Lines Matching full:bit
36 /// four unsigned 8-bit integers from the 256-bit integer vectors \a X and
40 /// vectors, and another eight using the upper half. These 16-bit values
41 /// are returned in the lower and upper halves of the 256-bit result,
47 /// difference, and sums these four values to form one 16-bit result. The
52 /// bytes from \a Y; the starting bit position for these four bytes is
54 /// sets of four bytes from \a X; the starting bit position for the first
55 /// set of four bytes is specified by \a M[2] times 32. These bit positions
56 /// are all relative to the 128-bit lane for each set of eight operations.
85 /// A 256-bit integer vector containing one of the inputs.
87 /// A 256-bit integer vector containing one of the inputs.
91 /// \returns A 256-bit vector of [16 x i16] containing the result.
96 /// Computes the absolute value of each signed byte in the 256-bit integer
105 /// A 256-bit integer vector.
106 /// \returns A 256-bit integer vector containing the result.
113 /// Computes the absolute value of each signed 16-bit element in the 256-bit
122 /// A 256-bit vector of [16 x i16].
123 /// \returns A 256-bit vector of [16 x i16] containing the result.
130 /// Computes the absolute value of each signed 32-bit element in the 256-bit
139 /// A 256-bit vector of [8 x i32].
140 /// \returns A 256-bit vector of [8 x i32] containing the result.
147 /// Converts the elements of two 256-bit vectors of [16 x i16] to 8-bit
148 /// integers using signed saturation, and returns the 256-bit result.
166 /// A 256-bit vector of [16 x i16] used to generate result[63:0] and
169 /// A 256-bit vector of [16 x i16] used to generate result[127:64] and
171 /// \returns A 256-bit integer vector containing the result.
178 /// Converts the elements of two 256-bit vectors of [8 x i32] to 16-bit
179 /// integers using signed saturation, and returns the resulting 256-bit
198 /// A 256-bit vector of [8 x i32] used to generate result[63:0] and
201 /// A 256-bit vector of [8 x i32] used to generate result[127:64] and
203 /// \returns A 256-bit vector of [16 x i16] containing the result.
210 /// Converts elements from two 256-bit vectors of [16 x i16] to 8-bit integers
211 /// using unsigned saturation, and returns the 256-bit result.
229 /// A 256-bit vector of [16 x i16] used to generate result[63:0] and
232 /// A 256-bit vector of [16 x i16] used to generate result[127:64] and
234 /// \returns A 256-bit integer vector containing the result.
241 /// Converts elements from two 256-bit vectors of [8 x i32] to 16-bit integers
242 /// using unsigned saturation, and returns the resulting 256-bit vector of
261 /// A 256-bit vector of [8 x i32] used to generate result[63:0] and
264 /// A 256-bit vector of [8 x i32] used to generate result[127:64] and
266 /// \returns A 256-bit vector of [16 x i16] containing the result.
273 /// Adds 8-bit integers from corresponding bytes of two 256-bit integer
275 /// byte of the 256-bit integer vector result (overflow is ignored).
282 /// A 256-bit integer vector containing one of the source operands.
284 /// A 256-bit integer vector containing one of the source operands.
285 /// \returns A 256-bit integer vector containing the sums.
292 /// Adds 16-bit integers from corresponding elements of two 256-bit vectors of
301 /// A 256-bit vector of [16 x i16] containing one of the source operands.
303 /// A 256-bit vector of [16 x i16] containing one of the source operands.
304 /// \returns A 256-bit vector of [16 x i16] containing the sums.
311 /// Adds 32-bit integers from corresponding elements of two 256-bit vectors of
320 /// A 256-bit vector of [8 x i32] containing one of the source operands.
322 /// A 256-bit vector of [8 x i32] containing one of the source operands.
323 /// \returns A 256-bit vector of [8 x i32] containing the sums.
330 /// Adds 64-bit integers from corresponding elements of two 256-bit vectors of
339 /// A 256-bit vector of [4 x i64] containing one of the source operands.
341 /// A 256-bit vector of [4 x i64] containing one of the source operands.
342 /// \returns A 256-bit vector of [4 x i64] containing the sums.
349 /// Adds 8-bit integers from corresponding bytes of two 256-bit integer
351 /// corresponding byte of the 256-bit integer vector result.
358 /// A 256-bit integer vector containing one of the source operands.
360 /// A 256-bit integer vector containing one of the source operands.
361 /// \returns A 256-bit integer vector containing the sums.
368 /// Adds 16-bit integers from corresponding elements of two 256-bit vectors of
376 /// A 256-bit vector of [16 x i16] containing one of the source operands.
378 /// A 256-bit vector of [16 x i16] containing one of the source operands.
379 /// \returns A 256-bit vector of [16 x i16] containing the sums.
386 /// Adds 8-bit integers from corresponding bytes of two 256-bit integer
388 /// corresponding byte of the 256-bit integer vector result.
395 /// A 256-bit integer vector containing one of the source operands.
397 /// A 256-bit integer vector containing one of the source operands.
398 /// \returns A 256-bit integer vector containing the sums.
405 /// Adds 16-bit integers from corresponding elements of two 256-bit vectors of
413 /// A 256-bit vector of [16 x i16] containing one of the source operands.
415 /// A 256-bit vector of [16 x i16] containing one of the source operands.
416 /// \returns A 256-bit vector of [16 x i16] containing the sums.
423 /// Uses the lower half of the 256-bit vector \a a as the upper half of a
424 /// temporary 256-bit value, and the lower half of the 256-bit vector \a b
441 /// A 256-bit integer vector containing source values.
443 /// A 256-bit integer vector containing source values.
446 /// \returns A 256-bit integer vector containing the result.
451 /// Computes the bitwise AND of the 256-bit integer vectors in \a __a and
459 /// A 256-bit integer vector.
461 /// A 256-bit integer vector.
462 /// \returns A 256-bit integer vector containing the result.
469 /// Computes the bitwise AND of the 256-bit integer vector in \a __b with
470 /// the bitwise NOT of the 256-bit integer vector in \a __a.
477 /// A 256-bit integer vector.
479 /// A 256-bit integer vector.
480 /// \returns A 256-bit integer vector containing the result.
488 /// 256-bit integer vectors in \a __a and \a __b and returns each
489 /// average in the corresponding byte of the 256-bit result.
503 /// A 256-bit integer vector.
505 /// A 256-bit integer vector.
506 /// \returns A 256-bit integer vector containing the result.
513 /// Computes the averages of the corresponding unsigned 16-bit integers in
514 /// the two 256-bit vectors of [16 x i16] in \a __a and \a __b and returns
515 /// each average in the corresponding element of the 256-bit result.
529 /// A 256-bit vector of [16 x i16].
531 /// A 256-bit vector of [16 x i16].
532 /// \returns A 256-bit vector of [16 x i16] containing the result.
539 /// Merges 8-bit integer values from either of the two 256-bit vectors
540 /// \a __V1 or \a __V2, as specified by the 256-bit mask \a __M and returns
541 /// the resulting 256-bit integer vector.
559 /// A 256-bit integer vector containing source values.
561 /// A 256-bit integer vector containing source values.
563 /// A 256-bit integer vector, with bit [7] of each byte specifying the
564 /// source for each corresponding byte of the result. When the mask bit
567 /// \returns A 256-bit integer vector containing the result.
575 /// Merges 16-bit integer values from either of the two 256-bit vectors
577 /// and returns the resulting 256-bit vector of [16 x i16].
601 /// A 256-bit vector of [16 x i16] containing source values.
603 /// A 256-bit vector of [16 x i16] containing source values.
605 /// An immediate 8-bit integer operand, with bits [7:0] specifying the
606 /// source for each element of the result. The position of the mask bit
607 /// corresponds to the index of a copied value. When a mask bit is 0, the
611 /// \returns A 256-bit vector of [16 x i16] containing the result.
616 /// Compares corresponding bytes in the 256-bit integer vectors in \a __a and
618 /// bytes of the 256-bit result.
632 /// A 256-bit integer vector containing one of the inputs.
634 /// A 256-bit integer vector containing one of the inputs.
635 /// \returns A 256-bit integer vector containing the result.
