20 typedef float __v4sf __attribute__((__vector_size__(16)));
21 typedef float __m128 __attribute__((__vector_size__(16), __aligned__(16)));
23 typedef float __m128_u __attribute__((__vector_size__(16), __aligned__(1)));
42 /// Adds the 32-bit float values in the low-order bits of the operands.
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
83 /// Subtracts the 32-bit float value in the low-order bits of the second
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
126 /// Multiplies two 32-bit float values in the low-order bits of the
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
315 /// Compares two 32-bit float values in the low-order bits of both
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
361 /// Compares two 32-bit float values in the low-order bits of both
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
484 /// Compares two 32-bit float values in the low-order bits of both
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
509 /// Compares each of the corresponding 32-bit float values of the
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.
530 /// Compares two 32-bit float values in the low-order bits of both
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
556 /// Compares each of the corresponding 32-bit float values of the
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.
578 /// Compares two 32-bit float values in the low-order bits of both
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
604 /// Compares each of the corresponding 32-bit float values of the
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.
626 /// Compares two 32-bit float values in the low-order bits of both
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
654 /// Compares each of the corresponding 32-bit float values of the
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.
676 /// Compares two 32-bit float values in the low-order bits of both
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
704 /// Compares each of the corresponding 32-bit float values of the
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.
726 /// Compares two 32-bit float values in the low-order bits of both operands
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
752 /// Compares each of the corresponding 32-bit float values of the
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.
774 /// Compares two 32-bit float values in the low-order bits of both
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
801 /// Compares each of the corresponding 32-bit float values of the
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.
824 /// Compares two 32-bit float values in the low-order bits of both
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
851 /// Compares each of the corresponding 32-bit float values of the
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.
874 /// Compares two 32-bit float values in the low-order bits of both
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
903 /// Compares each of the corresponding 32-bit float values of the
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.
926 /// Compares two 32-bit float values in the low-order bits of both
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
955 /// Compares each of the corresponding 32-bit float values of the
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.
978 /// Compares two 32-bit float values in the low-order bits of both
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
1005 /// Compares each of the corresponding 32-bit float values of the
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.
1029 /// Compares two 32-bit float values in the low-order bits of both
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
1056 /// Compares each of the corresponding 32-bit float values of the
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.
1080 /// Compares two 32-bit float values in the low-order bits of both
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
1104 /// Compares two 32-bit float values in the low-order bits of both
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
1129 /// Compares two 32-bit float values in the low-order bits of both
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
1153 /// Compares two 32-bit float values in the low-order bits of both
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
1177 /// Compares two 32-bit float values in the low-order bits of both
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
1201 /// Compares two 32-bit float values in the low-order bits of both
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
1225 /// Performs an unordered comparison of two 32-bit float values using
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
1248 /// Performs an unordered comparison of two 32-bit float values using
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
1272 /// Performs an unordered comparison of two 32-bit float values using
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
1296 /// Performs an unordered comparison of two 32-bit float values using
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
1320 /// Performs an unordered comparison of two 32-bit float values using
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
1344 /// Performs an unordered comparison of two 32-bit float values using
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
1367 /// Converts a float value contained in the lower 32 bits of a vector of
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
1389 /// Converts a float value contained in the lower 32 bits of a vector of
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
1413 /// Converts a float value contained in the lower 32 bits of a vector of
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
1437 /// Converts two low-order float values in a 128-bit vector of
1438 ///    [4 x float] into a 64-bit vector of [2 x i32].
1449 ///    A 128-bit vector of [4 x float].
1457 /// Converts two low-order float values in a 128-bit vector of
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]
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]
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
1670 ///    A 128-bit vector of [4 x float].
1674 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
1693 ///    A 128-bit vector of [4 x float].
1697 /// \returns A 128-bit vector of [4 x float] whose lower 64 bits contain the
1706 /// Extracts a float value contained in the lower 32 bits of a vector of
1707 ///    [4 x float].
1714 ///    A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
1716 /// \returns A 32-bit float containing the extracted value.
