Lines Matching refs:__p1
433 __ai uint8x16_t vabdq_u8(uint8x16_t __p0, uint8x16_t __p1) {
435 __ret = (uint8x16_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
439 __ai uint8x16_t vabdq_u8(uint8x16_t __p0, uint8x16_t __p1) {
441 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
447 __ai uint8x16_t __noswap_vabdq_u8(uint8x16_t __p0, uint8x16_t __p1) {
449 __ret = (uint8x16_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
455 __ai uint32x4_t vabdq_u32(uint32x4_t __p0, uint32x4_t __p1) {
457 __ret = (uint32x4_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
461 __ai uint32x4_t vabdq_u32(uint32x4_t __p0, uint32x4_t __p1) {
463 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
469 __ai uint32x4_t __noswap_vabdq_u32(uint32x4_t __p0, uint32x4_t __p1) {
471 __ret = (uint32x4_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
477 __ai uint16x8_t vabdq_u16(uint16x8_t __p0, uint16x8_t __p1) {
479 __ret = (uint16x8_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
483 __ai uint16x8_t vabdq_u16(uint16x8_t __p0, uint16x8_t __p1) {
485 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
491 __ai uint16x8_t __noswap_vabdq_u16(uint16x8_t __p0, uint16x8_t __p1) {
493 __ret = (uint16x8_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
499 __ai int8x16_t vabdq_s8(int8x16_t __p0, int8x16_t __p1) {
501 __ret = (int8x16_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
505 __ai int8x16_t vabdq_s8(int8x16_t __p0, int8x16_t __p1) {
507 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
513 __ai int8x16_t __noswap_vabdq_s8(int8x16_t __p0, int8x16_t __p1) {
515 __ret = (int8x16_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
521 __ai float32x4_t vabdq_f32(float32x4_t __p0, float32x4_t __p1) {
523 __ret = (float32x4_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
527 __ai float32x4_t vabdq_f32(float32x4_t __p0, float32x4_t __p1) {
529 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
538 __ai int32x4_t vabdq_s32(int32x4_t __p0, int32x4_t __p1) {
540 __ret = (int32x4_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
544 __ai int32x4_t vabdq_s32(int32x4_t __p0, int32x4_t __p1) {
546 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
552 __ai int32x4_t __noswap_vabdq_s32(int32x4_t __p0, int32x4_t __p1) {
554 __ret = (int32x4_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
560 __ai int16x8_t vabdq_s16(int16x8_t __p0, int16x8_t __p1) {
562 __ret = (int16x8_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
566 __ai int16x8_t vabdq_s16(int16x8_t __p0, int16x8_t __p1) {
568 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
574 __ai int16x8_t __noswap_vabdq_s16(int16x8_t __p0, int16x8_t __p1) {
576 __ret = (int16x8_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
582 __ai uint8x8_t vabd_u8(uint8x8_t __p0, uint8x8_t __p1) {
584 __ret = (uint8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
588 __ai uint8x8_t vabd_u8(uint8x8_t __p0, uint8x8_t __p1) {
590 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
596 __ai uint8x8_t __noswap_vabd_u8(uint8x8_t __p0, uint8x8_t __p1) {
598 __ret = (uint8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
604 __ai uint32x2_t vabd_u32(uint32x2_t __p0, uint32x2_t __p1) {
606 __ret = (uint32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
610 __ai uint32x2_t vabd_u32(uint32x2_t __p0, uint32x2_t __p1) {
612 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
618 __ai uint32x2_t __noswap_vabd_u32(uint32x2_t __p0, uint32x2_t __p1) {
620 __ret = (uint32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
626 __ai uint16x4_t vabd_u16(uint16x4_t __p0, uint16x4_t __p1) {
628 __ret = (uint16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
632 __ai uint16x4_t vabd_u16(uint16x4_t __p0, uint16x4_t __p1) {
634 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
640 __ai uint16x4_t __noswap_vabd_u16(uint16x4_t __p0, uint16x4_t __p1) {
642 __ret = (uint16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
648 __ai int8x8_t vabd_s8(int8x8_t __p0, int8x8_t __p1) {
650 __ret = (int8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
654 __ai int8x8_t vabd_s8(int8x8_t __p0, int8x8_t __p1) {
656 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
662 __ai int8x8_t __noswap_vabd_s8(int8x8_t __p0, int8x8_t __p1) {
664 __ret = (int8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
670 __ai float32x2_t vabd_f32(float32x2_t __p0, float32x2_t __p1) {
672 __ret = (float32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
676 __ai float32x2_t vabd_f32(float32x2_t __p0, float32x2_t __p1) {
678 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
687 __ai int32x2_t vabd_s32(int32x2_t __p0, int32x2_t __p1) {
689 __ret = (int32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
693 __ai int32x2_t vabd_s32(int32x2_t __p0, int32x2_t __p1) {
695 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
701 __ai int32x2_t __noswap_vabd_s32(int32x2_t __p0, int32x2_t __p1) {
703 __ret = (int32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
709 __ai int16x4_t vabd_s16(int16x4_t __p0, int16x4_t __p1) {
711 __ret = (int16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
715 __ai int16x4_t vabd_s16(int16x4_t __p0, int16x4_t __p1) {
717 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
723 __ai int16x4_t __noswap_vabd_s16(int16x4_t __p0, int16x4_t __p1) {
725 __ret = (int16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
859 __ai uint8x16_t vaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
861 __ret = __p0 + __p1;
865 __ai uint8x16_t vaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
867 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
876 __ai uint32x4_t vaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
878 __ret = __p0 + __p1;
882 __ai uint32x4_t vaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
884 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
893 __ai uint64x2_t vaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
895 __ret = __p0 + __p1;
899 __ai uint64x2_t vaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
901 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
910 __ai uint16x8_t vaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
912 __ret = __p0 + __p1;
916 __ai uint16x8_t vaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
918 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
927 __ai int8x16_t vaddq_s8(int8x16_t __p0, int8x16_t __p1) {
929 __ret = __p0 + __p1;
933 __ai int8x16_t vaddq_s8(int8x16_t __p0, int8x16_t __p1) {
935 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
944 __ai float32x4_t vaddq_f32(float32x4_t __p0, float32x4_t __p1) {
946 __ret = __p0 + __p1;
950 __ai float32x4_t vaddq_f32(float32x4_t __p0, float32x4_t __p1) {
952 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
961 __ai int32x4_t vaddq_s32(int32x4_t __p0, int32x4_t __p1) {
963 __ret = __p0 + __p1;
967 __ai int32x4_t vaddq_s32(int32x4_t __p0, int32x4_t __p1) {
969 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
978 __ai int64x2_t vaddq_s64(int64x2_t __p0, int64x2_t __p1) {
980 __ret = __p0 + __p1;
984 __ai int64x2_t vaddq_s64(int64x2_t __p0, int64x2_t __p1) {
986 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
995 __ai int16x8_t vaddq_s16(int16x8_t __p0, int16x8_t __p1) {
997 __ret = __p0 + __p1;
1001 __ai int16x8_t vaddq_s16(int16x8_t __p0, int16x8_t __p1) {
1003 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1012 __ai uint8x8_t vadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
1014 __ret = __p0 + __p1;
1018 __ai uint8x8_t vadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
1020 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1029 __ai uint32x2_t vadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
1031 __ret = __p0 + __p1;
1035 __ai uint32x2_t vadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
1037 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1046 __ai uint64x1_t vadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
1048 __ret = __p0 + __p1;
1052 __ai uint64x1_t vadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
1054 __ret = __p0 + __p1;
1060 __ai uint16x4_t vadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
1062 __ret = __p0 + __p1;
1066 __ai uint16x4_t vadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
1068 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1077 __ai int8x8_t vadd_s8(int8x8_t __p0, int8x8_t __p1) {
1079 __ret = __p0 + __p1;
1083 __ai int8x8_t vadd_s8(int8x8_t __p0, int8x8_t __p1) {
1085 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1094 __ai float32x2_t vadd_f32(float32x2_t __p0, float32x2_t __p1) {
1096 __ret = __p0 + __p1;
1100 __ai float32x2_t vadd_f32(float32x2_t __p0, float32x2_t __p1) {
1102 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1111 __ai int32x2_t vadd_s32(int32x2_t __p0, int32x2_t __p1) {
1113 __ret = __p0 + __p1;
1117 __ai int32x2_t vadd_s32(int32x2_t __p0, int32x2_t __p1) {
1119 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1128 __ai int64x1_t vadd_s64(int64x1_t __p0, int64x1_t __p1) {
1130 __ret = __p0 + __p1;
1134 __ai int64x1_t vadd_s64(int64x1_t __p0, int64x1_t __p1) {
1136 __ret = __p0 + __p1;
1142 __ai int16x4_t vadd_s16(int16x4_t __p0, int16x4_t __p1) {
1144 __ret = __p0 + __p1;
1148 __ai int16x4_t vadd_s16(int16x4_t __p0, int16x4_t __p1) {
1150 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1159 __ai uint16x4_t vaddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
1161 __ret = (uint16x4_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
1165 __ai uint16x4_t vaddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
1167 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1173 __ai uint16x4_t __noswap_vaddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
1175 __ret = (uint16x4_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
1181 __ai uint32x2_t vaddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
1183 __ret = (uint32x2_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
1187 __ai uint32x2_t vaddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
1189 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1195 __ai uint32x2_t __noswap_vaddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
1197 __ret = (uint32x2_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
1203 __ai uint8x8_t vaddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
1205 __ret = (uint8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
1209 __ai uint8x8_t vaddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
1211 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1217 __ai uint8x8_t __noswap_vaddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
1219 __ret = (uint8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
1225 __ai int16x4_t vaddhn_s32(int32x4_t __p0, int32x4_t __p1) {
1227 __ret = (int16x4_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
1231 __ai int16x4_t vaddhn_s32(int32x4_t __p0, int32x4_t __p1) {
1233 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1239 __ai int16x4_t __noswap_vaddhn_s32(int32x4_t __p0, int32x4_t __p1) {
1241 __ret = (int16x4_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
1247 __ai int32x2_t vaddhn_s64(int64x2_t __p0, int64x2_t __p1) {
1249 __ret = (int32x2_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
1253 __ai int32x2_t vaddhn_s64(int64x2_t __p0, int64x2_t __p1) {
1255 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1261 __ai int32x2_t __noswap_vaddhn_s64(int64x2_t __p0, int64x2_t __p1) {
1263 __ret = (int32x2_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
1269 __ai int8x8_t vaddhn_s16(int16x8_t __p0, int16x8_t __p1) {
1271 __ret = (int8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
1275 __ai int8x8_t vaddhn_s16(int16x8_t __p0, int16x8_t __p1) {
1277 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1283 __ai int8x8_t __noswap_vaddhn_s16(int16x8_t __p0, int16x8_t __p1) {
1285 __ret = (int8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
1291 __ai uint8x16_t vandq_u8(uint8x16_t __p0, uint8x16_t __p1) {
1293 __ret = __p0 & __p1;
1297 __ai uint8x16_t vandq_u8(uint8x16_t __p0, uint8x16_t __p1) {
1299 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1308 __ai uint32x4_t vandq_u32(uint32x4_t __p0, uint32x4_t __p1) {
1310 __ret = __p0 & __p1;
1314 __ai uint32x4_t vandq_u32(uint32x4_t __p0, uint32x4_t __p1) {
1316 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1325 __ai uint64x2_t vandq_u64(uint64x2_t __p0, uint64x2_t __p1) {
1327 __ret = __p0 & __p1;
1331 __ai uint64x2_t vandq_u64(uint64x2_t __p0, uint64x2_t __p1) {
1333 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1342 __ai uint16x8_t vandq_u16(uint16x8_t __p0, uint16x8_t __p1) {
1344 __ret = __p0 & __p1;
1348 __ai uint16x8_t vandq_u16(uint16x8_t __p0, uint16x8_t __p1) {
1350 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1359 __ai int8x16_t vandq_s8(int8x16_t __p0, int8x16_t __p1) {
1361 __ret = __p0 & __p1;
1365 __ai int8x16_t vandq_s8(int8x16_t __p0, int8x16_t __p1) {
1367 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1376 __ai int32x4_t vandq_s32(int32x4_t __p0, int32x4_t __p1) {
1378 __ret = __p0 & __p1;
1382 __ai int32x4_t vandq_s32(int32x4_t __p0, int32x4_t __p1) {
1384 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1393 __ai int64x2_t vandq_s64(int64x2_t __p0, int64x2_t __p1) {
1395 __ret = __p0 & __p1;
1399 __ai int64x2_t vandq_s64(int64x2_t __p0, int64x2_t __p1) {
1401 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1410 __ai int16x8_t vandq_s16(int16x8_t __p0, int16x8_t __p1) {
1412 __ret = __p0 & __p1;
1416 __ai int16x8_t vandq_s16(int16x8_t __p0, int16x8_t __p1) {
1418 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1427 __ai uint8x8_t vand_u8(uint8x8_t __p0, uint8x8_t __p1) {
1429 __ret = __p0 & __p1;
1433 __ai uint8x8_t vand_u8(uint8x8_t __p0, uint8x8_t __p1) {
1435 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1444 __ai uint32x2_t vand_u32(uint32x2_t __p0, uint32x2_t __p1) {
1446 __ret = __p0 & __p1;
1450 __ai uint32x2_t vand_u32(uint32x2_t __p0, uint32x2_t __p1) {
1452 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1461 __ai uint64x1_t vand_u64(uint64x1_t __p0, uint64x1_t __p1) {
1463 __ret = __p0 & __p1;
1467 __ai uint64x1_t vand_u64(uint64x1_t __p0, uint64x1_t __p1) {
1469 __ret = __p0 & __p1;
1475 __ai uint16x4_t vand_u16(uint16x4_t __p0, uint16x4_t __p1) {
1477 __ret = __p0 & __p1;
1481 __ai uint16x4_t vand_u16(uint16x4_t __p0, uint16x4_t __p1) {
1483 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1492 __ai int8x8_t vand_s8(int8x8_t __p0, int8x8_t __p1) {
1494 __ret = __p0 & __p1;
1498 __ai int8x8_t vand_s8(int8x8_t __p0, int8x8_t __p1) {
1500 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1509 __ai int32x2_t vand_s32(int32x2_t __p0, int32x2_t __p1) {
1511 __ret = __p0 & __p1;
1515 __ai int32x2_t vand_s32(int32x2_t __p0, int32x2_t __p1) {
1517 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1526 __ai int64x1_t vand_s64(int64x1_t __p0, int64x1_t __p1) {
1528 __ret = __p0 & __p1;
1532 __ai int64x1_t vand_s64(int64x1_t __p0, int64x1_t __p1) {
1534 __ret = __p0 & __p1;
1540 __ai int16x4_t vand_s16(int16x4_t __p0, int16x4_t __p1) {
1542 __ret = __p0 & __p1;
1546 __ai int16x4_t vand_s16(int16x4_t __p0, int16x4_t __p1) {
1548 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1557 __ai uint8x16_t vbicq_u8(uint8x16_t __p0, uint8x16_t __p1) {
1559 __ret = __p0 & ~__p1;
1563 __ai uint8x16_t vbicq_u8(uint8x16_t __p0, uint8x16_t __p1) {
1565 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1574 __ai uint32x4_t vbicq_u32(uint32x4_t __p0, uint32x4_t __p1) {
1576 __ret = __p0 & ~__p1;
1580 __ai uint32x4_t vbicq_u32(uint32x4_t __p0, uint32x4_t __p1) {
1582 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1591 __ai uint64x2_t vbicq_u64(uint64x2_t __p0, uint64x2_t __p1) {
1593 __ret = __p0 & ~__p1;
1597 __ai uint64x2_t vbicq_u64(uint64x2_t __p0, uint64x2_t __p1) {
1599 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1608 __ai uint16x8_t vbicq_u16(uint16x8_t __p0, uint16x8_t __p1) {
1610 __ret = __p0 & ~__p1;
1614 __ai uint16x8_t vbicq_u16(uint16x8_t __p0, uint16x8_t __p1) {
1616 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1625 __ai int8x16_t vbicq_s8(int8x16_t __p0, int8x16_t __p1) {
1627 __ret = __p0 & ~__p1;
1631 __ai int8x16_t vbicq_s8(int8x16_t __p0, int8x16_t __p1) {
1633 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1642 __ai int32x4_t vbicq_s32(int32x4_t __p0, int32x4_t __p1) {
1644 __ret = __p0 & ~__p1;
1648 __ai int32x4_t vbicq_s32(int32x4_t __p0, int32x4_t __p1) {
1650 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1659 __ai int64x2_t vbicq_s64(int64x2_t __p0, int64x2_t __p1) {
1661 __ret = __p0 & ~__p1;
1665 __ai int64x2_t vbicq_s64(int64x2_t __p0, int64x2_t __p1) {
1667 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1676 __ai int16x8_t vbicq_s16(int16x8_t __p0, int16x8_t __p1) {
1678 __ret = __p0 & ~__p1;
1682 __ai int16x8_t vbicq_s16(int16x8_t __p0, int16x8_t __p1) {
1684 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1693 __ai uint8x8_t vbic_u8(uint8x8_t __p0, uint8x8_t __p1) {
1695 __ret = __p0 & ~__p1;
1699 __ai uint8x8_t vbic_u8(uint8x8_t __p0, uint8x8_t __p1) {
1701 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1710 __ai uint32x2_t vbic_u32(uint32x2_t __p0, uint32x2_t __p1) {
1712 __ret = __p0 & ~__p1;
1716 __ai uint32x2_t vbic_u32(uint32x2_t __p0, uint32x2_t __p1) {
1718 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1727 __ai uint64x1_t vbic_u64(uint64x1_t __p0, uint64x1_t __p1) {
1729 __ret = __p0 & ~__p1;
1733 __ai uint64x1_t vbic_u64(uint64x1_t __p0, uint64x1_t __p1) {
1735 __ret = __p0 & ~__p1;
1741 __ai uint16x4_t vbic_u16(uint16x4_t __p0, uint16x4_t __p1) {
1743 __ret = __p0 & ~__p1;
1747 __ai uint16x4_t vbic_u16(uint16x4_t __p0, uint16x4_t __p1) {
1749 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1758 __ai int8x8_t vbic_s8(int8x8_t __p0, int8x8_t __p1) {
1760 __ret = __p0 & ~__p1;
1764 __ai int8x8_t vbic_s8(int8x8_t __p0, int8x8_t __p1) {
1766 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1775 __ai int32x2_t vbic_s32(int32x2_t __p0, int32x2_t __p1) {
1777 __ret = __p0 & ~__p1;
1781 __ai int32x2_t vbic_s32(int32x2_t __p0, int32x2_t __p1) {
1783 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1792 __ai int64x1_t vbic_s64(int64x1_t __p0, int64x1_t __p1) {
1794 __ret = __p0 & ~__p1;
1798 __ai int64x1_t vbic_s64(int64x1_t __p0, int64x1_t __p1) {
1800 __ret = __p0 & ~__p1;
1806 __ai int16x4_t vbic_s16(int16x4_t __p0, int16x4_t __p1) {
1808 __ret = __p0 & ~__p1;
1812 __ai int16x4_t vbic_s16(int16x4_t __p0, int16x4_t __p1) {
1814 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1823 __ai poly8x8_t vbsl_p8(uint8x8_t __p0, poly8x8_t __p1, poly8x8_t __p2) {
1825 __ret = (poly8x8_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 4);
1829 __ai poly8x8_t vbsl_p8(uint8x8_t __p0, poly8x8_t __p1, poly8x8_t __p2) {
1831 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1841 __ai poly16x4_t vbsl_p16(uint16x4_t __p0, poly16x4_t __p1, poly16x4_t __p2) {
1843 __ret = (poly16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 5);
1847 __ai poly16x4_t vbsl_p16(uint16x4_t __p0, poly16x4_t __p1, poly16x4_t __p2) {
1849 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1859 __ai poly8x16_t vbslq_p8(uint8x16_t __p0, poly8x16_t __p1, poly8x16_t __p2) {
1861 __ret = (poly8x16_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 36);
1865 __ai poly8x16_t vbslq_p8(uint8x16_t __p0, poly8x16_t __p1, poly8x16_t __p2) {
1867 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1877 __ai poly16x8_t vbslq_p16(uint16x8_t __p0, poly16x8_t __p1, poly16x8_t __p2) {
1879 __ret = (poly16x8_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 37);
1883 __ai poly16x8_t vbslq_p16(uint16x8_t __p0, poly16x8_t __p1, poly16x8_t __p2) {
1885 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1895 __ai uint8x16_t vbslq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
1897 __ret = (uint8x16_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 48);
1901 __ai uint8x16_t vbslq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
1903 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1913 __ai uint32x4_t vbslq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
1915 __ret = (uint32x4_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 50);
1919 __ai uint32x4_t vbslq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
1921 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
1931 __ai uint64x2_t vbslq_u64(uint64x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
1933 __ret = (uint64x2_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 51);
1937 __ai uint64x2_t vbslq_u64(uint64x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
1939 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
1949 __ai uint16x8_t vbslq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
1951 __ret = (uint16x8_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 49);
1955 __ai uint16x8_t vbslq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
1957 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1967 __ai int8x16_t vbslq_s8(uint8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
1969 __ret = (int8x16_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 32);
1973 __ai int8x16_t vbslq_s8(uint8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
1975 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
1985 __ai float32x4_t vbslq_f32(uint32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
1987 __ret = (float32x4_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 41);
1991 __ai float32x4_t vbslq_f32(uint32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
1993 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2003 __ai int32x4_t vbslq_s32(uint32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
2005 __ret = (int32x4_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 34);
2009 __ai int32x4_t vbslq_s32(uint32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
2011 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2021 __ai int64x2_t vbslq_s64(uint64x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
2023 __ret = (int64x2_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 35);
2027 __ai int64x2_t vbslq_s64(uint64x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
2029 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2039 __ai int16x8_t vbslq_s16(uint16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
2041 __ret = (int16x8_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 33);
2045 __ai int16x8_t vbslq_s16(uint16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
2047 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2057 __ai uint8x8_t vbsl_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
2059 __ret = (uint8x8_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 16);
2063 __ai uint8x8_t vbsl_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
2065 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2075 __ai uint32x2_t vbsl_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
2077 __ret = (uint32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 18);
2081 __ai uint32x2_t vbsl_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
2083 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2093 __ai uint64x1_t vbsl_u64(uint64x1_t __p0, uint64x1_t __p1, uint64x1_t __p2) {
2095 __ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2099 __ai uint64x1_t vbsl_u64(uint64x1_t __p0, uint64x1_t __p1, uint64x1_t __p2) {
2101 __ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2107 __ai uint16x4_t vbsl_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
2109 __ret = (uint16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 17);
2113 __ai uint16x4_t vbsl_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
2115 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2125 __ai int8x8_t vbsl_s8(uint8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
2127 __ret = (int8x8_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 0);
2131 __ai int8x8_t vbsl_s8(uint8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
2133 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2143 __ai float32x2_t vbsl_f32(uint32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
2145 __ret = (float32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
2149 __ai float32x2_t vbsl_f32(uint32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
2151 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2161 __ai int32x2_t vbsl_s32(uint32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
2163 __ret = (int32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 2);
2167 __ai int32x2_t vbsl_s32(uint32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
2169 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2179 __ai int64x1_t vbsl_s64(uint64x1_t __p0, int64x1_t __p1, int64x1_t __p2) {
2181 __ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2185 __ai int64x1_t vbsl_s64(uint64x1_t __p0, int64x1_t __p1, int64x1_t __p2) {
2187 __ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2193 __ai int16x4_t vbsl_s16(uint16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
2195 __ret = (int16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 1);
2199 __ai int16x4_t vbsl_s16(uint16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
2201 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2211 __ai uint32x4_t vcageq_f32(float32x4_t __p0, float32x4_t __p1) {
2213 __ret = (uint32x4_t) __builtin_neon_vcageq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
2217 __ai uint32x4_t vcageq_f32(float32x4_t __p0, float32x4_t __p1) {
2219 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2228 __ai uint32x2_t vcage_f32(float32x2_t __p0, float32x2_t __p1) {
2230 __ret = (uint32x2_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2234 __ai uint32x2_t vcage_f32(float32x2_t __p0, float32x2_t __p1) {
2236 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2245 __ai uint32x4_t vcagtq_f32(float32x4_t __p0, float32x4_t __p1) {
2247 __ret = (uint32x4_t) __builtin_neon_vcagtq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
2251 __ai uint32x4_t vcagtq_f32(float32x4_t __p0, float32x4_t __p1) {
2253 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2262 __ai uint32x2_t vcagt_f32(float32x2_t __p0, float32x2_t __p1) {
2264 __ret = (uint32x2_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2268 __ai uint32x2_t vcagt_f32(float32x2_t __p0, float32x2_t __p1) {
2270 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2279 __ai uint32x4_t vcaleq_f32(float32x4_t __p0, float32x4_t __p1) {
2281 __ret = (uint32x4_t) __builtin_neon_vcaleq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
2285 __ai uint32x4_t vcaleq_f32(float32x4_t __p0, float32x4_t __p1) {
2287 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2296 __ai uint32x2_t vcale_f32(float32x2_t __p0, float32x2_t __p1) {
2298 __ret = (uint32x2_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2302 __ai uint32x2_t vcale_f32(float32x2_t __p0, float32x2_t __p1) {
2304 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2313 __ai uint32x4_t vcaltq_f32(float32x4_t __p0, float32x4_t __p1) {
2315 __ret = (uint32x4_t) __builtin_neon_vcaltq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
2319 __ai uint32x4_t vcaltq_f32(float32x4_t __p0, float32x4_t __p1) {
2321 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2330 __ai uint32x2_t vcalt_f32(float32x2_t __p0, float32x2_t __p1) {
2332 __ret = (uint32x2_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2336 __ai uint32x2_t vcalt_f32(float32x2_t __p0, float32x2_t __p1) {
2338 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2347 __ai uint8x8_t vceq_p8(poly8x8_t __p0, poly8x8_t __p1) {
2349 __ret = (uint8x8_t)(__p0 == __p1);
2353 __ai uint8x8_t vceq_p8(poly8x8_t __p0, poly8x8_t __p1) {
2355 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2364 __ai uint8x16_t vceqq_p8(poly8x16_t __p0, poly8x16_t __p1) {
2366 __ret = (uint8x16_t)(__p0 == __p1);
2370 __ai uint8x16_t vceqq_p8(poly8x16_t __p0, poly8x16_t __p1) {
2372 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2381 __ai uint8x16_t vceqq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2383 __ret = (uint8x16_t)(__p0 == __p1);
2387 __ai uint8x16_t vceqq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2389 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2398 __ai uint32x4_t vceqq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2400 __ret = (uint32x4_t)(__p0 == __p1);
2404 __ai uint32x4_t vceqq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2406 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2415 __ai uint16x8_t vceqq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2417 __ret = (uint16x8_t)(__p0 == __p1);
2421 __ai uint16x8_t vceqq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2423 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2432 __ai uint8x16_t vceqq_s8(int8x16_t __p0, int8x16_t __p1) {
2434 __ret = (uint8x16_t)(__p0 == __p1);
2438 __ai uint8x16_t vceqq_s8(int8x16_t __p0, int8x16_t __p1) {
2440 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2449 __ai uint32x4_t vceqq_f32(float32x4_t __p0, float32x4_t __p1) {
2451 __ret = (uint32x4_t)(__p0 == __p1);
2455 __ai uint32x4_t vceqq_f32(float32x4_t __p0, float32x4_t __p1) {
2457 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2466 __ai uint32x4_t vceqq_s32(int32x4_t __p0, int32x4_t __p1) {
2468 __ret = (uint32x4_t)(__p0 == __p1);
2472 __ai uint32x4_t vceqq_s32(int32x4_t __p0, int32x4_t __p1) {
2474 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2483 __ai uint16x8_t vceqq_s16(int16x8_t __p0, int16x8_t __p1) {
2485 __ret = (uint16x8_t)(__p0 == __p1);
2489 __ai uint16x8_t vceqq_s16(int16x8_t __p0, int16x8_t __p1) {
2491 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2500 __ai uint8x8_t vceq_u8(uint8x8_t __p0, uint8x8_t __p1) {
2502 __ret = (uint8x8_t)(__p0 == __p1);
2506 __ai uint8x8_t vceq_u8(uint8x8_t __p0, uint8x8_t __p1) {
2508 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2517 __ai uint32x2_t vceq_u32(uint32x2_t __p0, uint32x2_t __p1) {
2519 __ret = (uint32x2_t)(__p0 == __p1);
2523 __ai uint32x2_t vceq_u32(uint32x2_t __p0, uint32x2_t __p1) {
2525 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2534 __ai uint16x4_t vceq_u16(uint16x4_t __p0, uint16x4_t __p1) {
2536 __ret = (uint16x4_t)(__p0 == __p1);
2540 __ai uint16x4_t vceq_u16(uint16x4_t __p0, uint16x4_t __p1) {
2542 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2551 __ai uint8x8_t vceq_s8(int8x8_t __p0, int8x8_t __p1) {
2553 __ret = (uint8x8_t)(__p0 == __p1);
2557 __ai uint8x8_t vceq_s8(int8x8_t __p0, int8x8_t __p1) {
2559 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2568 __ai uint32x2_t vceq_f32(float32x2_t __p0, float32x2_t __p1) {
2570 __ret = (uint32x2_t)(__p0 == __p1);
2574 __ai uint32x2_t vceq_f32(float32x2_t __p0, float32x2_t __p1) {
2576 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2585 __ai uint32x2_t vceq_s32(int32x2_t __p0, int32x2_t __p1) {
2587 __ret = (uint32x2_t)(__p0 == __p1);
2591 __ai uint32x2_t vceq_s32(int32x2_t __p0, int32x2_t __p1) {
2593 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2602 __ai uint16x4_t vceq_s16(int16x4_t __p0, int16x4_t __p1) {
2604 __ret = (uint16x4_t)(__p0 == __p1);
2608 __ai uint16x4_t vceq_s16(int16x4_t __p0, int16x4_t __p1) {
2610 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2619 __ai uint8x16_t vcgeq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2621 __ret = (uint8x16_t)(__p0 >= __p1);
2625 __ai uint8x16_t vcgeq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2627 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2636 __ai uint32x4_t vcgeq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2638 __ret = (uint32x4_t)(__p0 >= __p1);
2642 __ai uint32x4_t vcgeq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2644 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2653 __ai uint16x8_t vcgeq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2655 __ret = (uint16x8_t)(__p0 >= __p1);
2659 __ai uint16x8_t vcgeq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2661 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2670 __ai uint8x16_t vcgeq_s8(int8x16_t __p0, int8x16_t __p1) {
2672 __ret = (uint8x16_t)(__p0 >= __p1);
2676 __ai uint8x16_t vcgeq_s8(int8x16_t __p0, int8x16_t __p1) {
2678 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2687 __ai uint32x4_t vcgeq_f32(float32x4_t __p0, float32x4_t __p1) {
2689 __ret = (uint32x4_t)(__p0 >= __p1);
2693 __ai uint32x4_t vcgeq_f32(float32x4_t __p0, float32x4_t __p1) {
2695 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2704 __ai uint32x4_t vcgeq_s32(int32x4_t __p0, int32x4_t __p1) {
2706 __ret = (uint32x4_t)(__p0 >= __p1);
2710 __ai uint32x4_t vcgeq_s32(int32x4_t __p0, int32x4_t __p1) {
2712 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2721 __ai uint16x8_t vcgeq_s16(int16x8_t __p0, int16x8_t __p1) {
2723 __ret = (uint16x8_t)(__p0 >= __p1);
2727 __ai uint16x8_t vcgeq_s16(int16x8_t __p0, int16x8_t __p1) {
2729 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2738 __ai uint8x8_t vcge_u8(uint8x8_t __p0, uint8x8_t __p1) {
2740 __ret = (uint8x8_t)(__p0 >= __p1);
2744 __ai uint8x8_t vcge_u8(uint8x8_t __p0, uint8x8_t __p1) {
2746 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2755 __ai uint32x2_t vcge_u32(uint32x2_t __p0, uint32x2_t __p1) {
2757 __ret = (uint32x2_t)(__p0 >= __p1);
2761 __ai uint32x2_t vcge_u32(uint32x2_t __p0, uint32x2_t __p1) {
2763 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2772 __ai uint16x4_t vcge_u16(uint16x4_t __p0, uint16x4_t __p1) {
2774 __ret = (uint16x4_t)(__p0 >= __p1);
2778 __ai uint16x4_t vcge_u16(uint16x4_t __p0, uint16x4_t __p1) {
2780 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2789 __ai uint8x8_t vcge_s8(int8x8_t __p0, int8x8_t __p1) {
2791 __ret = (uint8x8_t)(__p0 >= __p1);
2795 __ai uint8x8_t vcge_s8(int8x8_t __p0, int8x8_t __p1) {
2797 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2806 __ai uint32x2_t vcge_f32(float32x2_t __p0, float32x2_t __p1) {
2808 __ret = (uint32x2_t)(__p0 >= __p1);
2812 __ai uint32x2_t vcge_f32(float32x2_t __p0, float32x2_t __p1) {
2814 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2823 __ai uint32x2_t vcge_s32(int32x2_t __p0, int32x2_t __p1) {
2825 __ret = (uint32x2_t)(__p0 >= __p1);
2829 __ai uint32x2_t vcge_s32(int32x2_t __p0, int32x2_t __p1) {
2831 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
2840 __ai uint16x4_t vcge_s16(int16x4_t __p0, int16x4_t __p1) {
2842 __ret = (uint16x4_t)(__p0 >= __p1);
2846 __ai uint16x4_t vcge_s16(int16x4_t __p0, int16x4_t __p1) {
2848 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2857 __ai uint8x16_t vcgtq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2859 __ret = (uint8x16_t)(__p0 > __p1);
2863 __ai uint8x16_t vcgtq_u8(uint8x16_t __p0, uint8x16_t __p1) {
2865 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2874 __ai uint32x4_t vcgtq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2876 __ret = (uint32x4_t)(__p0 > __p1);
2880 __ai uint32x4_t vcgtq_u32(uint32x4_t __p0, uint32x4_t __p1) {
2882 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2891 __ai uint16x8_t vcgtq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2893 __ret = (uint16x8_t)(__p0 > __p1);
2897 __ai uint16x8_t vcgtq_u16(uint16x8_t __p0, uint16x8_t __p1) {
2899 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2908 __ai uint8x16_t vcgtq_s8(int8x16_t __p0, int8x16_t __p1) {
2910 __ret = (uint8x16_t)(__p0 > __p1);
2914 __ai uint8x16_t vcgtq_s8(int8x16_t __p0, int8x16_t __p1) {
2916 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
2925 __ai uint32x4_t vcgtq_f32(float32x4_t __p0, float32x4_t __p1) {
2927 __ret = (uint32x4_t)(__p0 > __p1);
2931 __ai uint32x4_t vcgtq_f32(float32x4_t __p0, float32x4_t __p1) {
2933 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2942 __ai uint32x4_t vcgtq_s32(int32x4_t __p0, int32x4_t __p1) {
2944 __ret = (uint32x4_t)(__p0 > __p1);
2948 __ai uint32x4_t vcgtq_s32(int32x4_t __p0, int32x4_t __p1) {
2950 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
2959 __ai uint16x8_t vcgtq_s16(int16x8_t __p0, int16x8_t __p1) {
2961 __ret = (uint16x8_t)(__p0 > __p1);
2965 __ai uint16x8_t vcgtq_s16(int16x8_t __p0, int16x8_t __p1) {
2967 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2976 __ai uint8x8_t vcgt_u8(uint8x8_t __p0, uint8x8_t __p1) {
2978 __ret = (uint8x8_t)(__p0 > __p1);
2982 __ai uint8x8_t vcgt_u8(uint8x8_t __p0, uint8x8_t __p1) {
2984 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2993 __ai uint32x2_t vcgt_u32(uint32x2_t __p0, uint32x2_t __p1) {
2995 __ret = (uint32x2_t)(__p0 > __p1);
2999 __ai uint32x2_t vcgt_u32(uint32x2_t __p0, uint32x2_t __p1) {
3001 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3010 __ai uint16x4_t vcgt_u16(uint16x4_t __p0, uint16x4_t __p1) {
3012 __ret = (uint16x4_t)(__p0 > __p1);
3016 __ai uint16x4_t vcgt_u16(uint16x4_t __p0, uint16x4_t __p1) {
3018 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3027 __ai uint8x8_t vcgt_s8(int8x8_t __p0, int8x8_t __p1) {
3029 __ret = (uint8x8_t)(__p0 > __p1);
3033 __ai uint8x8_t vcgt_s8(int8x8_t __p0, int8x8_t __p1) {
3035 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3044 __ai uint32x2_t vcgt_f32(float32x2_t __p0, float32x2_t __p1) {
3046 __ret = (uint32x2_t)(__p0 > __p1);
3050 __ai uint32x2_t vcgt_f32(float32x2_t __p0, float32x2_t __p1) {
3052 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3061 __ai uint32x2_t vcgt_s32(int32x2_t __p0, int32x2_t __p1) {
3063 __ret = (uint32x2_t)(__p0 > __p1);
3067 __ai uint32x2_t vcgt_s32(int32x2_t __p0, int32x2_t __p1) {
3069 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3078 __ai uint16x4_t vcgt_s16(int16x4_t __p0, int16x4_t __p1) {
3080 __ret = (uint16x4_t)(__p0 > __p1);
3084 __ai uint16x4_t vcgt_s16(int16x4_t __p0, int16x4_t __p1) {
3086 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3095 __ai uint8x16_t vcleq_u8(uint8x16_t __p0, uint8x16_t __p1) {
3097 __ret = (uint8x16_t)(__p0 <= __p1);
3101 __ai uint8x16_t vcleq_u8(uint8x16_t __p0, uint8x16_t __p1) {
3103 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
3112 __ai uint32x4_t vcleq_u32(uint32x4_t __p0, uint32x4_t __p1) {
3114 __ret = (uint32x4_t)(__p0 <= __p1);
3118 __ai uint32x4_t vcleq_u32(uint32x4_t __p0, uint32x4_t __p1) {
3120 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3129 __ai uint16x8_t vcleq_u16(uint16x8_t __p0, uint16x8_t __p1) {
3131 __ret = (uint16x8_t)(__p0 <= __p1);
3135 __ai uint16x8_t vcleq_u16(uint16x8_t __p0, uint16x8_t __p1) {
3137 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3146 __ai uint8x16_t vcleq_s8(int8x16_t __p0, int8x16_t __p1) {
3148 __ret = (uint8x16_t)(__p0 <= __p1);
3152 __ai uint8x16_t vcleq_s8(int8x16_t __p0, int8x16_t __p1) {
3154 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
3163 __ai uint32x4_t vcleq_f32(float32x4_t __p0, float32x4_t __p1) {
3165 __ret = (uint32x4_t)(__p0 <= __p1);
3169 __ai uint32x4_t vcleq_f32(float32x4_t __p0, float32x4_t __p1) {
3171 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3180 __ai uint32x4_t vcleq_s32(int32x4_t __p0, int32x4_t __p1) {
3182 __ret = (uint32x4_t)(__p0 <= __p1);
3186 __ai uint32x4_t vcleq_s32(int32x4_t __p0, int32x4_t __p1) {
3188 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3197 __ai uint16x8_t vcleq_s16(int16x8_t __p0, int16x8_t __p1) {