642 /// Compares corresponding elements in the 256-bit vectors of [16 x i16] in
644 /// corresponding elements of the 256-bit result.
658 /// A 256-bit vector of [16 x i16] containing one of the inputs.
660 /// A 256-bit vector of [16 x i16] containing one of the inputs.
661 /// \returns A 256-bit vector of [16 x i16] containing the result.
668 /// Compares corresponding elements in the 256-bit vectors of [8 x i32] in
670 /// corresponding elements of the 256-bit result.
684 /// A 256-bit vector of [8 x i32] containing one of the inputs.
686 /// A 256-bit vector of [8 x i32] containing one of the inputs.
687 /// \returns A 256-bit vector of [8 x i32] containing the result.
694 /// Compares corresponding elements in the 256-bit vectors of [4 x i64] in
696 /// corresponding elements of the 256-bit result.
710 /// A 256-bit vector of [4 x i64] containing one of the inputs.
712 /// A 256-bit vector of [4 x i64] containing one of the inputs.
713 /// \returns A 256-bit vector of [4 x i64] containing the result.
720 /// Compares corresponding signed bytes in the 256-bit integer vectors in
722 /// corresponding bytes of the 256-bit result.
736 /// A 256-bit integer vector containing one of the inputs.
738 /// A 256-bit integer vector containing one of the inputs.
739 /// \returns A 256-bit integer vector containing the result.
748 /// Compares corresponding signed elements in the 256-bit vectors of
750 /// outcomes in the corresponding elements of the 256-bit result.
764 /// A 256-bit vector of [16 x i16] containing one of the inputs.
766 /// A 256-bit vector of [16 x i16] containing one of the inputs.
767 /// \returns A 256-bit vector of [16 x i16] containing the result.
774 /// Compares corresponding signed elements in the 256-bit vectors of
776 /// outcomes in the corresponding elements of the 256-bit result.
790 /// A 256-bit vector of [8 x i32] containing one of the inputs.
792 /// A 256-bit vector of [8 x i32] containing one of the inputs.
793 /// \returns A 256-bit vector of [8 x i32] containing the result.
800 /// Compares corresponding signed elements in the 256-bit vectors of
802 /// outcomes in the corresponding elements of the 256-bit result.
816 /// A 256-bit vector of [4 x i64] containing one of the inputs.
818 /// A 256-bit vector of [4 x i64] containing one of the inputs.
819 /// \returns A 256-bit vector of [4 x i64] containing the result.
826 /// Horizontally adds the adjacent pairs of 16-bit integers from two 256-bit
829 /// \a __a are returned in the lower 64 bits of each 128-bit half of the
831 /// 128-bit half of the result.
852 /// A 256-bit vector of [16 x i16] containing one of the source operands.
854 /// A 256-bit vector of [16 x i16] containing one of the source operands.
855 /// \returns A 256-bit vector of [16 x i16] containing the sums.
862 /// Horizontally adds the adjacent pairs of 32-bit integers from two 256-bit
865 /// are returned in the lower 64 bits of each 128-bit half of the result;
866 /// sums from \a __b are returned in the upper 64 bits of each 128-bit half
884 /// A 256-bit vector of [8 x i32] containing one of the source operands.
886 /// A 256-bit vector of [8 x i32] containing one of the source operands.
887 /// \returns A 256-bit vector of [8 x i32] containing the sums.
894 /// Horizontally adds the adjacent pairs of 16-bit integers from two 256-bit
897 /// the lower 64 bits of each 128-bit half of the result; sums from \a __b
898 /// are returned in the upper 64 bits of each 128-bit half of the result.
919 /// A 256-bit vector of [16 x i16] containing one of the source operands.
921 /// A 256-bit vector of [16 x i16] containing one of the source operands.
922 /// \returns A 256-bit vector of [16 x i16] containing the sums.
929 /// Horizontally subtracts adjacent pairs of 16-bit integers from two 256-bit
933 /// 128-bit half of the result; differences from \a __b are returned in the
934 /// upper 64 bits of each 128-bit half of the result.
955 /// A 256-bit vector of [16 x i16] containing one of the source operands.
957 /// A 256-bit vector of [16 x i16] containing one of the source operands.
958 /// \returns A 256-bit vector of [16 x i16] containing the differences.
965 /// Horizontally subtracts adjacent pairs of 32-bit integers from two 256-bit
968 /// from \a __a are returned in the lower 64 bits of each 128-bit half of
970 /// of each 128-bit half of the result.
987 /// A 256-bit vector of [8 x i32] containing one of the source operands.
989 /// A 256-bit vector of [8 x i32] containing one of the source operands.
990 /// \returns A 256-bit vector of [8 x i32] containing the differences.
997 /// Horizontally subtracts adjacent pairs of 16-bit integers from two 256-bit
1000 /// returned in the lower 64 bits of each 128-bit half of the result;
1002 /// 128-bit half of the result.
1023 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1025 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1026 /// \returns A 256-bit vector of [16 x i16] containing the differences.
1033 /// Multiplies each unsigned byte from the 256-bit integer vector in \a __a
1034 /// with the corresponding signed byte from the 256-bit integer vector in
1035 /// \a __b, forming signed 16-bit intermediate products. Adds adjacent
1036 /// pairs of those products using signed saturation to form 16-bit sums
1053 /// A 256-bit vector containing one of the source operands.
1055 /// A 256-bit vector containing one of the source operands.
1056 /// \returns A 256-bit vector of [16 x i16] containing the result.
1063 /// Multiplies corresponding 16-bit elements of two 256-bit vectors of
1064 /// [16 x i16], forming 32-bit intermediate products, and adds pairs of
1065 /// those products to form 32-bit sums returned as elements of the
1068 /// There is only one wraparound case: when all four of the 16-bit sources
1085 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1087 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1088 /// \returns A 256-bit vector of [8 x i32] containing the result.
1095 /// Compares the corresponding signed bytes in the two 256-bit integer vectors
1097 /// corresponding byte of the 256-bit result.
1104 /// A 256-bit integer vector.
1106 /// A 256-bit integer vector.
1107 /// \returns A 256-bit integer vector containing the result.
1114 /// Compares the corresponding signed 16-bit integers in the two 256-bit
1116 /// each pair in the corresponding element of the 256-bit result.
1123 /// A 256-bit vector of [16 x i16].
1125 /// A 256-bit vector of [16 x i16].
1126 /// \returns A 256-bit vector of [16 x i16] containing the result.
1133 /// Compares the corresponding signed 32-bit integers in the two 256-bit
1135 /// each pair in the corresponding element of the 256-bit result.
1142 /// A 256-bit vector of [8 x i32].
1144 /// A 256-bit vector of [8 x i32].
1145 /// \returns A 256-bit vector of [8 x i32] containing the result.
1152 /// Compares the corresponding unsigned bytes in the two 256-bit integer
1154 /// the corresponding byte of the 256-bit result.
1161 /// A 256-bit integer vector.
1163 /// A 256-bit integer vector.
1164 /// \returns A 256-bit integer vector containing the result.
1171 /// Compares the corresponding unsigned 16-bit integers in the two 256-bit
1173 /// each pair in the corresponding element of the 256-bit result.
1180 /// A 256-bit vector of [16 x i16].
1182 /// A 256-bit vector of [16 x i16].
1183 /// \returns A 256-bit vector of [16 x i16] containing the result.
1190 /// Compares the corresponding unsigned 32-bit integers in the two 256-bit
1192 /// each pair in the corresponding element of the 256-bit result.
1199 /// A 256-bit vector of [8 x i32].
1201 /// A 256-bit vector of [8 x i32].
1202 /// \returns A 256-bit vector of [8 x i32] containing the result.
1209 /// Compares the corresponding signed bytes in the two 256-bit integer vectors
1211 /// corresponding byte of the 256-bit result.
1218 /// A 256-bit integer vector.
1220 /// A 256-bit integer vector.
1221 /// \returns A 256-bit integer vector containing the result.
1228 /// Compares the corresponding signed 16-bit integers in the two 256-bit
1230 /// each pair in the corresponding element of the 256-bit result.
1237 /// A 256-bit vector of [16 x i16].
