Constructs a 128-bit floating-point vector of [4 x float]. The lower
1907 /// \returns An initialized 128-bit floating-point vector of [4 x float]. The
1916 /// Constructs a 128-bit floating-point vector of [4 x float], with each
1927 /// \returns An initialized 128-bit floating-point vector of [4 x float].
1935 /// Constructs a 128-bit floating-point vector of [4 x float], with each
1946 /// \returns An initialized 128-bit floating-point vector of [4 x float].
1953 /// Constructs a 128-bit floating-point vector of [4 x float]
1973 /// \returns An initialized 128-bit floating-point vector of [4 x float].
1980 /// Constructs a 128-bit floating-point vector of [4 x float],
2001 /// \returns An initialized 128-bit floating-point vector of [4 x float].
2008 /// Constructs a 128-bit floating-point vector of [4 x float] initialized
2015 /// \returns An initialized 128-bit floating-point vector of [4 x float] with
2023 /// Stores the upper 64 bits of a 128-bit vector of [4 x float] to a
2033 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2044 /// Stores the lower 64 bits of a 128-bit vector of [4 x float] to a
2054 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2065 /// Stores the lower 32 bits of a 128-bit vector of [4 x float] to a
2075 ///    A 128-bit vector of [4 x float] containing the value to be stored.
2085 /// Stores a 128-bit vector of [4 x float] to an unaligned memory
2096 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2106 /// Stores a 128-bit vector of [4 x float] into an aligned memory
2117 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2124 /// Stores the lower 32 bits of a 128-bit vector of [4 x float] into
2135 ///    A 128-bit vector of [4 x float] whose lower 32 bits are stored to each
2144 /// Stores the lower 32 bits of a 128-bit vector of [4 x float] into
2155 ///    A 128-bit vector of [4 x float] whose lower 32 bits are stored to each
2163 /// Stores float values from a 128-bit vector of [4 x float] to an
2175 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2240 /// Moves packed float values from a 128-bit vector of [4 x float] to a
2252 ///    A 128-bit vector of [4 x float] containing the values to be moved.
2278 /// Extracts 16-bit element from a 64-bit vector of [4 x i16] and
2290 ///    A 64-bit vector of [4 x i16].
2301 /// Copies data from the 64-bit vector of [4 x i16] to the destination,
2314 ///    A 64-bit vector of [4 x i16].
2445 /// Shuffles the 4 16-bit integers from a 64-bit integer vector to the
2466 ///    Bits [5:4] are used to assign values to bits [47:32] in the
2636 ///      _MM_SET_EXCEPTION_STATE(x) where x is one of these macros.
2641 ///      There is a convenience wrapper _MM_SET_EXCEPTION_MASK(x) where x is one
2647 ///      _MM_SET_ROUNDING_MODE(x) where x is one of these macros.
2651 ///      There is a convenience wrapper _MM_SET_FLUSH_ZERO_MODE(x) where x is
2657 ///      _MM_SET_DENORMALS_ZERO_MODE(x) where x is one of these macros.
2685 /// Selects 4 float values from the 128-bit operands of [4 x float], as
2697 ///    A 128-bit vector of [4 x float].
2699 ///    A 128-bit vector of [4 x float].
2704 ///    Bits [7:4] specify the values copied from operand \a b. \n
2711 ///    Bits [5:4] are used to assign values to bits [95:64] in the
2723 /// \returns A 128-bit vector of [4 x float] containing the shuffled values.
2729 ///    [4 x float] and interleaves them into a 128-bit vector of [4 x float].
2736 ///    A 128-bit vector of [4 x float]. \n
2740 ///    A 128-bit vector of [4 x float].
2743 /// \returns A 128-bit vector of [4 x float] containing the interleaved values.
2751 ///    [4 x float] and interleaves them into a 128-bit vector of [4 x float].
2758 ///    A 128-bit vector of [4 x float]. \n
2762 ///    A 128-bit vector of [4 x float]. \n
2765 /// \returns A 128-bit vector of [4 x float] containing the interleaved values.
2769   return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 0, 4, 1, 5);  in _mm_unpacklo_ps()
2772 /// Constructs a 128-bit floating-point vector of [4 x float]. The lower
2782 ///    A 128-bit floating-point vector of [4 x float]. The upper 96 bits are
2785 ///    A 128-bit floating-point vector of [4 x float]. The lower 32 bits are
2787 /// \returns A 128-bit floating-point vector of [4 x float].