3199 __ret = (uint16x8_t)(__p0 <= __p1);
3203 __ai uint16x8_t vcleq_s16(int16x8_t __p0, int16x8_t __p1) {
3205 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3214 __ai uint8x8_t vcle_u8(uint8x8_t __p0, uint8x8_t __p1) {
3216 __ret = (uint8x8_t)(__p0 <= __p1);
3220 __ai uint8x8_t vcle_u8(uint8x8_t __p0, uint8x8_t __p1) {
3222 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3231 __ai uint32x2_t vcle_u32(uint32x2_t __p0, uint32x2_t __p1) {
3233 __ret = (uint32x2_t)(__p0 <= __p1);
3237 __ai uint32x2_t vcle_u32(uint32x2_t __p0, uint32x2_t __p1) {
3239 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3248 __ai uint16x4_t vcle_u16(uint16x4_t __p0, uint16x4_t __p1) {
3250 __ret = (uint16x4_t)(__p0 <= __p1);
3254 __ai uint16x4_t vcle_u16(uint16x4_t __p0, uint16x4_t __p1) {
3256 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3265 __ai uint8x8_t vcle_s8(int8x8_t __p0, int8x8_t __p1) {
3267 __ret = (uint8x8_t)(__p0 <= __p1);
3271 __ai uint8x8_t vcle_s8(int8x8_t __p0, int8x8_t __p1) {
3273 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3282 __ai uint32x2_t vcle_f32(float32x2_t __p0, float32x2_t __p1) {
3284 __ret = (uint32x2_t)(__p0 <= __p1);
3288 __ai uint32x2_t vcle_f32(float32x2_t __p0, float32x2_t __p1) {
3290 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3299 __ai uint32x2_t vcle_s32(int32x2_t __p0, int32x2_t __p1) {
3301 __ret = (uint32x2_t)(__p0 <= __p1);
3305 __ai uint32x2_t vcle_s32(int32x2_t __p0, int32x2_t __p1) {
3307 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3316 __ai uint16x4_t vcle_s16(int16x4_t __p0, int16x4_t __p1) {
3318 __ret = (uint16x4_t)(__p0 <= __p1);
3322 __ai uint16x4_t vcle_s16(int16x4_t __p0, int16x4_t __p1) {
3324 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3429 __ai uint8x16_t vcltq_u8(uint8x16_t __p0, uint8x16_t __p1) {
3431 __ret = (uint8x16_t)(__p0 < __p1);
3435 __ai uint8x16_t vcltq_u8(uint8x16_t __p0, uint8x16_t __p1) {
3437 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
3446 __ai uint32x4_t vcltq_u32(uint32x4_t __p0, uint32x4_t __p1) {
3448 __ret = (uint32x4_t)(__p0 < __p1);
3452 __ai uint32x4_t vcltq_u32(uint32x4_t __p0, uint32x4_t __p1) {
3454 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3463 __ai uint16x8_t vcltq_u16(uint16x8_t __p0, uint16x8_t __p1) {
3465 __ret = (uint16x8_t)(__p0 < __p1);
3469 __ai uint16x8_t vcltq_u16(uint16x8_t __p0, uint16x8_t __p1) {
3471 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3480 __ai uint8x16_t vcltq_s8(int8x16_t __p0, int8x16_t __p1) {
3482 __ret = (uint8x16_t)(__p0 < __p1);
3486 __ai uint8x16_t vcltq_s8(int8x16_t __p0, int8x16_t __p1) {
3488 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
3497 __ai uint32x4_t vcltq_f32(float32x4_t __p0, float32x4_t __p1) {
3499 __ret = (uint32x4_t)(__p0 < __p1);
3503 __ai uint32x4_t vcltq_f32(float32x4_t __p0, float32x4_t __p1) {
3505 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3514 __ai uint32x4_t vcltq_s32(int32x4_t __p0, int32x4_t __p1) {
3516 __ret = (uint32x4_t)(__p0 < __p1);
3520 __ai uint32x4_t vcltq_s32(int32x4_t __p0, int32x4_t __p1) {
3522 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3531 __ai uint16x8_t vcltq_s16(int16x8_t __p0, int16x8_t __p1) {
3533 __ret = (uint16x8_t)(__p0 < __p1);
3537 __ai uint16x8_t vcltq_s16(int16x8_t __p0, int16x8_t __p1) {
3539 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3548 __ai uint8x8_t vclt_u8(uint8x8_t __p0, uint8x8_t __p1) {
3550 __ret = (uint8x8_t)(__p0 < __p1);
3554 __ai uint8x8_t vclt_u8(uint8x8_t __p0, uint8x8_t __p1) {
3556 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3565 __ai uint32x2_t vclt_u32(uint32x2_t __p0, uint32x2_t __p1) {
3567 __ret = (uint32x2_t)(__p0 < __p1);
3571 __ai uint32x2_t vclt_u32(uint32x2_t __p0, uint32x2_t __p1) {
3573 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3582 __ai uint16x4_t vclt_u16(uint16x4_t __p0, uint16x4_t __p1) {
3584 __ret = (uint16x4_t)(__p0 < __p1);
3588 __ai uint16x4_t vclt_u16(uint16x4_t __p0, uint16x4_t __p1) {
3590 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3599 __ai uint8x8_t vclt_s8(int8x8_t __p0, int8x8_t __p1) {
3601 __ret = (uint8x8_t)(__p0 < __p1);
3605 __ai uint8x8_t vclt_s8(int8x8_t __p0, int8x8_t __p1) {
3607 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3616 __ai uint32x2_t vclt_f32(float32x2_t __p0, float32x2_t __p1) {
3618 __ret = (uint32x2_t)(__p0 < __p1);
3622 __ai uint32x2_t vclt_f32(float32x2_t __p0, float32x2_t __p1) {
3624 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3633 __ai uint32x2_t vclt_s32(int32x2_t __p0, int32x2_t __p1) {
3635 __ret = (uint32x2_t)(__p0 < __p1);
3639 __ai uint32x2_t vclt_s32(int32x2_t __p0, int32x2_t __p1) {
3641 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
3650 __ai uint16x4_t vclt_s16(int16x4_t __p0, int16x4_t __p1) {
3652 __ret = (uint16x4_t)(__p0 < __p1);
3656 __ai uint16x4_t vclt_s16(int16x4_t __p0, int16x4_t __p1) {
3658 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3955 __ai poly8x16_t vcombine_p8(poly8x8_t __p0, poly8x8_t __p1) {
3957 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
3961 __ai poly8x16_t vcombine_p8(poly8x8_t __p0, poly8x8_t __p1) {
3963 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3972 __ai poly16x8_t vcombine_p16(poly16x4_t __p0, poly16x4_t __p1) {
3974 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
3978 __ai poly16x8_t vcombine_p16(poly16x4_t __p0, poly16x4_t __p1) {
3980 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
3989 __ai uint8x16_t vcombine_u8(uint8x8_t __p0, uint8x8_t __p1) {
3991 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
3995 __ai uint8x16_t vcombine_u8(uint8x8_t __p0, uint8x8_t __p1) {
3997 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
4003 __ai uint8x16_t __noswap_vcombine_u8(uint8x8_t __p0, uint8x8_t __p1) {
4005 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
4011 __ai uint32x4_t vcombine_u32(uint32x2_t __p0, uint32x2_t __p1) {
4013 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4017 __ai uint32x4_t vcombine_u32(uint32x2_t __p0, uint32x2_t __p1) {
4019 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
4025 __ai uint32x4_t __noswap_vcombine_u32(uint32x2_t __p0, uint32x2_t __p1) {
4027 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4033 __ai uint64x2_t vcombine_u64(uint64x1_t __p0, uint64x1_t __p1) {
4035 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
4039 __ai uint64x2_t vcombine_u64(uint64x1_t __p0, uint64x1_t __p1) {
4041 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
4048 __ai uint16x8_t vcombine_u16(uint16x4_t __p0, uint16x4_t __p1) {
4050 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4054 __ai uint16x8_t vcombine_u16(uint16x4_t __p0, uint16x4_t __p1) {
4056 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
4062 __ai uint16x8_t __noswap_vcombine_u16(uint16x4_t __p0, uint16x4_t __p1) {
4064 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4070 __ai int8x16_t vcombine_s8(int8x8_t __p0, int8x8_t __p1) {
4072 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
4076 __ai int8x16_t vcombine_s8(int8x8_t __p0, int8x8_t __p1) {
4078 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
4084 __ai int8x16_t __noswap_vcombine_s8(int8x8_t __p0, int8x8_t __p1) {
4086 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
4092 __ai float32x4_t vcombine_f32(float32x2_t __p0, float32x2_t __p1) {
4094 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4098 __ai float32x4_t vcombine_f32(float32x2_t __p0, float32x2_t __p1) {
4100 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
4106 __ai float32x4_t __noswap_vcombine_f32(float32x2_t __p0, float32x2_t __p1) {
4108 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4114 __ai float16x8_t vcombine_f16(float16x4_t __p0, float16x4_t __p1) {
4116 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4120 __ai float16x8_t vcombine_f16(float16x4_t __p0, float16x4_t __p1) {
4122 float16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
4128 __ai float16x8_t __noswap_vcombine_f16(float16x4_t __p0, float16x4_t __p1) {
4130 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4136 __ai int32x4_t vcombine_s32(int32x2_t __p0, int32x2_t __p1) {
4138 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4142 __ai int32x4_t vcombine_s32(int32x2_t __p0, int32x2_t __p1) {
4144 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
4150 __ai int32x4_t __noswap_vcombine_s32(int32x2_t __p0, int32x2_t __p1) {
4152 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3);
4158 __ai int64x2_t vcombine_s64(int64x1_t __p0, int64x1_t __p1) {
4160 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
4164 __ai int64x2_t vcombine_s64(int64x1_t __p0, int64x1_t __p1) {
4166 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
4173 __ai int16x8_t vcombine_s16(int16x4_t __p0, int16x4_t __p1) {
4175 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4179 __ai int16x8_t vcombine_s16(int16x4_t __p0, int16x4_t __p1) {
4181 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
4187 __ai int16x8_t __noswap_vcombine_s16(int16x4_t __p0, int16x4_t __p1) {
4189 __ret = __builtin_shufflevector(__p0, __p1, 0, 1, 2, 3, 4, 5, 6, 7);
4427 #define vcvtq_n_f32_u32(__p0, __p1) __extension__ ({ \
4430 __ret = (float32x4_t) __builtin_neon_vcvtq_n_f32_v((int8x16_t)__s0, __p1, 50); \
4434 #define vcvtq_n_f32_u32(__p0, __p1) __extension__ ({ \
4438 __ret = (float32x4_t) __builtin_neon_vcvtq_n_f32_v((int8x16_t)__rev0, __p1, 50); \
4445 #define vcvtq_n_f32_s32(__p0, __p1) __extension__ ({ \
4448 __ret = (float32x4_t) __builtin_neon_vcvtq_n_f32_v((int8x16_t)__s0, __p1, 34); \
4452 #define vcvtq_n_f32_s32(__p0, __p1) __extension__ ({ \
4456 __ret = (float32x4_t) __builtin_neon_vcvtq_n_f32_v((int8x16_t)__rev0, __p1, 34); \
4463 #define vcvt_n_f32_u32(__p0, __p1) __extension__ ({ \
4466 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__s0, __p1, 18); \
4470 #define vcvt_n_f32_u32(__p0, __p1) __extension__ ({ \
4474 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__rev0, __p1, 18); \
4481 #define vcvt_n_f32_s32(__p0, __p1) __extension__ ({ \
4484 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__s0, __p1, 2); \
4488 #define vcvt_n_f32_s32(__p0, __p1) __extension__ ({ \
4492 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__rev0, __p1, 2); \
4499 #define vcvtq_n_s32_f32(__p0, __p1) __extension__ ({ \
4502 __ret = (int32x4_t) __builtin_neon_vcvtq_n_s32_v((int8x16_t)__s0, __p1, 34); \
4506 #define vcvtq_n_s32_f32(__p0, __p1) __extension__ ({ \
4510 __ret = (int32x4_t) __builtin_neon_vcvtq_n_s32_v((int8x16_t)__rev0, __p1, 34); \
4517 #define vcvt_n_s32_f32(__p0, __p1) __extension__ ({ \
4520 __ret = (int32x2_t) __builtin_neon_vcvt_n_s32_v((int8x8_t)__s0, __p1, 2); \
4524 #define vcvt_n_s32_f32(__p0, __p1) __extension__ ({ \
4528 __ret = (int32x2_t) __builtin_neon_vcvt_n_s32_v((int8x8_t)__rev0, __p1, 2); \
4535 #define vcvtq_n_u32_f32(__p0, __p1) __extension__ ({ \
4538 __ret = (uint32x4_t) __builtin_neon_vcvtq_n_u32_v((int8x16_t)__s0, __p1, 50); \
4542 #define vcvtq_n_u32_f32(__p0, __p1) __extension__ ({ \
4546 __ret = (uint32x4_t) __builtin_neon_vcvtq_n_u32_v((int8x16_t)__rev0, __p1, 50); \
4553 #define vcvt_n_u32_f32(__p0, __p1) __extension__ ({ \
4556 __ret = (uint32x2_t) __builtin_neon_vcvt_n_u32_v((int8x8_t)__s0, __p1, 18); \
4560 #define vcvt_n_u32_f32(__p0, __p1) __extension__ ({ \
4564 __ret = (uint32x2_t) __builtin_neon_vcvt_n_u32_v((int8x8_t)__rev0, __p1, 18); \
4635 #define vdup_lane_p8(__p0, __p1) __extension__ ({ \
4638 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4642 #define vdup_lane_p8(__p0, __p1) __extension__ ({ \
4646 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4653 #define vdup_lane_p16(__p0, __p1) __extension__ ({ \
4656 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
4660 #define vdup_lane_p16(__p0, __p1) __extension__ ({ \
4664 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
4671 #define vdupq_lane_p8(__p0, __p1) __extension__ ({ \
4674 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4678 #define vdupq_lane_p8(__p0, __p1) __extension__ ({ \
4682 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4689 #define vdupq_lane_p16(__p0, __p1) __extension__ ({ \
4692 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4696 #define vdupq_lane_p16(__p0, __p1) __extension__ ({ \
4700 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4707 #define vdupq_lane_u8(__p0, __p1) __extension__ ({ \
4710 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4714 #define vdupq_lane_u8(__p0, __p1) __extension__ ({ \
4718 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4725 #define vdupq_lane_u32(__p0, __p1) __extension__ ({ \
4728 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
4732 #define vdupq_lane_u32(__p0, __p1) __extension__ ({ \
4736 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
4743 #define vdupq_lane_u64(__p0, __p1) __extension__ ({ \
4746 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4750 #define vdupq_lane_u64(__p0, __p1) __extension__ ({ \
4753 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4760 #define vdupq_lane_u16(__p0, __p1) __extension__ ({ \
4763 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4767 #define vdupq_lane_u16(__p0, __p1) __extension__ ({ \
4771 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4778 #define vdupq_lane_s8(__p0, __p1) __extension__ ({ \
4781 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4785 #define vdupq_lane_s8(__p0, __p1) __extension__ ({ \
4789 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4796 #define vdupq_lane_f32(__p0, __p1) __extension__ ({ \
4799 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
4803 #define vdupq_lane_f32(__p0, __p1) __extension__ ({ \
4807 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
4814 #define vdupq_lane_s32(__p0, __p1) __extension__ ({ \
4817 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
4821 #define vdupq_lane_s32(__p0, __p1) __extension__ ({ \
4825 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
4832 #define vdupq_lane_s64(__p0, __p1) __extension__ ({ \
4835 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4839 #define vdupq_lane_s64(__p0, __p1) __extension__ ({ \
4842 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4849 #define vdupq_lane_s16(__p0, __p1) __extension__ ({ \
4852 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4856 #define vdupq_lane_s16(__p0, __p1) __extension__ ({ \
4860 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4867 #define vdup_lane_u8(__p0, __p1) __extension__ ({ \
4870 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4874 #define vdup_lane_u8(__p0, __p1) __extension__ ({ \
4878 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4885 #define vdup_lane_u32(__p0, __p1) __extension__ ({ \
4888 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4892 #define vdup_lane_u32(__p0, __p1) __extension__ ({ \
4896 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
4903 #define vdup_lane_u64(__p0, __p1) __extension__ ({ \
4906 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
4910 #define vdup_lane_u64(__p0, __p1) __extension__ ({ \
4913 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
4919 #define vdup_lane_u16(__p0, __p1) __extension__ ({ \
4922 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
4926 #define vdup_lane_u16(__p0, __p1) __extension__ ({ \
4930 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
4937 #define vdup_lane_s8(__p0, __p1) __extension__ ({ \
4940 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4944 #define vdup_lane_s8(__p0, __p1) __extension__ ({ \
4948 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
4955 #define vdup_lane_f32(__p0, __p1) __extension__ ({ \
4958 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4962 #define vdup_lane_f32(__p0, __p1) __extension__ ({ \
4966 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
4973 #define vdup_lane_s32(__p0, __p1) __extension__ ({ \
4976 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
4980 #define vdup_lane_s32(__p0, __p1) __extension__ ({ \
4984 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
4991 #define vdup_lane_s64(__p0, __p1) __extension__ ({ \
4994 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
4998 #define vdup_lane_s64(__p0, __p1) __extension__ ({ \
5001 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
5007 #define vdup_lane_s16(__p0, __p1) __extension__ ({ \
5010 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
5014 #define vdup_lane_s16(__p0, __p1) __extension__ ({ \
5018 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
5387 __ai uint8x16_t veorq_u8(uint8x16_t __p0, uint8x16_t __p1) {
5389 __ret = __p0 ^ __p1;
5393 __ai uint8x16_t veorq_u8(uint8x16_t __p0, uint8x16_t __p1) {
5395 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
5404 __ai uint32x4_t veorq_u32(uint32x4_t __p0, uint32x4_t __p1) {
5406 __ret = __p0 ^ __p1;
5410 __ai uint32x4_t veorq_u32(uint32x4_t __p0, uint32x4_t __p1) {
5412 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
5421 __ai uint64x2_t veorq_u64(uint64x2_t __p0, uint64x2_t __p1) {
5423 __ret = __p0 ^ __p1;
5427 __ai uint64x2_t veorq_u64(uint64x2_t __p0, uint64x2_t __p1) {
5429 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
5438 __ai uint16x8_t veorq_u16(uint16x8_t __p0, uint16x8_t __p1) {
5440 __ret = __p0 ^ __p1;
5444 __ai uint16x8_t veorq_u16(uint16x8_t __p0, uint16x8_t __p1) {
5446 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
5455 __ai int8x16_t veorq_s8(int8x16_t __p0, int8x16_t __p1) {
5457 __ret = __p0 ^ __p1;
5461 __ai int8x16_t veorq_s8(int8x16_t __p0, int8x16_t __p1) {
5463 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
5472 __ai int32x4_t veorq_s32(int32x4_t __p0, int32x4_t __p1) {
5474 __ret = __p0 ^ __p1;
5478 __ai int32x4_t veorq_s32(int32x4_t __p0, int32x4_t __p1) {
5480 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
5489 __ai int64x2_t veorq_s64(int64x2_t __p0, int64x2_t __p1) {
5491 __ret = __p0 ^ __p1;
5495 __ai int64x2_t veorq_s64(int64x2_t __p0, int64x2_t __p1) {
5497 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
5506 __ai int16x8_t veorq_s16(int16x8_t __p0, int16x8_t __p1) {
5508 __ret = __p0 ^ __p1;
5512 __ai int16x8_t veorq_s16(int16x8_t __p0, int16x8_t __p1) {
5514 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
5523 __ai uint8x8_t veor_u8(uint8x8_t __p0, uint8x8_t __p1) {
5525 __ret = __p0 ^ __p1;
5529 __ai uint8x8_t veor_u8(uint8x8_t __p0, uint8x8_t __p1) {
5531 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
5540 __ai uint32x2_t veor_u32(uint32x2_t __p0, uint32x2_t __p1) {
5542 __ret = __p0 ^ __p1;
5546 __ai uint32x2_t veor_u32(uint32x2_t __p0, uint32x2_t __p1) {
5548 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
5557 __ai uint64x1_t veor_u64(uint64x1_t __p0, uint64x1_t __p1) {
5559 __ret = __p0 ^ __p1;
5563 __ai uint64x1_t veor_u64(uint64x1_t __p0, uint64x1_t __p1) {
5565 __ret = __p0 ^ __p1;
5571 __ai uint16x4_t veor_u16(uint16x4_t __p0, uint16x4_t __p1) {
5573 __ret = __p0 ^ __p1;
5577 __ai uint16x4_t veor_u16(uint16x4_t __p0, uint16x4_t __p1) {
5579 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
5588 __ai int8x8_t veor_s8(int8x8_t __p0, int8x8_t __p1) {
5590 __ret = __p0 ^ __p1;
5594 __ai int8x8_t veor_s8(int8x8_t __p0, int8x8_t __p1) {
5596 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
5605 __ai int32x2_t veor_s32(int32x2_t __p0, int32x2_t __p1) {
5607 __ret = __p0 ^ __p1;
5611 __ai int32x2_t veor_s32(int32x2_t __p0, int32x2_t __p1) {
5613 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
5622 __ai int64x1_t veor_s64(int64x1_t __p0, int64x1_t __p1) {
5624 __ret = __p0 ^ __p1;
5628 __ai int64x1_t veor_s64(int64x1_t __p0, int64x1_t __p1) {
5630 __ret = __p0 ^ __p1;
5636 __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
5638 __ret = __p0 ^ __p1;
5642 __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
5644 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
5653 #define vext_p8(__p0, __p1, __p2) __extension__ ({ \
5655 poly8x8_t __s1 = __p1; \
5661 #define vext_p8(__p0, __p1, __p2) __extension__ ({ \
5663 poly8x8_t __s1 = __p1; \
5674 #define vext_p16(__p0, __p1, __p2) __extension__ ({ \
5676 poly16x4_t __s1 = __p1; \
5682 #define vext_p16(__p0, __p1, __p2) __extension__ ({ \
5684 poly16x4_t __s1 = __p1; \
5695 #define vextq_p8(__p0, __p1, __p2) __extension__ ({ \
5697 poly8x16_t __s1 = __p1; \
5703 #define vextq_p8(__p0, __p1, __p2) __extension__ ({ \
5705 poly8x16_t __s1 = __p1; \
5716 #define vextq_p16(__p0, __p1, __p2) __extension__ ({ \
5718 poly16x8_t __s1 = __p1; \
5724 #define vextq_p16(__p0, __p1, __p2) __extension__ ({ \
5726 poly16x8_t __s1 = __p1; \
5737 #define vextq_u8(__p0, __p1, __p2) __extension__ ({ \
5739 uint8x16_t __s1 = __p1; \
5745 #define vextq_u8(__p0, __p1, __p2) __extension__ ({ \
5747 uint8x16_t __s1 = __p1; \
5758 #define vextq_u32(__p0, __p1, __p2) __extension__ ({ \
5760 uint32x4_t __s1 = __p1; \
5766 #define vextq_u32(__p0, __p1, __p2) __extension__ ({ \
5768 uint32x4_t __s1 = __p1; \
5779 #define vextq_u64(__p0, __p1, __p2) __extension__ ({ \
5781 uint64x2_t __s1 = __p1; \
5787 #define vextq_u64(__p0, __p1, __p2) __extension__ ({ \
5789 uint64x2_t __s1 = __p1; \
5800 #define vextq_u16(__p0, __p1, __p2) __extension__ ({ \
5802 uint16x8_t __s1 = __p1; \
5808 #define vextq_u16(__p0, __p1, __p2) __extension__ ({ \
5810 uint16x8_t __s1 = __p1; \
5821 #define vextq_s8(__p0, __p1, __p2) __extension__ ({ \
5823 int8x16_t __s1 = __p1; \
5829 #define vextq_s8(__p0, __p1, __p2) __extension__ ({ \
5831 int8x16_t __s1 = __p1; \
5842 #define vextq_f32(__p0, __p1, __p2) __extension__ ({ \
5844 float32x4_t __s1 = __p1; \
5850 #define vextq_f32(__p0, __p1, __p2) __extension__ ({ \
5852 float32x4_t __s1 = __p1; \
5863 #define vextq_s32(__p0, __p1, __p2) __extension__ ({ \
5865 int32x4_t __s1 = __p1; \
5871 #define vextq_s32(__p0, __p1, __p2) __extension__ ({ \
5873 int32x4_t __s1 = __p1; \
5884 #define vextq_s64(__p0, __p1, __p2) __extension__ ({ \
5886 int64x2_t __s1 = __p1; \
5892 #define vextq_s64(__p0, __p1, __p2) __extension__ ({ \
5894 int64x2_t __s1 = __p1; \
5905 #define vextq_s16(__p0, __p1, __p2) __extension__ ({ \
5907 int16x8_t __s1 = __p1; \
5913 #define vextq_s16(__p0, __p1, __p2) __extension__ ({ \
5915 int16x8_t __s1 = __p1; \
5926 #define vext_u8(__p0, __p1, __p2) __extension__ ({ \
5928 uint8x8_t __s1 = __p1; \
5934 #define vext_u8(__p0, __p1, __p2) __extension__ ({ \
5936 uint8x8_t __s1 = __p1; \
5947 #define vext_u32(__p0, __p1, __p2) __extension__ ({ \
5949 uint32x2_t __s1 = __p1; \
5955 #define vext_u32(__p0, __p1, __p2) __extension__ ({ \
5957 uint32x2_t __s1 = __p1; \
5968 #define vext_u64(__p0, __p1, __p2) __extension__ ({ \
5970 uint64x1_t __s1 = __p1; \
5976 #define vext_u64(__p0, __p1, __p2) __extension__ ({ \
5978 uint64x1_t __s1 = __p1; \
5986 #define vext_u16(__p0, __p1, __p2) __extension__ ({ \
5988 uint16x4_t __s1 = __p1; \
5994 #define vext_u16(__p0, __p1, __p2) __extension__ ({ \
5996 uint16x4_t __s1 = __p1; \
6007 #define vext_s8(__p0, __p1, __p2) __extension__ ({ \
6009 int8x8_t __s1 = __p1; \
6015 #define vext_s8(__p0, __p1, __p2) __extension__ ({ \
6017 int8x8_t __s1 = __p1; \
6028 #define vext_f32(__p0, __p1, __p2) __extension__ ({ \
6030 float32x2_t __s1 = __p1; \
6036 #define vext_f32(__p0, __p1, __p2) __extension__ ({ \
6038 float32x2_t __s1 = __p1; \
6049 #define vext_s32(__p0, __p1, __p2) __extension__ ({ \
6051 int32x2_t __s1 = __p1; \
6057 #define vext_s32(__p0, __p1, __p2) __extension__ ({ \
6059 int32x2_t __s1 = __p1; \
6070 #define vext_s64(__p0, __p1, __p2) __extension__ ({ \
6072 int64x1_t __s1 = __p1; \
6078 #define vext_s64(__p0, __p1, __p2) __extension__ ({ \
6080 int64x1_t __s1 = __p1; \
6088 #define vext_s16(__p0, __p1, __p2) __extension__ ({ \
6090 int16x4_t __s1 = __p1; \
6096 #define vext_s16(__p0, __p1, __p2) __extension__ ({ \
6098 int16x4_t __s1 = __p1; \
6344 #define vget_lane_p8(__p0, __p1) __extension__ ({ \
6347 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6351 #define vget_lane_p8(__p0, __p1) __extension__ ({ \
6355 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6358 #define __noswap_vget_lane_p8(__p0, __p1) __extension__ ({ \
6361 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6367 #define vget_lane_p16(__p0, __p1) __extension__ ({ \
6370 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6374 #define vget_lane_p16(__p0, __p1) __extension__ ({ \
6378 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6381 #define __noswap_vget_lane_p16(__p0, __p1) __extension__ ({ \
6384 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6390 #define vgetq_lane_p8(__p0, __p1) __extension__ ({ \
6393 __ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6397 #define vgetq_lane_p8(__p0, __p1) __extension__ ({ \
6401 __ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__rev0, __p1); \
6404 #define __noswap_vgetq_lane_p8(__p0, __p1) __extension__ ({ \
6407 __ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6413 #define vgetq_lane_p16(__p0, __p1) __extension__ ({ \
6416 __ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6420 #define vgetq_lane_p16(__p0, __p1) __extension__ ({ \
6424 __ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \
6427 #define __noswap_vgetq_lane_p16(__p0, __p1) __extension__ ({ \
6430 __ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6436 #define vgetq_lane_u8(__p0, __p1) __extension__ ({ \
6439 __ret = (uint8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6443 #define vgetq_lane_u8(__p0, __p1) __extension__ ({ \
6447 __ret = (uint8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__rev0, __p1); \
6450 #define __noswap_vgetq_lane_u8(__p0, __p1) __extension__ ({ \
6453 __ret = (uint8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6459 #define vgetq_lane_u32(__p0, __p1) __extension__ ({ \
6462 __ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \
6466 #define vgetq_lane_u32(__p0, __p1) __extension__ ({ \
6470 __ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__rev0, __p1); \
6473 #define __noswap_vgetq_lane_u32(__p0, __p1) __extension__ ({ \
6476 __ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \
6482 #define vgetq_lane_u64(__p0, __p1) __extension__ ({ \
6485 __ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
6489 #define vgetq_lane_u64(__p0, __p1) __extension__ ({ \
6493 __ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \
6496 #define __noswap_vgetq_lane_u64(__p0, __p1) __extension__ ({ \
6499 __ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
6505 #define vgetq_lane_u16(__p0, __p1) __extension__ ({ \
6508 __ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6512 #define vgetq_lane_u16(__p0, __p1) __extension__ ({ \
6516 __ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \
6519 #define __noswap_vgetq_lane_u16(__p0, __p1) __extension__ ({ \
6522 __ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6528 #define vgetq_lane_s8(__p0, __p1) __extension__ ({ \
6531 __ret = (int8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6535 #define vgetq_lane_s8(__p0, __p1) __extension__ ({ \
6539 __ret = (int8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__rev0, __p1); \
6542 #define __noswap_vgetq_lane_s8(__p0, __p1) __extension__ ({ \
6545 __ret = (int8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \
6551 #define vgetq_lane_f32(__p0, __p1) __extension__ ({ \
6554 __ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__s0, __p1); \
6558 #define vgetq_lane_f32(__p0, __p1) __extension__ ({ \
6562 __ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__rev0, __p1); \
6565 #define __noswap_vgetq_lane_f32(__p0, __p1) __extension__ ({ \
6568 __ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__s0, __p1); \
6574 #define vgetq_lane_s32(__p0, __p1) __extension__ ({ \
6577 __ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \
6581 #define vgetq_lane_s32(__p0, __p1) __extension__ ({ \
6585 __ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__rev0, __p1); \
6588 #define __noswap_vgetq_lane_s32(__p0, __p1) __extension__ ({ \
6591 __ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \
6597 #define vgetq_lane_s64(__p0, __p1) __extension__ ({ \
6600 __ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
6604 #define vgetq_lane_s64(__p0, __p1) __extension__ ({ \
6608 __ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \
6611 #define __noswap_vgetq_lane_s64(__p0, __p1) __extension__ ({ \
6614 __ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
6620 #define vgetq_lane_s16(__p0, __p1) __extension__ ({ \
6623 __ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6627 #define vgetq_lane_s16(__p0, __p1) __extension__ ({ \
6631 __ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \
6634 #define __noswap_vgetq_lane_s16(__p0, __p1) __extension__ ({ \
6637 __ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \
6643 #define vget_lane_u8(__p0, __p1) __extension__ ({ \
6646 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6650 #define vget_lane_u8(__p0, __p1) __extension__ ({ \
6654 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6657 #define __noswap_vget_lane_u8(__p0, __p1) __extension__ ({ \
6660 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6666 #define vget_lane_u32(__p0, __p1) __extension__ ({ \
6669 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6673 #define vget_lane_u32(__p0, __p1) __extension__ ({ \
6677 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \
6680 #define __noswap_vget_lane_u32(__p0, __p1) __extension__ ({ \
6683 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6689 #define vget_lane_u64(__p0, __p1) __extension__ ({ \
6692 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6696 #define vget_lane_u64(__p0, __p1) __extension__ ({ \
6699 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6702 #define __noswap_vget_lane_u64(__p0, __p1) __extension__ ({ \
6705 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6711 #define vget_lane_u16(__p0, __p1) __extension__ ({ \
6714 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6718 #define vget_lane_u16(__p0, __p1) __extension__ ({ \
6722 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6725 #define __noswap_vget_lane_u16(__p0, __p1) __extension__ ({ \
6728 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6734 #define vget_lane_s8(__p0, __p1) __extension__ ({ \
6737 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6741 #define vget_lane_s8(__p0, __p1) __extension__ ({ \
6745 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6748 #define __noswap_vget_lane_s8(__p0, __p1) __extension__ ({ \
6751 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6757 #define vget_lane_f32(__p0, __p1) __extension__ ({ \
6760 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \
6764 #define vget_lane_f32(__p0, __p1) __extension__ ({ \
6768 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__rev0, __p1); \
6771 #define __noswap_vget_lane_f32(__p0, __p1) __extension__ ({ \
6774 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \
6780 #define vget_lane_s32(__p0, __p1) __extension__ ({ \
6783 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6787 #define vget_lane_s32(__p0, __p1) __extension__ ({ \
6791 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \
6794 #define __noswap_vget_lane_s32(__p0, __p1) __extension__ ({ \
6797 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6803 #define vget_lane_s64(__p0, __p1) __extension__ ({ \
6806 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6810 #define vget_lane_s64(__p0, __p1) __extension__ ({ \
6813 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6816 #define __noswap_vget_lane_s64(__p0, __p1) __extension__ ({ \
6819 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6825 #define vget_lane_s16(__p0, __p1) __extension__ ({ \
6828 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6832 #define vget_lane_s16(__p0, __p1) __extension__ ({ \
6836 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6839 #define __noswap_vget_lane_s16(__p0, __p1) __extension__ ({ \
6842 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
7038 __ai uint8x16_t vhaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
7040 __ret = (uint8x16_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
7044 __ai uint8x16_t vhaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
7046 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
7055 __ai uint32x4_t vhaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
7057 __ret = (uint32x4_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
7061 __ai uint32x4_t vhaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
7063 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7072 __ai uint16x8_t vhaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
7074 __ret = (uint16x8_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
7078 __ai uint16x8_t vhaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
7080 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7089 __ai int8x16_t vhaddq_s8(int8x16_t __p0, int8x16_t __p1) {
7091 __ret = (int8x16_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
7095 __ai int8x16_t vhaddq_s8(int8x16_t __p0, int8x16_t __p1) {
7097 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
7106 __ai int32x4_t vhaddq_s32(int32x4_t __p0, int32x4_t __p1) {
7108 __ret = (int32x4_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
7112 __ai int32x4_t vhaddq_s32(int32x4_t __p0, int32x4_t __p1) {
7114 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7123 __ai int16x8_t vhaddq_s16(int16x8_t __p0, int16x8_t __p1) {
7125 __ret = (int16x8_t) __builtin_neon_vhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
7129 __ai int16x8_t vhaddq_s16(int16x8_t __p0, int16x8_t __p1) {
7131 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7140 __ai uint8x8_t vhadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
7142 __ret = (uint8x8_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
7146 __ai uint8x8_t vhadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
7148 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7157 __ai uint32x2_t vhadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
7159 __ret = (uint32x2_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
7163 __ai uint32x2_t vhadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
7165 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
7174 __ai uint16x4_t vhadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
7176 __ret = (uint16x4_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
7180 __ai uint16x4_t vhadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
7182 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7191 __ai int8x8_t vhadd_s8(int8x8_t __p0, int8x8_t __p1) {
7193 __ret = (int8x8_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
7197 __ai int8x8_t vhadd_s8(int8x8_t __p0, int8x8_t __p1) {
7199 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7208 __ai int32x2_t vhadd_s32(int32x2_t __p0, int32x2_t __p1) {
7210 __ret = (int32x2_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
7214 __ai int32x2_t vhadd_s32(int32x2_t __p0, int32x2_t __p1) {
7216 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
7225 __ai int16x4_t vhadd_s16(int16x4_t __p0, int16x4_t __p1) {
7227 __ret = (int16x4_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
7231 __ai int16x4_t vhadd_s16(int16x4_t __p0, int16x4_t __p1) {
7233 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7242 __ai uint8x16_t vhsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
7244 __ret = (uint8x16_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
7248 __ai uint8x16_t vhsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
7250 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
7259 __ai uint32x4_t vhsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
7261 __ret = (uint32x4_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
7265 __ai uint32x4_t vhsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
7267 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7276 __ai uint16x8_t vhsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
7278 __ret = (uint16x8_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
7282 __ai uint16x8_t vhsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
7284 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7293 __ai int8x16_t vhsubq_s8(int8x16_t __p0, int8x16_t __p1) {
7295 __ret = (int8x16_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
7299 __ai int8x16_t vhsubq_s8(int8x16_t __p0, int8x16_t __p1) {
7301 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
7310 __ai int32x4_t vhsubq_s32(int32x4_t __p0, int32x4_t __p1) {
7312 __ret = (int32x4_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
7316 __ai int32x4_t vhsubq_s32(int32x4_t __p0, int32x4_t __p1) {
7318 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7327 __ai int16x8_t vhsubq_s16(int16x8_t __p0, int16x8_t __p1) {
7329 __ret = (int16x8_t) __builtin_neon_vhsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
7333 __ai int16x8_t vhsubq_s16(int16x8_t __p0, int16x8_t __p1) {
7335 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7344 __ai uint8x8_t vhsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
7346 __ret = (uint8x8_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
7350 __ai uint8x8_t vhsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
7352 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7361 __ai uint32x2_t vhsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
7363 __ret = (uint32x2_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
7367 __ai uint32x2_t vhsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
7369 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
7378 __ai uint16x4_t vhsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
7380 __ret = (uint16x4_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
7384 __ai uint16x4_t vhsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
7386 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
7395 __ai int8x8_t vhsub_s8(int8x8_t __p0, int8x8_t __p1) {
7397 __ret = (int8x8_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
7401 __ai int8x8_t vhsub_s8(int8x8_t __p0, int8x8_t __p1) {
7403 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7412 __ai int32x2_t vhsub_s32(int32x2_t __p0, int32x2_t __p1) {
7414 __ret = (int32x2_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
7418 __ai int32x2_t vhsub_s32(int32x2_t __p0, int32x2_t __p1) {
7420 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
7429 __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
7431 __ret = (int16x4_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
7435 __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
7437 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
8162 #define vld1_lane_p8(__p0, __p1, __p2) __extension__ ({ \
8163 poly8x8_t __s1 = __p1; \
8169 #define vld1_lane_p8(__p0, __p1, __p2) __extension__ ({ \
8170 poly8x8_t __s1 = __p1; \
8180 #define vld1_lane_p16(__p0, __p1, __p2) __extension__ ({ \
8181 poly16x4_t __s1 = __p1; \
8187 #define vld1_lane_p16(__p0, __p1, __p2) __extension__ ({ \
8188 poly16x4_t __s1 = __p1; \
8198 #define vld1q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
8199 poly8x16_t __s1 = __p1; \
8205 #define vld1q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
8206 poly8x16_t __s1 = __p1; \
8216 #define vld1q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