1239 /// A 256-bit vector of [16 x i16].
1240 /// \returns A 256-bit vector of [16 x i16] containing the result.
1247 /// Compares the corresponding signed 32-bit integers in the two 256-bit
1249 /// each pair in the corresponding element of the 256-bit result.
1256 /// A 256-bit vector of [8 x i32].
1258 /// A 256-bit vector of [8 x i32].
1259 /// \returns A 256-bit vector of [8 x i32] containing the result.
1266 /// Compares the corresponding unsigned bytes in the two 256-bit integer
1268 /// the corresponding byte of the 256-bit result.
1275 /// A 256-bit integer vector.
1277 /// A 256-bit integer vector.
1278 /// \returns A 256-bit integer vector containing the result.
1285 /// Compares the corresponding unsigned 16-bit integers in the two 256-bit
1287 /// each pair in the corresponding element of the 256-bit result.
1294 /// A 256-bit vector of [16 x i16].
1296 /// A 256-bit vector of [16 x i16].
1297 /// \returns A 256-bit vector of [16 x i16] containing the result.
1304 /// Compares the corresponding unsigned 32-bit integers in the two 256-bit
1306 /// each pair in the corresponding element of the 256-bit result.
1313 /// A 256-bit vector of [8 x i32].
1315 /// A 256-bit vector of [8 x i32].
1316 /// \returns A 256-bit vector of [8 x i32] containing the result.
1323 /// Creates a 32-bit integer mask from the most significant bit of each byte
1324 /// in the 256-bit integer vector in \a __a and returns the result.
1338 /// A 256-bit integer vector containing the source bytes.
1339 /// \returns The 32-bit integer mask.
1346 /// Sign-extends bytes from the 128-bit integer vector in \a __V and returns
1347 /// the 16-bit values in the corresponding elements of a 256-bit vector
1363 /// A 128-bit integer vector containing the source bytes.
1364 /// \returns A 256-bit vector of [16 x i16] containing the sign-extended
1374 /// Sign-extends bytes from the lower half of the 128-bit integer vector in
1375 /// \a __V and returns the 32-bit values in the corresponding elements of a
1376 /// 256-bit vector of [8 x i32].
1391 /// A 128-bit integer vector containing the source bytes.
1392 /// \returns A 256-bit vector of [8 x i32] containing the sign-extended
1402 /// Sign-extends the first four bytes from the 128-bit integer vector in
1403 /// \a __V and returns the 64-bit values in the corresponding elements of a
1404 /// 256-bit vector of [4 x i64].
1418 /// A 128-bit integer vector containing the source bytes.
1419 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
1429 /// Sign-extends 16-bit elements from the 128-bit vector of [8 x i16] in
1430 /// \a __V and returns the 32-bit values in the corresponding elements of a
1431 /// 256-bit vector of [8 x i32].
1446 /// A 128-bit vector of [8 x i16] containing the source values.
1447 /// \returns A 256-bit vector of [8 x i32] containing the sign-extended
1455 /// Sign-extends 16-bit elements from the lower half of the 128-bit vector of
1456 /// [8 x i16] in \a __V and returns the 64-bit values in the corresponding
1457 /// elements of a 256-bit vector of [4 x i64].
1471 /// A 128-bit vector of [8 x i16] containing the source values.
1472 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
1480 /// Sign-extends 32-bit elements from the 128-bit vector of [4 x i32] in
1481 /// \a __V and returns the 64-bit values in the corresponding elements of a
1482 /// 256-bit vector of [4 x i64].
1496 /// A 128-bit vector of [4 x i32] containing the source values.
1497 /// \returns A 256-bit vector of [4 x i64] containing the sign-extended
1505 /// Zero-extends bytes from the 128-bit integer vector in \a __V and returns
1506 /// the 16-bit values in the corresponding elements of a 256-bit vector
1522 /// A 128-bit integer vector containing the source bytes.
1523 /// \returns A 256-bit vector of [16 x i16] containing the zero-extended
1531 /// Zero-extends bytes from the lower half of the 128-bit integer vector in
1532 /// \a __V and returns the 32-bit values in the corresponding elements of a
1533 /// 256-bit vector of [8 x i32].
1548 /// A 128-bit integer vector containing the source bytes.
1549 /// \returns A 256-bit vector of [8 x i32] containing the zero-extended
1557 /// Zero-extends the first four bytes from the 128-bit integer vector in
1558 /// \a __V and returns the 64-bit values in the corresponding elements of a
1559 /// 256-bit vector of [4 x i64].
1573 /// A 128-bit integer vector containing the source bytes.
1574 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
1582 /// Zero-extends 16-bit elements from the 128-bit vector of [8 x i16] in
1583 /// \a __V and returns the 32-bit values in the corresponding elements of a
1584 /// 256-bit vector of [8 x i32].
1599 /// A 128-bit vector of [8 x i16] containing the source values.
1600 /// \returns A 256-bit vector of [8 x i32] containing the zero-extended
1608 /// Zero-extends 16-bit elements from the lower half of the 128-bit vector of
1609 /// [8 x i16] in \a __V and returns the 64-bit values in the corresponding
1610 /// elements of a 256-bit vector of [4 x i64].
1624 /// A 128-bit vector of [8 x i16] containing the source values.
1625 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
1633 /// Zero-extends 32-bit elements from the 128-bit vector of [4 x i32] in
1634 /// \a __V and returns the 64-bit values in the corresponding elements of a
1635 /// 256-bit vector of [4 x i64].
1649 /// A 128-bit vector of [4 x i32] containing the source values.
1650 /// \returns A 256-bit vector of [4 x i64] containing the zero-extended
1658 /// Multiplies signed 32-bit integers from even-numbered elements of two
1659 /// 256-bit vectors of [8 x i32] and returns the 64-bit products in the
1674 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1676 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1677 /// \returns A 256-bit vector of [4 x i64] containing the products.
1684 /// Multiplies signed 16-bit integer elements of two 256-bit vectors of
1685 /// [16 x i16], truncates the 32-bit results to the most significant 18
1701 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1703 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1704 /// \returns A 256-bit vector of [16 x i16] containing the rounded products.
1711 /// Multiplies unsigned 16-bit integer elements of two 256-bit vectors of
1712 /// [16 x i16], and returns the upper 16 bits of each 32-bit product in the
1720 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1722 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1723 /// \returns A 256-bit vector of [16 x i16] containing the products.
1730 /// Multiplies signed 16-bit integer elements of two 256-bit vectors of
1731 /// [16 x i16], and returns the upper 16 bits of each 32-bit product in the
1739 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1741 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1742 /// \returns A 256-bit vector of [16 x i16] containing the products.
1749 /// Multiplies signed 16-bit integer elements of two 256-bit vectors of
1750 /// [16 x i16], and returns the lower 16 bits of each 32-bit product in the
1758 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1760 /// A 256-bit vector of [16 x i16] containing one of the source operands.
1761 /// \returns A 256-bit vector of [16 x i16] containing the products.
1768 /// Multiplies signed 32-bit integer elements of two 256-bit vectors of
1769 /// [8 x i32], and returns the lower 32 bits of each 64-bit product in the
1777 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1779 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1780 /// \returns A 256-bit vector of [8 x i32] containing the products.
1787 /// Multiplies unsigned 32-bit integers from even-numered elements of two
1788 /// 256-bit vectors of [8 x i32] and returns the 64-bit products in the
1803 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1805 /// A 256-bit vector of [8 x i32] containing one of the source operands.
1806 /// \returns A 256-bit vector of [4 x i64] containing the products.
1813 /// Computes the bitwise OR of the 256-bit integer vectors in \a __a and
1821 /// A 256-bit integer vector.
1823 /// A 256-bit integer vector.
1824 /// \returns A 256-bit integer vector containing the result.
1832 /// unsigned 8-bit integers from the 256-bit integer vectors \a __a and
1837 /// corresponding 64-bit element of the result.
1841 /// and sums these eight values to form one 16-bit result. This operation
1866 /// A 256-bit integer vector.
1868 /// A 256-bit integer vector.
1869 /// \returns A 256-bit integer vector containing the result.