2795 /// Constructs a 128-bit floating-point vector of [4 x float]. The lower
2804 ///    A 128-bit floating-point vector of [4 x float]. The upper 64 bits are
2807 ///    A 128-bit floating-point vector of [4 x float]. The upper 64 bits are
2809 /// \returns A 128-bit floating-point vector of [4 x float].
2816 /// Constructs a 128-bit floating-point vector of [4 x float]. The lower
2825 ///    A 128-bit floating-point vector of [4 x float]. The lower 64 bits are
2828 ///    A 128-bit floating-point vector of [4 x float]. The lower 64 bits are
2830 /// \returns A 128-bit floating-point vector of [4 x float].
2834   return __builtin_shufflevector((__v4sf)__a, (__v4sf)__b, 0, 1, 4, 5);  in _mm_movelh_ps()
2837 /// Converts a 64-bit vector of [4 x i16] into a 128-bit vector of [4 x
2845 ///    A 64-bit vector of [4 x i16]. The elements of the destination are copied
2847 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
2868 ///    128-bit vector of [4 x float].
2877 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
2896 /// Converts the lower four 8-bit values from a 64-bit vector of [8 x i8]
2897 ///    into a 128-bit vector of [4 x float].
2904 ///    A 64-bit vector of [8 x i8]. The elements of the destination are copied
2905 ///    from the corresponding lower 4 elements in this operand.
2906 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
2921 ///    vector of [8 x u8] into a 128-bit vector of [4 x float].
2929 ///    destination are copied from the corresponding lower 4 elements in this
2931 /// \returns A 128-bit vector of [4 x float] containing the copied and converted
2945 ///    operand of [2 x i32] into a 128-bit vector of [4 x float].
2952 ///    A 64-bit vector of [2 x i32]. The lower elements of the destination are
2955 ///    A 64-bit vector of [2 x i32]. The upper elements of the destination are
2957 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
2973 ///    floating-point vector of [4 x float] into a 16-bit signed integer, and
2974 ///    packs the results into a 64-bit integer vector of [4 x i16].
2986 ///    A 128-bit floating-point vector of [4 x float].
2987 /// \returns A 64-bit integer vector of [4 x i16] containing the converted
3002 ///    floating-point vector of [4 x float] into an 8-bit signed integer, and
3004 ///    [8 x i8]. The upper 32 bits of the vector are set to 0.
3016 ///    128-bit floating-point vector of [4 x float].
3017 /// \returns A 64-bit integer vector of [8 x i8]. The lower 32 bits contain the
3031 ///    element of a 128-bit floating-point vector of [4 x float] and returns the
3032 ///    sign bits in bits [0:3] of the result. Bits [31:4] of the result are set
3040 ///    A 128-bit floating-point vector of [4 x float].
3042 ///    single-precision floating-point element of the parameter. Bits [31:4] are
3061 ///    [4 x float], using the operation specified by the immediate integer
3077 ///    A 128-bit vector of [4 x float].
3079 ///    A 128-bit vector of [4 x float].
3081 ///    An immediate integer operand, with bits [4:0] specifying which comparison
3091 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
3096 ///    vectors of [4 x float], using the operation specified by the immediate
3112 ///    A 128-bit vector of [4 x float].
3114 ///    A 128-bit vector of [4 x float].
3116 ///    An immediate integer operand, with bits [4:0] specifying which comparison
3126 /// \returns A 128-bit vector of [4 x float] containing the comparison results.
3132 #define _MM_SHUFFLE(z, y, x, w) (((z) << 6) | ((y) << 4) | ((x) << 2) | (w))  argument
3165 #define _MM_SET_EXCEPTION_MASK(x) (_mm_setcsr((_mm_getcsr() & ~_MM_MASK_MASK) | (x)))  argument
3166 #define _MM_SET_EXCEPTION_STATE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_EXCEPT_MASK) | (x)))  argument
3167 #define _MM_SET_FLUSH_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_FLUSH_ZERO_MASK) | (x)))  argument
3168 #define _MM_SET_ROUNDING_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_ROUND_MASK) | (x)))  argument