8217 poly16x8_t __s1 = __p1; \
8223 #define vld1q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
8224 poly16x8_t __s1 = __p1; \
8234 #define vld1q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
8235 uint8x16_t __s1 = __p1; \
8241 #define vld1q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
8242 uint8x16_t __s1 = __p1; \
8252 #define vld1q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
8253 uint32x4_t __s1 = __p1; \
8259 #define vld1q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
8260 uint32x4_t __s1 = __p1; \
8270 #define vld1q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8271 uint64x2_t __s1 = __p1; \
8277 #define vld1q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8278 uint64x2_t __s1 = __p1; \
8288 #define vld1q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
8289 uint16x8_t __s1 = __p1; \
8295 #define vld1q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
8296 uint16x8_t __s1 = __p1; \
8306 #define vld1q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
8307 int8x16_t __s1 = __p1; \
8313 #define vld1q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
8314 int8x16_t __s1 = __p1; \
8324 #define vld1q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
8325 float32x4_t __s1 = __p1; \
8331 #define vld1q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
8332 float32x4_t __s1 = __p1; \
8342 #define vld1q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
8343 float16x8_t __s1 = __p1; \
8349 #define vld1q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
8350 float16x8_t __s1 = __p1; \
8360 #define vld1q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
8361 int32x4_t __s1 = __p1; \
8367 #define vld1q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
8368 int32x4_t __s1 = __p1; \
8378 #define vld1q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8379 int64x2_t __s1 = __p1; \
8385 #define vld1q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8386 int64x2_t __s1 = __p1; \
8396 #define vld1q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
8397 int16x8_t __s1 = __p1; \
8403 #define vld1q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
8404 int16x8_t __s1 = __p1; \
8414 #define vld1_lane_u8(__p0, __p1, __p2) __extension__ ({ \
8415 uint8x8_t __s1 = __p1; \
8421 #define vld1_lane_u8(__p0, __p1, __p2) __extension__ ({ \
8422 uint8x8_t __s1 = __p1; \
8432 #define vld1_lane_u32(__p0, __p1, __p2) __extension__ ({ \
8433 uint32x2_t __s1 = __p1; \
8439 #define vld1_lane_u32(__p0, __p1, __p2) __extension__ ({ \
8440 uint32x2_t __s1 = __p1; \
8450 #define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8451 uint64x1_t __s1 = __p1; \
8457 #define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8458 uint64x1_t __s1 = __p1; \
8466 #define vld1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
8467 uint16x4_t __s1 = __p1; \
8473 #define vld1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
8474 uint16x4_t __s1 = __p1; \
8484 #define vld1_lane_s8(__p0, __p1, __p2) __extension__ ({ \
8485 int8x8_t __s1 = __p1; \
8491 #define vld1_lane_s8(__p0, __p1, __p2) __extension__ ({ \
8492 int8x8_t __s1 = __p1; \
8502 #define vld1_lane_f32(__p0, __p1, __p2) __extension__ ({ \
8503 float32x2_t __s1 = __p1; \
8509 #define vld1_lane_f32(__p0, __p1, __p2) __extension__ ({ \
8510 float32x2_t __s1 = __p1; \
8520 #define vld1_lane_f16(__p0, __p1, __p2) __extension__ ({ \
8521 float16x4_t __s1 = __p1; \
8527 #define vld1_lane_f16(__p0, __p1, __p2) __extension__ ({ \
8528 float16x4_t __s1 = __p1; \
8538 #define vld1_lane_s32(__p0, __p1, __p2) __extension__ ({ \
8539 int32x2_t __s1 = __p1; \
8545 #define vld1_lane_s32(__p0, __p1, __p2) __extension__ ({ \
8546 int32x2_t __s1 = __p1; \
8556 #define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8557 int64x1_t __s1 = __p1; \
8563 #define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8564 int64x1_t __s1 = __p1; \
8572 #define vld1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
8573 int16x4_t __s1 = __p1; \
8579 #define vld1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
8580 int16x4_t __s1 = __p1; \
9156 #define vld2_lane_p8(__p0, __p1, __p2) __extension__ ({ \
9157 poly8x8x2_t __s1 = __p1; \
9163 #define vld2_lane_p8(__p0, __p1, __p2) __extension__ ({ \
9164 poly8x8x2_t __s1 = __p1; \
9178 #define vld2_lane_p16(__p0, __p1, __p2) __extension__ ({ \
9179 poly16x4x2_t __s1 = __p1; \
9185 #define vld2_lane_p16(__p0, __p1, __p2) __extension__ ({ \
9186 poly16x4x2_t __s1 = __p1; \
9200 #define vld2q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
9201 poly16x8x2_t __s1 = __p1; \
9207 #define vld2q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
9208 poly16x8x2_t __s1 = __p1; \
9222 #define vld2q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
9223 uint32x4x2_t __s1 = __p1; \
9229 #define vld2q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
9230 uint32x4x2_t __s1 = __p1; \
9244 #define vld2q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
9245 uint16x8x2_t __s1 = __p1; \
9251 #define vld2q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
9252 uint16x8x2_t __s1 = __p1; \
9266 #define vld2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
9267 float32x4x2_t __s1 = __p1; \
9273 #define vld2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
9274 float32x4x2_t __s1 = __p1; \
9288 #define vld2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
9289 float16x8x2_t __s1 = __p1; \
9295 #define vld2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
9296 float16x8x2_t __s1 = __p1; \
9310 #define vld2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
9311 int32x4x2_t __s1 = __p1; \
9317 #define vld2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
9318 int32x4x2_t __s1 = __p1; \
9332 #define vld2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
9333 int16x8x2_t __s1 = __p1; \
9339 #define vld2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
9340 int16x8x2_t __s1 = __p1; \
9354 #define vld2_lane_u8(__p0, __p1, __p2) __extension__ ({ \
9355 uint8x8x2_t __s1 = __p1; \
9361 #define vld2_lane_u8(__p0, __p1, __p2) __extension__ ({ \
9362 uint8x8x2_t __s1 = __p1; \
9376 #define vld2_lane_u32(__p0, __p1, __p2) __extension__ ({ \
9377 uint32x2x2_t __s1 = __p1; \
9383 #define vld2_lane_u32(__p0, __p1, __p2) __extension__ ({ \
9384 uint32x2x2_t __s1 = __p1; \
9398 #define vld2_lane_u16(__p0, __p1, __p2) __extension__ ({ \
9399 uint16x4x2_t __s1 = __p1; \
9405 #define vld2_lane_u16(__p0, __p1, __p2) __extension__ ({ \
9406 uint16x4x2_t __s1 = __p1; \
9420 #define vld2_lane_s8(__p0, __p1, __p2) __extension__ ({ \
9421 int8x8x2_t __s1 = __p1; \
9427 #define vld2_lane_s8(__p0, __p1, __p2) __extension__ ({ \
9428 int8x8x2_t __s1 = __p1; \
9442 #define vld2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
9443 float32x2x2_t __s1 = __p1; \
9449 #define vld2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
9450 float32x2x2_t __s1 = __p1; \
9464 #define vld2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
9465 float16x4x2_t __s1 = __p1; \
9471 #define vld2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
9472 float16x4x2_t __s1 = __p1; \
9486 #define vld2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
9487 int32x2x2_t __s1 = __p1; \
9493 #define vld2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
9494 int32x2x2_t __s1 = __p1; \
9508 #define vld2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
9509 int16x4x2_t __s1 = __p1; \
9515 #define vld2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
9516 int16x4x2_t __s1 = __p1; \
10126 #define vld3_lane_p8(__p0, __p1, __p2) __extension__ ({ \
10127 poly8x8x3_t __s1 = __p1; \
10133 #define vld3_lane_p8(__p0, __p1, __p2) __extension__ ({ \
10134 poly8x8x3_t __s1 = __p1; \
10150 #define vld3_lane_p16(__p0, __p1, __p2) __extension__ ({ \
10151 poly16x4x3_t __s1 = __p1; \
10157 #define vld3_lane_p16(__p0, __p1, __p2) __extension__ ({ \
10158 poly16x4x3_t __s1 = __p1; \
10174 #define vld3q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
10175 poly16x8x3_t __s1 = __p1; \
10181 #define vld3q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
10182 poly16x8x3_t __s1 = __p1; \
10198 #define vld3q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
10199 uint32x4x3_t __s1 = __p1; \
10205 #define vld3q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
10206 uint32x4x3_t __s1 = __p1; \
10222 #define vld3q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
10223 uint16x8x3_t __s1 = __p1; \
10229 #define vld3q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
10230 uint16x8x3_t __s1 = __p1; \
10246 #define vld3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10247 float32x4x3_t __s1 = __p1; \
10253 #define vld3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10254 float32x4x3_t __s1 = __p1; \
10270 #define vld3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
10271 float16x8x3_t __s1 = __p1; \
10277 #define vld3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
10278 float16x8x3_t __s1 = __p1; \
10294 #define vld3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10295 int32x4x3_t __s1 = __p1; \
10301 #define vld3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10302 int32x4x3_t __s1 = __p1; \
10318 #define vld3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10319 int16x8x3_t __s1 = __p1; \
10325 #define vld3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10326 int16x8x3_t __s1 = __p1; \
10342 #define vld3_lane_u8(__p0, __p1, __p2) __extension__ ({ \
10343 uint8x8x3_t __s1 = __p1; \
10349 #define vld3_lane_u8(__p0, __p1, __p2) __extension__ ({ \
10350 uint8x8x3_t __s1 = __p1; \
10366 #define vld3_lane_u32(__p0, __p1, __p2) __extension__ ({ \
10367 uint32x2x3_t __s1 = __p1; \
10373 #define vld3_lane_u32(__p0, __p1, __p2) __extension__ ({ \
10374 uint32x2x3_t __s1 = __p1; \
10390 #define vld3_lane_u16(__p0, __p1, __p2) __extension__ ({ \
10391 uint16x4x3_t __s1 = __p1; \
10397 #define vld3_lane_u16(__p0, __p1, __p2) __extension__ ({ \
10398 uint16x4x3_t __s1 = __p1; \
10414 #define vld3_lane_s8(__p0, __p1, __p2) __extension__ ({ \
10415 int8x8x3_t __s1 = __p1; \
10421 #define vld3_lane_s8(__p0, __p1, __p2) __extension__ ({ \
10422 int8x8x3_t __s1 = __p1; \
10438 #define vld3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10439 float32x2x3_t __s1 = __p1; \
10445 #define vld3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10446 float32x2x3_t __s1 = __p1; \
10462 #define vld3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
10463 float16x4x3_t __s1 = __p1; \
10469 #define vld3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
10470 float16x4x3_t __s1 = __p1; \
10486 #define vld3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10487 int32x2x3_t __s1 = __p1; \
10493 #define vld3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10494 int32x2x3_t __s1 = __p1; \
10510 #define vld3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10511 int16x4x3_t __s1 = __p1; \
10517 #define vld3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10518 int16x4x3_t __s1 = __p1; \
11160 #define vld4_lane_p8(__p0, __p1, __p2) __extension__ ({ \
11161 poly8x8x4_t __s1 = __p1; \
11167 #define vld4_lane_p8(__p0, __p1, __p2) __extension__ ({ \
11168 poly8x8x4_t __s1 = __p1; \
11186 #define vld4_lane_p16(__p0, __p1, __p2) __extension__ ({ \
11187 poly16x4x4_t __s1 = __p1; \
11193 #define vld4_lane_p16(__p0, __p1, __p2) __extension__ ({ \
11194 poly16x4x4_t __s1 = __p1; \
11212 #define vld4q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
11213 poly16x8x4_t __s1 = __p1; \
11219 #define vld4q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
11220 poly16x8x4_t __s1 = __p1; \
11238 #define vld4q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
11239 uint32x4x4_t __s1 = __p1; \
11245 #define vld4q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
11246 uint32x4x4_t __s1 = __p1; \
11264 #define vld4q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
11265 uint16x8x4_t __s1 = __p1; \
11271 #define vld4q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
11272 uint16x8x4_t __s1 = __p1; \
11290 #define vld4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11291 float32x4x4_t __s1 = __p1; \
11297 #define vld4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11298 float32x4x4_t __s1 = __p1; \
11316 #define vld4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
11317 float16x8x4_t __s1 = __p1; \
11323 #define vld4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
11324 float16x8x4_t __s1 = __p1; \
11342 #define vld4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11343 int32x4x4_t __s1 = __p1; \
11349 #define vld4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11350 int32x4x4_t __s1 = __p1; \
11368 #define vld4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11369 int16x8x4_t __s1 = __p1; \
11375 #define vld4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11376 int16x8x4_t __s1 = __p1; \
11394 #define vld4_lane_u8(__p0, __p1, __p2) __extension__ ({ \
11395 uint8x8x4_t __s1 = __p1; \
11401 #define vld4_lane_u8(__p0, __p1, __p2) __extension__ ({ \
11402 uint8x8x4_t __s1 = __p1; \
11420 #define vld4_lane_u32(__p0, __p1, __p2) __extension__ ({ \
11421 uint32x2x4_t __s1 = __p1; \
11427 #define vld4_lane_u32(__p0, __p1, __p2) __extension__ ({ \
11428 uint32x2x4_t __s1 = __p1; \
11446 #define vld4_lane_u16(__p0, __p1, __p2) __extension__ ({ \
11447 uint16x4x4_t __s1 = __p1; \
11453 #define vld4_lane_u16(__p0, __p1, __p2) __extension__ ({ \
11454 uint16x4x4_t __s1 = __p1; \
11472 #define vld4_lane_s8(__p0, __p1, __p2) __extension__ ({ \
11473 int8x8x4_t __s1 = __p1; \
11479 #define vld4_lane_s8(__p0, __p1, __p2) __extension__ ({ \
11480 int8x8x4_t __s1 = __p1; \
11498 #define vld4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11499 float32x2x4_t __s1 = __p1; \
11505 #define vld4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11506 float32x2x4_t __s1 = __p1; \
11524 #define vld4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
11525 float16x4x4_t __s1 = __p1; \
11531 #define vld4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
11532 float16x4x4_t __s1 = __p1; \
11550 #define vld4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11551 int32x2x4_t __s1 = __p1; \
11557 #define vld4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11558 int32x2x4_t __s1 = __p1; \
11576 #define vld4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11577 int16x4x4_t __s1 = __p1; \
11583 #define vld4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11584 int16x4x4_t __s1 = __p1; \
11602 __ai uint8x16_t vmaxq_u8(uint8x16_t __p0, uint8x16_t __p1) {
11604 __ret = (uint8x16_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
11608 __ai uint8x16_t vmaxq_u8(uint8x16_t __p0, uint8x16_t __p1) {
11610 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
11619 __ai uint32x4_t vmaxq_u32(uint32x4_t __p0, uint32x4_t __p1) {
11621 __ret = (uint32x4_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
11625 __ai uint32x4_t vmaxq_u32(uint32x4_t __p0, uint32x4_t __p1) {
11627 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11636 __ai uint16x8_t vmaxq_u16(uint16x8_t __p0, uint16x8_t __p1) {
11638 __ret = (uint16x8_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
11642 __ai uint16x8_t vmaxq_u16(uint16x8_t __p0, uint16x8_t __p1) {
11644 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11653 __ai int8x16_t vmaxq_s8(int8x16_t __p0, int8x16_t __p1) {
11655 __ret = (int8x16_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
11659 __ai int8x16_t vmaxq_s8(int8x16_t __p0, int8x16_t __p1) {
11661 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
11670 __ai float32x4_t vmaxq_f32(float32x4_t __p0, float32x4_t __p1) {
11672 __ret = (float32x4_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
11676 __ai float32x4_t vmaxq_f32(float32x4_t __p0, float32x4_t __p1) {
11678 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11687 __ai int32x4_t vmaxq_s32(int32x4_t __p0, int32x4_t __p1) {
11689 __ret = (int32x4_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
11693 __ai int32x4_t vmaxq_s32(int32x4_t __p0, int32x4_t __p1) {
11695 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11704 __ai int16x8_t vmaxq_s16(int16x8_t __p0, int16x8_t __p1) {
11706 __ret = (int16x8_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
11710 __ai int16x8_t vmaxq_s16(int16x8_t __p0, int16x8_t __p1) {
11712 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11721 __ai uint8x8_t vmax_u8(uint8x8_t __p0, uint8x8_t __p1) {
11723 __ret = (uint8x8_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
11727 __ai uint8x8_t vmax_u8(uint8x8_t __p0, uint8x8_t __p1) {
11729 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11738 __ai uint32x2_t vmax_u32(uint32x2_t __p0, uint32x2_t __p1) {
11740 __ret = (uint32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
11744 __ai uint32x2_t vmax_u32(uint32x2_t __p0, uint32x2_t __p1) {
11746 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
11755 __ai uint16x4_t vmax_u16(uint16x4_t __p0, uint16x4_t __p1) {
11757 __ret = (uint16x4_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
11761 __ai uint16x4_t vmax_u16(uint16x4_t __p0, uint16x4_t __p1) {
11763 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11772 __ai int8x8_t vmax_s8(int8x8_t __p0, int8x8_t __p1) {
11774 __ret = (int8x8_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
11778 __ai int8x8_t vmax_s8(int8x8_t __p0, int8x8_t __p1) {
11780 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11789 __ai float32x2_t vmax_f32(float32x2_t __p0, float32x2_t __p1) {
11791 __ret = (float32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
11795 __ai float32x2_t vmax_f32(float32x2_t __p0, float32x2_t __p1) {
11797 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
11806 __ai int32x2_t vmax_s32(int32x2_t __p0, int32x2_t __p1) {
11808 __ret = (int32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
11812 __ai int32x2_t vmax_s32(int32x2_t __p0, int32x2_t __p1) {
11814 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
11823 __ai int16x4_t vmax_s16(int16x4_t __p0, int16x4_t __p1) {
11825 __ret = (int16x4_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
11829 __ai int16x4_t vmax_s16(int16x4_t __p0, int16x4_t __p1) {
11831 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11840 __ai uint8x16_t vminq_u8(uint8x16_t __p0, uint8x16_t __p1) {
11842 __ret = (uint8x16_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
11846 __ai uint8x16_t vminq_u8(uint8x16_t __p0, uint8x16_t __p1) {
11848 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
11857 __ai uint32x4_t vminq_u32(uint32x4_t __p0, uint32x4_t __p1) {
11859 __ret = (uint32x4_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
11863 __ai uint32x4_t vminq_u32(uint32x4_t __p0, uint32x4_t __p1) {
11865 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11874 __ai uint16x8_t vminq_u16(uint16x8_t __p0, uint16x8_t __p1) {
11876 __ret = (uint16x8_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
11880 __ai uint16x8_t vminq_u16(uint16x8_t __p0, uint16x8_t __p1) {
11882 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11891 __ai int8x16_t vminq_s8(int8x16_t __p0, int8x16_t __p1) {
11893 __ret = (int8x16_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
11897 __ai int8x16_t vminq_s8(int8x16_t __p0, int8x16_t __p1) {
11899 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
11908 __ai float32x4_t vminq_f32(float32x4_t __p0, float32x4_t __p1) {
11910 __ret = (float32x4_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
11914 __ai float32x4_t vminq_f32(float32x4_t __p0, float32x4_t __p1) {
11916 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11925 __ai int32x4_t vminq_s32(int32x4_t __p0, int32x4_t __p1) {
11927 __ret = (int32x4_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
11931 __ai int32x4_t vminq_s32(int32x4_t __p0, int32x4_t __p1) {
11933 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
11942 __ai int16x8_t vminq_s16(int16x8_t __p0, int16x8_t __p1) {
11944 __ret = (int16x8_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
11948 __ai int16x8_t vminq_s16(int16x8_t __p0, int16x8_t __p1) {
11950 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11959 __ai uint8x8_t vmin_u8(uint8x8_t __p0, uint8x8_t __p1) {
11961 __ret = (uint8x8_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
11965 __ai uint8x8_t vmin_u8(uint8x8_t __p0, uint8x8_t __p1) {
11967 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11976 __ai uint32x2_t vmin_u32(uint32x2_t __p0, uint32x2_t __p1) {
11978 __ret = (uint32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
11982 __ai uint32x2_t vmin_u32(uint32x2_t __p0, uint32x2_t __p1) {
11984 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
11993 __ai uint16x4_t vmin_u16(uint16x4_t __p0, uint16x4_t __p1) {
11995 __ret = (uint16x4_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
11999 __ai uint16x4_t vmin_u16(uint16x4_t __p0, uint16x4_t __p1) {
12001 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12010 __ai int8x8_t vmin_s8(int8x8_t __p0, int8x8_t __p1) {
12012 __ret = (int8x8_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
12016 __ai int8x8_t vmin_s8(int8x8_t __p0, int8x8_t __p1) {
12018 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12027 __ai float32x2_t vmin_f32(float32x2_t __p0, float32x2_t __p1) {
12029 __ret = (float32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
12033 __ai float32x2_t vmin_f32(float32x2_t __p0, float32x2_t __p1) {
12035 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12044 __ai int32x2_t vmin_s32(int32x2_t __p0, int32x2_t __p1) {
12046 __ret = (int32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
12050 __ai int32x2_t vmin_s32(int32x2_t __p0, int32x2_t __p1) {
12052 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12061 __ai int16x4_t vmin_s16(int16x4_t __p0, int16x4_t __p1) {
12063 __ret = (int16x4_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
12067 __ai int16x4_t vmin_s16(int16x4_t __p0, int16x4_t __p1) {
12069 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12078 __ai uint8x16_t vmlaq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
12080 __ret = __p0 + __p1 * __p2;
12084 __ai uint8x16_t vmlaq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
12086 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
12096 __ai uint32x4_t vmlaq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
12098 __ret = __p0 + __p1 * __p2;
12102 __ai uint32x4_t vmlaq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
12104 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12114 __ai uint16x8_t vmlaq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
12116 __ret = __p0 + __p1 * __p2;
12120 __ai uint16x8_t vmlaq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
12122 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12132 __ai int8x16_t vmlaq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
12134 __ret = __p0 + __p1 * __p2;
12138 __ai int8x16_t vmlaq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
12140 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
12150 __ai float32x4_t vmlaq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
12152 __ret = __p0 + __p1 * __p2;
12156 __ai float32x4_t vmlaq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
12158 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12168 __ai int32x4_t vmlaq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
12170 __ret = __p0 + __p1 * __p2;
12174 __ai int32x4_t vmlaq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
12176 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12186 __ai int16x8_t vmlaq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
12188 __ret = __p0 + __p1 * __p2;
12192 __ai int16x8_t vmlaq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
12194 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12204 __ai uint8x8_t vmla_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
12206 __ret = __p0 + __p1 * __p2;
12210 __ai uint8x8_t vmla_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
12212 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12222 __ai uint32x2_t vmla_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
12224 __ret = __p0 + __p1 * __p2;
12228 __ai uint32x2_t vmla_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
12230 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12240 __ai uint16x4_t vmla_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
12242 __ret = __p0 + __p1 * __p2;
12246 __ai uint16x4_t vmla_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
12248 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12258 __ai int8x8_t vmla_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12260 __ret = __p0 + __p1 * __p2;
12264 __ai int8x8_t vmla_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12266 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12276 __ai float32x2_t vmla_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
12278 __ret = __p0 + __p1 * __p2;
12282 __ai float32x2_t vmla_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
12284 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12294 __ai int32x2_t vmla_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
12296 __ret = __p0 + __p1 * __p2;
12300 __ai int32x2_t vmla_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
12302 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12312 __ai int16x4_t vmla_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
12314 __ret = __p0 + __p1 * __p2;
12318 __ai int16x4_t vmla_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
12320 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12330 #define vmlaq_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
12332 uint32x4_t __s1 = __p1; \
12339 #define vmlaq_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
12341 uint32x4_t __s1 = __p1; \
12354 #define vmlaq_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
12356 uint16x8_t __s1 = __p1; \
12363 #define vmlaq_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
12365 uint16x8_t __s1 = __p1; \
12378 #define vmlaq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
12380 float32x4_t __s1 = __p1; \
12387 #define vmlaq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
12389 float32x4_t __s1 = __p1; \
12402 #define vmlaq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
12404 int32x4_t __s1 = __p1; \
12411 #define vmlaq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
12413 int32x4_t __s1 = __p1; \
12426 #define vmlaq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
12428 int16x8_t __s1 = __p1; \
12435 #define vmlaq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
12437 int16x8_t __s1 = __p1; \
12450 #define vmla_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
12452 uint32x2_t __s1 = __p1; \
12459 #define vmla_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
12461 uint32x2_t __s1 = __p1; \
12474 #define vmla_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
12476 uint16x4_t __s1 = __p1; \
12483 #define vmla_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
12485 uint16x4_t __s1 = __p1; \
12498 #define vmla_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
12500 float32x2_t __s1 = __p1; \
12507 #define vmla_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
12509 float32x2_t __s1 = __p1; \
12522 #define vmla_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
12524 int32x2_t __s1 = __p1; \
12531 #define vmla_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
12533 int32x2_t __s1 = __p1; \
12546 #define vmla_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
12548 int16x4_t __s1 = __p1; \
12555 #define vmla_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
12557 int16x4_t __s1 = __p1; \
12570 __ai uint32x4_t vmlaq_n_u32(uint32x4_t __p0, uint32x4_t __p1, uint32_t __p2) {
12572 __ret = __p0 + __p1 * (uint32x4_t) {__p2, __p2, __p2, __p2};
12576 __ai uint32x4_t vmlaq_n_u32(uint32x4_t __p0, uint32x4_t __p1, uint32_t __p2) {
12578 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12587 __ai uint16x8_t vmlaq_n_u16(uint16x8_t __p0, uint16x8_t __p1, uint16_t __p2) {
12589 __ret = __p0 + __p1 * (uint16x8_t) {__p2, __p2, __p2, __p2, __p2, __p2, __p2, __p2};
12593 __ai uint16x8_t vmlaq_n_u16(uint16x8_t __p0, uint16x8_t __p1, uint16_t __p2) {
12595 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12604 __ai float32x4_t vmlaq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
12606 __ret = __p0 + __p1 * (float32x4_t) {__p2, __p2, __p2, __p2};
12610 __ai float32x4_t vmlaq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
12612 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12621 __ai int32x4_t vmlaq_n_s32(int32x4_t __p0, int32x4_t __p1, int32_t __p2) {
12623 __ret = __p0 + __p1 * (int32x4_t) {__p2, __p2, __p2, __p2};
12627 __ai int32x4_t vmlaq_n_s32(int32x4_t __p0, int32x4_t __p1, int32_t __p2) {
12629 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12638 __ai int16x8_t vmlaq_n_s16(int16x8_t __p0, int16x8_t __p1, int16_t __p2) {
12640 __ret = __p0 + __p1 * (int16x8_t) {__p2, __p2, __p2, __p2, __p2, __p2, __p2, __p2};
12644 __ai int16x8_t vmlaq_n_s16(int16x8_t __p0, int16x8_t __p1, int16_t __p2) {
12646 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12655 __ai uint32x2_t vmla_n_u32(uint32x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
12657 __ret = __p0 + __p1 * (uint32x2_t) {__p2, __p2};
12661 __ai uint32x2_t vmla_n_u32(uint32x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
12663 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12672 __ai uint16x4_t vmla_n_u16(uint16x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
12674 __ret = __p0 + __p1 * (uint16x4_t) {__p2, __p2, __p2, __p2};
12678 __ai uint16x4_t vmla_n_u16(uint16x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
12680 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12689 __ai float32x2_t vmla_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
12691 __ret = __p0 + __p1 * (float32x2_t) {__p2, __p2};
12695 __ai float32x2_t vmla_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
12697 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12706 __ai int32x2_t vmla_n_s32(int32x2_t __p0, int32x2_t __p1, int32_t __p2) {
12708 __ret = __p0 + __p1 * (int32x2_t) {__p2, __p2};
12712 __ai int32x2_t vmla_n_s32(int32x2_t __p0, int32x2_t __p1, int32_t __p2) {
12714 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12723 __ai int16x4_t vmla_n_s16(int16x4_t __p0, int16x4_t __p1, int16_t __p2) {
12725 __ret = __p0 + __p1 * (int16x4_t) {__p2, __p2, __p2, __p2};
12729 __ai int16x4_t vmla_n_s16(int16x4_t __p0, int16x4_t __p1, int16_t __p2) {
12731 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12740 __ai uint8x16_t vmlsq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
12742 __ret = __p0 - __p1 * __p2;
12746 __ai uint8x16_t vmlsq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
12748 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
12758 __ai uint32x4_t vmlsq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
12760 __ret = __p0 - __p1 * __p2;
12764 __ai uint32x4_t vmlsq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
12766 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12776 __ai uint16x8_t vmlsq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
12778 __ret = __p0 - __p1 * __p2;
12782 __ai uint16x8_t vmlsq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
12784 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12794 __ai int8x16_t vmlsq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
12796 __ret = __p0 - __p1 * __p2;
12800 __ai int8x16_t vmlsq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
12802 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
12812 __ai float32x4_t vmlsq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
12814 __ret = __p0 - __p1 * __p2;
12818 __ai float32x4_t vmlsq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
12820 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12830 __ai int32x4_t vmlsq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
12832 __ret = __p0 - __p1 * __p2;
12836 __ai int32x4_t vmlsq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
12838 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12848 __ai int16x8_t vmlsq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
12850 __ret = __p0 - __p1 * __p2;
12854 __ai int16x8_t vmlsq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
12856 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12866 __ai uint8x8_t vmls_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
12868 __ret = __p0 - __p1 * __p2;
12872 __ai uint8x8_t vmls_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
12874 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12884 __ai uint32x2_t vmls_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
12886 __ret = __p0 - __p1 * __p2;
12890 __ai uint32x2_t vmls_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
12892 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12902 __ai uint16x4_t vmls_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
12904 __ret = __p0 - __p1 * __p2;
12908 __ai uint16x4_t vmls_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
12910 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12920 __ai int8x8_t vmls_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12922 __ret = __p0 - __p1 * __p2;
12926 __ai int8x8_t vmls_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12928 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12938 __ai float32x2_t vmls_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
12940 __ret = __p0 - __p1 * __p2;
12944 __ai float32x2_t vmls_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
12946 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12956 __ai int32x2_t vmls_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
12958 __ret = __p0 - __p1 * __p2;
12962 __ai int32x2_t vmls_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
12964 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
12974 __ai int16x4_t vmls_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
12976 __ret = __p0 - __p1 * __p2;
12980 __ai int16x4_t vmls_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
12982 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
12992 #define vmlsq_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
12994 uint32x4_t __s1 = __p1; \
13001 #define vmlsq_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
13003 uint32x4_t __s1 = __p1; \
13016 #define vmlsq_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
13018 uint16x8_t __s1 = __p1; \
13025 #define vmlsq_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
13027 uint16x8_t __s1 = __p1; \
13040 #define vmlsq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
13042 float32x4_t __s1 = __p1; \
13049 #define vmlsq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
13051 float32x4_t __s1 = __p1; \
13064 #define vmlsq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
13066 int32x4_t __s1 = __p1; \
13073 #define vmlsq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
13075 int32x4_t __s1 = __p1; \
13088 #define vmlsq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
13090 int16x8_t __s1 = __p1; \
13097 #define vmlsq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
13099 int16x8_t __s1 = __p1; \
13112 #define vmls_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
13114 uint32x2_t __s1 = __p1; \
13121 #define vmls_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
13123 uint32x2_t __s1 = __p1; \
13136 #define vmls_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
13138 uint16x4_t __s1 = __p1; \
13145 #define vmls_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
13147 uint16x4_t __s1 = __p1; \
13160 #define vmls_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
13162 float32x2_t __s1 = __p1; \
13169 #define vmls_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
13171 float32x2_t __s1 = __p1; \
13184 #define vmls_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
13186 int32x2_t __s1 = __p1; \
13193 #define vmls_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
13195 int32x2_t __s1 = __p1; \
13208 #define vmls_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
13210 int16x4_t __s1 = __p1; \
13217 #define vmls_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
13219 int16x4_t __s1 = __p1; \
13232 __ai uint32x4_t vmlsq_n_u32(uint32x4_t __p0, uint32x4_t __p1, uint32_t __p2) {
13234 __ret = __p0 - __p1 * (uint32x4_t) {__p2, __p2, __p2, __p2};
13238 __ai uint32x4_t vmlsq_n_u32(uint32x4_t __p0, uint32x4_t __p1, uint32_t __p2) {
13240 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
13249 __ai uint16x8_t vmlsq_n_u16(uint16x8_t __p0, uint16x8_t __p1, uint16_t __p2) {
13251 __ret = __p0 - __p1 * (uint16x8_t) {__p2, __p2, __p2, __p2, __p2, __p2, __p2, __p2};
13255 __ai uint16x8_t vmlsq_n_u16(uint16x8_t __p0, uint16x8_t __p1, uint16_t __p2) {
13257 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
13266 __ai float32x4_t vmlsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
13268 __ret = __p0 - __p1 * (float32x4_t) {__p2, __p2, __p2, __p2};
13272 __ai float32x4_t vmlsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
13274 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
13283 __ai int32x4_t vmlsq_n_s32(int32x4_t __p0, int32x4_t __p1, int32_t __p2) {
13285 __ret = __p0 - __p1 * (int32x4_t) {__p2, __p2, __p2, __p2};
13289 __ai int32x4_t vmlsq_n_s32(int32x4_t __p0, int32x4_t __p1, int32_t __p2) {
13291 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
13300 __ai int16x8_t vmlsq_n_s16(int16x8_t __p0, int16x8_t __p1, int16_t __p2) {
13302 __ret = __p0 - __p1 * (int16x8_t) {__p2, __p2, __p2, __p2, __p2, __p2, __p2, __p2};
13306 __ai int16x8_t vmlsq_n_s16(int16x8_t __p0, int16x8_t __p1, int16_t __p2) {
13308 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
13317 __ai uint32x2_t vmls_n_u32(uint32x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
13319 __ret = __p0 - __p1 * (uint32x2_t) {__p2, __p2};
13323 __ai uint32x2_t vmls_n_u32(uint32x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
13325 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
13334 __ai uint16x4_t vmls_n_u16(uint16x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
13336 __ret = __p0 - __p1 * (uint16x4_t) {__p2, __p2, __p2, __p2};
13340 __ai uint16x4_t vmls_n_u16(uint16x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
13342 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
13351 __ai float32x2_t vmls_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
13353 __ret = __p0 - __p1 * (float32x2_t) {__p2, __p2};
13357 __ai float32x2_t vmls_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
13359 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
13368 __ai int32x2_t vmls_n_s32(int32x2_t __p0, int32x2_t __p1, int32_t __p2) {
13370 __ret = __p0 - __p1 * (int32x2_t) {__p2, __p2};
13374 __ai int32x2_t vmls_n_s32(int32x2_t __p0, int32x2_t __p1, int32_t __p2) {
13376 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
13385 __ai int16x4_t vmls_n_s16(int16x4_t __p0, int16x4_t __p1, int16_t __p2) {
13387 __ret = __p0 - __p1 * (int16x4_t) {__p2, __p2, __p2, __p2};
13391 __ai int16x4_t vmls_n_s16(int16x4_t __p0, int16x4_t __p1, int16_t __p2) {
13393 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14016 __ai uint8x16_t vmulq_u8(uint8x16_t __p0, uint8x16_t __p1) {
14018 __ret = __p0 * __p1;