1876 /// Shuffles 8-bit integers in the 256-bit integer vector \a __a according
1877 /// to control information in the 256-bit integer vector \a __b, and
1878 /// returns the 256-bit result. In effect there are two separate 128-bit
1901 /// A 256-bit integer vector containing source values.
1903 /// A 256-bit integer vector containing control information to determine
1904 /// what goes into the corresponding byte of the result. If bit 7 of the
1906 /// control byte specify the index (within the same 128-bit half) of \a __a
1908 /// \returns A 256-bit integer vector containing the result.
1915 /// Shuffles 32-bit integers from the 256-bit vector of [8 x i32] in \a a
1917 /// returns the 256-bit result. In effect there are two parallel 128-bit
1938 /// A 256-bit vector of [8 x i32] containing source values.
1940 /// An immediate 8-bit value specifying which elements to copy from \a a.
1944 /// \returns A 256-bit vector of [8 x i32] containing the result.
1948 /// Shuffles 16-bit integers from the 256-bit vector of [16 x i16] in \a a
1950 /// returns the 256-bit result. The upper 64 bits of each 128-bit half
1951 /// are shuffled in parallel; the lower 64 bits of each 128-bit half are
1974 /// A 256-bit vector of [16 x i16] containing source values.
1976 /// An immediate 8-bit value specifying which elements to copy from \a a.
1980 /// \returns A 256-bit vector of [16 x i16] containing the result.
1984 /// Shuffles 16-bit integers from the 256-bit vector of [16 x i16] \a a
1986 /// returns the 256-bit [16 x i16] result. The lower 64 bits of each
1987 /// 128-bit half are shuffled; the upper 64 bits of each 128-bit half are
2010 /// A 256-bit vector of [16 x i16] to use as a source of data for the
2013 /// An immediate 8-bit value specifying which elements to copy from \a a.
2017 /// \returns A 256-bit vector of [16 x i16] containing the result.
2021 /// Sets each byte of the result to the corresponding byte of the 256-bit
2023 /// on whether the corresponding byte of the 256-bit integer vector in
2032 /// A 256-bit integer vector.
2034 /// A 256-bit integer vector].
2035 /// \returns A 256-bit integer vector containing the result.
2043 /// 256-bit vector of [16 x i16] in \a __a, the negative of that element,
2044 /// or zero, depending on whether the corresponding element of the 256-bit
2053 /// A 256-bit vector of [16 x i16].
2055 /// A 256-bit vector of [16 x i16].
2056 /// \returns A 256-bit vector of [16 x i16] containing the result.
2064 /// 256-bit vector of [8 x i32] in \a __a, the negative of that element, or
2065 /// zero, depending on whether the corresponding element of the 256-bit
2074 /// A 256-bit vector of [8 x i32].
2076 /// A 256-bit vector of [8 x i32].
2077 /// \returns A 256-bit vector of [8 x i32] containing the result.
2084 /// Shifts each 128-bit half of the 256-bit integer vector \a a left by
2097 /// A 256-bit integer vector to be shifted.
2100 /// \returns A 256-bit integer vector containing the result.
2104 /// Shifts each 128-bit half of the 256-bit integer vector \a a left by
2117 /// A 256-bit integer vector to be shifted.
2120 /// \returns A 256-bit integer vector containing the result.
2124 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2133 /// A 256-bit vector of [16 x i16] to be shifted.
2136 /// \returns A 256-bit vector of [16 x i16] containing the result.
2143 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2153 /// A 256-bit vector of [16 x i16] to be shifted.
2155 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2157 /// \returns A 256-bit vector of [16 x i16] containing the result.
2164 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2173 /// A 256-bit vector of [8 x i32] to be shifted.
2176 /// \returns A 256-bit vector of [8 x i32] containing the result.
2183 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2193 /// A 256-bit vector of [8 x i32] to be shifted.
2195 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2197 /// \returns A 256-bit vector of [8 x i32] containing the result.
2204 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __a
2213 /// A 256-bit vector of [4 x i64] to be shifted.
2216 /// \returns A 256-bit vector of [4 x i64] containing the result.
2223 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __a
2233 /// A 256-bit vector of [4 x i64] to be shifted.
2235 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2237 /// \returns A 256-bit vector of [4 x i64] containing the result.
2244 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2247 /// 0 or -1 according to the corresponding input sign bit.
2254 /// A 256-bit vector of [16 x i16] to be shifted.
2257 /// \returns A 256-bit vector of [16 x i16] containing the result.
2264 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2268 /// corresponding input sign bit.
2275 /// A 256-bit vector of [16 x i16] to be shifted.
2277 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2279 /// \returns A 256-bit vector of [16 x i16] containing the result.
2286 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2289 /// 0 or -1 according to the corresponding input sign bit.
2296 /// A 256-bit vector of [8 x i32] to be shifted.
2299 /// \returns A 256-bit vector of [8 x i32] containing the result.
2306 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2310 /// corresponding input sign bit.
2317 /// A 256-bit vector of [8 x i32] to be shifted.
2319 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2321 /// \returns A 256-bit vector of [8 x i32] containing the result.
2328 /// Shifts each 128-bit half of the 256-bit integer vector in \a a right by
2341 /// A 256-bit integer vector to be shifted.
2344 /// \returns A 256-bit integer vector containing the result.
2348 /// Shifts each 128-bit half of the 256-bit integer vector in \a a right by
2361 /// A 256-bit integer vector to be shifted.
2364 /// \returns A 256-bit integer vector containing the result.
2368 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2377 /// A 256-bit vector of [16 x i16] to be shifted.
2380 /// \returns A 256-bit vector of [16 x i16] containing the result.
2387 /// Shifts each 16-bit element of the 256-bit vector of [16 x i16] in \a __a
2397 /// A 256-bit vector of [16 x i16] to be shifted.
2399 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2401 /// \returns A 256-bit vector of [16 x i16] containing the result.
2408 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2417 /// A 256-bit vector of [8 x i32] to be shifted.
2420 /// \returns A 256-bit vector of [8 x i32] containing the result.
2427 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __a
2437 /// A 256-bit vector of [8 x i32] to be shifted.
2439 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2441 /// \returns A 256-bit vector of [8 x i32] containing the result.
2448 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __a
2457 /// A 256-bit vector of [4 x i64] to be shifted.
2460 /// \returns A 256-bit vector of [4 x i64] containing the result.
2467 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __a
2477 /// A 256-bit vector of [4 x i64] to be shifted.
2479 /// A 128-bit vector of [2 x i64] whose lower element gives the unsigned
2481 /// \returns A 256-bit vector of [4 x i64] containing the result.
2488 /// Subtracts 8-bit integers from corresponding bytes of two 256-bit integer
2490 /// corresponding byte of the 256-bit integer vector result (overflow is
2505 /// A 256-bit integer vector containing the minuends.
2507 /// A 256-bit integer vector containing the subtrahends.
2508 /// \returns A 256-bit integer vector containing the differences.
2515 /// Subtracts 16-bit integers from corresponding elements of two 256-bit
2532 /// A 256-bit vector of [16 x i16] containing the minuends.
2534 /// A 256-bit vector of [16 x i16] containing the subtrahends.
2535 /// \returns A 256-bit vector of [16 x i16] containing the differences.
2542 /// Subtracts 32-bit integers from corresponding elements of two 256-bit
2558 /// A 256-bit vector of [8 x i32] containing the minuends.
2560 /// A 256-bit vector of [8 x i32] containing the subtrahends.
2561 /// \returns A 256-bit vector of [8 x i32] containing the differences.
2568 /// Subtracts 64-bit integers from corresponding elements of two 256-bit
2584 /// A 256-bit vector of [4 x i64] containing the minuends.
2586 /// A 256-bit vector of [4 x i64] containing the subtrahends.
2587 /// \returns A 256-bit vector of [4 x i64] containing the differences.
2594 /// Subtracts 8-bit integers from corresponding bytes of two 256-bit integer
2596 /// corresponding byte of the 256-bit integer vector result.
2610 /// A 256-bit integer vector containing the minuends.
2612 /// A 256-bit integer vector containing the subtrahends.
2613 /// \returns A 256-bit integer vector containing the differences.