1717 static __inline__ float __DEFAULT_FN_ATTRS
1723 /// Loads two packed float values from the address \a __p into the
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]
1735 ///    A pointer to two packed float values. Bits [63:0] are written to bits
1737 /// \returns A 128-bit vector of [4 x float] containing the moved values.
1741   typedef float __mm_loadh_pi_v2f32 __attribute__((__vector_size__(8)));  in _mm_loadh_pi()
1750 /// Loads two packed float values from the address \a __p into the
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
1762 ///    A pointer to two packed float values. Bits [63:0] are written to bits
1764 /// \returns A 128-bit vector of [4 x float] containing the moved values.
1768   typedef float __mm_loadl_pi_v2f32 __attribute__((__vector_size__(8)));  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
1793 _mm_load_ss(const float *__p)  in _mm_load_ss()
1796     float __u;  in _mm_load_ss()
1798   float __u = ((const struct __mm_load_ss_struct*)__p)->__u;  in _mm_load_ss()
1802 /// Loads a 32-bit float value and duplicates it to all four vector
1803 ///    elements of a 128-bit vector of [4 x float].
1811 ///    A pointer to a float value to be loaded and duplicated.
1812 /// \returns A 128-bit vector of [4 x float] containing the loaded and
1815 _mm_load1_ps(const float *__p)  in _mm_load1_ps()
1818     float __u;  in _mm_load1_ps()
1820   float __u = ((const struct __mm_load1_ps_struct*)__p)->__u;  in _mm_load1_ps()
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.
1838 _mm_load_ps(const float *__p)  in _mm_load_ps()
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.
1855 _mm_loadu_ps(const float *__p)  in _mm_loadu_ps()
1863 /// Loads four packed float values, in reverse order, from an aligned
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
1877 _mm_loadr_ps(const float *__p)  in _mm_loadr_ps()
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
1911 _mm_set_ss(float __w)  in _mm_set_ss()
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].
1929 _mm_set1_ps(float __w)  in _mm_set1_ps()
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].
1948 _mm_set_ps1(float __w)  in _mm_set_ps1()
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].
1975 _mm_set_ps(float __z, float __y, float __x, float __w)  in _mm_set_ps()
1980 /// Constructs a 128-bit floating-point vector of [4 x float],
1982 ///    float-point values.
2001 /// \returns An initialized 128-bit floating-point vector of [4 x float].
2003 _mm_setr_ps(float __z, float __y, float __x, float __w)  in _mm_setr_ps()
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.
2037   typedef float __mm_storeh_pi_v2f32 __attribute__((__vector_size__(8)));  in _mm_storeh_pi()
2044 /// Stores the lower 64 bits of a 128-bit vector of [4 x float] to a
2052 ///    A pointer to a memory location that will receive the float values.
2054 ///    A 128-bit vector of [4 x float] containing the values to be stored.
2058   typedef float __mm_storeh_pi_v2f32 __attribute__((__vector_size__(8)));  in _mm_storel_pi()
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.
2077 _mm_store_ss(float *__p, __m128 __a)  in _mm_store_ss()
2080     float __u;  in _mm_store_ss()
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.
2098 _mm_storeu_ps(float *__p, __m128 __a)  in _mm_storeu_ps()
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.
2119 _mm_store_ps(float *__p, __m128 __a)  in _mm_store_ps()
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
2138 _mm_store1_ps(float *__p, __m128 __a)  in _mm_store1_ps()
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
2158 _mm_store_ps1(float *__p, __m128 __a)  in _mm_store_ps1()
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.
2177 _mm_storer_ps(float *__p, __m128 __a)  in _mm_storer_ps()
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.
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].
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.
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].
2838 ///    float].
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
2897 ///    into a 128-bit vector of [4 x float].
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].
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].
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
2986 ///    A 128-bit floating-point vector of [4 x float].
3002 ///    floating-point vector of [4 x float] into an 8-bit signed integer, and
3016 ///    128-bit floating-point vector of [4 x float].
3031 ///    element of a 128-bit floating-point vector of [4 x float] and returns the
3040 ///    A 128-bit floating-point vector of [4 x float].
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].
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].
3126 /// \returns A 128-bit vector of [4 x float] containing the comparison results.