14022 __ai uint8x16_t vmulq_u8(uint8x16_t __p0, uint8x16_t __p1) {
14024 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
14033 __ai uint32x4_t vmulq_u32(uint32x4_t __p0, uint32x4_t __p1) {
14035 __ret = __p0 * __p1;
14039 __ai uint32x4_t vmulq_u32(uint32x4_t __p0, uint32x4_t __p1) {
14041 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14050 __ai uint16x8_t vmulq_u16(uint16x8_t __p0, uint16x8_t __p1) {
14052 __ret = __p0 * __p1;
14056 __ai uint16x8_t vmulq_u16(uint16x8_t __p0, uint16x8_t __p1) {
14058 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14067 __ai int8x16_t vmulq_s8(int8x16_t __p0, int8x16_t __p1) {
14069 __ret = __p0 * __p1;
14073 __ai int8x16_t vmulq_s8(int8x16_t __p0, int8x16_t __p1) {
14075 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
14084 __ai float32x4_t vmulq_f32(float32x4_t __p0, float32x4_t __p1) {
14086 __ret = __p0 * __p1;
14090 __ai float32x4_t vmulq_f32(float32x4_t __p0, float32x4_t __p1) {
14092 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14101 __ai int32x4_t vmulq_s32(int32x4_t __p0, int32x4_t __p1) {
14103 __ret = __p0 * __p1;
14107 __ai int32x4_t vmulq_s32(int32x4_t __p0, int32x4_t __p1) {
14109 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14118 __ai int16x8_t vmulq_s16(int16x8_t __p0, int16x8_t __p1) {
14120 __ret = __p0 * __p1;
14124 __ai int16x8_t vmulq_s16(int16x8_t __p0, int16x8_t __p1) {
14126 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14135 __ai uint8x8_t vmul_u8(uint8x8_t __p0, uint8x8_t __p1) {
14137 __ret = __p0 * __p1;
14141 __ai uint8x8_t vmul_u8(uint8x8_t __p0, uint8x8_t __p1) {
14143 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14152 __ai uint32x2_t vmul_u32(uint32x2_t __p0, uint32x2_t __p1) {
14154 __ret = __p0 * __p1;
14158 __ai uint32x2_t vmul_u32(uint32x2_t __p0, uint32x2_t __p1) {
14160 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
14169 __ai uint16x4_t vmul_u16(uint16x4_t __p0, uint16x4_t __p1) {
14171 __ret = __p0 * __p1;
14175 __ai uint16x4_t vmul_u16(uint16x4_t __p0, uint16x4_t __p1) {
14177 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14186 __ai int8x8_t vmul_s8(int8x8_t __p0, int8x8_t __p1) {
14188 __ret = __p0 * __p1;
14192 __ai int8x8_t vmul_s8(int8x8_t __p0, int8x8_t __p1) {
14194 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14203 __ai float32x2_t vmul_f32(float32x2_t __p0, float32x2_t __p1) {
14205 __ret = __p0 * __p1;
14209 __ai float32x2_t vmul_f32(float32x2_t __p0, float32x2_t __p1) {
14211 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
14220 __ai int32x2_t vmul_s32(int32x2_t __p0, int32x2_t __p1) {
14222 __ret = __p0 * __p1;
14226 __ai int32x2_t vmul_s32(int32x2_t __p0, int32x2_t __p1) {
14228 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
14237 __ai int16x4_t vmul_s16(int16x4_t __p0, int16x4_t __p1) {
14239 __ret = __p0 * __p1;
14243 __ai int16x4_t vmul_s16(int16x4_t __p0, int16x4_t __p1) {
14245 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14254 __ai poly8x8_t vmul_p8(poly8x8_t __p0, poly8x8_t __p1) {
14256 __ret = (poly8x8_t) __builtin_neon_vmul_v((int8x8_t)__p0, (int8x8_t)__p1, 4);
14260 __ai poly8x8_t vmul_p8(poly8x8_t __p0, poly8x8_t __p1) {
14262 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14271 __ai poly8x16_t vmulq_p8(poly8x16_t __p0, poly8x16_t __p1) {
14273 __ret = (poly8x16_t) __builtin_neon_vmulq_v((int8x16_t)__p0, (int8x16_t)__p1, 36);
14277 __ai poly8x16_t vmulq_p8(poly8x16_t __p0, poly8x16_t __p1) {
14279 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
14288 #define vmulq_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14290 uint32x2_t __s1 = __p1; \
14296 #define vmulq_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14298 uint32x2_t __s1 = __p1; \
14309 #define vmulq_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14311 uint16x4_t __s1 = __p1; \
14317 #define vmulq_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14319 uint16x4_t __s1 = __p1; \
14330 #define vmulq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
14332 float32x2_t __s1 = __p1; \
14338 #define vmulq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
14340 float32x2_t __s1 = __p1; \
14351 #define vmulq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14353 int32x2_t __s1 = __p1; \
14359 #define vmulq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14361 int32x2_t __s1 = __p1; \
14372 #define vmulq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14374 int16x4_t __s1 = __p1; \
14380 #define vmulq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14382 int16x4_t __s1 = __p1; \
14393 #define vmul_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14395 uint32x2_t __s1 = __p1; \
14401 #define vmul_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14403 uint32x2_t __s1 = __p1; \
14414 #define vmul_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14416 uint16x4_t __s1 = __p1; \
14422 #define vmul_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14424 uint16x4_t __s1 = __p1; \
14435 #define vmul_lane_f32(__p0, __p1, __p2) __extension__ ({ \
14437 float32x2_t __s1 = __p1; \
14443 #define vmul_lane_f32(__p0, __p1, __p2) __extension__ ({ \
14445 float32x2_t __s1 = __p1; \
14456 #define vmul_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14458 int32x2_t __s1 = __p1; \
14464 #define vmul_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14466 int32x2_t __s1 = __p1; \
14477 #define vmul_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14479 int16x4_t __s1 = __p1; \
14485 #define vmul_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14487 int16x4_t __s1 = __p1; \
14498 __ai uint32x4_t vmulq_n_u32(uint32x4_t __p0, uint32_t __p1) {
14500 __ret = __p0 * (uint32x4_t) {__p1, __p1, __p1, __p1};
14504 __ai uint32x4_t vmulq_n_u32(uint32x4_t __p0, uint32_t __p1) {
14507 __ret = __rev0 * (uint32x4_t) {__p1, __p1, __p1, __p1};
14514 __ai uint16x8_t vmulq_n_u16(uint16x8_t __p0, uint16_t __p1) {
14516 __ret = __p0 * (uint16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1};
14520 __ai uint16x8_t vmulq_n_u16(uint16x8_t __p0, uint16_t __p1) {
14523 __ret = __rev0 * (uint16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1};
14530 __ai float32x4_t vmulq_n_f32(float32x4_t __p0, float32_t __p1) {
14532 __ret = __p0 * (float32x4_t) {__p1, __p1, __p1, __p1};
14536 __ai float32x4_t vmulq_n_f32(float32x4_t __p0, float32_t __p1) {
14539 __ret = __rev0 * (float32x4_t) {__p1, __p1, __p1, __p1};
14546 __ai int32x4_t vmulq_n_s32(int32x4_t __p0, int32_t __p1) {
14548 __ret = __p0 * (int32x4_t) {__p1, __p1, __p1, __p1};
14552 __ai int32x4_t vmulq_n_s32(int32x4_t __p0, int32_t __p1) {
14555 __ret = __rev0 * (int32x4_t) {__p1, __p1, __p1, __p1};
14562 __ai int16x8_t vmulq_n_s16(int16x8_t __p0, int16_t __p1) {
14564 __ret = __p0 * (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1};
14568 __ai int16x8_t vmulq_n_s16(int16x8_t __p0, int16_t __p1) {
14571 __ret = __rev0 * (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1};
14578 __ai uint32x2_t vmul_n_u32(uint32x2_t __p0, uint32_t __p1) {
14580 __ret = __p0 * (uint32x2_t) {__p1, __p1};
14584 __ai uint32x2_t vmul_n_u32(uint32x2_t __p0, uint32_t __p1) {
14587 __ret = __rev0 * (uint32x2_t) {__p1, __p1};
14594 __ai uint16x4_t vmul_n_u16(uint16x4_t __p0, uint16_t __p1) {
14596 __ret = __p0 * (uint16x4_t) {__p1, __p1, __p1, __p1};
14600 __ai uint16x4_t vmul_n_u16(uint16x4_t __p0, uint16_t __p1) {
14603 __ret = __rev0 * (uint16x4_t) {__p1, __p1, __p1, __p1};
14610 __ai float32x2_t vmul_n_f32(float32x2_t __p0, float32_t __p1) {
14612 __ret = __p0 * (float32x2_t) {__p1, __p1};
14616 __ai float32x2_t vmul_n_f32(float32x2_t __p0, float32_t __p1) {
14619 __ret = __rev0 * (float32x2_t) {__p1, __p1};
14626 __ai int32x2_t vmul_n_s32(int32x2_t __p0, int32_t __p1) {
14628 __ret = __p0 * (int32x2_t) {__p1, __p1};
14632 __ai int32x2_t vmul_n_s32(int32x2_t __p0, int32_t __p1) {
14635 __ret = __rev0 * (int32x2_t) {__p1, __p1};
14642 __ai int16x4_t vmul_n_s16(int16x4_t __p0, int16_t __p1) {
14644 __ret = __p0 * (int16x4_t) {__p1, __p1, __p1, __p1};
14648 __ai int16x4_t vmul_n_s16(int16x4_t __p0, int16_t __p1) {
14651 __ret = __rev0 * (int16x4_t) {__p1, __p1, __p1, __p1};
14658 __ai poly16x8_t vmull_p8(poly8x8_t __p0, poly8x8_t __p1) {
14660 __ret = (poly16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 37);
14664 __ai poly16x8_t vmull_p8(poly8x8_t __p0, poly8x8_t __p1) {
14666 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14672 __ai poly16x8_t __noswap_vmull_p8(poly8x8_t __p0, poly8x8_t __p1) {
14674 __ret = (poly16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 37);
14680 __ai uint16x8_t vmull_u8(uint8x8_t __p0, uint8x8_t __p1) {
14682 __ret = (uint16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 49);
14686 __ai uint16x8_t vmull_u8(uint8x8_t __p0, uint8x8_t __p1) {
14688 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14694 __ai uint16x8_t __noswap_vmull_u8(uint8x8_t __p0, uint8x8_t __p1) {
14696 __ret = (uint16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 49);
14702 __ai uint64x2_t vmull_u32(uint32x2_t __p0, uint32x2_t __p1) {
14704 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 51);
14708 __ai uint64x2_t vmull_u32(uint32x2_t __p0, uint32x2_t __p1) {
14710 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
14716 __ai uint64x2_t __noswap_vmull_u32(uint32x2_t __p0, uint32x2_t __p1) {
14718 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 51);
14724 __ai uint32x4_t vmull_u16(uint16x4_t __p0, uint16x4_t __p1) {
14726 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 50);
14730 __ai uint32x4_t vmull_u16(uint16x4_t __p0, uint16x4_t __p1) {
14732 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14738 __ai uint32x4_t __noswap_vmull_u16(uint16x4_t __p0, uint16x4_t __p1) {
14740 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 50);
14746 __ai int16x8_t vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14748 __ret = (int16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 33);
14752 __ai int16x8_t vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14754 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14760 __ai int16x8_t __noswap_vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14762 __ret = (int16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 33);
14768 __ai int64x2_t vmull_s32(int32x2_t __p0, int32x2_t __p1) {
14770 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
14774 __ai int64x2_t vmull_s32(int32x2_t __p0, int32x2_t __p1) {
14776 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
14782 __ai int64x2_t __noswap_vmull_s32(int32x2_t __p0, int32x2_t __p1) {
14784 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
14790 __ai int32x4_t vmull_s16(int16x4_t __p0, int16x4_t __p1) {
14792 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
14796 __ai int32x4_t vmull_s16(int16x4_t __p0, int16x4_t __p1) {
14798 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
14804 __ai int32x4_t __noswap_vmull_s16(int16x4_t __p0, int16x4_t __p1) {
14806 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
14812 #define vmull_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14814 uint32x2_t __s1 = __p1; \
14820 #define vmull_lane_u32(__p0, __p1, __p2) __extension__ ({ \
14822 uint32x2_t __s1 = __p1; \
14833 #define vmull_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14835 uint16x4_t __s1 = __p1; \
14841 #define vmull_lane_u16(__p0, __p1, __p2) __extension__ ({ \
14843 uint16x4_t __s1 = __p1; \
14854 #define vmull_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14856 int32x2_t __s1 = __p1; \
14862 #define vmull_lane_s32(__p0, __p1, __p2) __extension__ ({ \
14864 int32x2_t __s1 = __p1; \
14875 #define vmull_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14877 int16x4_t __s1 = __p1; \
14883 #define vmull_lane_s16(__p0, __p1, __p2) __extension__ ({ \
14885 int16x4_t __s1 = __p1; \
14896 __ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
14898 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
14902 __ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
14905 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
14909 __ai uint64x2_t __noswap_vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
14911 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
14917 __ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
14919 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
14923 __ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
14926 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
14930 __ai uint32x4_t __noswap_vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
14932 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
14938 __ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {
14940 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
14944 __ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {
14947 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
14951 __ai int64x2_t __noswap_vmull_n_s32(int32x2_t __p0, int32_t __p1) {
14953 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
14959 __ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {
14961 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
14965 __ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {
14968 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
14972 __ai int32x4_t __noswap_vmull_n_s16(int16x4_t __p0, int16_t __p1) {
14974 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
15332 __ai uint8x16_t vornq_u8(uint8x16_t __p0, uint8x16_t __p1) {
15334 __ret = __p0 | ~__p1;
15338 __ai uint8x16_t vornq_u8(uint8x16_t __p0, uint8x16_t __p1) {
15340 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15349 __ai uint32x4_t vornq_u32(uint32x4_t __p0, uint32x4_t __p1) {
15351 __ret = __p0 | ~__p1;
15355 __ai uint32x4_t vornq_u32(uint32x4_t __p0, uint32x4_t __p1) {
15357 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15366 __ai uint64x2_t vornq_u64(uint64x2_t __p0, uint64x2_t __p1) {
15368 __ret = __p0 | ~__p1;
15372 __ai uint64x2_t vornq_u64(uint64x2_t __p0, uint64x2_t __p1) {
15374 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15383 __ai uint16x8_t vornq_u16(uint16x8_t __p0, uint16x8_t __p1) {
15385 __ret = __p0 | ~__p1;
15389 __ai uint16x8_t vornq_u16(uint16x8_t __p0, uint16x8_t __p1) {
15391 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15400 __ai int8x16_t vornq_s8(int8x16_t __p0, int8x16_t __p1) {
15402 __ret = __p0 | ~__p1;
15406 __ai int8x16_t vornq_s8(int8x16_t __p0, int8x16_t __p1) {
15408 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15417 __ai int32x4_t vornq_s32(int32x4_t __p0, int32x4_t __p1) {
15419 __ret = __p0 | ~__p1;
15423 __ai int32x4_t vornq_s32(int32x4_t __p0, int32x4_t __p1) {
15425 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15434 __ai int64x2_t vornq_s64(int64x2_t __p0, int64x2_t __p1) {
15436 __ret = __p0 | ~__p1;
15440 __ai int64x2_t vornq_s64(int64x2_t __p0, int64x2_t __p1) {
15442 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15451 __ai int16x8_t vornq_s16(int16x8_t __p0, int16x8_t __p1) {
15453 __ret = __p0 | ~__p1;
15457 __ai int16x8_t vornq_s16(int16x8_t __p0, int16x8_t __p1) {
15459 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15468 __ai uint8x8_t vorn_u8(uint8x8_t __p0, uint8x8_t __p1) {
15470 __ret = __p0 | ~__p1;
15474 __ai uint8x8_t vorn_u8(uint8x8_t __p0, uint8x8_t __p1) {
15476 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15485 __ai uint32x2_t vorn_u32(uint32x2_t __p0, uint32x2_t __p1) {
15487 __ret = __p0 | ~__p1;
15491 __ai uint32x2_t vorn_u32(uint32x2_t __p0, uint32x2_t __p1) {
15493 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15502 __ai uint64x1_t vorn_u64(uint64x1_t __p0, uint64x1_t __p1) {
15504 __ret = __p0 | ~__p1;
15508 __ai uint64x1_t vorn_u64(uint64x1_t __p0, uint64x1_t __p1) {
15510 __ret = __p0 | ~__p1;
15516 __ai uint16x4_t vorn_u16(uint16x4_t __p0, uint16x4_t __p1) {
15518 __ret = __p0 | ~__p1;
15522 __ai uint16x4_t vorn_u16(uint16x4_t __p0, uint16x4_t __p1) {
15524 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15533 __ai int8x8_t vorn_s8(int8x8_t __p0, int8x8_t __p1) {
15535 __ret = __p0 | ~__p1;
15539 __ai int8x8_t vorn_s8(int8x8_t __p0, int8x8_t __p1) {
15541 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15550 __ai int32x2_t vorn_s32(int32x2_t __p0, int32x2_t __p1) {
15552 __ret = __p0 | ~__p1;
15556 __ai int32x2_t vorn_s32(int32x2_t __p0, int32x2_t __p1) {
15558 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15567 __ai int64x1_t vorn_s64(int64x1_t __p0, int64x1_t __p1) {
15569 __ret = __p0 | ~__p1;
15573 __ai int64x1_t vorn_s64(int64x1_t __p0, int64x1_t __p1) {
15575 __ret = __p0 | ~__p1;
15581 __ai int16x4_t vorn_s16(int16x4_t __p0, int16x4_t __p1) {
15583 __ret = __p0 | ~__p1;
15587 __ai int16x4_t vorn_s16(int16x4_t __p0, int16x4_t __p1) {
15589 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15598 __ai uint8x16_t vorrq_u8(uint8x16_t __p0, uint8x16_t __p1) {
15600 __ret = __p0 | __p1;
15604 __ai uint8x16_t vorrq_u8(uint8x16_t __p0, uint8x16_t __p1) {
15606 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15615 __ai uint32x4_t vorrq_u32(uint32x4_t __p0, uint32x4_t __p1) {
15617 __ret = __p0 | __p1;
15621 __ai uint32x4_t vorrq_u32(uint32x4_t __p0, uint32x4_t __p1) {
15623 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15632 __ai uint64x2_t vorrq_u64(uint64x2_t __p0, uint64x2_t __p1) {
15634 __ret = __p0 | __p1;
15638 __ai uint64x2_t vorrq_u64(uint64x2_t __p0, uint64x2_t __p1) {
15640 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15649 __ai uint16x8_t vorrq_u16(uint16x8_t __p0, uint16x8_t __p1) {
15651 __ret = __p0 | __p1;
15655 __ai uint16x8_t vorrq_u16(uint16x8_t __p0, uint16x8_t __p1) {
15657 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15666 __ai int8x16_t vorrq_s8(int8x16_t __p0, int8x16_t __p1) {
15668 __ret = __p0 | __p1;
15672 __ai int8x16_t vorrq_s8(int8x16_t __p0, int8x16_t __p1) {
15674 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15683 __ai int32x4_t vorrq_s32(int32x4_t __p0, int32x4_t __p1) {
15685 __ret = __p0 | __p1;
15689 __ai int32x4_t vorrq_s32(int32x4_t __p0, int32x4_t __p1) {
15691 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15700 __ai int64x2_t vorrq_s64(int64x2_t __p0, int64x2_t __p1) {
15702 __ret = __p0 | __p1;
15706 __ai int64x2_t vorrq_s64(int64x2_t __p0, int64x2_t __p1) {
15708 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15717 __ai int16x8_t vorrq_s16(int16x8_t __p0, int16x8_t __p1) {
15719 __ret = __p0 | __p1;
15723 __ai int16x8_t vorrq_s16(int16x8_t __p0, int16x8_t __p1) {
15725 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15734 __ai uint8x8_t vorr_u8(uint8x8_t __p0, uint8x8_t __p1) {
15736 __ret = __p0 | __p1;
15740 __ai uint8x8_t vorr_u8(uint8x8_t __p0, uint8x8_t __p1) {
15742 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15751 __ai uint32x2_t vorr_u32(uint32x2_t __p0, uint32x2_t __p1) {
15753 __ret = __p0 | __p1;
15757 __ai uint32x2_t vorr_u32(uint32x2_t __p0, uint32x2_t __p1) {
15759 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15768 __ai uint64x1_t vorr_u64(uint64x1_t __p0, uint64x1_t __p1) {
15770 __ret = __p0 | __p1;
15774 __ai uint64x1_t vorr_u64(uint64x1_t __p0, uint64x1_t __p1) {
15776 __ret = __p0 | __p1;
15782 __ai uint16x4_t vorr_u16(uint16x4_t __p0, uint16x4_t __p1) {
15784 __ret = __p0 | __p1;
15788 __ai uint16x4_t vorr_u16(uint16x4_t __p0, uint16x4_t __p1) {
15790 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15799 __ai int8x8_t vorr_s8(int8x8_t __p0, int8x8_t __p1) {
15801 __ret = __p0 | __p1;
15805 __ai int8x8_t vorr_s8(int8x8_t __p0, int8x8_t __p1) {
15807 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15816 __ai int32x2_t vorr_s32(int32x2_t __p0, int32x2_t __p1) {
15818 __ret = __p0 | __p1;
15822 __ai int32x2_t vorr_s32(int32x2_t __p0, int32x2_t __p1) {
15824 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15833 __ai int64x1_t vorr_s64(int64x1_t __p0, int64x1_t __p1) {
15835 __ret = __p0 | __p1;
15839 __ai int64x1_t vorr_s64(int64x1_t __p0, int64x1_t __p1) {
15841 __ret = __p0 | __p1;
15847 __ai int16x4_t vorr_s16(int16x4_t __p0, int16x4_t __p1) {
15849 __ret = __p0 | __p1;
15853 __ai int16x4_t vorr_s16(int16x4_t __p0, int16x4_t __p1) {
15855 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15864 __ai uint16x8_t vpadalq_u8(uint16x8_t __p0, uint8x16_t __p1) {
15866 __ret = (uint16x8_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
15870 __ai uint16x8_t vpadalq_u8(uint16x8_t __p0, uint8x16_t __p1) {
15872 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15881 __ai uint64x2_t vpadalq_u32(uint64x2_t __p0, uint32x4_t __p1) {
15883 __ret = (uint64x2_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
15887 __ai uint64x2_t vpadalq_u32(uint64x2_t __p0, uint32x4_t __p1) {
15889 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15898 __ai uint32x4_t vpadalq_u16(uint32x4_t __p0, uint16x8_t __p1) {
15900 __ret = (uint32x4_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
15904 __ai uint32x4_t vpadalq_u16(uint32x4_t __p0, uint16x8_t __p1) {
15906 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15915 __ai int16x8_t vpadalq_s8(int16x8_t __p0, int8x16_t __p1) {
15917 __ret = (int16x8_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
15921 __ai int16x8_t vpadalq_s8(int16x8_t __p0, int8x16_t __p1) {
15923 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
15932 __ai int64x2_t vpadalq_s32(int64x2_t __p0, int32x4_t __p1) {
15934 __ret = (int64x2_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
15938 __ai int64x2_t vpadalq_s32(int64x2_t __p0, int32x4_t __p1) {
15940 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
15949 __ai int32x4_t vpadalq_s16(int32x4_t __p0, int16x8_t __p1) {
15951 __ret = (int32x4_t) __builtin_neon_vpadalq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
15955 __ai int32x4_t vpadalq_s16(int32x4_t __p0, int16x8_t __p1) {
15957 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15966 __ai uint16x4_t vpadal_u8(uint16x4_t __p0, uint8x8_t __p1) {
15968 __ret = (uint16x4_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
15972 __ai uint16x4_t vpadal_u8(uint16x4_t __p0, uint8x8_t __p1) {
15974 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15983 __ai uint64x1_t vpadal_u32(uint64x1_t __p0, uint32x2_t __p1) {
15985 __ret = (uint64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
15989 __ai uint64x1_t vpadal_u32(uint64x1_t __p0, uint32x2_t __p1) {
15990 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
15998 __ai uint32x2_t vpadal_u16(uint32x2_t __p0, uint16x4_t __p1) {
16000 __ret = (uint32x2_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16004 __ai uint32x2_t vpadal_u16(uint32x2_t __p0, uint16x4_t __p1) {
16006 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16015 __ai int16x4_t vpadal_s8(int16x4_t __p0, int8x8_t __p1) {
16017 __ret = (int16x4_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16021 __ai int16x4_t vpadal_s8(int16x4_t __p0, int8x8_t __p1) {
16023 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16032 __ai int64x1_t vpadal_s32(int64x1_t __p0, int32x2_t __p1) {
16034 __ret = (int64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
16038 __ai int64x1_t vpadal_s32(int64x1_t __p0, int32x2_t __p1) {
16039 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16047 __ai int32x2_t vpadal_s16(int32x2_t __p0, int16x4_t __p1) {
16049 __ret = (int32x2_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16053 __ai int32x2_t vpadal_s16(int32x2_t __p0, int16x4_t __p1) {
16055 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16064 __ai uint8x8_t vpadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
16066 __ret = (uint8x8_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16070 __ai uint8x8_t vpadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
16072 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16081 __ai uint32x2_t vpadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
16083 __ret = (uint32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16087 __ai uint32x2_t vpadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
16089 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16098 __ai uint16x4_t vpadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
16100 __ret = (uint16x4_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16104 __ai uint16x4_t vpadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
16106 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16115 __ai int8x8_t vpadd_s8(int8x8_t __p0, int8x8_t __p1) {
16117 __ret = (int8x8_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16121 __ai int8x8_t vpadd_s8(int8x8_t __p0, int8x8_t __p1) {
16123 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16132 __ai float32x2_t vpadd_f32(float32x2_t __p0, float32x2_t __p1) {
16134 __ret = (float32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16138 __ai float32x2_t vpadd_f32(float32x2_t __p0, float32x2_t __p1) {
16140 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16149 __ai int32x2_t vpadd_s32(int32x2_t __p0, int32x2_t __p1) {
16151 __ret = (int32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16155 __ai int32x2_t vpadd_s32(int32x2_t __p0, int32x2_t __p1) {
16157 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16166 __ai int16x4_t vpadd_s16(int16x4_t __p0, int16x4_t __p1) {
16168 __ret = (int16x4_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16172 __ai int16x4_t vpadd_s16(int16x4_t __p0, int16x4_t __p1) {
16174 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16373 __ai uint8x8_t vpmax_u8(uint8x8_t __p0, uint8x8_t __p1) {
16375 __ret = (uint8x8_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16379 __ai uint8x8_t vpmax_u8(uint8x8_t __p0, uint8x8_t __p1) {
16381 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16390 __ai uint32x2_t vpmax_u32(uint32x2_t __p0, uint32x2_t __p1) {
16392 __ret = (uint32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16396 __ai uint32x2_t vpmax_u32(uint32x2_t __p0, uint32x2_t __p1) {
16398 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16407 __ai uint16x4_t vpmax_u16(uint16x4_t __p0, uint16x4_t __p1) {
16409 __ret = (uint16x4_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16413 __ai uint16x4_t vpmax_u16(uint16x4_t __p0, uint16x4_t __p1) {
16415 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16424 __ai int8x8_t vpmax_s8(int8x8_t __p0, int8x8_t __p1) {
16426 __ret = (int8x8_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16430 __ai int8x8_t vpmax_s8(int8x8_t __p0, int8x8_t __p1) {
16432 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16441 __ai float32x2_t vpmax_f32(float32x2_t __p0, float32x2_t __p1) {
16443 __ret = (float32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16447 __ai float32x2_t vpmax_f32(float32x2_t __p0, float32x2_t __p1) {
16449 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16458 __ai int32x2_t vpmax_s32(int32x2_t __p0, int32x2_t __p1) {
16460 __ret = (int32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16464 __ai int32x2_t vpmax_s32(int32x2_t __p0, int32x2_t __p1) {
16466 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16475 __ai int16x4_t vpmax_s16(int16x4_t __p0, int16x4_t __p1) {
16477 __ret = (int16x4_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16481 __ai int16x4_t vpmax_s16(int16x4_t __p0, int16x4_t __p1) {
16483 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16492 __ai uint8x8_t vpmin_u8(uint8x8_t __p0, uint8x8_t __p1) {
16494 __ret = (uint8x8_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16498 __ai uint8x8_t vpmin_u8(uint8x8_t __p0, uint8x8_t __p1) {
16500 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16509 __ai uint32x2_t vpmin_u32(uint32x2_t __p0, uint32x2_t __p1) {
16511 __ret = (uint32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16515 __ai uint32x2_t vpmin_u32(uint32x2_t __p0, uint32x2_t __p1) {
16517 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16526 __ai uint16x4_t vpmin_u16(uint16x4_t __p0, uint16x4_t __p1) {
16528 __ret = (uint16x4_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16532 __ai uint16x4_t vpmin_u16(uint16x4_t __p0, uint16x4_t __p1) {
16534 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16543 __ai int8x8_t vpmin_s8(int8x8_t __p0, int8x8_t __p1) {
16545 __ret = (int8x8_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16549 __ai int8x8_t vpmin_s8(int8x8_t __p0, int8x8_t __p1) {
16551 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16560 __ai float32x2_t vpmin_f32(float32x2_t __p0, float32x2_t __p1) {
16562 __ret = (float32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16566 __ai float32x2_t vpmin_f32(float32x2_t __p0, float32x2_t __p1) {
16568 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16577 __ai int32x2_t vpmin_s32(int32x2_t __p0, int32x2_t __p1) {
16579 __ret = (int32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16583 __ai int32x2_t vpmin_s32(int32x2_t __p0, int32x2_t __p1) {
16585 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16594 __ai int16x4_t vpmin_s16(int16x4_t __p0, int16x4_t __p1) {
16596 __ret = (int16x4_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16600 __ai int16x4_t vpmin_s16(int16x4_t __p0, int16x4_t __p1) {
16602 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16707 __ai uint8x16_t vqaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
16709 __ret = (uint8x16_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
16713 __ai uint8x16_t vqaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
16715 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
16724 __ai uint32x4_t vqaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
16726 __ret = (uint32x4_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
16730 __ai uint32x4_t vqaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
16732 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16741 __ai uint64x2_t vqaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
16743 __ret = (uint64x2_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
16747 __ai uint64x2_t vqaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
16749 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16758 __ai uint16x8_t vqaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
16760 __ret = (uint16x8_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
16764 __ai uint16x8_t vqaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
16766 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16775 __ai int8x16_t vqaddq_s8(int8x16_t __p0, int8x16_t __p1) {
16777 __ret = (int8x16_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
16781 __ai int8x16_t vqaddq_s8(int8x16_t __p0, int8x16_t __p1) {
16783 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
16792 __ai int32x4_t vqaddq_s32(int32x4_t __p0, int32x4_t __p1) {
16794 __ret = (int32x4_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
16798 __ai int32x4_t vqaddq_s32(int32x4_t __p0, int32x4_t __p1) {
16800 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16806 __ai int32x4_t __noswap_vqaddq_s32(int32x4_t __p0, int32x4_t __p1) {
16808 __ret = (int32x4_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
16814 __ai int64x2_t vqaddq_s64(int64x2_t __p0, int64x2_t __p1) {
16816 __ret = (int64x2_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
16820 __ai int64x2_t vqaddq_s64(int64x2_t __p0, int64x2_t __p1) {
16822 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16831 __ai int16x8_t vqaddq_s16(int16x8_t __p0, int16x8_t __p1) {
16833 __ret = (int16x8_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
16837 __ai int16x8_t vqaddq_s16(int16x8_t __p0, int16x8_t __p1) {
16839 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16845 __ai int16x8_t __noswap_vqaddq_s16(int16x8_t __p0, int16x8_t __p1) {
16847 __ret = (int16x8_t) __builtin_neon_vqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
16853 __ai uint8x8_t vqadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
16855 __ret = (uint8x8_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16859 __ai uint8x8_t vqadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
16861 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16870 __ai uint32x2_t vqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
16872 __ret = (uint32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16876 __ai uint32x2_t vqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
16878 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16887 __ai uint64x1_t vqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
16889 __ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
16893 __ai uint64x1_t vqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
16895 __ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
16901 __ai uint16x4_t vqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
16903 __ret = (uint16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16907 __ai uint16x4_t vqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
16909 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16918 __ai int8x8_t vqadd_s8(int8x8_t __p0, int8x8_t __p1) {
16920 __ret = (int8x8_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16924 __ai int8x8_t vqadd_s8(int8x8_t __p0, int8x8_t __p1) {
16926 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16935 __ai int32x2_t vqadd_s32(int32x2_t __p0, int32x2_t __p1) {
16937 __ret = (int32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16941 __ai int32x2_t vqadd_s32(int32x2_t __p0, int32x2_t __p1) {
16943 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
16949 __ai int32x2_t __noswap_vqadd_s32(int32x2_t __p0, int32x2_t __p1) {
16951 __ret = (int32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16957 __ai int64x1_t vqadd_s64(int64x1_t __p0, int64x1_t __p1) {
16959 __ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
16963 __ai int64x1_t vqadd_s64(int64x1_t __p0, int64x1_t __p1) {
16965 __ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
16971 __ai int16x4_t vqadd_s16(int16x4_t __p0, int16x4_t __p1) {
16973 __ret = (int16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16977 __ai int16x4_t vqadd_s16(int16x4_t __p0, int16x4_t __p1) {
16979 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
16985 __ai int16x4_t __noswap_vqadd_s16(int16x4_t __p0, int16x4_t __p1) {
16987 __ret = (int16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16993 __ai int64x2_t vqdmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
16995 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
16999 __ai int64x2_t vqdmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
17001 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17008 __ai int64x2_t __noswap_vqdmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
17010 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17016 __ai int32x4_t vqdmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17018 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17022 __ai int32x4_t vqdmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17024 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17031 __ai int32x4_t __noswap_vqdmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17033 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17039 #define vqdmlal_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
17041 int32x2_t __s1 = __p1; \
17048 #define vqdmlal_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
17050 int32x2_t __s1 = __p1; \
17063 #define vqdmlal_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
17065 int16x4_t __s1 = __p1; \
17072 #define vqdmlal_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
17074 int16x4_t __s1 = __p1; \
17087 __ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17089 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17093 __ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17095 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17101 __ai int64x2_t __noswap_vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17103 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17109 __ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17111 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17115 __ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17117 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17123 __ai int32x4_t __noswap_vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17125 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17131 __ai int64x2_t vqdmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
17133 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17137 __ai int64x2_t vqdmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
17139 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17146 __ai int64x2_t __noswap_vqdmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
17148 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17154 __ai int32x4_t vqdmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17156 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17160 __ai int32x4_t vqdmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17162 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17169 __ai int32x4_t __noswap_vqdmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
17171 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17177 #define vqdmlsl_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
17179 int32x2_t __s1 = __p1; \
17186 #define vqdmlsl_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
17188 int32x2_t __s1 = __p1; \
17201 #define vqdmlsl_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
17203 int16x4_t __s1 = __p1; \
17210 #define vqdmlsl_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
17212 int16x4_t __s1 = __p1; \
17225 __ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17227 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17231 __ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17233 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17239 __ai int64x2_t __noswap_vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
17241 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17247 __ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17249 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17253 __ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17255 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17261 __ai int32x4_t __noswap_vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
17263 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17269 __ai int32x4_t vqdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17271 __ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
17275 __ai int32x4_t vqdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17277 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17283 __ai int32x4_t __noswap_vqdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17285 __ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
17291 __ai int16x8_t vqdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17293 __ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
17297 __ai int16x8_t vqdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17299 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
17305 __ai int16x8_t __noswap_vqdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17307 __ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
17313 __ai int32x2_t vqdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17315 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17319 __ai int32x2_t vqdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17321 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17327 __ai int32x2_t __noswap_vqdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17329 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17335 __ai int16x4_t vqdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