2620 /// Subtracts 16-bit integers from corresponding elements of two 256-bit
2636 /// A 256-bit vector of [16 x i16] containing the minuends.
2638 /// A 256-bit vector of [16 x i16] containing the subtrahends.
2639 /// \returns A 256-bit vector of [16 x i16] containing the differences.
2646 /// Subtracts 8-bit integers from corresponding bytes of two 256-bit integer
2648 /// corresponding byte of the 256-bit integer vector result. For each byte,
2663 /// A 256-bit integer vector containing the minuends.
2665 /// A 256-bit integer vector containing the subtrahends.
2666 /// \returns A 256-bit integer vector containing the differences.
2673 /// Subtracts 16-bit integers from corresponding elements of two 256-bit
2689 /// A 256-bit vector of [16 x i16] containing the minuends.
2691 /// A 256-bit vector of [16 x i16] containing the subtrahends.
2692 /// \returns A 256-bit vector of [16 x i16] containing the differences.
2699 /// Unpacks and interleaves 8-bit integers from parts of the 256-bit integer
2700 /// vectors in \a __a and \a __b to form the 256-bit result. Specifically,
2701 /// uses the upper 64 bits of each 128-bit half of \a __a and \a __b as
2721 /// A 256-bit integer vector used as the source for the even-numbered bytes
2724 /// A 256-bit integer vector used as the source for the odd-numbered bytes
2726 /// \returns A 256-bit integer vector containing the result.
2733 /// Unpacks and interleaves 16-bit integers from parts of the 256-bit vectors
2734 /// of [16 x i16] in \a __a and \a __b to return the resulting 256-bit
2736 /// 128-bit half of \a __a and \a __b as input; other bits in these
2756 /// A 256-bit vector of [16 x i16] used as the source for the even-numbered
2759 /// A 256-bit vector of [16 x i16] used as the source for the odd-numbered
2761 /// \returns A 256-bit vector of [16 x i16] containing the result.
2768 /// Unpacks and interleaves 32-bit integers from parts of the 256-bit vectors
2769 /// of [8 x i32] in \a __a and \a __b to return the resulting 256-bit vector
2770 /// of [8 x i32]. Specifically, uses the upper 64 bits of each 128-bit half
2790 /// A 256-bit vector of [8 x i32] used as the source for the even-numbered
2793 /// A 256-bit vector of [8 x i32] used as the source for the odd-numbered
2795 /// \returns A 256-bit vector of [8 x i32] containing the result.
2802 /// Unpacks and interleaves 64-bit integers from parts of the 256-bit vectors
2803 /// of [4 x i64] in \a __a and \a __b to return the resulting 256-bit vector
2804 /// of [4 x i64]. Specifically, uses the upper 64 bits of each 128-bit half
2820 /// A 256-bit vector of [4 x i64] used as the source for the even-numbered
2823 /// A 256-bit vector of [4 x i64] used as the source for the odd-numbered
2825 /// \returns A 256-bit vector of [4 x i64] containing the result.
2832 /// Unpacks and interleaves 8-bit integers from parts of the 256-bit integer
2833 /// vectors in \a __a and \a __b to form the 256-bit result. Specifically,
2834 /// uses the lower 64 bits of each 128-bit half of \a __a and \a __b as
2854 /// A 256-bit integer vector used as the source for the even-numbered bytes
2857 /// A 256-bit integer vector used as the source for the odd-numbered bytes
2859 /// \returns A 256-bit integer vector containing the result.
2866 /// Unpacks and interleaves 16-bit integers from parts of the 256-bit vectors
2867 /// of [16 x i16] in \a __a and \a __b to return the resulting 256-bit
2869 /// 128-bit half of \a __a and \a __b as input; other bits in these
2889 /// A 256-bit vector of [16 x i16] used as the source for the even-numbered
2892 /// A 256-bit vector of [16 x i16] used as the source for the odd-numbered
2894 /// \returns A 256-bit vector of [16 x i16] containing the result.
2901 /// Unpacks and interleaves 32-bit integers from parts of the 256-bit vectors
2902 /// of [8 x i32] in \a __a and \a __b to return the resulting 256-bit vector
2903 /// of [8 x i32]. Specifically, uses the lower 64 bits of each 128-bit half
2923 /// A 256-bit vector of [8 x i32] used as the source for the even-numbered
2926 /// A 256-bit vector of [8 x i32] used as the source for the odd-numbered
2928 /// \returns A 256-bit vector of [8 x i32] containing the result.
2935 /// Unpacks and interleaves 64-bit integers from parts of the 256-bit vectors
2936 /// of [4 x i64] in \a __a and \a __b to return the resulting 256-bit vector
2937 /// of [4 x i64]. Specifically, uses the lower 64 bits of each 128-bit half
2953 /// A 256-bit vector of [4 x i64] used as the source for the even-numbered
2956 /// A 256-bit vector of [4 x i64] used as the source for the odd-numbered
2958 /// \returns A 256-bit vector of [4 x i64] containing the result.
2965 /// Computes the bitwise XOR of the 256-bit integer vectors in \a __a and
2973 /// A 256-bit integer vector.
2975 /// A 256-bit integer vector.
2976 /// \returns A 256-bit integer vector containing the result.
2983 /// Loads the 256-bit integer vector from memory \a __V using a non-temporal
2993 /// \returns A 256-bit integer vector loaded from memory.
3001 /// Broadcasts the 32-bit floating-point value from the low element of the
3002 /// 128-bit vector of [4 x float] in \a __X to all elements of the result's
3003 /// 128-bit vector of [4 x float].
3010 /// A 128-bit vector of [4 x float] whose low element will be broadcast.
3011 /// \returns A 128-bit vector of [4 x float] containing the result.
3018 /// Broadcasts the 64-bit floating-point value from the low element of the
3019 /// 128-bit vector of [2 x double] in \a __a to both elements of the
3020 /// result's 128-bit vector of [2 x double].
3027 /// A 128-bit vector of [2 x double] whose low element will be broadcast.
3028 /// \returns A 128-bit vector of [2 x double] containing the result.
3035 /// Broadcasts the 32-bit floating-point value from the low element of the
3036 /// 128-bit vector of [4 x float] in \a __X to all elements of the
3037 /// result's 256-bit vector of [8 x float].
3044 /// A 128-bit vector of [4 x float] whose low element will be broadcast.
3045 /// \returns A 256-bit vector of [8 x float] containing the result.
3052 /// Broadcasts the 64-bit floating-point value from the low element of the
3053 /// 128-bit vector of [2 x double] in \a __X to all elements of the
3054 /// result's 256-bit vector of [4 x double].
3061 /// A 128-bit vector of [2 x double] whose low element will be broadcast.
3062 /// \returns A 256-bit vector of [4 x double] containing the result.
3069 /// Broadcasts the 128-bit integer data from \a __X to both the lower and
3070 /// upper halves of the 256-bit result.
3077 /// A 128-bit integer vector to be broadcast.
3078 /// \returns A 256-bit integer vector containing the result.
3087 /// Merges 32-bit integer elements from either of the two 128-bit vectors of
3088 /// [4 x i32] in \a V1 or \a V2 to the result's 128-bit vector of [4 x i32],
3111 /// A 128-bit vector of [4 x i32] containing source values.
3113 /// A 128-bit vector of [4 x i32] containing source values.
3115 /// An immediate 8-bit integer operand, with bits [3:0] specifying the
3116 /// source for each element of the result. The position of the mask bit
3117 /// corresponds to the index of a copied value. When a mask bit is 0, the
3119 /// \returns A 128-bit vector of [4 x i32] containing the result.
3124 /// Merges 32-bit integer elements from either of the two 256-bit vectors of
3125 /// [8 x i32] in \a V1 or \a V2 to return a 256-bit vector of [8 x i32],
3148 /// A 256-bit vector of [8 x i32] containing source values.
3150 /// A 256-bit vector of [8 x i32] containing source values.
3152 /// An immediate 8-bit integer operand, with bits [7:0] specifying the
3153 /// source for each element of the result. The position of the mask bit
3154 /// corresponds to the index of a copied value. When a mask bit is 0, the
3156 /// \returns A 256-bit vector of [8 x i32] containing the result.