17337 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17341 __ai int16x4_t vqdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
17343 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17349 __ai int16x4_t __noswap_vqdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
17351 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17357 #define vqdmulhq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17359 int32x2_t __s1 = __p1; \
17365 #define vqdmulhq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17367 int32x2_t __s1 = __p1; \
17378 #define vqdmulhq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17380 int16x4_t __s1 = __p1; \
17386 #define vqdmulhq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17388 int16x4_t __s1 = __p1; \
17399 #define vqdmulh_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17401 int32x2_t __s1 = __p1; \
17407 #define vqdmulh_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17409 int32x2_t __s1 = __p1; \
17420 #define vqdmulh_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17422 int16x4_t __s1 = __p1; \
17428 #define vqdmulh_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17430 int16x4_t __s1 = __p1; \
17441 __ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
17443 __ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);
17447 __ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
17450 __ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);
17457 __ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
17459 __ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);
17463 __ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
17466 __ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);
17473 __ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
17475 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
17479 __ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
17482 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
17489 __ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
17491 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
17495 __ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
17498 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
17505 __ai int64x2_t vqdmull_s32(int32x2_t __p0, int32x2_t __p1) {
17507 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
17511 __ai int64x2_t vqdmull_s32(int32x2_t __p0, int32x2_t __p1) {
17513 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17519 __ai int64x2_t __noswap_vqdmull_s32(int32x2_t __p0, int32x2_t __p1) {
17521 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
17527 __ai int32x4_t vqdmull_s16(int16x4_t __p0, int16x4_t __p1) {
17529 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
17533 __ai int32x4_t vqdmull_s16(int16x4_t __p0, int16x4_t __p1) {
17535 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17541 __ai int32x4_t __noswap_vqdmull_s16(int16x4_t __p0, int16x4_t __p1) {
17543 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
17549 #define vqdmull_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17551 int32x2_t __s1 = __p1; \
17557 #define vqdmull_lane_s32(__p0, __p1, __p2) __extension__ ({ \
17559 int32x2_t __s1 = __p1; \
17570 #define vqdmull_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17572 int16x4_t __s1 = __p1; \
17578 #define vqdmull_lane_s16(__p0, __p1, __p2) __extension__ ({ \
17580 int16x4_t __s1 = __p1; \
17591 __ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
17593 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17597 __ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
17600 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17604 __ai int64x2_t __noswap_vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
17606 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17612 __ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
17614 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17618 __ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
17621 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17625 __ai int32x4_t __noswap_vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
17627 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17918 __ai int32x4_t vqrdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17920 __ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
17924 __ai int32x4_t vqrdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17926 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17932 __ai int32x4_t __noswap_vqrdmulhq_s32(int32x4_t __p0, int32x4_t __p1) {
17934 __ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
17940 __ai int16x8_t vqrdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17942 __ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
17946 __ai int16x8_t vqrdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17948 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
17954 __ai int16x8_t __noswap_vqrdmulhq_s16(int16x8_t __p0, int16x8_t __p1) {
17956 __ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
17962 __ai int32x2_t vqrdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17964 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17968 __ai int32x2_t vqrdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17970 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
17976 __ai int32x2_t __noswap_vqrdmulh_s32(int32x2_t __p0, int32x2_t __p1) {
17978 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17984 __ai int16x4_t vqrdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
17986 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17990 __ai int16x4_t vqrdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
17992 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
17998 __ai int16x4_t __noswap_vqrdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
18000 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18006 #define vqrdmulhq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
18008 int32x2_t __s1 = __p1; \
18014 #define vqrdmulhq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
18016 int32x2_t __s1 = __p1; \
18027 #define vqrdmulhq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
18029 int16x4_t __s1 = __p1; \
18035 #define vqrdmulhq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
18037 int16x4_t __s1 = __p1; \
18048 #define vqrdmulh_lane_s32(__p0, __p1, __p2) __extension__ ({ \
18050 int32x2_t __s1 = __p1; \
18056 #define vqrdmulh_lane_s32(__p0, __p1, __p2) __extension__ ({ \
18058 int32x2_t __s1 = __p1; \
18069 #define vqrdmulh_lane_s16(__p0, __p1, __p2) __extension__ ({ \
18071 int16x4_t __s1 = __p1; \
18077 #define vqrdmulh_lane_s16(__p0, __p1, __p2) __extension__ ({ \
18079 int16x4_t __s1 = __p1; \
18090 __ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
18092 __ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);
18096 __ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
18099 __ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);
18106 __ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
18108 __ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);
18112 __ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
18115 __ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);
18122 __ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
18124 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
18128 __ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
18131 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
18138 __ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
18140 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
18144 __ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
18147 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
18154 __ai uint8x16_t vqrshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
18156 __ret = (uint8x16_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
18160 __ai uint8x16_t vqrshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
18162 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
18171 __ai uint32x4_t vqrshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
18173 __ret = (uint32x4_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
18177 __ai uint32x4_t vqrshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
18179 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18188 __ai uint64x2_t vqrshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
18190 __ret = (uint64x2_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
18194 __ai uint64x2_t vqrshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
18196 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18205 __ai uint16x8_t vqrshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
18207 __ret = (uint16x8_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
18211 __ai uint16x8_t vqrshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
18213 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18222 __ai int8x16_t vqrshlq_s8(int8x16_t __p0, int8x16_t __p1) {
18224 __ret = (int8x16_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
18228 __ai int8x16_t vqrshlq_s8(int8x16_t __p0, int8x16_t __p1) {
18230 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
18239 __ai int32x4_t vqrshlq_s32(int32x4_t __p0, int32x4_t __p1) {
18241 __ret = (int32x4_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
18245 __ai int32x4_t vqrshlq_s32(int32x4_t __p0, int32x4_t __p1) {
18247 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18256 __ai int64x2_t vqrshlq_s64(int64x2_t __p0, int64x2_t __p1) {
18258 __ret = (int64x2_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
18262 __ai int64x2_t vqrshlq_s64(int64x2_t __p0, int64x2_t __p1) {
18264 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18273 __ai int16x8_t vqrshlq_s16(int16x8_t __p0, int16x8_t __p1) {
18275 __ret = (int16x8_t) __builtin_neon_vqrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
18279 __ai int16x8_t vqrshlq_s16(int16x8_t __p0, int16x8_t __p1) {
18281 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18290 __ai uint8x8_t vqrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18292 __ret = (uint8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
18296 __ai uint8x8_t vqrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18298 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18307 __ai uint32x2_t vqrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
18309 __ret = (uint32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
18313 __ai uint32x2_t vqrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
18315 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18324 __ai uint64x1_t vqrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
18326 __ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18330 __ai uint64x1_t vqrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
18332 __ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18338 __ai uint16x4_t vqrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
18340 __ret = (uint16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
18344 __ai uint16x4_t vqrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
18346 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18355 __ai int8x8_t vqrshl_s8(int8x8_t __p0, int8x8_t __p1) {
18357 __ret = (int8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
18361 __ai int8x8_t vqrshl_s8(int8x8_t __p0, int8x8_t __p1) {
18363 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18372 __ai int32x2_t vqrshl_s32(int32x2_t __p0, int32x2_t __p1) {
18374 __ret = (int32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18378 __ai int32x2_t vqrshl_s32(int32x2_t __p0, int32x2_t __p1) {
18380 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18389 __ai int64x1_t vqrshl_s64(int64x1_t __p0, int64x1_t __p1) {
18391 __ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18395 __ai int64x1_t vqrshl_s64(int64x1_t __p0, int64x1_t __p1) {
18397 __ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18403 __ai int16x4_t vqrshl_s16(int16x4_t __p0, int16x4_t __p1) {
18405 __ret = (int16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18409 __ai int16x4_t vqrshl_s16(int16x4_t __p0, int16x4_t __p1) {
18411 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18420 #define vqrshrn_n_u32(__p0, __p1) __extension__ ({ \
18423 __ret = (uint16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 17); \
18427 #define vqrshrn_n_u32(__p0, __p1) __extension__ ({ \
18431 __ret = (uint16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 17); \
18435 #define __noswap_vqrshrn_n_u32(__p0, __p1) __extension__ ({ \
18438 __ret = (uint16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 17); \
18444 #define vqrshrn_n_u64(__p0, __p1) __extension__ ({ \
18447 __ret = (uint32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 18); \
18451 #define vqrshrn_n_u64(__p0, __p1) __extension__ ({ \
18455 __ret = (uint32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 18); \
18459 #define __noswap_vqrshrn_n_u64(__p0, __p1) __extension__ ({ \
18462 __ret = (uint32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 18); \
18468 #define vqrshrn_n_u16(__p0, __p1) __extension__ ({ \
18471 __ret = (uint8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 16); \
18475 #define vqrshrn_n_u16(__p0, __p1) __extension__ ({ \
18479 __ret = (uint8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 16); \
18483 #define __noswap_vqrshrn_n_u16(__p0, __p1) __extension__ ({ \
18486 __ret = (uint8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 16); \
18492 #define vqrshrn_n_s32(__p0, __p1) __extension__ ({ \
18495 __ret = (int16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 1); \
18499 #define vqrshrn_n_s32(__p0, __p1) __extension__ ({ \
18503 __ret = (int16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 1); \
18507 #define __noswap_vqrshrn_n_s32(__p0, __p1) __extension__ ({ \
18510 __ret = (int16x4_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 1); \
18516 #define vqrshrn_n_s64(__p0, __p1) __extension__ ({ \
18519 __ret = (int32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 2); \
18523 #define vqrshrn_n_s64(__p0, __p1) __extension__ ({ \
18527 __ret = (int32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 2); \
18531 #define __noswap_vqrshrn_n_s64(__p0, __p1) __extension__ ({ \
18534 __ret = (int32x2_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 2); \
18540 #define vqrshrn_n_s16(__p0, __p1) __extension__ ({ \
18543 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 0); \
18547 #define vqrshrn_n_s16(__p0, __p1) __extension__ ({ \
18551 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 0); \
18555 #define __noswap_vqrshrn_n_s16(__p0, __p1) __extension__ ({ \
18558 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 0); \
18564 #define vqrshrun_n_s32(__p0, __p1) __extension__ ({ \
18567 __ret = (uint16x4_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 17); \
18571 #define vqrshrun_n_s32(__p0, __p1) __extension__ ({ \
18575 __ret = (uint16x4_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__rev0, __p1, 17); \
18579 #define __noswap_vqrshrun_n_s32(__p0, __p1) __extension__ ({ \
18582 __ret = (uint16x4_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 17); \
18588 #define vqrshrun_n_s64(__p0, __p1) __extension__ ({ \
18591 __ret = (uint32x2_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 18); \
18595 #define vqrshrun_n_s64(__p0, __p1) __extension__ ({ \
18599 __ret = (uint32x2_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__rev0, __p1, 18); \
18603 #define __noswap_vqrshrun_n_s64(__p0, __p1) __extension__ ({ \
18606 __ret = (uint32x2_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 18); \
18612 #define vqrshrun_n_s16(__p0, __p1) __extension__ ({ \
18615 __ret = (uint8x8_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 16); \
18619 #define vqrshrun_n_s16(__p0, __p1) __extension__ ({ \
18623 __ret = (uint8x8_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__rev0, __p1, 16); \
18627 #define __noswap_vqrshrun_n_s16(__p0, __p1) __extension__ ({ \
18630 __ret = (uint8x8_t) __builtin_neon_vqrshrun_n_v((int8x16_t)__s0, __p1, 16); \
18636 __ai uint8x16_t vqshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
18638 __ret = (uint8x16_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
18642 __ai uint8x16_t vqshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
18644 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
18653 __ai uint32x4_t vqshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
18655 __ret = (uint32x4_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
18659 __ai uint32x4_t vqshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
18661 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18670 __ai uint64x2_t vqshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
18672 __ret = (uint64x2_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
18676 __ai uint64x2_t vqshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
18678 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18687 __ai uint16x8_t vqshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
18689 __ret = (uint16x8_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
18693 __ai uint16x8_t vqshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
18695 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18704 __ai int8x16_t vqshlq_s8(int8x16_t __p0, int8x16_t __p1) {
18706 __ret = (int8x16_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
18710 __ai int8x16_t vqshlq_s8(int8x16_t __p0, int8x16_t __p1) {
18712 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
18721 __ai int32x4_t vqshlq_s32(int32x4_t __p0, int32x4_t __p1) {
18723 __ret = (int32x4_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
18727 __ai int32x4_t vqshlq_s32(int32x4_t __p0, int32x4_t __p1) {
18729 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18738 __ai int64x2_t vqshlq_s64(int64x2_t __p0, int64x2_t __p1) {
18740 __ret = (int64x2_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
18744 __ai int64x2_t vqshlq_s64(int64x2_t __p0, int64x2_t __p1) {
18746 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18755 __ai int16x8_t vqshlq_s16(int16x8_t __p0, int16x8_t __p1) {
18757 __ret = (int16x8_t) __builtin_neon_vqshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
18761 __ai int16x8_t vqshlq_s16(int16x8_t __p0, int16x8_t __p1) {
18763 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18772 __ai uint8x8_t vqshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18774 __ret = (uint8x8_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
18778 __ai uint8x8_t vqshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18780 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18789 __ai uint32x2_t vqshl_u32(uint32x2_t __p0, int32x2_t __p1) {
18791 __ret = (uint32x2_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
18795 __ai uint32x2_t vqshl_u32(uint32x2_t __p0, int32x2_t __p1) {
18797 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18806 __ai uint64x1_t vqshl_u64(uint64x1_t __p0, int64x1_t __p1) {
18808 __ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18812 __ai uint64x1_t vqshl_u64(uint64x1_t __p0, int64x1_t __p1) {
18814 __ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18820 __ai uint16x4_t vqshl_u16(uint16x4_t __p0, int16x4_t __p1) {
18822 __ret = (uint16x4_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
18826 __ai uint16x4_t vqshl_u16(uint16x4_t __p0, int16x4_t __p1) {
18828 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18837 __ai int8x8_t vqshl_s8(int8x8_t __p0, int8x8_t __p1) {
18839 __ret = (int8x8_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
18843 __ai int8x8_t vqshl_s8(int8x8_t __p0, int8x8_t __p1) {
18845 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18854 __ai int32x2_t vqshl_s32(int32x2_t __p0, int32x2_t __p1) {
18856 __ret = (int32x2_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18860 __ai int32x2_t vqshl_s32(int32x2_t __p0, int32x2_t __p1) {
18862 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18871 __ai int64x1_t vqshl_s64(int64x1_t __p0, int64x1_t __p1) {
18873 __ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18877 __ai int64x1_t vqshl_s64(int64x1_t __p0, int64x1_t __p1) {
18879 __ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18885 __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
18887 __ret = (int16x4_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18891 __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
18893 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18902 #define vqshlq_n_u8(__p0, __p1) __extension__ ({ \
18905 __ret = (uint8x16_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 48); \
18909 #define vqshlq_n_u8(__p0, __p1) __extension__ ({ \
18913 __ret = (uint8x16_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 48); \
18920 #define vqshlq_n_u32(__p0, __p1) __extension__ ({ \
18923 __ret = (uint32x4_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 50); \
18927 #define vqshlq_n_u32(__p0, __p1) __extension__ ({ \
18931 __ret = (uint32x4_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 50); \
18938 #define vqshlq_n_u64(__p0, __p1) __extension__ ({ \
18941 __ret = (uint64x2_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 51); \
18945 #define vqshlq_n_u64(__p0, __p1) __extension__ ({ \
18949 __ret = (uint64x2_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 51); \
18956 #define vqshlq_n_u16(__p0, __p1) __extension__ ({ \
18959 __ret = (uint16x8_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 49); \
18963 #define vqshlq_n_u16(__p0, __p1) __extension__ ({ \
18967 __ret = (uint16x8_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 49); \
18974 #define vqshlq_n_s8(__p0, __p1) __extension__ ({ \
18977 __ret = (int8x16_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 32); \
18981 #define vqshlq_n_s8(__p0, __p1) __extension__ ({ \
18985 __ret = (int8x16_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 32); \
18992 #define vqshlq_n_s32(__p0, __p1) __extension__ ({ \
18995 __ret = (int32x4_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 34); \
18999 #define vqshlq_n_s32(__p0, __p1) __extension__ ({ \
19003 __ret = (int32x4_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 34); \
19010 #define vqshlq_n_s64(__p0, __p1) __extension__ ({ \
19013 __ret = (int64x2_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 35); \
19017 #define vqshlq_n_s64(__p0, __p1) __extension__ ({ \
19021 __ret = (int64x2_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 35); \
19028 #define vqshlq_n_s16(__p0, __p1) __extension__ ({ \
19031 __ret = (int16x8_t) __builtin_neon_vqshlq_n_v((int8x16_t)__s0, __p1, 33); \
19035 #define vqshlq_n_s16(__p0, __p1) __extension__ ({ \
19039 __ret = (int16x8_t) __builtin_neon_vqshlq_n_v((int8x16_t)__rev0, __p1, 33); \
19046 #define vqshl_n_u8(__p0, __p1) __extension__ ({ \
19049 __ret = (uint8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 16); \
19053 #define vqshl_n_u8(__p0, __p1) __extension__ ({ \
19057 __ret = (uint8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 16); \
19064 #define vqshl_n_u32(__p0, __p1) __extension__ ({ \
19067 __ret = (uint32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 18); \
19071 #define vqshl_n_u32(__p0, __p1) __extension__ ({ \
19075 __ret = (uint32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 18); \
19082 #define vqshl_n_u64(__p0, __p1) __extension__ ({ \
19085 __ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
19089 #define vqshl_n_u64(__p0, __p1) __extension__ ({ \
19092 __ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
19098 #define vqshl_n_u16(__p0, __p1) __extension__ ({ \
19101 __ret = (uint16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 17); \
19105 #define vqshl_n_u16(__p0, __p1) __extension__ ({ \
19109 __ret = (uint16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 17); \
19116 #define vqshl_n_s8(__p0, __p1) __extension__ ({ \
19119 __ret = (int8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 0); \
19123 #define vqshl_n_s8(__p0, __p1) __extension__ ({ \
19127 __ret = (int8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 0); \
19134 #define vqshl_n_s32(__p0, __p1) __extension__ ({ \
19137 __ret = (int32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 2); \
19141 #define vqshl_n_s32(__p0, __p1) __extension__ ({ \
19145 __ret = (int32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 2); \
19152 #define vqshl_n_s64(__p0, __p1) __extension__ ({ \
19155 __ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
19159 #define vqshl_n_s64(__p0, __p1) __extension__ ({ \
19162 __ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
19168 #define vqshl_n_s16(__p0, __p1) __extension__ ({ \
19171 __ret = (int16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 1); \
19175 #define vqshl_n_s16(__p0, __p1) __extension__ ({ \
19179 __ret = (int16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 1); \
19186 #define vqshluq_n_s8(__p0, __p1) __extension__ ({ \
19189 __ret = (uint8x16_t) __builtin_neon_vqshluq_n_v((int8x16_t)__s0, __p1, 48); \
19193 #define vqshluq_n_s8(__p0, __p1) __extension__ ({ \
19197 __ret = (uint8x16_t) __builtin_neon_vqshluq_n_v((int8x16_t)__rev0, __p1, 48); \
19204 #define vqshluq_n_s32(__p0, __p1) __extension__ ({ \
19207 __ret = (uint32x4_t) __builtin_neon_vqshluq_n_v((int8x16_t)__s0, __p1, 50); \
19211 #define vqshluq_n_s32(__p0, __p1) __extension__ ({ \
19215 __ret = (uint32x4_t) __builtin_neon_vqshluq_n_v((int8x16_t)__rev0, __p1, 50); \
19222 #define vqshluq_n_s64(__p0, __p1) __extension__ ({ \
19225 __ret = (uint64x2_t) __builtin_neon_vqshluq_n_v((int8x16_t)__s0, __p1, 51); \
19229 #define vqshluq_n_s64(__p0, __p1) __extension__ ({ \
19233 __ret = (uint64x2_t) __builtin_neon_vqshluq_n_v((int8x16_t)__rev0, __p1, 51); \
19240 #define vqshluq_n_s16(__p0, __p1) __extension__ ({ \
19243 __ret = (uint16x8_t) __builtin_neon_vqshluq_n_v((int8x16_t)__s0, __p1, 49); \
19247 #define vqshluq_n_s16(__p0, __p1) __extension__ ({ \
19251 __ret = (uint16x8_t) __builtin_neon_vqshluq_n_v((int8x16_t)__rev0, __p1, 49); \
19258 #define vqshlu_n_s8(__p0, __p1) __extension__ ({ \
19261 __ret = (uint8x8_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 16); \
19265 #define vqshlu_n_s8(__p0, __p1) __extension__ ({ \
19269 __ret = (uint8x8_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 16); \
19276 #define vqshlu_n_s32(__p0, __p1) __extension__ ({ \
19279 __ret = (uint32x2_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 18); \
19283 #define vqshlu_n_s32(__p0, __p1) __extension__ ({ \
19287 __ret = (uint32x2_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 18); \
19294 #define vqshlu_n_s64(__p0, __p1) __extension__ ({ \
19297 __ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
19301 #define vqshlu_n_s64(__p0, __p1) __extension__ ({ \
19304 __ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
19310 #define vqshlu_n_s16(__p0, __p1) __extension__ ({ \
19313 __ret = (uint16x4_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 17); \
19317 #define vqshlu_n_s16(__p0, __p1) __extension__ ({ \
19321 __ret = (uint16x4_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 17); \
19328 #define vqshrn_n_u32(__p0, __p1) __extension__ ({ \
19331 __ret = (uint16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 17); \
19335 #define vqshrn_n_u32(__p0, __p1) __extension__ ({ \
19339 __ret = (uint16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 17); \
19343 #define __noswap_vqshrn_n_u32(__p0, __p1) __extension__ ({ \
19346 __ret = (uint16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 17); \
19352 #define vqshrn_n_u64(__p0, __p1) __extension__ ({ \
19355 __ret = (uint32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 18); \
19359 #define vqshrn_n_u64(__p0, __p1) __extension__ ({ \
19363 __ret = (uint32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 18); \
19367 #define __noswap_vqshrn_n_u64(__p0, __p1) __extension__ ({ \
19370 __ret = (uint32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 18); \
19376 #define vqshrn_n_u16(__p0, __p1) __extension__ ({ \
19379 __ret = (uint8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 16); \
19383 #define vqshrn_n_u16(__p0, __p1) __extension__ ({ \
19387 __ret = (uint8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 16); \
19391 #define __noswap_vqshrn_n_u16(__p0, __p1) __extension__ ({ \
19394 __ret = (uint8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 16); \
19400 #define vqshrn_n_s32(__p0, __p1) __extension__ ({ \
19403 __ret = (int16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 1); \
19407 #define vqshrn_n_s32(__p0, __p1) __extension__ ({ \
19411 __ret = (int16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 1); \
19415 #define __noswap_vqshrn_n_s32(__p0, __p1) __extension__ ({ \
19418 __ret = (int16x4_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 1); \
19424 #define vqshrn_n_s64(__p0, __p1) __extension__ ({ \
19427 __ret = (int32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 2); \
19431 #define vqshrn_n_s64(__p0, __p1) __extension__ ({ \
19435 __ret = (int32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 2); \
19439 #define __noswap_vqshrn_n_s64(__p0, __p1) __extension__ ({ \
19442 __ret = (int32x2_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 2); \
19448 #define vqshrn_n_s16(__p0, __p1) __extension__ ({ \
19451 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 0); \
19455 #define vqshrn_n_s16(__p0, __p1) __extension__ ({ \
19459 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 0); \
19463 #define __noswap_vqshrn_n_s16(__p0, __p1) __extension__ ({ \
19466 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 0); \
19472 #define vqshrun_n_s32(__p0, __p1) __extension__ ({ \
19475 __ret = (uint16x4_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 17); \
19479 #define vqshrun_n_s32(__p0, __p1) __extension__ ({ \
19483 __ret = (uint16x4_t) __builtin_neon_vqshrun_n_v((int8x16_t)__rev0, __p1, 17); \
19487 #define __noswap_vqshrun_n_s32(__p0, __p1) __extension__ ({ \
19490 __ret = (uint16x4_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 17); \
19496 #define vqshrun_n_s64(__p0, __p1) __extension__ ({ \
19499 __ret = (uint32x2_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 18); \
19503 #define vqshrun_n_s64(__p0, __p1) __extension__ ({ \
19507 __ret = (uint32x2_t) __builtin_neon_vqshrun_n_v((int8x16_t)__rev0, __p1, 18); \
19511 #define __noswap_vqshrun_n_s64(__p0, __p1) __extension__ ({ \
19514 __ret = (uint32x2_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 18); \
19520 #define vqshrun_n_s16(__p0, __p1) __extension__ ({ \
19523 __ret = (uint8x8_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 16); \
19527 #define vqshrun_n_s16(__p0, __p1) __extension__ ({ \
19531 __ret = (uint8x8_t) __builtin_neon_vqshrun_n_v((int8x16_t)__rev0, __p1, 16); \
19535 #define __noswap_vqshrun_n_s16(__p0, __p1) __extension__ ({ \
19538 __ret = (uint8x8_t) __builtin_neon_vqshrun_n_v((int8x16_t)__s0, __p1, 16); \
19544 __ai uint8x16_t vqsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
19546 __ret = (uint8x16_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
19550 __ai uint8x16_t vqsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
19552 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
19561 __ai uint32x4_t vqsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
19563 __ret = (uint32x4_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
19567 __ai uint32x4_t vqsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
19569 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19578 __ai uint64x2_t vqsubq_u64(uint64x2_t __p0, uint64x2_t __p1) {
19580 __ret = (uint64x2_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
19584 __ai uint64x2_t vqsubq_u64(uint64x2_t __p0, uint64x2_t __p1) {
19586 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19595 __ai uint16x8_t vqsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
19597 __ret = (uint16x8_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
19601 __ai uint16x8_t vqsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
19603 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19612 __ai int8x16_t vqsubq_s8(int8x16_t __p0, int8x16_t __p1) {
19614 __ret = (int8x16_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
19618 __ai int8x16_t vqsubq_s8(int8x16_t __p0, int8x16_t __p1) {
19620 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
19629 __ai int32x4_t vqsubq_s32(int32x4_t __p0, int32x4_t __p1) {
19631 __ret = (int32x4_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
19635 __ai int32x4_t vqsubq_s32(int32x4_t __p0, int32x4_t __p1) {
19637 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19643 __ai int32x4_t __noswap_vqsubq_s32(int32x4_t __p0, int32x4_t __p1) {
19645 __ret = (int32x4_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
19651 __ai int64x2_t vqsubq_s64(int64x2_t __p0, int64x2_t __p1) {
19653 __ret = (int64x2_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
19657 __ai int64x2_t vqsubq_s64(int64x2_t __p0, int64x2_t __p1) {
19659 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19668 __ai int16x8_t vqsubq_s16(int16x8_t __p0, int16x8_t __p1) {
19670 __ret = (int16x8_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
19674 __ai int16x8_t vqsubq_s16(int16x8_t __p0, int16x8_t __p1) {
19676 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19682 __ai int16x8_t __noswap_vqsubq_s16(int16x8_t __p0, int16x8_t __p1) {
19684 __ret = (int16x8_t) __builtin_neon_vqsubq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
19690 __ai uint8x8_t vqsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
19692 __ret = (uint8x8_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
19696 __ai uint8x8_t vqsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
19698 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19707 __ai uint32x2_t vqsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
19709 __ret = (uint32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
19713 __ai uint32x2_t vqsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
19715 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19724 __ai uint64x1_t vqsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
19726 __ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19730 __ai uint64x1_t vqsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
19732 __ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19738 __ai uint16x4_t vqsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
19740 __ret = (uint16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
19744 __ai uint16x4_t vqsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
19746 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19755 __ai int8x8_t vqsub_s8(int8x8_t __p0, int8x8_t __p1) {
19757 __ret = (int8x8_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
19761 __ai int8x8_t vqsub_s8(int8x8_t __p0, int8x8_t __p1) {
19763 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19772 __ai int32x2_t vqsub_s32(int32x2_t __p0, int32x2_t __p1) {
19774 __ret = (int32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
19778 __ai int32x2_t vqsub_s32(int32x2_t __p0, int32x2_t __p1) {
19780 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19786 __ai int32x2_t __noswap_vqsub_s32(int32x2_t __p0, int32x2_t __p1) {
19788 __ret = (int32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
19794 __ai int64x1_t vqsub_s64(int64x1_t __p0, int64x1_t __p1) {
19796 __ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19800 __ai int64x1_t vqsub_s64(int64x1_t __p0, int64x1_t __p1) {
19802 __ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19808 __ai int16x4_t vqsub_s16(int16x4_t __p0, int16x4_t __p1) {
19810 __ret = (int16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
19814 __ai int16x4_t vqsub_s16(int16x4_t __p0, int16x4_t __p1) {
19816 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19822 __ai int16x4_t __noswap_vqsub_s16(int16x4_t __p0, int16x4_t __p1) {
19824 __ret = (int16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
19830 __ai uint16x4_t vraddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
19832 __ret = (uint16x4_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
19836 __ai uint16x4_t vraddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
19838 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19844 __ai uint16x4_t __noswap_vraddhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
19846 __ret = (uint16x4_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
19852 __ai uint32x2_t vraddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
19854 __ret = (uint32x2_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
19858 __ai uint32x2_t vraddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
19860 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19866 __ai uint32x2_t __noswap_vraddhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
19868 __ret = (uint32x2_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
19874 __ai uint8x8_t vraddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
19876 __ret = (uint8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
19880 __ai uint8x8_t vraddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
19882 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19888 __ai uint8x8_t __noswap_vraddhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
19890 __ret = (uint8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
19896 __ai int16x4_t vraddhn_s32(int32x4_t __p0, int32x4_t __p1) {
19898 __ret = (int16x4_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
19902 __ai int16x4_t vraddhn_s32(int32x4_t __p0, int32x4_t __p1) {
19904 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
19910 __ai int16x4_t __noswap_vraddhn_s32(int32x4_t __p0, int32x4_t __p1) {
19912 __ret = (int16x4_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
19918 __ai int32x2_t vraddhn_s64(int64x2_t __p0, int64x2_t __p1) {
19920 __ret = (int32x2_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
19924 __ai int32x2_t vraddhn_s64(int64x2_t __p0, int64x2_t __p1) {
19926 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
19932 __ai int32x2_t __noswap_vraddhn_s64(int64x2_t __p0, int64x2_t __p1) {
19934 __ret = (int32x2_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
19940 __ai int8x8_t vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
19942 __ret = (int8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
19946 __ai int8x8_t vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
19948 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19954 __ai int8x8_t __noswap_vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
19956 __ret = (int8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
20026 __ai float32x4_t vrecpsq_f32(float32x4_t __p0, float32x4_t __p1) {
20028 __ret = (float32x4_t) __builtin_neon_vrecpsq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
20032 __ai float32x4_t vrecpsq_f32(float32x4_t __p0, float32x4_t __p1) {
20034 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20043 __ai float32x2_t vrecps_f32(float32x2_t __p0, float32x2_t __p1) {
20045 __ret = (float32x2_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
20049 __ai float32x2_t vrecps_f32(float32x2_t __p0, float32x2_t __p1) {
20051 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
20636 __ai uint8x16_t vrhaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
20638 __ret = (uint8x16_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
20642 __ai uint8x16_t vrhaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
20644 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
20653 __ai uint32x4_t vrhaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
20655 __ret = (uint32x4_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
20659 __ai uint32x4_t vrhaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
20661 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20670 __ai uint16x8_t vrhaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
20672 __ret = (uint16x8_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
20676 __ai uint16x8_t vrhaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
20678 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20687 __ai int8x16_t vrhaddq_s8(int8x16_t __p0, int8x16_t __p1) {
20689 __ret = (int8x16_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
20693 __ai int8x16_t vrhaddq_s8(int8x16_t __p0, int8x16_t __p1) {
20695 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
20704 __ai int32x4_t vrhaddq_s32(int32x4_t __p0, int32x4_t __p1) {
20706 __ret = (int32x4_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
20710 __ai int32x4_t vrhaddq_s32(int32x4_t __p0, int32x4_t __p1) {
20712 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20721 __ai int16x8_t vrhaddq_s16(int16x8_t __p0, int16x8_t __p1) {
20723 __ret = (int16x8_t) __builtin_neon_vrhaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
20727 __ai int16x8_t vrhaddq_s16(int16x8_t __p0, int16x8_t __p1) {
20729 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20738 __ai uint8x8_t vrhadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
20740 __ret = (uint8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
20744 __ai uint8x8_t vrhadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
20746 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20755 __ai uint32x2_t vrhadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
20757 __ret = (uint32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
20761 __ai uint32x2_t vrhadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
20763 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
20772 __ai uint16x4_t vrhadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
20774 __ret = (uint16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
20778 __ai uint16x4_t vrhadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
20780 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20789 __ai int8x8_t vrhadd_s8(int8x8_t __p0, int8x8_t __p1) {
20791 __ret = (int8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
20795 __ai int8x8_t vrhadd_s8(int8x8_t __p0, int8x8_t __p1) {
20797 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20806 __ai int32x2_t vrhadd_s32(int32x2_t __p0, int32x2_t __p1) {
20808 __ret = (int32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
20812 __ai int32x2_t vrhadd_s32(int32x2_t __p0, int32x2_t __p1) {
20814 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
20823 __ai int16x4_t vrhadd_s16(int16x4_t __p0, int16x4_t __p1) {
20825 __ret = (int16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
20829 __ai int16x4_t vrhadd_s16(int16x4_t __p0, int16x4_t __p1) {
20831 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20840 __ai uint8x16_t vrshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
20842 __ret = (uint8x16_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
20846 __ai uint8x16_t vrshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
20848 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
20857 __ai uint32x4_t vrshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
20859 __ret = (uint32x4_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
20863 __ai uint32x4_t vrshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
20865 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20874 __ai uint64x2_t vrshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
20876 __ret = (uint64x2_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
20880 __ai uint64x2_t vrshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
20882 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
20891 __ai uint16x8_t vrshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
20893 __ret = (uint16x8_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
20897 __ai uint16x8_t vrshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
20899 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20908 __ai int8x16_t vrshlq_s8(int8x16_t __p0, int8x16_t __p1) {
20910 __ret = (int8x16_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
20914 __ai int8x16_t vrshlq_s8(int8x16_t __p0, int8x16_t __p1) {
20916 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
20925 __ai int32x4_t vrshlq_s32(int32x4_t __p0, int32x4_t __p1) {
20927 __ret = (int32x4_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
20931 __ai int32x4_t vrshlq_s32(int32x4_t __p0, int32x4_t __p1) {
20933 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
20942 __ai int64x2_t vrshlq_s64(int64x2_t __p0, int64x2_t __p1) {
20944 __ret = (int64x2_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
20948 __ai int64x2_t vrshlq_s64(int64x2_t __p0, int64x2_t __p1) {
20950 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
20959 __ai int16x8_t vrshlq_s16(int16x8_t __p0, int16x8_t __p1) {
20961 __ret = (int16x8_t) __builtin_neon_vrshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
20965 __ai int16x8_t vrshlq_s16(int16x8_t __p0, int16x8_t __p1) {
20967 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20976 __ai uint8x8_t vrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
20978 __ret = (uint8x8_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
20982 __ai uint8x8_t vrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
20984 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20993 __ai uint32x2_t vrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
20995 __ret = (uint32x2_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
20999 __ai uint32x2_t vrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
21001 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
21010 __ai uint64x1_t vrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
21012 __ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21016 __ai uint64x1_t vrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
21018 __ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21024 __ai uint16x4_t vrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
21026 __ret = (uint16x4_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
21030 __ai uint16x4_t vrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
21032 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
21041 __ai int8x8_t vrshl_s8(int8x8_t __p0, int8x8_t __p1) {
21043 __ret = (int8x8_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
21047 __ai int8x8_t vrshl_s8(int8x8_t __p0, int8x8_t __p1) {
21049 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
21058 __ai int32x2_t vrshl_s32(int32x2_t __p0, int32x2_t __p1) {
21060 __ret = (int32x2_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
21064 __ai int32x2_t vrshl_s32(int32x2_t __p0, int32x2_t __p1) {
21066 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
21075 __ai int64x1_t vrshl_s64(int64x1_t __p0, int64x1_t __p1) {
21077 __ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21081 __ai int64x1_t vrshl_s64(int64x1_t __p0, int64x1_t __p1) {
21083 __ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21089 __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {
21091 __ret = (int16x4_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
21095 __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {
21097 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
21106 #define vrshrq_n_u8(__p0, __p1) __extension__ ({ \
21109 __ret = (uint8x16_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 48); \
21113 #define vrshrq_n_u8(__p0, __p1) __extension__ ({ \
21117 __ret = (uint8x16_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 48); \
21124 #define vrshrq_n_u32(__p0, __p1) __extension__ ({ \
21127 __ret = (uint32x4_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 50); \
21131 #define vrshrq_n_u32(__p0, __p1) __extension__ ({ \
21135 __ret = (uint32x4_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 50); \
21142 #define vrshrq_n_u64(__p0, __p1) __extension__ ({ \
21145 __ret = (uint64x2_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 51); \
21149 #define vrshrq_n_u64(__p0, __p1) __extension__ ({ \
21153 __ret = (uint64x2_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 51); \
21160 #define vrshrq_n_u16(__p0, __p1) __extension__ ({ \
21163 __ret = (uint16x8_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 49); \
21167 #define vrshrq_n_u16(__p0, __p1) __extension__ ({ \
21171 __ret = (uint16x8_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 49); \
21178 #define vrshrq_n_s8(__p0, __p1) __extension__ ({ \
21181 __ret = (int8x16_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 32); \
21185 #define vrshrq_n_s8(__p0, __p1) __extension__ ({ \
21189 __ret = (int8x16_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 32); \
21196 #define vrshrq_n_s32(__p0, __p1) __extension__ ({ \
21199 __ret = (int32x4_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 34); \
21203 #define vrshrq_n_s32(__p0, __p1) __extension__ ({ \
21207 __ret = (int32x4_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 34); \
21214 #define vrshrq_n_s64(__p0, __p1) __extension__ ({ \
21217 __ret = (int64x2_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 35); \
21221 #define vrshrq_n_s64(__p0, __p1) __extension__ ({ \
21225 __ret = (int64x2_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 35); \
21232 #define vrshrq_n_s16(__p0, __p1) __extension__ ({ \
21235 __ret = (int16x8_t) __builtin_neon_vrshrq_n_v((int8x16_t)__s0, __p1, 33); \
21239 #define vrshrq_n_s16(__p0, __p1) __extension__ ({ \
21243 __ret = (int16x8_t) __builtin_neon_vrshrq_n_v((int8x16_t)__rev0, __p1, 33); \
21250 #define vrshr_n_u8(__p0, __p1) __extension__ ({ \
21253 __ret = (uint8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 16); \
21257 #define vrshr_n_u8(__p0, __p1) __extension__ ({ \
21261 __ret = (uint8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 16); \
21268 #define vrshr_n_u32(__p0, __p1) __extension__ ({ \
21271 __ret = (uint32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 18); \
21275 #define vrshr_n_u32(__p0, __p1) __extension__ ({ \
21279 __ret = (uint32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 18); \
21286 #define vrshr_n_u64(__p0, __p1) __extension__ ({ \
21289 __ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
21293 #define vrshr_n_u64(__p0, __p1) __extension__ ({ \
21296 __ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
21302 #define vrshr_n_u16(__p0, __p1) __extension__ ({ \
21305 __ret = (uint16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 17); \
21309 #define vrshr_n_u16(__p0, __p1) __extension__ ({ \
21313 __ret = (uint16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 17); \
21320 #define vrshr_n_s8(__p0, __p1) __extension__ ({ \
21323 __ret = (int8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 0); \
21327 #define vrshr_n_s8(__p0, __p1) __extension__ ({ \
21331 __ret = (int8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 0); \
21338 #define vrshr_n_s32(__p0, __p1) __extension__ ({ \
21341 __ret = (int32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 2); \
21345 #define vrshr_n_s32(__p0, __p1) __extension__ ({ \
21349 __ret = (int32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 2); \
21356 #define vrshr_n_s64(__p0, __p1) __extension__ ({ \
21359 __ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
21363 #define vrshr_n_s64(__p0, __p1) __extension__ ({ \
21366 __ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
21372 #define vrshr_n_s16(__p0, __p1) __extension__ ({ \
21375 __ret = (int16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 1); \
21379 #define vrshr_n_s16(__p0, __p1) __extension__ ({ \
21383 __ret = (int16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 1); \
21390 #define vrshrn_n_u32(__p0, __p1) __extension__ ({ \
21393 __ret = (uint16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 17); \
21397 #define vrshrn_n_u32(__p0, __p1) __extension__ ({ \
21401 __ret = (uint16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 17); \
21405 #define __noswap_vrshrn_n_u32(__p0, __p1) __extension__ ({ \
21408 __ret = (uint16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 17); \
21414 #define vrshrn_n_u64(__p0, __p1) __extension__ ({ \
21417 __ret = (uint32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 18); \
21421 #define vrshrn_n_u64(__p0, __p1) __extension__ ({ \
21425 __ret = (uint32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 18); \
21429 #define __noswap_vrshrn_n_u64(__p0, __p1) __extension__ ({ \
21432 __ret = (uint32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 18); \
21438 #define vrshrn_n_u16(__p0, __p1) __extension__ ({ \
21441 __ret = (uint8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 16); \
21445 #define vrshrn_n_u16(__p0, __p1) __extension__ ({ \
21449 __ret = (uint8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 16); \
21453 #define __noswap_vrshrn_n_u16(__p0, __p1) __extension__ ({ \
21456 __ret = (uint8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 16); \
21462 #define vrshrn_n_s32(__p0, __p1) __extension__ ({ \
21465 __ret = (int16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 1); \
21469 #define vrshrn_n_s32(__p0, __p1) __extension__ ({ \
21473 __ret = (int16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 1); \
21477 #define __noswap_vrshrn_n_s32(__p0, __p1) __extension__ ({ \
21480 __ret = (int16x4_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 1); \
21486 #define vrshrn_n_s64(__p0, __p1) __extension__ ({ \
21489 __ret = (int32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 2); \
21493 #define vrshrn_n_s64(__p0, __p1) __extension__ ({ \
21497 __ret = (int32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 2); \
21501 #define __noswap_vrshrn_n_s64(__p0, __p1) __extension__ ({ \
21504 __ret = (int32x2_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 2); \
21510 #define vrshrn_n_s16(__p0, __p1) __extension__ ({ \
21513 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 0); \
21517 #define vrshrn_n_s16(__p0, __p1) __extension__ ({ \
21521 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 0); \
21525 #define __noswap_vrshrn_n_s16(__p0, __p1) __extension__ ({ \
21528 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 0); \
21598 __ai float32x4_t vrsqrtsq_f32(float32x4_t __p0, float32x4_t __p1) {
21600 __ret = (float32x4_t) __builtin_neon_vrsqrtsq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
21604 __ai float32x4_t vrsqrtsq_f32(float32x4_t __p0, float32x4_t __p1) {
21606 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
21615 __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
21617 __ret = (float32x2_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
21621 __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
21623 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
21632 #define vrsraq_n_u8(__p0, __p1, __p2) __extension__ ({ \
21634 uint8x16_t __s1 = __p1; \
21640 #define vrsraq_n_u8(__p0, __p1, __p2) __extension__ ({ \
21642 uint8x16_t __s1 = __p1; \
21653 #define vrsraq_n_u32(__p0, __p1, __p2) __extension__ ({ \
21655 uint32x4_t __s1 = __p1; \
21661 #define vrsraq_n_u32(__p0, __p1, __p2) __extension__ ({ \
21663 uint32x4_t __s1 = __p1; \
21674 #define vrsraq_n_u64(__p0, __p1, __p2) __extension__ ({ \
21676 uint64x2_t __s1 = __p1; \
21682 #define vrsraq_n_u64(__p0, __p1, __p2) __extension__ ({ \
21684 uint64x2_t __s1 = __p1; \
21695 #define vrsraq_n_u16(__p0, __p1, __p2) __extension__ ({ \
21697 uint16x8_t __s1 = __p1; \
21703 #define vrsraq_n_u16(__p0, __p1, __p2) __extension__ ({ \
21705 uint16x8_t __s1 = __p1; \
21716 #define vrsraq_n_s8(__p0, __p1, __p2) __extension__ ({ \
21718 int8x16_t __s1 = __p1; \
21724 #define vrsraq_n_s8(__p0, __p1, __p2) __extension__ ({ \
21726 int8x16_t __s1 = __p1; \
21737 #define vrsraq_n_s32(__p0, __p1, __p2) __extension__ ({ \
21739 int32x4_t __s1 = __p1; \
21745 #define vrsraq_n_s32(__p0, __p1, __p2) __extension__ ({ \
21747 int32x4_t __s1 = __p1; \
21758 #define vrsraq_n_s64(__p0, __p1, __p2) __extension__ ({ \
21760 int64x2_t __s1 = __p1; \
21766 #define vrsraq_n_s64(__p0, __p1, __p2) __extension__ ({ \
21768 int64x2_t __s1 = __p1; \
21779 #define vrsraq_n_s16(__p0, __p1, __p2) __extension__ ({ \
21781 int16x8_t __s1 = __p1; \
21787 #define vrsraq_n_s16(__p0, __p1, __p2) __extension__ ({ \
21789 int16x8_t __s1 = __p1; \
21800 #define vrsra_n_u8(__p0, __p1, __p2) __extension__ ({ \
21802 uint8x8_t __s1 = __p1; \
21808 #define vrsra_n_u8(__p0, __p1, __p2) __extension__ ({ \
21810 uint8x8_t __s1 = __p1; \
21821 #define vrsra_n_u32(__p0, __p1, __p2) __extension__ ({ \
21823 uint32x2_t __s1 = __p1; \
21829 #define vrsra_n_u32(__p0, __p1, __p2) __extension__ ({ \
21831 uint32x2_t __s1 = __p1; \
21842 #define vrsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
21844 uint64x1_t __s1 = __p1; \
21850 #define vrsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
21852 uint64x1_t __s1 = __p1; \
21860 #define vrsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
21862 uint16x4_t __s1 = __p1; \
21868 #define vrsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
21870 uint16x4_t __s1 = __p1; \
21881 #define vrsra_n_s8(__p0, __p1, __p2) __extension__ ({ \
21883 int8x8_t __s1 = __p1; \
21889 #define vrsra_n_s8(__p0, __p1, __p2) __extension__ ({ \
21891 int8x8_t __s1 = __p1; \
21902 #define vrsra_n_s32(__p0, __p1, __p2) __extension__ ({ \
21904 int32x2_t __s1 = __p1; \
21910 #define vrsra_n_s32(__p0, __p1, __p2) __extension__ ({ \
21912 int32x2_t __s1 = __p1; \
21923 #define vrsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
21925 int64x1_t __s1 = __p1; \
21931 #define vrsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
21933 int64x1_t __s1 = __p1; \
21941 #define vrsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
21943 int16x4_t __s1 = __p1; \
21949 #define vrsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
21951 int16x4_t __s1 = __p1; \
21962 __ai uint16x4_t vrsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
21964 __ret = (uint16x4_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
21968 __ai uint16x4_t vrsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
21970 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
21976 __ai uint16x4_t __noswap_vrsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
21978 __ret = (uint16x4_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
21984 __ai uint32x2_t vrsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
21986 __ret = (uint32x2_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
21990 __ai uint32x2_t vrsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
21992 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
21998 __ai uint32x2_t __noswap_vrsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
22000 __ret = (uint32x2_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
22006 __ai uint8x8_t vrsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
22008 __ret = (uint8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
22012 __ai uint8x8_t vrsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
22014 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22020 __ai uint8x8_t __noswap_vrsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
22022 __ret = (uint8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
22028 __ai int16x4_t vrsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
22030 __ret = (int16x4_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
22034 __ai int16x4_t vrsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
22036 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
22042 __ai int16x4_t __noswap_vrsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
22044 __ret = (int16x4_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
22050 __ai int32x2_t vrsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
22052 __ret = (int32x2_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
22056 __ai int32x2_t vrsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
22058 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
22064 __ai int32x2_t __noswap_vrsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
22066 __ret = (int32x2_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
22072 __ai int8x8_t vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22074 __ret = (int8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
22078 __ai int8x8_t vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22080 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22086 __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22088 __ret = (int8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
22094 #define vset_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22096 poly8x8_t __s1 = __p1; \
22102 #define vset_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22104 poly8x8_t __s1 = __p1; \
22111 #define __noswap_vset_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22113 poly8x8_t __s1 = __p1; \
22121 #define vset_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22123 poly16x4_t __s1 = __p1; \
22129 #define vset_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22131 poly16x4_t __s1 = __p1; \
22138 #define __noswap_vset_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22140 poly16x4_t __s1 = __p1; \
22148 #define vsetq_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22150 poly8x16_t __s1 = __p1; \
22156 #define vsetq_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22158 poly8x16_t __s1 = __p1; \
22165 #define __noswap_vsetq_lane_p8(__p0, __p1, __p2) __extension__ ({ \
22167 poly8x16_t __s1 = __p1; \
22175 #define vsetq_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22177 poly16x8_t __s1 = __p1; \
22183 #define vsetq_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22185 poly16x8_t __s1 = __p1; \
22192 #define __noswap_vsetq_lane_p16(__p0, __p1, __p2) __extension__ ({ \
22194 poly16x8_t __s1 = __p1; \
22202 #define vsetq_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22204 uint8x16_t __s1 = __p1; \
22210 #define vsetq_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22212 uint8x16_t __s1 = __p1; \
22219 #define __noswap_vsetq_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22221 uint8x16_t __s1 = __p1; \
22229 #define vsetq_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22231 uint32x4_t __s1 = __p1; \
22237 #define vsetq_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22239 uint32x4_t __s1 = __p1; \
22246 #define __noswap_vsetq_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22248 uint32x4_t __s1 = __p1; \
22256 #define vsetq_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22258 uint64x2_t __s1 = __p1; \
22264 #define vsetq_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22266 uint64x2_t __s1 = __p1; \
22273 #define __noswap_vsetq_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22275 uint64x2_t __s1 = __p1; \
22283 #define vsetq_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22285 uint16x8_t __s1 = __p1; \
22291 #define vsetq_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22293 uint16x8_t __s1 = __p1; \
22300 #define __noswap_vsetq_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22302 uint16x8_t __s1 = __p1; \
22310 #define vsetq_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22312 int8x16_t __s1 = __p1; \
22318 #define vsetq_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22320 int8x16_t __s1 = __p1; \
22327 #define __noswap_vsetq_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22329 int8x16_t __s1 = __p1; \
22337 #define vsetq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22339 float32x4_t __s1 = __p1; \
22345 #define vsetq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22347 float32x4_t __s1 = __p1; \
22354 #define __noswap_vsetq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22356 float32x4_t __s1 = __p1; \
22364 #define vsetq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22366 int32x4_t __s1 = __p1; \
22372 #define vsetq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22374 int32x4_t __s1 = __p1; \
22381 #define __noswap_vsetq_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22383 int32x4_t __s1 = __p1; \
22391 #define vsetq_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22393 int64x2_t __s1 = __p1; \
22399 #define vsetq_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22401 int64x2_t __s1 = __p1; \
22408 #define __noswap_vsetq_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22410 int64x2_t __s1 = __p1; \
22418 #define vsetq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22420 int16x8_t __s1 = __p1; \
22426 #define vsetq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22428 int16x8_t __s1 = __p1; \
22435 #define __noswap_vsetq_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22437 int16x8_t __s1 = __p1; \
22445 #define vset_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22447 uint8x8_t __s1 = __p1; \
22453 #define vset_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22455 uint8x8_t __s1 = __p1; \
22462 #define __noswap_vset_lane_u8(__p0, __p1, __p2) __extension__ ({ \
22464 uint8x8_t __s1 = __p1; \
22472 #define vset_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22474 uint32x2_t __s1 = __p1; \
22480 #define vset_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22482 uint32x2_t __s1 = __p1; \
22489 #define __noswap_vset_lane_u32(__p0, __p1, __p2) __extension__ ({ \
22491 uint32x2_t __s1 = __p1; \
22499 #define vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22501 uint64x1_t __s1 = __p1; \
22507 #define vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22509 uint64x1_t __s1 = __p1; \
22514 #define __noswap_vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
22516 uint64x1_t __s1 = __p1; \
22524 #define vset_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22526 uint16x4_t __s1 = __p1; \
22532 #define vset_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22534 uint16x4_t __s1 = __p1; \
22541 #define __noswap_vset_lane_u16(__p0, __p1, __p2) __extension__ ({ \
22543 uint16x4_t __s1 = __p1; \
22551 #define vset_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22553 int8x8_t __s1 = __p1; \
22559 #define vset_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22561 int8x8_t __s1 = __p1; \
22568 #define __noswap_vset_lane_s8(__p0, __p1, __p2) __extension__ ({ \
22570 int8x8_t __s1 = __p1; \
22578 #define vset_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22580 float32x2_t __s1 = __p1; \
22586 #define vset_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22588 float32x2_t __s1 = __p1; \
22595 #define __noswap_vset_lane_f32(__p0, __p1, __p2) __extension__ ({ \
22597 float32x2_t __s1 = __p1; \
22605 #define vset_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22607 int32x2_t __s1 = __p1; \
22613 #define vset_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22615 int32x2_t __s1 = __p1; \
22622 #define __noswap_vset_lane_s32(__p0, __p1, __p2) __extension__ ({ \
22624 int32x2_t __s1 = __p1; \
22632 #define vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22634 int64x1_t __s1 = __p1; \
22640 #define vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22642 int64x1_t __s1 = __p1; \
22647 #define __noswap_vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
22649 int64x1_t __s1 = __p1; \
22657 #define vset_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22659 int16x4_t __s1 = __p1; \
22665 #define vset_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22667 int16x4_t __s1 = __p1; \
22674 #define __noswap_vset_lane_s16(__p0, __p1, __p2) __extension__ ({ \
22676 int16x4_t __s1 = __p1; \
22684 __ai uint8x16_t vshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
22686 __ret = (uint8x16_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
22690 __ai uint8x16_t vshlq_u8(uint8x16_t __p0, int8x16_t __p1) {
22692 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
22701 __ai uint32x4_t vshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
22703 __ret = (uint32x4_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
22707 __ai uint32x4_t vshlq_u32(uint32x4_t __p0, int32x4_t __p1) {
22709 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
22718 __ai uint64x2_t vshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
22720 __ret = (uint64x2_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
22724 __ai uint64x2_t vshlq_u64(uint64x2_t __p0, int64x2_t __p1) {
22726 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
22735 __ai uint16x8_t vshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
22737 __ret = (uint16x8_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
22741 __ai uint16x8_t vshlq_u16(uint16x8_t __p0, int16x8_t __p1) {
22743 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22752 __ai int8x16_t vshlq_s8(int8x16_t __p0, int8x16_t __p1) {
22754 __ret = (int8x16_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
22758 __ai int8x16_t vshlq_s8(int8x16_t __p0, int8x16_t __p1) {
22760 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
22769 __ai int32x4_t vshlq_s32(int32x4_t __p0, int32x4_t __p1) {
22771 __ret = (int32x4_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
22775 __ai int32x4_t vshlq_s32(int32x4_t __p0, int32x4_t __p1) {
22777 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
22786 __ai int64x2_t vshlq_s64(int64x2_t __p0, int64x2_t __p1) {
22788 __ret = (int64x2_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
22792 __ai int64x2_t vshlq_s64(int64x2_t __p0, int64x2_t __p1) {
22794 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
22803 __ai int16x8_t vshlq_s16(int16x8_t __p0, int16x8_t __p1) {
22805 __ret = (int16x8_t) __builtin_neon_vshlq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
22809 __ai int16x8_t vshlq_s16(int16x8_t __p0, int16x8_t __p1) {
22811 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22820 __ai uint8x8_t vshl_u8(uint8x8_t __p0, int8x8_t __p1) {
22822 __ret = (uint8x8_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
22826 __ai uint8x8_t vshl_u8(uint8x8_t __p0, int8x8_t __p1) {
22828 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22837 __ai uint32x2_t vshl_u32(uint32x2_t __p0, int32x2_t __p1) {
22839 __ret = (uint32x2_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
22843 __ai uint32x2_t vshl_u32(uint32x2_t __p0, int32x2_t __p1) {
22845 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
22854 __ai uint64x1_t vshl_u64(uint64x1_t __p0, int64x1_t __p1) {
22856 __ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22860 __ai uint64x1_t vshl_u64(uint64x1_t __p0, int64x1_t __p1) {
22862 __ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22868 __ai uint16x4_t vshl_u16(uint16x4_t __p0, int16x4_t __p1) {
22870 __ret = (uint16x4_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
22874 __ai uint16x4_t vshl_u16(uint16x4_t __p0, int16x4_t __p1) {
22876 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
22885 __ai int8x8_t vshl_s8(int8x8_t __p0, int8x8_t __p1) {
22887 __ret = (int8x8_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
22891 __ai int8x8_t vshl_s8(int8x8_t __p0, int8x8_t __p1) {
22893 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22902 __ai int32x2_t vshl_s32(int32x2_t __p0, int32x2_t __p1) {
22904 __ret = (int32x2_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
22908 __ai int32x2_t vshl_s32(int32x2_t __p0, int32x2_t __p1) {
22910 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
22919 __ai int64x1_t vshl_s64(int64x1_t __p0, int64x1_t __p1) {
22921 __ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
22925 __ai int64x1_t vshl_s64(int64x1_t __p0, int64x1_t __p1) {
22927 __ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
22933 __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
22935 __ret = (int16x4_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
22939 __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
22941 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
22950 #define vshlq_n_u8(__p0, __p1) __extension__ ({ \
22953 __ret = (uint8x16_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 48); \
22957 #define vshlq_n_u8(__p0, __p1) __extension__ ({ \
22961 __ret = (uint8x16_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 48); \
22968 #define vshlq_n_u32(__p0, __p1) __extension__ ({ \
22971 __ret = (uint32x4_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 50); \
22975 #define vshlq_n_u32(__p0, __p1) __extension__ ({ \
22979 __ret = (uint32x4_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 50); \
22986 #define vshlq_n_u64(__p0, __p1) __extension__ ({ \
22989 __ret = (uint64x2_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 51); \
22993 #define vshlq_n_u64(__p0, __p1) __extension__ ({ \
22997 __ret = (uint64x2_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 51); \
23004 #define vshlq_n_u16(__p0, __p1) __extension__ ({ \
23007 __ret = (uint16x8_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 49); \
23011 #define vshlq_n_u16(__p0, __p1) __extension__ ({ \
23015 __ret = (uint16x8_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 49); \
23022 #define vshlq_n_s8(__p0, __p1) __extension__ ({ \
23025 __ret = (int8x16_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 32); \
23029 #define vshlq_n_s8(__p0, __p1) __extension__ ({ \
23033 __ret = (int8x16_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 32); \
23040 #define vshlq_n_s32(__p0, __p1) __extension__ ({ \
23043 __ret = (int32x4_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 34); \
23047 #define vshlq_n_s32(__p0, __p1) __extension__ ({ \
23051 __ret = (int32x4_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 34); \
23058 #define vshlq_n_s64(__p0, __p1) __extension__ ({ \
23061 __ret = (int64x2_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 35); \
23065 #define vshlq_n_s64(__p0, __p1) __extension__ ({ \
23069 __ret = (int64x2_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 35); \
23076 #define vshlq_n_s16(__p0, __p1) __extension__ ({ \
23079 __ret = (int16x8_t) __builtin_neon_vshlq_n_v((int8x16_t)__s0, __p1, 33); \
23083 #define vshlq_n_s16(__p0, __p1) __extension__ ({ \
23087 __ret = (int16x8_t) __builtin_neon_vshlq_n_v((int8x16_t)__rev0, __p1, 33); \
23094 #define vshl_n_u8(__p0, __p1) __extension__ ({ \
23097 __ret = (uint8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 16); \
23101 #define vshl_n_u8(__p0, __p1) __extension__ ({ \
23105 __ret = (uint8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 16); \
23112 #define vshl_n_u32(__p0, __p1) __extension__ ({ \
23115 __ret = (uint32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 18); \
23119 #define vshl_n_u32(__p0, __p1) __extension__ ({ \
23123 __ret = (uint32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 18); \
23130 #define vshl_n_u64(__p0, __p1) __extension__ ({ \
23133 __ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
23137 #define vshl_n_u64(__p0, __p1) __extension__ ({ \
23140 __ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
23146 #define vshl_n_u16(__p0, __p1) __extension__ ({ \
23149 __ret = (uint16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 17); \
23153 #define vshl_n_u16(__p0, __p1) __extension__ ({ \
23157 __ret = (uint16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 17); \
23164 #define vshl_n_s8(__p0, __p1) __extension__ ({ \
23167 __ret = (int8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 0); \
23171 #define vshl_n_s8(__p0, __p1) __extension__ ({ \
23175 __ret = (int8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 0); \
23182 #define vshl_n_s32(__p0, __p1) __extension__ ({ \
23185 __ret = (int32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 2); \
23189 #define vshl_n_s32(__p0, __p1) __extension__ ({ \
23193 __ret = (int32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 2); \
23200 #define vshl_n_s64(__p0, __p1) __extension__ ({ \
23203 __ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
23207 #define vshl_n_s64(__p0, __p1) __extension__ ({ \
23210 __ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
23216 #define vshl_n_s16(__p0, __p1) __extension__ ({ \
23219 __ret = (int16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 1); \
23223 #define vshl_n_s16(__p0, __p1) __extension__ ({ \
23227 __ret = (int16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 1); \
23234 #define vshll_n_u8(__p0, __p1) __extension__ ({ \
23237 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 49); \
23241 #define vshll_n_u8(__p0, __p1) __extension__ ({ \
23245 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 49); \
23249 #define __noswap_vshll_n_u8(__p0, __p1) __extension__ ({ \
23252 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 49); \
23258 #define vshll_n_u32(__p0, __p1) __extension__ ({ \
23261 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 51); \
23265 #define vshll_n_u32(__p0, __p1) __extension__ ({ \
23269 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 51); \
23273 #define __noswap_vshll_n_u32(__p0, __p1) __extension__ ({ \
23276 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 51); \
23282 #define vshll_n_u16(__p0, __p1) __extension__ ({ \
23285 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 50); \
23289 #define vshll_n_u16(__p0, __p1) __extension__ ({ \
23293 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 50); \
23297 #define __noswap_vshll_n_u16(__p0, __p1) __extension__ ({ \
23300 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 50); \
23306 #define vshll_n_s8(__p0, __p1) __extension__ ({ \
23309 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 33); \
23313 #define vshll_n_s8(__p0, __p1) __extension__ ({ \
23317 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 33); \
23321 #define __noswap_vshll_n_s8(__p0, __p1) __extension__ ({ \
23324 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 33); \
23330 #define vshll_n_s32(__p0, __p1) __extension__ ({ \
23333 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 35); \
23337 #define vshll_n_s32(__p0, __p1) __extension__ ({ \
23341 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 35); \
23345 #define __noswap_vshll_n_s32(__p0, __p1) __extension__ ({ \
23348 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 35); \
23354 #define vshll_n_s16(__p0, __p1) __extension__ ({ \
23357 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 34); \
23361 #define vshll_n_s16(__p0, __p1) __extension__ ({ \
23365 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 34); \
23369 #define __noswap_vshll_n_s16(__p0, __p1) __extension__ ({ \
23372 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 34); \
23378 #define vshrq_n_u8(__p0, __p1) __extension__ ({ \
23381 __ret = (uint8x16_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 48); \
23385 #define vshrq_n_u8(__p0, __p1) __extension__ ({ \