3161 /// Broadcasts the low byte from the 128-bit integer vector in \a __X to all
3162 /// bytes of the 256-bit result.
3169 /// A 128-bit integer vector whose low byte will be broadcast.
3170 /// \returns A 256-bit integer vector containing the result.
3177 /// Broadcasts the low element from the 128-bit vector of [8 x i16] in \a __X
3178 /// to all elements of the result's 256-bit vector of [16 x i16].
3185 /// A 128-bit vector of [8 x i16] whose low element will be broadcast.
3186 /// \returns A 256-bit vector of [16 x i16] containing the result.
3193 /// Broadcasts the low element from the 128-bit vector of [4 x i32] in \a __X
3194 /// to all elements of the result's 256-bit vector of [8 x i32].
3201 /// A 128-bit vector of [4 x i32] whose low element will be broadcast.
3202 /// \returns A 256-bit vector of [8 x i32] containing the result.
3209 /// Broadcasts the low element from the 128-bit vector of [2 x i64] in \a __X
3210 /// to all elements of the result's 256-bit vector of [4 x i64].
3217 /// A 128-bit vector of [2 x i64] whose low element will be broadcast.
3218 /// \returns A 256-bit vector of [4 x i64] containing the result.
3225 /// Broadcasts the low byte from the 128-bit integer vector in \a __X to all
3226 /// bytes of the 128-bit result.
3233 /// A 128-bit integer vector whose low byte will be broadcast.
3234 /// \returns A 128-bit integer vector containing the result.
3241 /// Broadcasts the low element from the 128-bit vector of [8 x i16] in
3242 /// \a __X to all elements of the result's 128-bit vector of [8 x i16].
3249 /// A 128-bit vector of [8 x i16] whose low element will be broadcast.
3250 /// \returns A 128-bit vector of [8 x i16] containing the result.
3257 /// Broadcasts the low element from the 128-bit vector of [4 x i32] in \a __X
3265 /// A 128-bit vector of [4 x i32] whose low element will be broadcast.
3266 /// \returns A 128-bit vector of [4 x i32] containing the result.
3273 /// Broadcasts the low element from the 128-bit vector of [2 x i64] in \a __X
3274 /// to both elements of the result's 128-bit vector of [2 x i64].
3281 /// A 128-bit vector of [2 x i64] whose low element will be broadcast.
3282 /// \returns A 128-bit vector of [2 x i64] containing the result.
3289 /// Sets the result's 256-bit vector of [8 x i32] to copies of elements of the
3290 /// 256-bit vector of [8 x i32] in \a __a as specified by indexes in the
3291 /// elements of the 256-bit vector of [8 x i32] in \a __b.
3306 /// A 256-bit vector of [8 x i32] containing the source values.
3308 /// A 256-bit vector of [8 x i32] containing indexes of values to use from
3310 /// \returns A 256-bit vector of [8 x i32] containing the result.
3317 /// Sets the result's 256-bit vector of [4 x double] to copies of elements of
3318 /// the 256-bit vector of [4 x double] in \a V as specified by the
3338 /// A 256-bit vector of [4 x double] containing the source values.
3340 /// An immediate 8-bit value specifying which elements to copy from \a V.
3343 /// \returns A 256-bit vector of [4 x double] containing the result.
3347 /// Sets the result's 256-bit vector of [8 x float] to copies of elements of
3348 /// the 256-bit vector of [8 x float] in \a __a as specified by indexes in
3349 /// the elements of the 256-bit vector of [8 x i32] in \a __b.
3364 /// A 256-bit vector of [8 x float] containing the source values.
3366 /// A 256-bit vector of [8 x i32] containing indexes of values to use from
3368 /// \returns A 256-bit vector of [8 x float] containing the result.
3375 /// Sets the result's 256-bit vector of [4 x i64] result to copies of elements
3376 /// of the 256-bit vector of [4 x i64] in \a V as specified by the
3396 /// A 256-bit vector of [4 x i64] containing the source values.
3398 /// An immediate 8-bit value specifying which elements to copy from \a V.
3401 /// \returns A 256-bit vector of [4 x i64] containing the result.
3405 /// Sets each half of the 256-bit result either to zero or to one of the
3406 /// four possible 128-bit halves of the 256-bit vectors \a V1 and \a V2,
3435 /// A 256-bit integer vector containing source values.
3437 /// A 256-bit integer vector containing source values.
3441 /// Within each 4-bit control value, if bit 3 is 1, the result is zero,
3447 /// \returns A 256-bit integer vector containing the result.
3451 /// Extracts half of the 256-bit vector \a V to the 128-bit result. If bit 0
3464 /// A 256-bit integer vector containing the source values.
3467 /// \returns A 128-bit integer vector containing the result.
3471 /// Copies the 256-bit vector \a V1 to the result, then overwrites half of the
3472 /// result with the 128-bit vector \a V2. If bit 0 of the immediate \a M
3485 /// A 256-bit integer vector containing a source value.
3487 /// A 128-bit integer vector containing a source value.
3490 /// \returns A 256-bit integer vector containing the result.
3495 /// Conditionally loads eight 32-bit integer elements from memory \a __X, if
3496 /// the most significant bit of the corresponding element in the mask
3498 /// Returns the 256-bit [8 x i32] result.
3518 /// A 256-bit vector of [8 x i32] containing the mask bits.
3519 /// \returns A 256-bit vector of [8 x i32] containing the loaded or zeroed
3527 /// Conditionally loads four 64-bit integer elements from memory \a __X, if
3528 /// the most significant bit of the corresponding element in the mask
3530 /// Returns the 256-bit [4 x i64] result.
3550 /// A 256-bit vector of [4 x i64] containing the mask bits.
3551 /// \returns A 256-bit vector of [4 x i64] containing the loaded or zeroed
3559 /// Conditionally loads four 32-bit integer elements from memory \a __X, if
3560 /// the most significant bit of the corresponding element in the mask
3562 /// Returns the 128-bit [4 x i32] result.
3582 /// A 128-bit vector of [4 x i32] containing the mask bits.
3583 /// \returns A 128-bit vector of [4 x i32] containing the loaded or zeroed
3591 /// Conditionally loads two 64-bit integer elements from memory \a __X, if
3592 /// the most significant bit of the corresponding element in the mask
3594 /// Returns the 128-bit [2 x i64] result.
3614 /// A 128-bit vector of [2 x i64] containing the mask bits.
3615 /// \returns A 128-bit vector of [2 x i64] containing the loaded or zeroed
3623 /// Conditionally stores eight 32-bit integer elements from the 256-bit vector
3624 /// of [8 x i32] in \a __Y to memory \a __X, if the most significant bit of
3644 /// A 256-bit vector of [8 x i32] containing the mask bits.
3646 /// A 256-bit vector of [8 x i32] containing the values to store.
3653 /// Conditionally stores four 64-bit integer elements from the 256-bit vector
3654 /// of [4 x i64] in \a __Y to memory \a __X, if the most significant bit of
3674 /// A 256-bit vector of [4 x i64] containing the mask bits.
3676 /// A 256-bit vector of [4 x i64] containing the values to store.
3683 /// Conditionally stores four 32-bit integer elements from the 128-bit vector
3684 /// of [4 x i32] in \a __Y to memory \a __X, if the most significant bit of
3704 /// A 128-bit vector of [4 x i32] containing the mask bits.
3706 /// A 128-bit vector of [4 x i32] containing the values to store.
3713 /// Conditionally stores two 64-bit integer elements from the 128-bit vector
3714 /// of [2 x i64] in \a __Y to memory \a __X, if the most significant bit of
3734 /// A 128-bit vector of [2 x i64] containing the mask bits.
3736 /// A 128-bit vector of [2 x i64] containing the values to store.
3743 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3745 /// 256-bit vector of [8 x i32] in \a __Y, shifting in zero bits, and
3754 /// A 256-bit vector of [8 x i32] to be shifted.
3756 /// A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
3758 /// \returns A 256-bit vector of [8 x i32] containing the result.