23389 __ret = (uint8x16_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 48); \
23396 #define vshrq_n_u32(__p0, __p1) __extension__ ({ \
23399 __ret = (uint32x4_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 50); \
23403 #define vshrq_n_u32(__p0, __p1) __extension__ ({ \
23407 __ret = (uint32x4_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 50); \
23414 #define vshrq_n_u64(__p0, __p1) __extension__ ({ \
23417 __ret = (uint64x2_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 51); \
23421 #define vshrq_n_u64(__p0, __p1) __extension__ ({ \
23425 __ret = (uint64x2_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 51); \
23432 #define vshrq_n_u16(__p0, __p1) __extension__ ({ \
23435 __ret = (uint16x8_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 49); \
23439 #define vshrq_n_u16(__p0, __p1) __extension__ ({ \
23443 __ret = (uint16x8_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 49); \
23450 #define vshrq_n_s8(__p0, __p1) __extension__ ({ \
23453 __ret = (int8x16_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 32); \
23457 #define vshrq_n_s8(__p0, __p1) __extension__ ({ \
23461 __ret = (int8x16_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 32); \
23468 #define vshrq_n_s32(__p0, __p1) __extension__ ({ \
23471 __ret = (int32x4_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 34); \
23475 #define vshrq_n_s32(__p0, __p1) __extension__ ({ \
23479 __ret = (int32x4_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 34); \
23486 #define vshrq_n_s64(__p0, __p1) __extension__ ({ \
23489 __ret = (int64x2_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 35); \
23493 #define vshrq_n_s64(__p0, __p1) __extension__ ({ \
23497 __ret = (int64x2_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 35); \
23504 #define vshrq_n_s16(__p0, __p1) __extension__ ({ \
23507 __ret = (int16x8_t) __builtin_neon_vshrq_n_v((int8x16_t)__s0, __p1, 33); \
23511 #define vshrq_n_s16(__p0, __p1) __extension__ ({ \
23515 __ret = (int16x8_t) __builtin_neon_vshrq_n_v((int8x16_t)__rev0, __p1, 33); \
23522 #define vshr_n_u8(__p0, __p1) __extension__ ({ \
23525 __ret = (uint8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 16); \
23529 #define vshr_n_u8(__p0, __p1) __extension__ ({ \
23533 __ret = (uint8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 16); \
23540 #define vshr_n_u32(__p0, __p1) __extension__ ({ \
23543 __ret = (uint32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 18); \
23547 #define vshr_n_u32(__p0, __p1) __extension__ ({ \
23551 __ret = (uint32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 18); \
23558 #define vshr_n_u64(__p0, __p1) __extension__ ({ \
23561 __ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
23565 #define vshr_n_u64(__p0, __p1) __extension__ ({ \
23568 __ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
23574 #define vshr_n_u16(__p0, __p1) __extension__ ({ \
23577 __ret = (uint16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 17); \
23581 #define vshr_n_u16(__p0, __p1) __extension__ ({ \
23585 __ret = (uint16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 17); \
23592 #define vshr_n_s8(__p0, __p1) __extension__ ({ \
23595 __ret = (int8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 0); \
23599 #define vshr_n_s8(__p0, __p1) __extension__ ({ \
23603 __ret = (int8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 0); \
23610 #define vshr_n_s32(__p0, __p1) __extension__ ({ \
23613 __ret = (int32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 2); \
23617 #define vshr_n_s32(__p0, __p1) __extension__ ({ \
23621 __ret = (int32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 2); \
23628 #define vshr_n_s64(__p0, __p1) __extension__ ({ \
23631 __ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
23635 #define vshr_n_s64(__p0, __p1) __extension__ ({ \
23638 __ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
23644 #define vshr_n_s16(__p0, __p1) __extension__ ({ \
23647 __ret = (int16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 1); \
23651 #define vshr_n_s16(__p0, __p1) __extension__ ({ \
23655 __ret = (int16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 1); \
23662 #define vshrn_n_u32(__p0, __p1) __extension__ ({ \
23665 __ret = (uint16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 17); \
23669 #define vshrn_n_u32(__p0, __p1) __extension__ ({ \
23673 __ret = (uint16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 17); \
23677 #define __noswap_vshrn_n_u32(__p0, __p1) __extension__ ({ \
23680 __ret = (uint16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 17); \
23686 #define vshrn_n_u64(__p0, __p1) __extension__ ({ \
23689 __ret = (uint32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 18); \
23693 #define vshrn_n_u64(__p0, __p1) __extension__ ({ \
23697 __ret = (uint32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 18); \
23701 #define __noswap_vshrn_n_u64(__p0, __p1) __extension__ ({ \
23704 __ret = (uint32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 18); \
23710 #define vshrn_n_u16(__p0, __p1) __extension__ ({ \
23713 __ret = (uint8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 16); \
23717 #define vshrn_n_u16(__p0, __p1) __extension__ ({ \
23721 __ret = (uint8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 16); \
23725 #define __noswap_vshrn_n_u16(__p0, __p1) __extension__ ({ \
23728 __ret = (uint8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 16); \
23734 #define vshrn_n_s32(__p0, __p1) __extension__ ({ \
23737 __ret = (int16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 1); \
23741 #define vshrn_n_s32(__p0, __p1) __extension__ ({ \
23745 __ret = (int16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 1); \
23749 #define __noswap_vshrn_n_s32(__p0, __p1) __extension__ ({ \
23752 __ret = (int16x4_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 1); \
23758 #define vshrn_n_s64(__p0, __p1) __extension__ ({ \
23761 __ret = (int32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 2); \
23765 #define vshrn_n_s64(__p0, __p1) __extension__ ({ \
23769 __ret = (int32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 2); \
23773 #define __noswap_vshrn_n_s64(__p0, __p1) __extension__ ({ \
23776 __ret = (int32x2_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 2); \
23782 #define vshrn_n_s16(__p0, __p1) __extension__ ({ \
23785 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 0); \
23789 #define vshrn_n_s16(__p0, __p1) __extension__ ({ \
23793 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 0); \
23797 #define __noswap_vshrn_n_s16(__p0, __p1) __extension__ ({ \
23800 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 0); \
23806 #define vsli_n_p8(__p0, __p1, __p2) __extension__ ({ \
23808 poly8x8_t __s1 = __p1; \
23814 #define vsli_n_p8(__p0, __p1, __p2) __extension__ ({ \
23816 poly8x8_t __s1 = __p1; \
23827 #define vsli_n_p16(__p0, __p1, __p2) __extension__ ({ \
23829 poly16x4_t __s1 = __p1; \
23835 #define vsli_n_p16(__p0, __p1, __p2) __extension__ ({ \
23837 poly16x4_t __s1 = __p1; \
23848 #define vsliq_n_p8(__p0, __p1, __p2) __extension__ ({ \
23850 poly8x16_t __s1 = __p1; \
23856 #define vsliq_n_p8(__p0, __p1, __p2) __extension__ ({ \
23858 poly8x16_t __s1 = __p1; \
23869 #define vsliq_n_p16(__p0, __p1, __p2) __extension__ ({ \
23871 poly16x8_t __s1 = __p1; \
23877 #define vsliq_n_p16(__p0, __p1, __p2) __extension__ ({ \
23879 poly16x8_t __s1 = __p1; \
23890 #define vsliq_n_u8(__p0, __p1, __p2) __extension__ ({ \
23892 uint8x16_t __s1 = __p1; \
23898 #define vsliq_n_u8(__p0, __p1, __p2) __extension__ ({ \
23900 uint8x16_t __s1 = __p1; \
23911 #define vsliq_n_u32(__p0, __p1, __p2) __extension__ ({ \
23913 uint32x4_t __s1 = __p1; \
23919 #define vsliq_n_u32(__p0, __p1, __p2) __extension__ ({ \
23921 uint32x4_t __s1 = __p1; \
23932 #define vsliq_n_u64(__p0, __p1, __p2) __extension__ ({ \
23934 uint64x2_t __s1 = __p1; \
23940 #define vsliq_n_u64(__p0, __p1, __p2) __extension__ ({ \
23942 uint64x2_t __s1 = __p1; \
23953 #define vsliq_n_u16(__p0, __p1, __p2) __extension__ ({ \
23955 uint16x8_t __s1 = __p1; \
23961 #define vsliq_n_u16(__p0, __p1, __p2) __extension__ ({ \
23963 uint16x8_t __s1 = __p1; \
23974 #define vsliq_n_s8(__p0, __p1, __p2) __extension__ ({ \
23976 int8x16_t __s1 = __p1; \
23982 #define vsliq_n_s8(__p0, __p1, __p2) __extension__ ({ \
23984 int8x16_t __s1 = __p1; \
23995 #define vsliq_n_s32(__p0, __p1, __p2) __extension__ ({ \
23997 int32x4_t __s1 = __p1; \
24003 #define vsliq_n_s32(__p0, __p1, __p2) __extension__ ({ \
24005 int32x4_t __s1 = __p1; \
24016 #define vsliq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24018 int64x2_t __s1 = __p1; \
24024 #define vsliq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24026 int64x2_t __s1 = __p1; \
24037 #define vsliq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24039 int16x8_t __s1 = __p1; \
24045 #define vsliq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24047 int16x8_t __s1 = __p1; \
24058 #define vsli_n_u8(__p0, __p1, __p2) __extension__ ({ \
24060 uint8x8_t __s1 = __p1; \
24066 #define vsli_n_u8(__p0, __p1, __p2) __extension__ ({ \
24068 uint8x8_t __s1 = __p1; \
24079 #define vsli_n_u32(__p0, __p1, __p2) __extension__ ({ \
24081 uint32x2_t __s1 = __p1; \
24087 #define vsli_n_u32(__p0, __p1, __p2) __extension__ ({ \
24089 uint32x2_t __s1 = __p1; \
24100 #define vsli_n_u64(__p0, __p1, __p2) __extension__ ({ \
24102 uint64x1_t __s1 = __p1; \
24108 #define vsli_n_u64(__p0, __p1, __p2) __extension__ ({ \
24110 uint64x1_t __s1 = __p1; \
24118 #define vsli_n_u16(__p0, __p1, __p2) __extension__ ({ \
24120 uint16x4_t __s1 = __p1; \
24126 #define vsli_n_u16(__p0, __p1, __p2) __extension__ ({ \
24128 uint16x4_t __s1 = __p1; \
24139 #define vsli_n_s8(__p0, __p1, __p2) __extension__ ({ \
24141 int8x8_t __s1 = __p1; \
24147 #define vsli_n_s8(__p0, __p1, __p2) __extension__ ({ \
24149 int8x8_t __s1 = __p1; \
24160 #define vsli_n_s32(__p0, __p1, __p2) __extension__ ({ \
24162 int32x2_t __s1 = __p1; \
24168 #define vsli_n_s32(__p0, __p1, __p2) __extension__ ({ \
24170 int32x2_t __s1 = __p1; \
24181 #define vsli_n_s64(__p0, __p1, __p2) __extension__ ({ \
24183 int64x1_t __s1 = __p1; \
24189 #define vsli_n_s64(__p0, __p1, __p2) __extension__ ({ \
24191 int64x1_t __s1 = __p1; \
24199 #define vsli_n_s16(__p0, __p1, __p2) __extension__ ({ \
24201 int16x4_t __s1 = __p1; \
24207 #define vsli_n_s16(__p0, __p1, __p2) __extension__ ({ \
24209 int16x4_t __s1 = __p1; \
24220 #define vsraq_n_u8(__p0, __p1, __p2) __extension__ ({ \
24222 uint8x16_t __s1 = __p1; \
24228 #define vsraq_n_u8(__p0, __p1, __p2) __extension__ ({ \
24230 uint8x16_t __s1 = __p1; \
24241 #define vsraq_n_u32(__p0, __p1, __p2) __extension__ ({ \
24243 uint32x4_t __s1 = __p1; \
24249 #define vsraq_n_u32(__p0, __p1, __p2) __extension__ ({ \
24251 uint32x4_t __s1 = __p1; \
24262 #define vsraq_n_u64(__p0, __p1, __p2) __extension__ ({ \
24264 uint64x2_t __s1 = __p1; \
24270 #define vsraq_n_u64(__p0, __p1, __p2) __extension__ ({ \
24272 uint64x2_t __s1 = __p1; \
24283 #define vsraq_n_u16(__p0, __p1, __p2) __extension__ ({ \
24285 uint16x8_t __s1 = __p1; \
24291 #define vsraq_n_u16(__p0, __p1, __p2) __extension__ ({ \
24293 uint16x8_t __s1 = __p1; \
24304 #define vsraq_n_s8(__p0, __p1, __p2) __extension__ ({ \
24306 int8x16_t __s1 = __p1; \
24312 #define vsraq_n_s8(__p0, __p1, __p2) __extension__ ({ \
24314 int8x16_t __s1 = __p1; \
24325 #define vsraq_n_s32(__p0, __p1, __p2) __extension__ ({ \
24327 int32x4_t __s1 = __p1; \
24333 #define vsraq_n_s32(__p0, __p1, __p2) __extension__ ({ \
24335 int32x4_t __s1 = __p1; \
24346 #define vsraq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24348 int64x2_t __s1 = __p1; \
24354 #define vsraq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24356 int64x2_t __s1 = __p1; \
24367 #define vsraq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24369 int16x8_t __s1 = __p1; \
24375 #define vsraq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24377 int16x8_t __s1 = __p1; \
24388 #define vsra_n_u8(__p0, __p1, __p2) __extension__ ({ \
24390 uint8x8_t __s1 = __p1; \
24396 #define vsra_n_u8(__p0, __p1, __p2) __extension__ ({ \
24398 uint8x8_t __s1 = __p1; \
24409 #define vsra_n_u32(__p0, __p1, __p2) __extension__ ({ \
24411 uint32x2_t __s1 = __p1; \
24417 #define vsra_n_u32(__p0, __p1, __p2) __extension__ ({ \
24419 uint32x2_t __s1 = __p1; \
24430 #define vsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
24432 uint64x1_t __s1 = __p1; \
24438 #define vsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
24440 uint64x1_t __s1 = __p1; \
24448 #define vsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
24450 uint16x4_t __s1 = __p1; \
24456 #define vsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
24458 uint16x4_t __s1 = __p1; \
24469 #define vsra_n_s8(__p0, __p1, __p2) __extension__ ({ \
24471 int8x8_t __s1 = __p1; \
24477 #define vsra_n_s8(__p0, __p1, __p2) __extension__ ({ \
24479 int8x8_t __s1 = __p1; \
24490 #define vsra_n_s32(__p0, __p1, __p2) __extension__ ({ \
24492 int32x2_t __s1 = __p1; \
24498 #define vsra_n_s32(__p0, __p1, __p2) __extension__ ({ \
24500 int32x2_t __s1 = __p1; \
24511 #define vsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
24513 int64x1_t __s1 = __p1; \
24519 #define vsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
24521 int64x1_t __s1 = __p1; \
24529 #define vsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
24531 int16x4_t __s1 = __p1; \
24537 #define vsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
24539 int16x4_t __s1 = __p1; \
24550 #define vsri_n_p8(__p0, __p1, __p2) __extension__ ({ \
24552 poly8x8_t __s1 = __p1; \
24558 #define vsri_n_p8(__p0, __p1, __p2) __extension__ ({ \
24560 poly8x8_t __s1 = __p1; \
24571 #define vsri_n_p16(__p0, __p1, __p2) __extension__ ({ \
24573 poly16x4_t __s1 = __p1; \
24579 #define vsri_n_p16(__p0, __p1, __p2) __extension__ ({ \
24581 poly16x4_t __s1 = __p1; \
24592 #define vsriq_n_p8(__p0, __p1, __p2) __extension__ ({ \
24594 poly8x16_t __s1 = __p1; \
24600 #define vsriq_n_p8(__p0, __p1, __p2) __extension__ ({ \
24602 poly8x16_t __s1 = __p1; \
24613 #define vsriq_n_p16(__p0, __p1, __p2) __extension__ ({ \
24615 poly16x8_t __s1 = __p1; \
24621 #define vsriq_n_p16(__p0, __p1, __p2) __extension__ ({ \
24623 poly16x8_t __s1 = __p1; \
24634 #define vsriq_n_u8(__p0, __p1, __p2) __extension__ ({ \
24636 uint8x16_t __s1 = __p1; \
24642 #define vsriq_n_u8(__p0, __p1, __p2) __extension__ ({ \
24644 uint8x16_t __s1 = __p1; \
24655 #define vsriq_n_u32(__p0, __p1, __p2) __extension__ ({ \
24657 uint32x4_t __s1 = __p1; \
24663 #define vsriq_n_u32(__p0, __p1, __p2) __extension__ ({ \
24665 uint32x4_t __s1 = __p1; \
24676 #define vsriq_n_u64(__p0, __p1, __p2) __extension__ ({ \
24678 uint64x2_t __s1 = __p1; \
24684 #define vsriq_n_u64(__p0, __p1, __p2) __extension__ ({ \
24686 uint64x2_t __s1 = __p1; \
24697 #define vsriq_n_u16(__p0, __p1, __p2) __extension__ ({ \
24699 uint16x8_t __s1 = __p1; \
24705 #define vsriq_n_u16(__p0, __p1, __p2) __extension__ ({ \
24707 uint16x8_t __s1 = __p1; \
24718 #define vsriq_n_s8(__p0, __p1, __p2) __extension__ ({ \
24720 int8x16_t __s1 = __p1; \
24726 #define vsriq_n_s8(__p0, __p1, __p2) __extension__ ({ \
24728 int8x16_t __s1 = __p1; \
24739 #define vsriq_n_s32(__p0, __p1, __p2) __extension__ ({ \
24741 int32x4_t __s1 = __p1; \
24747 #define vsriq_n_s32(__p0, __p1, __p2) __extension__ ({ \
24749 int32x4_t __s1 = __p1; \
24760 #define vsriq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24762 int64x2_t __s1 = __p1; \
24768 #define vsriq_n_s64(__p0, __p1, __p2) __extension__ ({ \
24770 int64x2_t __s1 = __p1; \
24781 #define vsriq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24783 int16x8_t __s1 = __p1; \
24789 #define vsriq_n_s16(__p0, __p1, __p2) __extension__ ({ \
24791 int16x8_t __s1 = __p1; \
24802 #define vsri_n_u8(__p0, __p1, __p2) __extension__ ({ \
24804 uint8x8_t __s1 = __p1; \
24810 #define vsri_n_u8(__p0, __p1, __p2) __extension__ ({ \
24812 uint8x8_t __s1 = __p1; \
24823 #define vsri_n_u32(__p0, __p1, __p2) __extension__ ({ \
24825 uint32x2_t __s1 = __p1; \
24831 #define vsri_n_u32(__p0, __p1, __p2) __extension__ ({ \
24833 uint32x2_t __s1 = __p1; \
24844 #define vsri_n_u64(__p0, __p1, __p2) __extension__ ({ \
24846 uint64x1_t __s1 = __p1; \
24852 #define vsri_n_u64(__p0, __p1, __p2) __extension__ ({ \
24854 uint64x1_t __s1 = __p1; \
24862 #define vsri_n_u16(__p0, __p1, __p2) __extension__ ({ \
24864 uint16x4_t __s1 = __p1; \
24870 #define vsri_n_u16(__p0, __p1, __p2) __extension__ ({ \
24872 uint16x4_t __s1 = __p1; \
24883 #define vsri_n_s8(__p0, __p1, __p2) __extension__ ({ \
24885 int8x8_t __s1 = __p1; \
24891 #define vsri_n_s8(__p0, __p1, __p2) __extension__ ({ \
24893 int8x8_t __s1 = __p1; \
24904 #define vsri_n_s32(__p0, __p1, __p2) __extension__ ({ \
24906 int32x2_t __s1 = __p1; \
24912 #define vsri_n_s32(__p0, __p1, __p2) __extension__ ({ \
24914 int32x2_t __s1 = __p1; \
24925 #define vsri_n_s64(__p0, __p1, __p2) __extension__ ({ \
24927 int64x1_t __s1 = __p1; \
24933 #define vsri_n_s64(__p0, __p1, __p2) __extension__ ({ \
24935 int64x1_t __s1 = __p1; \
24943 #define vsri_n_s16(__p0, __p1, __p2) __extension__ ({ \
24945 int16x4_t __s1 = __p1; \
24951 #define vsri_n_s16(__p0, __p1, __p2) __extension__ ({ \
24953 int16x4_t __s1 = __p1; \
24964 #define vst1_p8(__p0, __p1) __extension__ ({ \
24965 poly8x8_t __s1 = __p1; \
24969 #define vst1_p8(__p0, __p1) __extension__ ({ \
24970 poly8x8_t __s1 = __p1; \
24977 #define vst1_p16(__p0, __p1) __extension__ ({ \
24978 poly16x4_t __s1 = __p1; \
24982 #define vst1_p16(__p0, __p1) __extension__ ({ \
24983 poly16x4_t __s1 = __p1; \
24990 #define vst1q_p8(__p0, __p1) __extension__ ({ \
24991 poly8x16_t __s1 = __p1; \
24995 #define vst1q_p8(__p0, __p1) __extension__ ({ \
24996 poly8x16_t __s1 = __p1; \
25003 #define vst1q_p16(__p0, __p1) __extension__ ({ \
25004 poly16x8_t __s1 = __p1; \
25008 #define vst1q_p16(__p0, __p1) __extension__ ({ \
25009 poly16x8_t __s1 = __p1; \
25016 #define vst1q_u8(__p0, __p1) __extension__ ({ \
25017 uint8x16_t __s1 = __p1; \
25021 #define vst1q_u8(__p0, __p1) __extension__ ({ \
25022 uint8x16_t __s1 = __p1; \
25029 #define vst1q_u32(__p0, __p1) __extension__ ({ \
25030 uint32x4_t __s1 = __p1; \
25034 #define vst1q_u32(__p0, __p1) __extension__ ({ \
25035 uint32x4_t __s1 = __p1; \
25042 #define vst1q_u64(__p0, __p1) __extension__ ({ \
25043 uint64x2_t __s1 = __p1; \
25047 #define vst1q_u64(__p0, __p1) __extension__ ({ \
25048 uint64x2_t __s1 = __p1; \
25055 #define vst1q_u16(__p0, __p1) __extension__ ({ \
25056 uint16x8_t __s1 = __p1; \
25060 #define vst1q_u16(__p0, __p1) __extension__ ({ \
25061 uint16x8_t __s1 = __p1; \
25068 #define vst1q_s8(__p0, __p1) __extension__ ({ \
25069 int8x16_t __s1 = __p1; \
25073 #define vst1q_s8(__p0, __p1) __extension__ ({ \
25074 int8x16_t __s1 = __p1; \
25081 #define vst1q_f32(__p0, __p1) __extension__ ({ \
25082 float32x4_t __s1 = __p1; \
25086 #define vst1q_f32(__p0, __p1) __extension__ ({ \
25087 float32x4_t __s1 = __p1; \
25094 #define vst1q_f16(__p0, __p1) __extension__ ({ \
25095 float16x8_t __s1 = __p1; \
25099 #define vst1q_f16(__p0, __p1) __extension__ ({ \
25100 float16x8_t __s1 = __p1; \
25107 #define vst1q_s32(__p0, __p1) __extension__ ({ \
25108 int32x4_t __s1 = __p1; \
25112 #define vst1q_s32(__p0, __p1) __extension__ ({ \
25113 int32x4_t __s1 = __p1; \
25120 #define vst1q_s64(__p0, __p1) __extension__ ({ \
25121 int64x2_t __s1 = __p1; \
25125 #define vst1q_s64(__p0, __p1) __extension__ ({ \
25126 int64x2_t __s1 = __p1; \
25133 #define vst1q_s16(__p0, __p1) __extension__ ({ \
25134 int16x8_t __s1 = __p1; \
25138 #define vst1q_s16(__p0, __p1) __extension__ ({ \
25139 int16x8_t __s1 = __p1; \
25146 #define vst1_u8(__p0, __p1) __extension__ ({ \
25147 uint8x8_t __s1 = __p1; \
25151 #define vst1_u8(__p0, __p1) __extension__ ({ \
25152 uint8x8_t __s1 = __p1; \
25159 #define vst1_u32(__p0, __p1) __extension__ ({ \
25160 uint32x2_t __s1 = __p1; \
25164 #define vst1_u32(__p0, __p1) __extension__ ({ \
25165 uint32x2_t __s1 = __p1; \
25172 #define vst1_u64(__p0, __p1) __extension__ ({ \
25173 uint64x1_t __s1 = __p1; \
25177 #define vst1_u64(__p0, __p1) __extension__ ({ \
25178 uint64x1_t __s1 = __p1; \
25184 #define vst1_u16(__p0, __p1) __extension__ ({ \
25185 uint16x4_t __s1 = __p1; \
25189 #define vst1_u16(__p0, __p1) __extension__ ({ \
25190 uint16x4_t __s1 = __p1; \
25197 #define vst1_s8(__p0, __p1) __extension__ ({ \
25198 int8x8_t __s1 = __p1; \
25202 #define vst1_s8(__p0, __p1) __extension__ ({ \
25203 int8x8_t __s1 = __p1; \
25210 #define vst1_f32(__p0, __p1) __extension__ ({ \
25211 float32x2_t __s1 = __p1; \
25215 #define vst1_f32(__p0, __p1) __extension__ ({ \
25216 float32x2_t __s1 = __p1; \
25223 #define vst1_f16(__p0, __p1) __extension__ ({ \
25224 float16x4_t __s1 = __p1; \
25228 #define vst1_f16(__p0, __p1) __extension__ ({ \
25229 float16x4_t __s1 = __p1; \
25236 #define vst1_s32(__p0, __p1) __extension__ ({ \
25237 int32x2_t __s1 = __p1; \
25241 #define vst1_s32(__p0, __p1) __extension__ ({ \
25242 int32x2_t __s1 = __p1; \
25249 #define vst1_s64(__p0, __p1) __extension__ ({ \
25250 int64x1_t __s1 = __p1; \
25254 #define vst1_s64(__p0, __p1) __extension__ ({ \
25255 int64x1_t __s1 = __p1; \
25261 #define vst1_s16(__p0, __p1) __extension__ ({ \
25262 int16x4_t __s1 = __p1; \
25266 #define vst1_s16(__p0, __p1) __extension__ ({ \
25267 int16x4_t __s1 = __p1; \
25274 #define vst1_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25275 poly8x8_t __s1 = __p1; \
25279 #define vst1_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25280 poly8x8_t __s1 = __p1; \
25287 #define vst1_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25288 poly16x4_t __s1 = __p1; \
25292 #define vst1_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25293 poly16x4_t __s1 = __p1; \
25300 #define vst1q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25301 poly8x16_t __s1 = __p1; \
25305 #define vst1q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25306 poly8x16_t __s1 = __p1; \
25313 #define vst1q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25314 poly16x8_t __s1 = __p1; \
25318 #define vst1q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25319 poly16x8_t __s1 = __p1; \
25326 #define vst1q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
25327 uint8x16_t __s1 = __p1; \
25331 #define vst1q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
25332 uint8x16_t __s1 = __p1; \
25339 #define vst1q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25340 uint32x4_t __s1 = __p1; \
25344 #define vst1q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25345 uint32x4_t __s1 = __p1; \
25352 #define vst1q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
25353 uint64x2_t __s1 = __p1; \
25357 #define vst1q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
25358 uint64x2_t __s1 = __p1; \
25365 #define vst1q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25366 uint16x8_t __s1 = __p1; \
25370 #define vst1q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25371 uint16x8_t __s1 = __p1; \
25378 #define vst1q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
25379 int8x16_t __s1 = __p1; \
25383 #define vst1q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
25384 int8x16_t __s1 = __p1; \
25391 #define vst1q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25392 float32x4_t __s1 = __p1; \
25396 #define vst1q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25397 float32x4_t __s1 = __p1; \
25404 #define vst1q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
25405 float16x8_t __s1 = __p1; \
25409 #define vst1q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
25410 float16x8_t __s1 = __p1; \
25417 #define vst1q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
25418 int32x4_t __s1 = __p1; \
25422 #define vst1q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
25423 int32x4_t __s1 = __p1; \
25430 #define vst1q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
25431 int64x2_t __s1 = __p1; \
25435 #define vst1q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
25436 int64x2_t __s1 = __p1; \
25443 #define vst1q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
25444 int16x8_t __s1 = __p1; \
25448 #define vst1q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
25449 int16x8_t __s1 = __p1; \
25456 #define vst1_lane_u8(__p0, __p1, __p2) __extension__ ({ \
25457 uint8x8_t __s1 = __p1; \
25461 #define vst1_lane_u8(__p0, __p1, __p2) __extension__ ({ \
25462 uint8x8_t __s1 = __p1; \
25469 #define vst1_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25470 uint32x2_t __s1 = __p1; \
25474 #define vst1_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25475 uint32x2_t __s1 = __p1; \
25482 #define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
25483 uint64x1_t __s1 = __p1; \
25487 #define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
25488 uint64x1_t __s1 = __p1; \
25494 #define vst1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25495 uint16x4_t __s1 = __p1; \
25499 #define vst1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25500 uint16x4_t __s1 = __p1; \
25507 #define vst1_lane_s8(__p0, __p1, __p2) __extension__ ({ \
25508 int8x8_t __s1 = __p1; \
25512 #define vst1_lane_s8(__p0, __p1, __p2) __extension__ ({ \
25513 int8x8_t __s1 = __p1; \
25520 #define vst1_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25521 float32x2_t __s1 = __p1; \
25525 #define vst1_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25526 float32x2_t __s1 = __p1; \
25533 #define vst1_lane_f16(__p0, __p1, __p2) __extension__ ({ \
25534 float16x4_t __s1 = __p1; \
25538 #define vst1_lane_f16(__p0, __p1, __p2) __extension__ ({ \
25539 float16x4_t __s1 = __p1; \
25546 #define vst1_lane_s32(__p0, __p1, __p2) __extension__ ({ \
25547 int32x2_t __s1 = __p1; \
25551 #define vst1_lane_s32(__p0, __p1, __p2) __extension__ ({ \
25552 int32x2_t __s1 = __p1; \
25559 #define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
25560 int64x1_t __s1 = __p1; \
25564 #define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
25565 int64x1_t __s1 = __p1; \
25571 #define vst1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
25572 int16x4_t __s1 = __p1; \
25576 #define vst1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
25577 int16x4_t __s1 = __p1; \
25584 #define vst2_p8(__p0, __p1) __extension__ ({ \
25585 poly8x8x2_t __s1 = __p1; \
25589 #define vst2_p8(__p0, __p1) __extension__ ({ \
25590 poly8x8x2_t __s1 = __p1; \
25599 #define vst2_p16(__p0, __p1) __extension__ ({ \
25600 poly16x4x2_t __s1 = __p1; \
25604 #define vst2_p16(__p0, __p1) __extension__ ({ \
25605 poly16x4x2_t __s1 = __p1; \
25614 #define vst2q_p8(__p0, __p1) __extension__ ({ \
25615 poly8x16x2_t __s1 = __p1; \
25619 #define vst2q_p8(__p0, __p1) __extension__ ({ \
25620 poly8x16x2_t __s1 = __p1; \
25629 #define vst2q_p16(__p0, __p1) __extension__ ({ \
25630 poly16x8x2_t __s1 = __p1; \
25634 #define vst2q_p16(__p0, __p1) __extension__ ({ \
25635 poly16x8x2_t __s1 = __p1; \
25644 #define vst2q_u8(__p0, __p1) __extension__ ({ \
25645 uint8x16x2_t __s1 = __p1; \
25649 #define vst2q_u8(__p0, __p1) __extension__ ({ \
25650 uint8x16x2_t __s1 = __p1; \
25659 #define vst2q_u32(__p0, __p1) __extension__ ({ \
25660 uint32x4x2_t __s1 = __p1; \
25664 #define vst2q_u32(__p0, __p1) __extension__ ({ \
25665 uint32x4x2_t __s1 = __p1; \
25674 #define vst2q_u16(__p0, __p1) __extension__ ({ \
25675 uint16x8x2_t __s1 = __p1; \
25679 #define vst2q_u16(__p0, __p1) __extension__ ({ \
25680 uint16x8x2_t __s1 = __p1; \
25689 #define vst2q_s8(__p0, __p1) __extension__ ({ \
25690 int8x16x2_t __s1 = __p1; \
25694 #define vst2q_s8(__p0, __p1) __extension__ ({ \
25695 int8x16x2_t __s1 = __p1; \
25704 #define vst2q_f32(__p0, __p1) __extension__ ({ \
25705 float32x4x2_t __s1 = __p1; \
25709 #define vst2q_f32(__p0, __p1) __extension__ ({ \
25710 float32x4x2_t __s1 = __p1; \
25719 #define vst2q_f16(__p0, __p1) __extension__ ({ \
25720 float16x8x2_t __s1 = __p1; \
25724 #define vst2q_f16(__p0, __p1) __extension__ ({ \
25725 float16x8x2_t __s1 = __p1; \
25734 #define vst2q_s32(__p0, __p1) __extension__ ({ \
25735 int32x4x2_t __s1 = __p1; \
25739 #define vst2q_s32(__p0, __p1) __extension__ ({ \
25740 int32x4x2_t __s1 = __p1; \
25749 #define vst2q_s16(__p0, __p1) __extension__ ({ \
25750 int16x8x2_t __s1 = __p1; \
25754 #define vst2q_s16(__p0, __p1) __extension__ ({ \
25755 int16x8x2_t __s1 = __p1; \
25764 #define vst2_u8(__p0, __p1) __extension__ ({ \
25765 uint8x8x2_t __s1 = __p1; \
25769 #define vst2_u8(__p0, __p1) __extension__ ({ \
25770 uint8x8x2_t __s1 = __p1; \
25779 #define vst2_u32(__p0, __p1) __extension__ ({ \
25780 uint32x2x2_t __s1 = __p1; \
25784 #define vst2_u32(__p0, __p1) __extension__ ({ \
25785 uint32x2x2_t __s1 = __p1; \
25794 #define vst2_u64(__p0, __p1) __extension__ ({ \
25795 uint64x1x2_t __s1 = __p1; \
25799 #define vst2_u64(__p0, __p1) __extension__ ({ \
25800 uint64x1x2_t __s1 = __p1; \
25806 #define vst2_u16(__p0, __p1) __extension__ ({ \
25807 uint16x4x2_t __s1 = __p1; \
25811 #define vst2_u16(__p0, __p1) __extension__ ({ \
25812 uint16x4x2_t __s1 = __p1; \
25821 #define vst2_s8(__p0, __p1) __extension__ ({ \
25822 int8x8x2_t __s1 = __p1; \
25826 #define vst2_s8(__p0, __p1) __extension__ ({ \
25827 int8x8x2_t __s1 = __p1; \
25836 #define vst2_f32(__p0, __p1) __extension__ ({ \
25837 float32x2x2_t __s1 = __p1; \
25841 #define vst2_f32(__p0, __p1) __extension__ ({ \
25842 float32x2x2_t __s1 = __p1; \
25851 #define vst2_f16(__p0, __p1) __extension__ ({ \
25852 float16x4x2_t __s1 = __p1; \
25856 #define vst2_f16(__p0, __p1) __extension__ ({ \
25857 float16x4x2_t __s1 = __p1; \
25866 #define vst2_s32(__p0, __p1) __extension__ ({ \
25867 int32x2x2_t __s1 = __p1; \
25871 #define vst2_s32(__p0, __p1) __extension__ ({ \
25872 int32x2x2_t __s1 = __p1; \
25881 #define vst2_s64(__p0, __p1) __extension__ ({ \
25882 int64x1x2_t __s1 = __p1; \
25886 #define vst2_s64(__p0, __p1) __extension__ ({ \
25887 int64x1x2_t __s1 = __p1; \
25893 #define vst2_s16(__p0, __p1) __extension__ ({ \
25894 int16x4x2_t __s1 = __p1; \
25898 #define vst2_s16(__p0, __p1) __extension__ ({ \
25899 int16x4x2_t __s1 = __p1; \
25908 #define vst2_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25909 poly8x8x2_t __s1 = __p1; \
25913 #define vst2_lane_p8(__p0, __p1, __p2) __extension__ ({ \
25914 poly8x8x2_t __s1 = __p1; \
25923 #define vst2_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25924 poly16x4x2_t __s1 = __p1; \
25928 #define vst2_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25929 poly16x4x2_t __s1 = __p1; \
25938 #define vst2q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25939 poly16x8x2_t __s1 = __p1; \
25943 #define vst2q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
25944 poly16x8x2_t __s1 = __p1; \
25953 #define vst2q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25954 uint32x4x2_t __s1 = __p1; \
25958 #define vst2q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
25959 uint32x4x2_t __s1 = __p1; \
25968 #define vst2q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25969 uint16x8x2_t __s1 = __p1; \
25973 #define vst2q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
25974 uint16x8x2_t __s1 = __p1; \
25983 #define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25984 float32x4x2_t __s1 = __p1; \
25988 #define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
25989 float32x4x2_t __s1 = __p1; \
25998 #define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
25999 float16x8x2_t __s1 = __p1; \
26003 #define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26004 float16x8x2_t __s1 = __p1; \
26013 #define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26014 int32x4x2_t __s1 = __p1; \
26018 #define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26019 int32x4x2_t __s1 = __p1; \
26028 #define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26029 int16x8x2_t __s1 = __p1; \
26033 #define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26034 int16x8x2_t __s1 = __p1; \
26043 #define vst2_lane_u8(__p0, __p1, __p2) __extension__ ({ \
26044 uint8x8x2_t __s1 = __p1; \
26048 #define vst2_lane_u8(__p0, __p1, __p2) __extension__ ({ \
26049 uint8x8x2_t __s1 = __p1; \
26058 #define vst2_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26059 uint32x2x2_t __s1 = __p1; \
26063 #define vst2_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26064 uint32x2x2_t __s1 = __p1; \
26073 #define vst2_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26074 uint16x4x2_t __s1 = __p1; \
26078 #define vst2_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26079 uint16x4x2_t __s1 = __p1; \
26088 #define vst2_lane_s8(__p0, __p1, __p2) __extension__ ({ \
26089 int8x8x2_t __s1 = __p1; \
26093 #define vst2_lane_s8(__p0, __p1, __p2) __extension__ ({ \
26094 int8x8x2_t __s1 = __p1; \
26103 #define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26104 float32x2x2_t __s1 = __p1; \
26108 #define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26109 float32x2x2_t __s1 = __p1; \
26118 #define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26119 float16x4x2_t __s1 = __p1; \
26123 #define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26124 float16x4x2_t __s1 = __p1; \
26133 #define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26134 int32x2x2_t __s1 = __p1; \
26138 #define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26139 int32x2x2_t __s1 = __p1; \
26148 #define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26149 int16x4x2_t __s1 = __p1; \
26153 #define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26154 int16x4x2_t __s1 = __p1; \
26163 #define vst3_p8(__p0, __p1) __extension__ ({ \
26164 poly8x8x3_t __s1 = __p1; \
26168 #define vst3_p8(__p0, __p1) __extension__ ({ \
26169 poly8x8x3_t __s1 = __p1; \
26179 #define vst3_p16(__p0, __p1) __extension__ ({ \
26180 poly16x4x3_t __s1 = __p1; \
26184 #define vst3_p16(__p0, __p1) __extension__ ({ \
26185 poly16x4x3_t __s1 = __p1; \
26195 #define vst3q_p8(__p0, __p1) __extension__ ({ \
26196 poly8x16x3_t __s1 = __p1; \
26200 #define vst3q_p8(__p0, __p1) __extension__ ({ \
26201 poly8x16x3_t __s1 = __p1; \
26211 #define vst3q_p16(__p0, __p1) __extension__ ({ \
26212 poly16x8x3_t __s1 = __p1; \
26216 #define vst3q_p16(__p0, __p1) __extension__ ({ \
26217 poly16x8x3_t __s1 = __p1; \
26227 #define vst3q_u8(__p0, __p1) __extension__ ({ \
26228 uint8x16x3_t __s1 = __p1; \
26232 #define vst3q_u8(__p0, __p1) __extension__ ({ \
26233 uint8x16x3_t __s1 = __p1; \
26243 #define vst3q_u32(__p0, __p1) __extension__ ({ \
26244 uint32x4x3_t __s1 = __p1; \
26248 #define vst3q_u32(__p0, __p1) __extension__ ({ \
26249 uint32x4x3_t __s1 = __p1; \
26259 #define vst3q_u16(__p0, __p1) __extension__ ({ \
26260 uint16x8x3_t __s1 = __p1; \
26264 #define vst3q_u16(__p0, __p1) __extension__ ({ \
26265 uint16x8x3_t __s1 = __p1; \
26275 #define vst3q_s8(__p0, __p1) __extension__ ({ \
26276 int8x16x3_t __s1 = __p1; \
26280 #define vst3q_s8(__p0, __p1) __extension__ ({ \
26281 int8x16x3_t __s1 = __p1; \
26291 #define vst3q_f32(__p0, __p1) __extension__ ({ \
26292 float32x4x3_t __s1 = __p1; \
26296 #define vst3q_f32(__p0, __p1) __extension__ ({ \
26297 float32x4x3_t __s1 = __p1; \
26307 #define vst3q_f16(__p0, __p1) __extension__ ({ \
26308 float16x8x3_t __s1 = __p1; \
26312 #define vst3q_f16(__p0, __p1) __extension__ ({ \
26313 float16x8x3_t __s1 = __p1; \
26323 #define vst3q_s32(__p0, __p1) __extension__ ({ \
26324 int32x4x3_t __s1 = __p1; \
26328 #define vst3q_s32(__p0, __p1) __extension__ ({ \
26329 int32x4x3_t __s1 = __p1; \
26339 #define vst3q_s16(__p0, __p1) __extension__ ({ \
26340 int16x8x3_t __s1 = __p1; \
26344 #define vst3q_s16(__p0, __p1) __extension__ ({ \
26345 int16x8x3_t __s1 = __p1; \
26355 #define vst3_u8(__p0, __p1) __extension__ ({ \
26356 uint8x8x3_t __s1 = __p1; \
26360 #define vst3_u8(__p0, __p1) __extension__ ({ \
26361 uint8x8x3_t __s1 = __p1; \
26371 #define vst3_u32(__p0, __p1) __extension__ ({ \
26372 uint32x2x3_t __s1 = __p1; \
26376 #define vst3_u32(__p0, __p1) __extension__ ({ \
26377 uint32x2x3_t __s1 = __p1; \
26387 #define vst3_u64(__p0, __p1) __extension__ ({ \
26388 uint64x1x3_t __s1 = __p1; \
26392 #define vst3_u64(__p0, __p1) __extension__ ({ \
26393 uint64x1x3_t __s1 = __p1; \
26399 #define vst3_u16(__p0, __p1) __extension__ ({ \
26400 uint16x4x3_t __s1 = __p1; \
26404 #define vst3_u16(__p0, __p1) __extension__ ({ \
26405 uint16x4x3_t __s1 = __p1; \
26415 #define vst3_s8(__p0, __p1) __extension__ ({ \
26416 int8x8x3_t __s1 = __p1; \
26420 #define vst3_s8(__p0, __p1) __extension__ ({ \
26421 int8x8x3_t __s1 = __p1; \
26431 #define vst3_f32(__p0, __p1) __extension__ ({ \
26432 float32x2x3_t __s1 = __p1; \
26436 #define vst3_f32(__p0, __p1) __extension__ ({ \
26437 float32x2x3_t __s1 = __p1; \
26447 #define vst3_f16(__p0, __p1) __extension__ ({ \
26448 float16x4x3_t __s1 = __p1; \
26452 #define vst3_f16(__p0, __p1) __extension__ ({ \
26453 float16x4x3_t __s1 = __p1; \
26463 #define vst3_s32(__p0, __p1) __extension__ ({ \
26464 int32x2x3_t __s1 = __p1; \
26468 #define vst3_s32(__p0, __p1) __extension__ ({ \
26469 int32x2x3_t __s1 = __p1; \
26479 #define vst3_s64(__p0, __p1) __extension__ ({ \
26480 int64x1x3_t __s1 = __p1; \
26484 #define vst3_s64(__p0, __p1) __extension__ ({ \
26485 int64x1x3_t __s1 = __p1; \
26491 #define vst3_s16(__p0, __p1) __extension__ ({ \
26492 int16x4x3_t __s1 = __p1; \
26496 #define vst3_s16(__p0, __p1) __extension__ ({ \
26497 int16x4x3_t __s1 = __p1; \
26507 #define vst3_lane_p8(__p0, __p1, __p2) __extension__ ({ \
26508 poly8x8x3_t __s1 = __p1; \
26512 #define vst3_lane_p8(__p0, __p1, __p2) __extension__ ({ \
26513 poly8x8x3_t __s1 = __p1; \
26523 #define vst3_lane_p16(__p0, __p1, __p2) __extension__ ({ \
26524 poly16x4x3_t __s1 = __p1; \
26528 #define vst3_lane_p16(__p0, __p1, __p2) __extension__ ({ \
26529 poly16x4x3_t __s1 = __p1; \
26539 #define vst3q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
26540 poly16x8x3_t __s1 = __p1; \
26544 #define vst3q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
26545 poly16x8x3_t __s1 = __p1; \
26555 #define vst3q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26556 uint32x4x3_t __s1 = __p1; \
26560 #define vst3q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26561 uint32x4x3_t __s1 = __p1; \
26571 #define vst3q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26572 uint16x8x3_t __s1 = __p1; \
26576 #define vst3q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26577 uint16x8x3_t __s1 = __p1; \
26587 #define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26588 float32x4x3_t __s1 = __p1; \
26592 #define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26593 float32x4x3_t __s1 = __p1; \
26603 #define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26604 float16x8x3_t __s1 = __p1; \
26608 #define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26609 float16x8x3_t __s1 = __p1; \
26619 #define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26620 int32x4x3_t __s1 = __p1; \
26624 #define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26625 int32x4x3_t __s1 = __p1; \
26635 #define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26636 int16x8x3_t __s1 = __p1; \
26640 #define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26641 int16x8x3_t __s1 = __p1; \