3765 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3767 /// 128-bit vector of [4 x i32] in \a __Y, shifting in zero bits, and
3776 /// A 128-bit vector of [4 x i32] to be shifted.
3778 /// A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
3780 /// \returns A 128-bit vector of [4 x i32] containing the result.
3787 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __X
3789 /// 128-bit vector of [4 x i64] in \a __Y, shifting in zero bits, and
3798 /// A 256-bit vector of [4 x i64] to be shifted.
3800 /// A 256-bit vector of [4 x i64] containing the unsigned shift counts (in
3802 /// \returns A 256-bit vector of [4 x i64] containing the result.
3809 /// Shifts each 64-bit element of the 128-bit vector of [2 x i64] in \a __X
3811 /// 128-bit vector of [2 x i64] in \a __Y, shifting in zero bits, and
3820 /// A 128-bit vector of [2 x i64] to be shifted.
3822 /// A 128-bit vector of [2 x i64] containing the unsigned shift counts (in
3824 /// \returns A 128-bit vector of [2 x i64] containing the result.
3831 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3833 /// 256-bit vector of [8 x i32] in \a __Y, shifting in sign bits, and
3835 /// 31, the result for that element is 0 or -1 according to the sign bit
3843 /// A 256-bit vector of [8 x i32] to be shifted.
3845 /// A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
3847 /// \returns A 256-bit vector of [8 x i32] containing the result.
3854 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3856 /// 128-bit vector of [4 x i32] in \a __Y, shifting in sign bits, and
3858 /// 31, the result for that element is 0 or -1 according to the sign bit
3866 /// A 128-bit vector of [4 x i32] to be shifted.
3868 /// A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
3870 /// \returns A 128-bit vector of [4 x i32] containing the result.
3877 /// Shifts each 32-bit element of the 256-bit vector of [8 x i32] in \a __X
3879 /// 256-bit vector of [8 x i32] in \a __Y, shifting in zero bits, and
3888 /// A 256-bit vector of [8 x i32] to be shifted.
3890 /// A 256-bit vector of [8 x i32] containing the unsigned shift counts (in
3892 /// \returns A 256-bit vector of [8 x i32] containing the result.
3899 /// Shifts each 32-bit element of the 128-bit vector of [4 x i32] in \a __X
3901 /// 128-bit vector of [4 x i32] in \a __Y, shifting in zero bits, and
3910 /// A 128-bit vector of [4 x i32] to be shifted.
3912 /// A 128-bit vector of [4 x i32] containing the unsigned shift counts (in
3914 /// \returns A 128-bit vector of [4 x i32] containing the result.
3921 /// Shifts each 64-bit element of the 256-bit vector of [4 x i64] in \a __X
3923 /// 128-bit vector of [4 x i64] in \a __Y, shifting in zero bits, and
3932 /// A 256-bit vector of [4 x i64] to be shifted.
3934 /// A 256-bit vector of [4 x i64] containing the unsigned shift counts (in
3936 /// \returns A 256-bit vector of [4 x i64] containing the result.
3943 /// Shifts each 64-bit element of the 128-bit vector of [2 x i64] in \a __X
3945 /// 128-bit vector of [2 x i64] in \a __Y, shifting in zero bits, and
3954 /// A 128-bit vector of [2 x i64] to be shifted.
3956 /// A 128-bit vector of [2 x i64] containing the unsigned shift counts (in
3958 /// \returns A 128-bit vector of [2 x i64] containing the result.
3965 /// Conditionally gathers two 64-bit floating-point values, either from the
3966 /// 128-bit vector of [2 x double] in \a a, or from memory \a m using scaled
3967 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 128-bit vector
3992 /// A 128-bit vector of [2 x double] used as the source when a mask bit is
3997 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m. Only
4000 /// A 128-bit vector of [2 x double] containing the mask. The most
4001 /// significant bit of each element in the mask vector represents the mask
4002 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4007 /// \returns A 128-bit vector of [2 x double] containing the gathered values.
4014 /// Conditionally gathers four 64-bit floating-point values, either from the
4015 /// 256-bit vector of [4 x double] in \a a, or from memory \a m using scaled
4016 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 256-bit vector
4041 /// A 256-bit vector of [4 x double] used as the source when a mask bit is
4046 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4048 /// A 256-bit vector of [4 x double] containing the mask. The most
4049 /// significant bit of each element in the mask vector represents the mask
4050 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4055 /// \returns A 256-bit vector of [4 x double] containing the gathered values.
4062 /// Conditionally gathers two 64-bit floating-point values, either from the
4063 /// 128-bit vector of [2 x double] in \a a, or from memory \a m using scaled
4064 /// indexes from the 128-bit vector of [2 x i64] in \a i. The 128-bit vector
4089 /// A 128-bit vector of [2 x double] used as the source when a mask bit is
4094 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
4096 /// A 128-bit vector of [2 x double] containing the mask. The most
4097 /// significant bit of each element in the mask vector represents the mask
4098 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4103 /// \returns A 128-bit vector of [2 x double] containing the gathered values.
4110 /// Conditionally gathers four 64-bit floating-point values, either from the
4111 /// 256-bit vector of [4 x double] in \a a, or from memory \a m using scaled
4112 /// indexes from the 256-bit vector of [4 x i64] in \a i. The 256-bit vector
4137 /// A 256-bit vector of [4 x double] used as the source when a mask bit is
4142 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
4144 /// A 256-bit vector of [4 x double] containing the mask. The most
4145 /// significant bit of each element in the mask vector represents the mask
4146 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4151 /// \returns A 256-bit vector of [4 x double] containing the gathered values.
4158 /// Conditionally gathers four 32-bit floating-point values, either from the
4159 /// 128-bit vector of [4 x float] in \a a, or from memory \a m using scaled
4160 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 128-bit vector
4185 /// A 128-bit vector of [4 x float] used as the source when a mask bit is
4190 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4192 /// A 128-bit vector of [4 x float] containing the mask. The most
4193 /// significant bit of each element in the mask vector represents the mask
4194 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4199 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
4206 /// Conditionally gathers eight 32-bit floating-point values, either from the
4207 /// 256-bit vector of [8 x float] in \a a, or from memory \a m using scaled
4208 /// indexes from the 256-bit vector of [8 x i32] in \a i. The 256-bit vector
4233 /// A 256-bit vector of [8 x float] used as the source when a mask bit is
4238 /// A 256-bit vector of [8 x i32] containing signed indexes into \a m.
4240 /// A 256-bit vector of [8 x float] containing the mask. The most
4241 /// significant bit of each element in the mask vector represents the mask
4242 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4247 /// \returns A 256-bit vector of [8 x float] containing the gathered values.
4254 /// Conditionally gathers two 32-bit floating-point values, either from the
4255 /// 128-bit vector of [4 x float] in \a a, or from memory \a m using scaled
4256 /// indexes from the 128-bit vector of [2 x i64] in \a i. The 128-bit vector
4283 /// A 128-bit vector of [4 x float] used as the source when a mask bit is
4288 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
4290 /// A 128-bit vector of [4 x float] containing the mask. The most
4291 /// significant bit of each element in the mask vector represents the mask
4292 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4298 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
4305 /// Conditionally gathers four 32-bit floating-point values, either from the
4306 /// 128-bit vector of [4 x float] in \a a, or from memory \a m using scaled
4307 /// indexes from the 256-bit vector of [4 x i64] in \a i. The 128-bit vector
4332 /// A 128-bit vector of [4 x float] used as the source when a mask bit is
4337 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
4339 /// A 128-bit vector of [4 x float] containing the mask. The most
4340 /// significant bit of each element in the mask vector represents the mask
4341 /// bits. If a mask bit is zero, the corresponding value from vector \a a
4346 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
4353 /// Conditionally gathers four 32-bit integer values, either from the
4354 /// 128-bit vector of [4 x i32] in \a a, or from memory \a m using scaled
4355 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 128-bit vector
4380 /// A 128-bit vector of [4 x i32] used as the source when a mask bit is
4385 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4387 /// A 128-bit vector of [4 x i32] containing the mask. The most significant
4388 /// bit of each element in the mask vector represents the mask bits. If a
4389 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4394 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
4401 /// Conditionally gathers eight 32-bit integer values, either from the
4402 /// 256-bit vector of [8 x i32] in \a a, or from memory \a m using scaled
4403 /// indexes from the 256-bit vector of [8 x i32] in \a i. The 256-bit vector
4428 /// A 256-bit vector of [8 x i32] used as the source when a mask bit is
4433 /// A 256-bit vector of [8 x i32] containing signed indexes into \a m.
4435 /// A 256-bit vector of [8 x i32] containing the mask. The most significant
4436 /// bit of each element in the mask vector represents the mask bits. If a
4437 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4442 /// \returns A 256-bit vector of [8 x i32] containing the gathered values.
4449 /// Conditionally gathers two 32-bit integer values, either from the
4450 /// 128-bit vector of [4 x i32] in \a a, or from memory \a m using scaled
4451 /// indexes from the 128-bit vector of [2 x i64] in \a i. The 128-bit vector
4478 /// A 128-bit vector of [4 x i32] used as the source when a mask bit is
4483 /// A 128-bit vector of [2 x i64] containing indexes into \a m.
4485 /// A 128-bit vector of [4 x i32] containing the mask. The most significant
4486 /// bit of each element in the mask vector represents the mask bits. If a
4487 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4493 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
4500 /// Conditionally gathers four 32-bit integer values, either from the
4501 /// 128-bit vector of [4 x i32] in \a a, or from memory \a m using scaled
4502 /// indexes from the 256-bit vector of [4 x i64] in \a i. The 128-bit vector
4527 /// A 128-bit vector of [4 x i32] used as the source when a mask bit is
4532 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
4534 /// A 128-bit vector of [4 x i32] containing the mask. The most significant
4535 /// bit of each element in the mask vector represents the mask bits. If a
4536 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4541 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
4548 /// Conditionally gathers two 64-bit integer values, either from the
4549 /// 128-bit vector of [2 x i64] in \a a, or from memory \a m using scaled
4550 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 128-bit vector
4575 /// A 128-bit vector of [2 x i64] used as the source when a mask bit is
4580 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m. Only
4583 /// A 128-bit vector of [2 x i64] containing the mask. The most significant
4584 /// bit of each element in the mask vector represents the mask bits. If a
4585 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4590 /// \returns A 128-bit vector of [2 x i64] containing the gathered values.
4597 /// Conditionally gathers four 64-bit integer values, either from the
4598 /// 256-bit vector of [4 x i64] in \a a, or from memory \a m using scaled
4599 /// indexes from the 128-bit vector of [4 x i32] in \a i. The 256-bit vector
4624 /// A 256-bit vector of [4 x i64] used as the source when a mask bit is
4629 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4631 /// A 256-bit vector of [4 x i64] containing the mask. The most significant
4632 /// bit of each element in the mask vector represents the mask bits. If a
4633 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4638 /// \returns A 256-bit vector of [4 x i64] containing the gathered values.
4645 /// Conditionally gathers two 64-bit integer values, either from the
4646 /// 128-bit vector of [2 x i64] in \a a, or from memory \a m using scaled
4647 /// indexes from the 128-bit vector of [2 x i64] in \a i. The 128-bit vector
4672 /// A 128-bit vector of [2 x i64] used as the source when a mask bit is
4677 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
4679 /// A 128-bit vector of [2 x i64] containing the mask. The most significant
4680 /// bit of each element in the mask vector represents the mask bits. If a
4681 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4686 /// \returns A 128-bit vector of [2 x i64] containing the gathered values.
4693 /// Conditionally gathers four 64-bit integer values, either from the
4694 /// 256-bit vector of [4 x i64] in \a a, or from memory \a m using scaled
4695 /// indexes from the 256-bit vector of [4 x i64] in \a i. The 256-bit vector
4720 /// A 256-bit vector of [4 x i64] used as the source when a mask bit is
4725 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
4727 /// A 256-bit vector of [4 x i64] containing the mask. The most significant
4728 /// bit of each element in the mask vector represents the mask bits. If a
4729 /// mask bit is zero, the corresponding value from vector \a a is gathered;
4734 /// \returns A 256-bit vector of [4 x i64] containing the gathered values.
4741 /// Gathers two 64-bit floating-point values from memory \a m using scaled
4742 /// indexes from the 128-bit vector of [4 x i32] in \a i.
4763 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m. Only
4768 /// \returns A 128-bit vector of [2 x double] containing the gathered values.
4777 /// Gathers four 64-bit floating-point values from memory \a m using scaled
4778 /// indexes from the 128-bit vector of [4 x i32] in \a i.
4799 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4803 /// \returns A 256-bit vector of [4 x double] containing the gathered values.
4813 /// Gathers two 64-bit floating-point values from memory \a m using scaled
4814 /// indexes from the 128-bit vector of [2 x i64] in \a i.
4835 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
4839 /// \returns A 128-bit vector of [2 x double] containing the gathered values.
4848 /// Gathers four 64-bit floating-point values from memory \a m using scaled
4849 /// indexes from the 256-bit vector of [4 x i64] in \a i.
4870 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
4874 /// \returns A 256-bit vector of [4 x double] containing the gathered values.
4884 /// Gathers four 32-bit floating-point values from memory \a m using scaled
4885 /// indexes from the 128-bit vector of [4 x i32] in \a i.
4906 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
4910 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
4919 /// Gathers eight 32-bit floating-point values from memory \a m using scaled
4920 /// indexes from the 256-bit vector of [8 x i32] in \a i.
4941 /// A 256-bit vector of [8 x i32] containing signed indexes into \a m.
4945 /// \returns A 256-bit vector of [8 x float] containing the gathered values.
4955 /// Gathers two 32-bit floating-point values from memory \a m using scaled
4956 /// indexes from the 128-bit vector of [2 x i64] in \a i. The upper two
4979 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
4983 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
4992 /// Gathers four 32-bit floating-point values from memory \a m using scaled
4993 /// indexes from the 256-bit vector of [4 x i64] in \a i.
5014 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
5018 /// \returns A 128-bit vector of [4 x float] containing the gathered values.
5027 /// Gathers four 32-bit floating-point values from memory \a m using scaled
5028 /// indexes from the 128-bit vector of [4 x i32] in \a i.
5049 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
5053 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
5059 /// Gathers eight 32-bit floating-point values from memory \a m using scaled
5060 /// indexes from the 256-bit vector of [8 x i32] in \a i.
5081 /// A 256-bit vector of [8 x i32] containing signed indexes into \a m.
5085 /// \returns A 256-bit vector of [8 x i32] containing the gathered values.
5091 /// Gathers two 32-bit integer values from memory \a m using scaled indexes
5092 /// from the 128-bit vector of [2 x i64] in \a i. The upper two elements
5115 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
5119 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
5125 /// Gathers four 32-bit integer values from memory \a m using scaled indexes
5126 /// from the 256-bit vector of [4 x i64] in \a i.
5147 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
5151 /// \returns A 128-bit vector of [4 x i32] containing the gathered values.
5157 /// Gathers two 64-bit integer values from memory \a m using scaled indexes
5158 /// from the 128-bit vector of [4 x i32] in \a i.
5179 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m. Only
5184 /// \returns A 128-bit vector of [2 x i64] containing the gathered values.
5191 /// Gathers four 64-bit integer values from memory \a m using scaled indexes
5192 /// from the 128-bit vector of [4 x i32] in \a i.
5213 /// A 128-bit vector of [4 x i32] containing signed indexes into \a m.
5217 /// \returns A 256-bit vector of [4 x i64] containing the gathered values.
5224 /// Gathers two 64-bit integer values from memory \a m using scaled indexes
5225 /// from the 128-bit vector of [2 x i64] in \a i.
5246 /// A 128-bit vector of [2 x i64] containing signed indexes into \a m.
5250 /// \returns A 128-bit vector of [2 x i64] containing the gathered values.
5257 /// Gathers four 64-bit integer values from memory \a m using scaled indexes
5258 /// from the 256-bit vector of [4 x i64] in \a i.
5279 /// A 256-bit vector of [4 x i64] containing signed indexes into \a m.
5283 /// \returns A 256-bit vector of [4 x i64] containing the gathered values.