26651 #define vst3_lane_u8(__p0, __p1, __p2) __extension__ ({ \
26652 uint8x8x3_t __s1 = __p1; \
26656 #define vst3_lane_u8(__p0, __p1, __p2) __extension__ ({ \
26657 uint8x8x3_t __s1 = __p1; \
26667 #define vst3_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26668 uint32x2x3_t __s1 = __p1; \
26672 #define vst3_lane_u32(__p0, __p1, __p2) __extension__ ({ \
26673 uint32x2x3_t __s1 = __p1; \
26683 #define vst3_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26684 uint16x4x3_t __s1 = __p1; \
26688 #define vst3_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26689 uint16x4x3_t __s1 = __p1; \
26699 #define vst3_lane_s8(__p0, __p1, __p2) __extension__ ({ \
26700 int8x8x3_t __s1 = __p1; \
26704 #define vst3_lane_s8(__p0, __p1, __p2) __extension__ ({ \
26705 int8x8x3_t __s1 = __p1; \
26715 #define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26716 float32x2x3_t __s1 = __p1; \
26720 #define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
26721 float32x2x3_t __s1 = __p1; \
26731 #define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26732 float16x4x3_t __s1 = __p1; \
26736 #define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
26737 float16x4x3_t __s1 = __p1; \
26747 #define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26748 int32x2x3_t __s1 = __p1; \
26752 #define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
26753 int32x2x3_t __s1 = __p1; \
26763 #define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26764 int16x4x3_t __s1 = __p1; \
26768 #define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26769 int16x4x3_t __s1 = __p1; \
26779 #define vst4_p8(__p0, __p1) __extension__ ({ \
26780 poly8x8x4_t __s1 = __p1; \
26784 #define vst4_p8(__p0, __p1) __extension__ ({ \
26785 poly8x8x4_t __s1 = __p1; \
26796 #define vst4_p16(__p0, __p1) __extension__ ({ \
26797 poly16x4x4_t __s1 = __p1; \
26801 #define vst4_p16(__p0, __p1) __extension__ ({ \
26802 poly16x4x4_t __s1 = __p1; \
26813 #define vst4q_p8(__p0, __p1) __extension__ ({ \
26814 poly8x16x4_t __s1 = __p1; \
26818 #define vst4q_p8(__p0, __p1) __extension__ ({ \
26819 poly8x16x4_t __s1 = __p1; \
26830 #define vst4q_p16(__p0, __p1) __extension__ ({ \
26831 poly16x8x4_t __s1 = __p1; \
26835 #define vst4q_p16(__p0, __p1) __extension__ ({ \
26836 poly16x8x4_t __s1 = __p1; \
26847 #define vst4q_u8(__p0, __p1) __extension__ ({ \
26848 uint8x16x4_t __s1 = __p1; \
26852 #define vst4q_u8(__p0, __p1) __extension__ ({ \
26853 uint8x16x4_t __s1 = __p1; \
26864 #define vst4q_u32(__p0, __p1) __extension__ ({ \
26865 uint32x4x4_t __s1 = __p1; \
26869 #define vst4q_u32(__p0, __p1) __extension__ ({ \
26870 uint32x4x4_t __s1 = __p1; \
26881 #define vst4q_u16(__p0, __p1) __extension__ ({ \
26882 uint16x8x4_t __s1 = __p1; \
26886 #define vst4q_u16(__p0, __p1) __extension__ ({ \
26887 uint16x8x4_t __s1 = __p1; \
26898 #define vst4q_s8(__p0, __p1) __extension__ ({ \
26899 int8x16x4_t __s1 = __p1; \
26903 #define vst4q_s8(__p0, __p1) __extension__ ({ \
26904 int8x16x4_t __s1 = __p1; \
26915 #define vst4q_f32(__p0, __p1) __extension__ ({ \
26916 float32x4x4_t __s1 = __p1; \
26920 #define vst4q_f32(__p0, __p1) __extension__ ({ \
26921 float32x4x4_t __s1 = __p1; \
26932 #define vst4q_f16(__p0, __p1) __extension__ ({ \
26933 float16x8x4_t __s1 = __p1; \
26937 #define vst4q_f16(__p0, __p1) __extension__ ({ \
26938 float16x8x4_t __s1 = __p1; \
26949 #define vst4q_s32(__p0, __p1) __extension__ ({ \
26950 int32x4x4_t __s1 = __p1; \
26954 #define vst4q_s32(__p0, __p1) __extension__ ({ \
26955 int32x4x4_t __s1 = __p1; \
26966 #define vst4q_s16(__p0, __p1) __extension__ ({ \
26967 int16x8x4_t __s1 = __p1; \
26971 #define vst4q_s16(__p0, __p1) __extension__ ({ \
26972 int16x8x4_t __s1 = __p1; \
26983 #define vst4_u8(__p0, __p1) __extension__ ({ \
26984 uint8x8x4_t __s1 = __p1; \
26988 #define vst4_u8(__p0, __p1) __extension__ ({ \
26989 uint8x8x4_t __s1 = __p1; \
27000 #define vst4_u32(__p0, __p1) __extension__ ({ \
27001 uint32x2x4_t __s1 = __p1; \
27005 #define vst4_u32(__p0, __p1) __extension__ ({ \
27006 uint32x2x4_t __s1 = __p1; \
27017 #define vst4_u64(__p0, __p1) __extension__ ({ \
27018 uint64x1x4_t __s1 = __p1; \
27022 #define vst4_u64(__p0, __p1) __extension__ ({ \
27023 uint64x1x4_t __s1 = __p1; \
27029 #define vst4_u16(__p0, __p1) __extension__ ({ \
27030 uint16x4x4_t __s1 = __p1; \
27034 #define vst4_u16(__p0, __p1) __extension__ ({ \
27035 uint16x4x4_t __s1 = __p1; \
27046 #define vst4_s8(__p0, __p1) __extension__ ({ \
27047 int8x8x4_t __s1 = __p1; \
27051 #define vst4_s8(__p0, __p1) __extension__ ({ \
27052 int8x8x4_t __s1 = __p1; \
27063 #define vst4_f32(__p0, __p1) __extension__ ({ \
27064 float32x2x4_t __s1 = __p1; \
27068 #define vst4_f32(__p0, __p1) __extension__ ({ \
27069 float32x2x4_t __s1 = __p1; \
27080 #define vst4_f16(__p0, __p1) __extension__ ({ \
27081 float16x4x4_t __s1 = __p1; \
27085 #define vst4_f16(__p0, __p1) __extension__ ({ \
27086 float16x4x4_t __s1 = __p1; \
27097 #define vst4_s32(__p0, __p1) __extension__ ({ \
27098 int32x2x4_t __s1 = __p1; \
27102 #define vst4_s32(__p0, __p1) __extension__ ({ \
27103 int32x2x4_t __s1 = __p1; \
27114 #define vst4_s64(__p0, __p1) __extension__ ({ \
27115 int64x1x4_t __s1 = __p1; \
27119 #define vst4_s64(__p0, __p1) __extension__ ({ \
27120 int64x1x4_t __s1 = __p1; \
27126 #define vst4_s16(__p0, __p1) __extension__ ({ \
27127 int16x4x4_t __s1 = __p1; \
27131 #define vst4_s16(__p0, __p1) __extension__ ({ \
27132 int16x4x4_t __s1 = __p1; \
27143 #define vst4_lane_p8(__p0, __p1, __p2) __extension__ ({ \
27144 poly8x8x4_t __s1 = __p1; \
27148 #define vst4_lane_p8(__p0, __p1, __p2) __extension__ ({ \
27149 poly8x8x4_t __s1 = __p1; \
27160 #define vst4_lane_p16(__p0, __p1, __p2) __extension__ ({ \
27161 poly16x4x4_t __s1 = __p1; \
27165 #define vst4_lane_p16(__p0, __p1, __p2) __extension__ ({ \
27166 poly16x4x4_t __s1 = __p1; \
27177 #define vst4q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
27178 poly16x8x4_t __s1 = __p1; \
27182 #define vst4q_lane_p16(__p0, __p1, __p2) __extension__ ({ \
27183 poly16x8x4_t __s1 = __p1; \
27194 #define vst4q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
27195 uint32x4x4_t __s1 = __p1; \
27199 #define vst4q_lane_u32(__p0, __p1, __p2) __extension__ ({ \
27200 uint32x4x4_t __s1 = __p1; \
27211 #define vst4q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
27212 uint16x8x4_t __s1 = __p1; \
27216 #define vst4q_lane_u16(__p0, __p1, __p2) __extension__ ({ \
27217 uint16x8x4_t __s1 = __p1; \
27228 #define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
27229 float32x4x4_t __s1 = __p1; \
27233 #define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
27234 float32x4x4_t __s1 = __p1; \
27245 #define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
27246 float16x8x4_t __s1 = __p1; \
27250 #define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
27251 float16x8x4_t __s1 = __p1; \
27262 #define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
27263 int32x4x4_t __s1 = __p1; \
27267 #define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
27268 int32x4x4_t __s1 = __p1; \
27279 #define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
27280 int16x8x4_t __s1 = __p1; \
27284 #define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
27285 int16x8x4_t __s1 = __p1; \
27296 #define vst4_lane_u8(__p0, __p1, __p2) __extension__ ({ \
27297 uint8x8x4_t __s1 = __p1; \
27301 #define vst4_lane_u8(__p0, __p1, __p2) __extension__ ({ \
27302 uint8x8x4_t __s1 = __p1; \
27313 #define vst4_lane_u32(__p0, __p1, __p2) __extension__ ({ \
27314 uint32x2x4_t __s1 = __p1; \
27318 #define vst4_lane_u32(__p0, __p1, __p2) __extension__ ({ \
27319 uint32x2x4_t __s1 = __p1; \
27330 #define vst4_lane_u16(__p0, __p1, __p2) __extension__ ({ \
27331 uint16x4x4_t __s1 = __p1; \
27335 #define vst4_lane_u16(__p0, __p1, __p2) __extension__ ({ \
27336 uint16x4x4_t __s1 = __p1; \
27347 #define vst4_lane_s8(__p0, __p1, __p2) __extension__ ({ \
27348 int8x8x4_t __s1 = __p1; \
27352 #define vst4_lane_s8(__p0, __p1, __p2) __extension__ ({ \
27353 int8x8x4_t __s1 = __p1; \
27364 #define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
27365 float32x2x4_t __s1 = __p1; \
27369 #define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
27370 float32x2x4_t __s1 = __p1; \
27381 #define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
27382 float16x4x4_t __s1 = __p1; \
27386 #define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
27387 float16x4x4_t __s1 = __p1; \
27398 #define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
27399 int32x2x4_t __s1 = __p1; \
27403 #define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
27404 int32x2x4_t __s1 = __p1; \
27415 #define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
27416 int16x4x4_t __s1 = __p1; \
27420 #define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
27421 int16x4x4_t __s1 = __p1; \
27432 __ai uint8x16_t vsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
27434 __ret = __p0 - __p1;
27438 __ai uint8x16_t vsubq_u8(uint8x16_t __p0, uint8x16_t __p1) {
27440 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
27449 __ai uint32x4_t vsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
27451 __ret = __p0 - __p1;
27455 __ai uint32x4_t vsubq_u32(uint32x4_t __p0, uint32x4_t __p1) {
27457 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27466 __ai uint64x2_t vsubq_u64(uint64x2_t __p0, uint64x2_t __p1) {
27468 __ret = __p0 - __p1;
27472 __ai uint64x2_t vsubq_u64(uint64x2_t __p0, uint64x2_t __p1) {
27474 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27483 __ai uint16x8_t vsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
27485 __ret = __p0 - __p1;
27489 __ai uint16x8_t vsubq_u16(uint16x8_t __p0, uint16x8_t __p1) {
27491 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27500 __ai int8x16_t vsubq_s8(int8x16_t __p0, int8x16_t __p1) {
27502 __ret = __p0 - __p1;
27506 __ai int8x16_t vsubq_s8(int8x16_t __p0, int8x16_t __p1) {
27508 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
27517 __ai float32x4_t vsubq_f32(float32x4_t __p0, float32x4_t __p1) {
27519 __ret = __p0 - __p1;
27523 __ai float32x4_t vsubq_f32(float32x4_t __p0, float32x4_t __p1) {
27525 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27534 __ai int32x4_t vsubq_s32(int32x4_t __p0, int32x4_t __p1) {
27536 __ret = __p0 - __p1;
27540 __ai int32x4_t vsubq_s32(int32x4_t __p0, int32x4_t __p1) {
27542 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27551 __ai int64x2_t vsubq_s64(int64x2_t __p0, int64x2_t __p1) {
27553 __ret = __p0 - __p1;
27557 __ai int64x2_t vsubq_s64(int64x2_t __p0, int64x2_t __p1) {
27559 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27568 __ai int16x8_t vsubq_s16(int16x8_t __p0, int16x8_t __p1) {
27570 __ret = __p0 - __p1;
27574 __ai int16x8_t vsubq_s16(int16x8_t __p0, int16x8_t __p1) {
27576 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27585 __ai uint8x8_t vsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
27587 __ret = __p0 - __p1;
27591 __ai uint8x8_t vsub_u8(uint8x8_t __p0, uint8x8_t __p1) {
27593 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27602 __ai uint32x2_t vsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
27604 __ret = __p0 - __p1;
27608 __ai uint32x2_t vsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
27610 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27619 __ai uint64x1_t vsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
27621 __ret = __p0 - __p1;
27625 __ai uint64x1_t vsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
27627 __ret = __p0 - __p1;
27633 __ai uint16x4_t vsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
27635 __ret = __p0 - __p1;
27639 __ai uint16x4_t vsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
27641 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27650 __ai int8x8_t vsub_s8(int8x8_t __p0, int8x8_t __p1) {
27652 __ret = __p0 - __p1;
27656 __ai int8x8_t vsub_s8(int8x8_t __p0, int8x8_t __p1) {
27658 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27667 __ai float32x2_t vsub_f32(float32x2_t __p0, float32x2_t __p1) {
27669 __ret = __p0 - __p1;
27673 __ai float32x2_t vsub_f32(float32x2_t __p0, float32x2_t __p1) {
27675 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27684 __ai int32x2_t vsub_s32(int32x2_t __p0, int32x2_t __p1) {
27686 __ret = __p0 - __p1;
27690 __ai int32x2_t vsub_s32(int32x2_t __p0, int32x2_t __p1) {
27692 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27701 __ai int64x1_t vsub_s64(int64x1_t __p0, int64x1_t __p1) {
27703 __ret = __p0 - __p1;
27707 __ai int64x1_t vsub_s64(int64x1_t __p0, int64x1_t __p1) {
27709 __ret = __p0 - __p1;
27715 __ai int16x4_t vsub_s16(int16x4_t __p0, int16x4_t __p1) {
27717 __ret = __p0 - __p1;
27721 __ai int16x4_t vsub_s16(int16x4_t __p0, int16x4_t __p1) {
27723 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27732 __ai uint16x4_t vsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
27734 __ret = (uint16x4_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
27738 __ai uint16x4_t vsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
27740 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27746 __ai uint16x4_t __noswap_vsubhn_u32(uint32x4_t __p0, uint32x4_t __p1) {
27748 __ret = (uint16x4_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 17);
27754 __ai uint32x2_t vsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
27756 __ret = (uint32x2_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
27760 __ai uint32x2_t vsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
27762 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27768 __ai uint32x2_t __noswap_vsubhn_u64(uint64x2_t __p0, uint64x2_t __p1) {
27770 __ret = (uint32x2_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 18);
27776 __ai uint8x8_t vsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
27778 __ret = (uint8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
27782 __ai uint8x8_t vsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
27784 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27790 __ai uint8x8_t __noswap_vsubhn_u16(uint16x8_t __p0, uint16x8_t __p1) {
27792 __ret = (uint8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 16);
27798 __ai int16x4_t vsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
27800 __ret = (int16x4_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
27804 __ai int16x4_t vsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
27806 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27812 __ai int16x4_t __noswap_vsubhn_s32(int32x4_t __p0, int32x4_t __p1) {
27814 __ret = (int16x4_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 1);
27820 __ai int32x2_t vsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
27822 __ret = (int32x2_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
27826 __ai int32x2_t vsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
27828 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27834 __ai int32x2_t __noswap_vsubhn_s64(int64x2_t __p0, int64x2_t __p1) {
27836 __ret = (int32x2_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 2);
27842 __ai int8x8_t vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27844 __ret = (int8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
27848 __ai int8x8_t vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27850 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27856 __ai int8x8_t __noswap_vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27858 __ret = (int8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
27864 __ai uint16x8_t vsubl_u8(uint8x8_t __p0, uint8x8_t __p1) {
27866 __ret = vmovl_u8(__p0) - vmovl_u8(__p1);
27870 __ai uint16x8_t vsubl_u8(uint8x8_t __p0, uint8x8_t __p1) {
27872 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27881 __ai uint64x2_t vsubl_u32(uint32x2_t __p0, uint32x2_t __p1) {
27883 __ret = vmovl_u32(__p0) - vmovl_u32(__p1);
27887 __ai uint64x2_t vsubl_u32(uint32x2_t __p0, uint32x2_t __p1) {
27889 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27898 __ai uint32x4_t vsubl_u16(uint16x4_t __p0, uint16x4_t __p1) {
27900 __ret = vmovl_u16(__p0) - vmovl_u16(__p1);
27904 __ai uint32x4_t vsubl_u16(uint16x4_t __p0, uint16x4_t __p1) {
27906 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27915 __ai int16x8_t vsubl_s8(int8x8_t __p0, int8x8_t __p1) {
27917 __ret = vmovl_s8(__p0) - vmovl_s8(__p1);
27921 __ai int16x8_t vsubl_s8(int8x8_t __p0, int8x8_t __p1) {
27923 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27932 __ai int64x2_t vsubl_s32(int32x2_t __p0, int32x2_t __p1) {
27934 __ret = vmovl_s32(__p0) - vmovl_s32(__p1);
27938 __ai int64x2_t vsubl_s32(int32x2_t __p0, int32x2_t __p1) {
27940 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
27949 __ai int32x4_t vsubl_s16(int16x4_t __p0, int16x4_t __p1) {
27951 __ret = vmovl_s16(__p0) - vmovl_s16(__p1);
27955 __ai int32x4_t vsubl_s16(int16x4_t __p0, int16x4_t __p1) {
27957 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
27966 __ai uint16x8_t vsubw_u8(uint16x8_t __p0, uint8x8_t __p1) {
27968 __ret = __p0 - vmovl_u8(__p1);
27972 __ai uint16x8_t vsubw_u8(uint16x8_t __p0, uint8x8_t __p1) {
27974 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27983 __ai uint64x2_t vsubw_u32(uint64x2_t __p0, uint32x2_t __p1) {
27985 __ret = __p0 - vmovl_u32(__p1);
27989 __ai uint64x2_t vsubw_u32(uint64x2_t __p0, uint32x2_t __p1) {
27991 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
28000 __ai uint32x4_t vsubw_u16(uint32x4_t __p0, uint16x4_t __p1) {
28002 __ret = __p0 - vmovl_u16(__p1);
28006 __ai uint32x4_t vsubw_u16(uint32x4_t __p0, uint16x4_t __p1) {
28008 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28017 __ai int16x8_t vsubw_s8(int16x8_t __p0, int8x8_t __p1) {
28019 __ret = __p0 - vmovl_s8(__p1);
28023 __ai int16x8_t vsubw_s8(int16x8_t __p0, int8x8_t __p1) {
28025 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28034 __ai int64x2_t vsubw_s32(int64x2_t __p0, int32x2_t __p1) {
28036 __ret = __p0 - vmovl_s32(__p1);
28040 __ai int64x2_t vsubw_s32(int64x2_t __p0, int32x2_t __p1) {
28042 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
28051 __ai int32x4_t vsubw_s16(int32x4_t __p0, int16x4_t __p1) {
28053 __ret = __p0 - vmovl_s16(__p1);
28057 __ai int32x4_t vsubw_s16(int32x4_t __p0, int16x4_t __p1) {
28059 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28068 __ai poly8x8_t vtbl1_p8(poly8x8_t __p0, uint8x8_t __p1) {
28070 __ret = (poly8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 4);
28074 __ai poly8x8_t vtbl1_p8(poly8x8_t __p0, uint8x8_t __p1) {
28076 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28085 __ai uint8x8_t vtbl1_u8(uint8x8_t __p0, uint8x8_t __p1) {
28087 __ret = (uint8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
28091 __ai uint8x8_t vtbl1_u8(uint8x8_t __p0, uint8x8_t __p1) {
28093 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28102 __ai int8x8_t vtbl1_s8(int8x8_t __p0, int8x8_t __p1) {
28104 __ret = (int8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
28108 __ai int8x8_t vtbl1_s8(int8x8_t __p0, int8x8_t __p1) {
28110 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28119 __ai poly8x8_t vtbl2_p8(poly8x8x2_t __p0, uint8x8_t __p1) {
28121 __ret = (poly8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 4);
28125 __ai poly8x8_t vtbl2_p8(poly8x8x2_t __p0, uint8x8_t __p1) {
28129 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28138 __ai uint8x8_t vtbl2_u8(uint8x8x2_t __p0, uint8x8_t __p1) {
28140 __ret = (uint8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 16);
28144 __ai uint8x8_t vtbl2_u8(uint8x8x2_t __p0, uint8x8_t __p1) {
28148 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28157 __ai int8x8_t vtbl2_s8(int8x8x2_t __p0, int8x8_t __p1) {
28159 __ret = (int8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 0);
28163 __ai int8x8_t vtbl2_s8(int8x8x2_t __p0, int8x8_t __p1) {
28167 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28176 __ai poly8x8_t vtbl3_p8(poly8x8x3_t __p0, uint8x8_t __p1) {
28178 __ret = (poly8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p1, 4);
28182 __ai poly8x8_t vtbl3_p8(poly8x8x3_t __p0, uint8x8_t __p1) {
28187 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28196 __ai uint8x8_t vtbl3_u8(uint8x8x3_t __p0, uint8x8_t __p1) {
28198 __ret = (uint8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p1, 16);
28202 __ai uint8x8_t vtbl3_u8(uint8x8x3_t __p0, uint8x8_t __p1) {
28207 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28216 __ai int8x8_t vtbl3_s8(int8x8x3_t __p0, int8x8_t __p1) {
28218 __ret = (int8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p1, 0);
28222 __ai int8x8_t vtbl3_s8(int8x8x3_t __p0, int8x8_t __p1) {
28227 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28236 __ai poly8x8_t vtbl4_p8(poly8x8x4_t __p0, uint8x8_t __p1) {
28238 __ret = (poly8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p0.val[3], (int8x8_t)__p1, 4);
28242 __ai poly8x8_t vtbl4_p8(poly8x8x4_t __p0, uint8x8_t __p1) {
28248 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28257 __ai uint8x8_t vtbl4_u8(uint8x8x4_t __p0, uint8x8_t __p1) {
28259 __ret = (uint8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p0.val[3], (int8x8_t)__p1, 16);
28263 __ai uint8x8_t vtbl4_u8(uint8x8x4_t __p0, uint8x8_t __p1) {
28269 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28278 __ai int8x8_t vtbl4_s8(int8x8x4_t __p0, int8x8_t __p1) {
28280 __ret = (int8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p0.val[2], (int8x8_t)__p0.val[3], (int8x8_t)__p1, 0);
28284 __ai int8x8_t vtbl4_s8(int8x8x4_t __p0, int8x8_t __p1) {
28290 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28299 __ai poly8x8_t vtbx1_p8(poly8x8_t __p0, poly8x8_t __p1, uint8x8_t __p2) {
28301 __ret = (poly8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 4);
28305 __ai poly8x8_t vtbx1_p8(poly8x8_t __p0, poly8x8_t __p1, uint8x8_t __p2) {
28307 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28317 __ai uint8x8_t vtbx1_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
28319 __ret = (uint8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 16);
28323 __ai uint8x8_t vtbx1_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
28325 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28335 __ai int8x8_t vtbx1_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
28337 __ret = (int8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 0);
28341 __ai int8x8_t vtbx1_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
28343 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28353 __ai poly8x8_t vtbx2_p8(poly8x8_t __p0, poly8x8x2_t __p1, uint8x8_t __p2) {
28355 __ret = (poly8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 4);
28359 __ai poly8x8_t vtbx2_p8(poly8x8_t __p0, poly8x8x2_t __p1, uint8x8_t __p2) {
28362 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28363 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28373 __ai uint8x8_t vtbx2_u8(uint8x8_t __p0, uint8x8x2_t __p1, uint8x8_t __p2) {
28375 __ret = (uint8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 16);
28379 __ai uint8x8_t vtbx2_u8(uint8x8_t __p0, uint8x8x2_t __p1, uint8x8_t __p2) {
28382 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28383 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28393 __ai int8x8_t vtbx2_s8(int8x8_t __p0, int8x8x2_t __p1, int8x8_t __p2) {
28395 __ret = (int8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 0);
28399 __ai int8x8_t vtbx2_s8(int8x8_t __p0, int8x8x2_t __p1, int8x8_t __p2) {
28402 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28403 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28413 __ai poly8x8_t vtbx3_p8(poly8x8_t __p0, poly8x8x3_t __p1, uint8x8_t __p2) {
28415 __ret = (poly8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p2, 4);
28419 __ai poly8x8_t vtbx3_p8(poly8x8_t __p0, poly8x8x3_t __p1, uint8x8_t __p2) {
28422 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28423 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28424 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28434 __ai uint8x8_t vtbx3_u8(uint8x8_t __p0, uint8x8x3_t __p1, uint8x8_t __p2) {
28436 __ret = (uint8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p2, 16);
28440 __ai uint8x8_t vtbx3_u8(uint8x8_t __p0, uint8x8x3_t __p1, uint8x8_t __p2) {
28443 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28444 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28445 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28455 __ai int8x8_t vtbx3_s8(int8x8_t __p0, int8x8x3_t __p1, int8x8_t __p2) {
28457 __ret = (int8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p2, 0);
28461 __ai int8x8_t vtbx3_s8(int8x8_t __p0, int8x8x3_t __p1, int8x8_t __p2) {
28464 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28465 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28466 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28476 __ai poly8x8_t vtbx4_p8(poly8x8_t __p0, poly8x8x4_t __p1, uint8x8_t __p2) {
28478 __ret = (poly8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p1.val[3], (int8x8_t)__p2, 4);
28482 __ai poly8x8_t vtbx4_p8(poly8x8_t __p0, poly8x8x4_t __p1, uint8x8_t __p2) {
28485 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28486 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28487 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28488 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 7, 6, 5, 4, 3, 2, 1, 0);
28498 __ai uint8x8_t vtbx4_u8(uint8x8_t __p0, uint8x8x4_t __p1, uint8x8_t __p2) {
28500 __ret = (uint8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p1.val[3], (int8x8_t)__p2, 16);
28504 __ai uint8x8_t vtbx4_u8(uint8x8_t __p0, uint8x8x4_t __p1, uint8x8_t __p2) {
28507 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28508 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28509 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28510 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 7, 6, 5, 4, 3, 2, 1, 0);
28520 __ai int8x8_t vtbx4_s8(int8x8_t __p0, int8x8x4_t __p1, int8x8_t __p2) {
28522 __ret = (int8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p1.val[2], (int8x8_t)__p1.val[3], (int8x8_t)__p2, 0);
28526 __ai int8x8_t vtbx4_s8(int8x8_t __p0, int8x8x4_t __p1, int8x8_t __p2) {
28529 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 7, 6, 5, 4, 3, 2, 1, 0);
28530 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 7, 6, 5, 4, 3, 2, 1, 0);
28531 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 7, 6, 5, 4, 3, 2, 1, 0);
28532 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 7, 6, 5, 4, 3, 2, 1, 0);
28542 __ai poly8x8x2_t vtrn_p8(poly8x8_t __p0, poly8x8_t __p1) {
28544 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
28548 __ai poly8x8x2_t vtrn_p8(poly8x8_t __p0, poly8x8_t __p1) {
28550 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28561 __ai poly16x4x2_t vtrn_p16(poly16x4_t __p0, poly16x4_t __p1) {
28563 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
28567 __ai poly16x4x2_t vtrn_p16(poly16x4_t __p0, poly16x4_t __p1) {
28569 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28580 __ai poly8x16x2_t vtrnq_p8(poly8x16_t __p0, poly8x16_t __p1) {
28582 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 36);
28586 __ai poly8x16x2_t vtrnq_p8(poly8x16_t __p0, poly8x16_t __p1) {
28588 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
28599 __ai poly16x8x2_t vtrnq_p16(poly16x8_t __p0, poly16x8_t __p1) {
28601 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 37);
28605 __ai poly16x8x2_t vtrnq_p16(poly16x8_t __p0, poly16x8_t __p1) {
28607 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28618 __ai uint8x16x2_t vtrnq_u8(uint8x16_t __p0, uint8x16_t __p1) {
28620 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 48);
28624 __ai uint8x16x2_t vtrnq_u8(uint8x16_t __p0, uint8x16_t __p1) {
28626 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
28637 __ai uint32x4x2_t vtrnq_u32(uint32x4_t __p0, uint32x4_t __p1) {
28639 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 50);
28643 __ai uint32x4x2_t vtrnq_u32(uint32x4_t __p0, uint32x4_t __p1) {
28645 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28656 __ai uint16x8x2_t vtrnq_u16(uint16x8_t __p0, uint16x8_t __p1) {
28658 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 49);
28662 __ai uint16x8x2_t vtrnq_u16(uint16x8_t __p0, uint16x8_t __p1) {
28664 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28675 __ai int8x16x2_t vtrnq_s8(int8x16_t __p0, int8x16_t __p1) {
28677 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 32);
28681 __ai int8x16x2_t vtrnq_s8(int8x16_t __p0, int8x16_t __p1) {
28683 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
28694 __ai float32x4x2_t vtrnq_f32(float32x4_t __p0, float32x4_t __p1) {
28696 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 41);
28700 __ai float32x4x2_t vtrnq_f32(float32x4_t __p0, float32x4_t __p1) {
28702 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28713 __ai int32x4x2_t vtrnq_s32(int32x4_t __p0, int32x4_t __p1) {
28715 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 34);
28719 __ai int32x4x2_t vtrnq_s32(int32x4_t __p0, int32x4_t __p1) {
28721 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28732 __ai int16x8x2_t vtrnq_s16(int16x8_t __p0, int16x8_t __p1) {
28734 __builtin_neon_vtrnq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 33);
28738 __ai int16x8x2_t vtrnq_s16(int16x8_t __p0, int16x8_t __p1) {
28740 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28751 __ai uint8x8x2_t vtrn_u8(uint8x8_t __p0, uint8x8_t __p1) {
28753 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
28757 __ai uint8x8x2_t vtrn_u8(uint8x8_t __p0, uint8x8_t __p1) {
28759 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28770 __ai uint32x2x2_t vtrn_u32(uint32x2_t __p0, uint32x2_t __p1) {
28772 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
28776 __ai uint32x2x2_t vtrn_u32(uint32x2_t __p0, uint32x2_t __p1) {
28778 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
28789 __ai uint16x4x2_t vtrn_u16(uint16x4_t __p0, uint16x4_t __p1) {
28791 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
28795 __ai uint16x4x2_t vtrn_u16(uint16x4_t __p0, uint16x4_t __p1) {
28797 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28808 __ai int8x8x2_t vtrn_s8(int8x8_t __p0, int8x8_t __p1) {
28810 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
28814 __ai int8x8x2_t vtrn_s8(int8x8_t __p0, int8x8_t __p1) {
28816 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28827 __ai float32x2x2_t vtrn_f32(float32x2_t __p0, float32x2_t __p1) {
28829 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
28833 __ai float32x2x2_t vtrn_f32(float32x2_t __p0, float32x2_t __p1) {
28835 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
28846 __ai int32x2x2_t vtrn_s32(int32x2_t __p0, int32x2_t __p1) {
28848 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
28852 __ai int32x2x2_t vtrn_s32(int32x2_t __p0, int32x2_t __p1) {
28854 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
28865 __ai int16x4x2_t vtrn_s16(int16x4_t __p0, int16x4_t __p1) {
28867 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
28871 __ai int16x4x2_t vtrn_s16(int16x4_t __p0, int16x4_t __p1) {
28873 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28884 __ai uint8x8_t vtst_p8(poly8x8_t __p0, poly8x8_t __p1) {
28886 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
28890 __ai uint8x8_t vtst_p8(poly8x8_t __p0, poly8x8_t __p1) {
28892 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28901 __ai uint16x4_t vtst_p16(poly16x4_t __p0, poly16x4_t __p1) {
28903 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
28907 __ai uint16x4_t vtst_p16(poly16x4_t __p0, poly16x4_t __p1) {
28909 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28918 __ai uint8x16_t vtstq_p8(poly8x16_t __p0, poly8x16_t __p1) {
28920 __ret = (uint8x16_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
28924 __ai uint8x16_t vtstq_p8(poly8x16_t __p0, poly8x16_t __p1) {
28926 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
28935 __ai uint16x8_t vtstq_p16(poly16x8_t __p0, poly16x8_t __p1) {
28937 __ret = (uint16x8_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
28941 __ai uint16x8_t vtstq_p16(poly16x8_t __p0, poly16x8_t __p1) {
28943 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28952 __ai uint8x16_t vtstq_u8(uint8x16_t __p0, uint8x16_t __p1) {
28954 __ret = (uint8x16_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
28958 __ai uint8x16_t vtstq_u8(uint8x16_t __p0, uint8x16_t __p1) {
28960 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
28969 __ai uint32x4_t vtstq_u32(uint32x4_t __p0, uint32x4_t __p1) {
28971 __ret = (uint32x4_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
28975 __ai uint32x4_t vtstq_u32(uint32x4_t __p0, uint32x4_t __p1) {
28977 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
28986 __ai uint16x8_t vtstq_u16(uint16x8_t __p0, uint16x8_t __p1) {
28988 __ret = (uint16x8_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
28992 __ai uint16x8_t vtstq_u16(uint16x8_t __p0, uint16x8_t __p1) {
28994 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29003 __ai uint8x16_t vtstq_s8(int8x16_t __p0, int8x16_t __p1) {
29005 __ret = (uint8x16_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
29009 __ai uint8x16_t vtstq_s8(int8x16_t __p0, int8x16_t __p1) {
29011 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29020 __ai uint32x4_t vtstq_s32(int32x4_t __p0, int32x4_t __p1) {
29022 __ret = (uint32x4_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
29026 __ai uint32x4_t vtstq_s32(int32x4_t __p0, int32x4_t __p1) {
29028 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29037 __ai uint16x8_t vtstq_s16(int16x8_t __p0, int16x8_t __p1) {
29039 __ret = (uint16x8_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
29043 __ai uint16x8_t vtstq_s16(int16x8_t __p0, int16x8_t __p1) {
29045 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29054 __ai uint8x8_t vtst_u8(uint8x8_t __p0, uint8x8_t __p1) {
29056 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
29060 __ai uint8x8_t vtst_u8(uint8x8_t __p0, uint8x8_t __p1) {
29062 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29071 __ai uint32x2_t vtst_u32(uint32x2_t __p0, uint32x2_t __p1) {
29073 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
29077 __ai uint32x2_t vtst_u32(uint32x2_t __p0, uint32x2_t __p1) {
29079 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29088 __ai uint16x4_t vtst_u16(uint16x4_t __p0, uint16x4_t __p1) {
29090 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
29094 __ai uint16x4_t vtst_u16(uint16x4_t __p0, uint16x4_t __p1) {
29096 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29105 __ai uint8x8_t vtst_s8(int8x8_t __p0, int8x8_t __p1) {
29107 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
29111 __ai uint8x8_t vtst_s8(int8x8_t __p0, int8x8_t __p1) {
29113 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29122 __ai uint32x2_t vtst_s32(int32x2_t __p0, int32x2_t __p1) {
29124 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
29128 __ai uint32x2_t vtst_s32(int32x2_t __p0, int32x2_t __p1) {
29130 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29139 __ai uint16x4_t vtst_s16(int16x4_t __p0, int16x4_t __p1) {
29141 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
29145 __ai uint16x4_t vtst_s16(int16x4_t __p0, int16x4_t __p1) {
29147 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29156 __ai poly8x8x2_t vuzp_p8(poly8x8_t __p0, poly8x8_t __p1) {
29158 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
29162 __ai poly8x8x2_t vuzp_p8(poly8x8_t __p0, poly8x8_t __p1) {
29164 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29175 __ai poly16x4x2_t vuzp_p16(poly16x4_t __p0, poly16x4_t __p1) {
29177 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
29181 __ai poly16x4x2_t vuzp_p16(poly16x4_t __p0, poly16x4_t __p1) {
29183 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29194 __ai poly8x16x2_t vuzpq_p8(poly8x16_t __p0, poly8x16_t __p1) {
29196 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 36);
29200 __ai poly8x16x2_t vuzpq_p8(poly8x16_t __p0, poly8x16_t __p1) {
29202 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29213 __ai poly16x8x2_t vuzpq_p16(poly16x8_t __p0, poly16x8_t __p1) {
29215 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 37);
29219 __ai poly16x8x2_t vuzpq_p16(poly16x8_t __p0, poly16x8_t __p1) {
29221 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29232 __ai uint8x16x2_t vuzpq_u8(uint8x16_t __p0, uint8x16_t __p1) {
29234 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 48);
29238 __ai uint8x16x2_t vuzpq_u8(uint8x16_t __p0, uint8x16_t __p1) {
29240 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29251 __ai uint32x4x2_t vuzpq_u32(uint32x4_t __p0, uint32x4_t __p1) {
29253 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 50);
29257 __ai uint32x4x2_t vuzpq_u32(uint32x4_t __p0, uint32x4_t __p1) {
29259 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29270 __ai uint16x8x2_t vuzpq_u16(uint16x8_t __p0, uint16x8_t __p1) {
29272 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 49);
29276 __ai uint16x8x2_t vuzpq_u16(uint16x8_t __p0, uint16x8_t __p1) {
29278 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29289 __ai int8x16x2_t vuzpq_s8(int8x16_t __p0, int8x16_t __p1) {
29291 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 32);
29295 __ai int8x16x2_t vuzpq_s8(int8x16_t __p0, int8x16_t __p1) {
29297 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29308 __ai float32x4x2_t vuzpq_f32(float32x4_t __p0, float32x4_t __p1) {
29310 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 41);
29314 __ai float32x4x2_t vuzpq_f32(float32x4_t __p0, float32x4_t __p1) {
29316 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29327 __ai int32x4x2_t vuzpq_s32(int32x4_t __p0, int32x4_t __p1) {
29329 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 34);
29333 __ai int32x4x2_t vuzpq_s32(int32x4_t __p0, int32x4_t __p1) {
29335 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29346 __ai int16x8x2_t vuzpq_s16(int16x8_t __p0, int16x8_t __p1) {
29348 __builtin_neon_vuzpq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 33);
29352 __ai int16x8x2_t vuzpq_s16(int16x8_t __p0, int16x8_t __p1) {
29354 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29365 __ai uint8x8x2_t vuzp_u8(uint8x8_t __p0, uint8x8_t __p1) {
29367 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
29371 __ai uint8x8x2_t vuzp_u8(uint8x8_t __p0, uint8x8_t __p1) {
29373 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29384 __ai uint32x2x2_t vuzp_u32(uint32x2_t __p0, uint32x2_t __p1) {
29386 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
29390 __ai uint32x2x2_t vuzp_u32(uint32x2_t __p0, uint32x2_t __p1) {
29392 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29403 __ai uint16x4x2_t vuzp_u16(uint16x4_t __p0, uint16x4_t __p1) {
29405 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
29409 __ai uint16x4x2_t vuzp_u16(uint16x4_t __p0, uint16x4_t __p1) {
29411 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29422 __ai int8x8x2_t vuzp_s8(int8x8_t __p0, int8x8_t __p1) {
29424 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
29428 __ai int8x8x2_t vuzp_s8(int8x8_t __p0, int8x8_t __p1) {
29430 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29441 __ai float32x2x2_t vuzp_f32(float32x2_t __p0, float32x2_t __p1) {
29443 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
29447 __ai float32x2x2_t vuzp_f32(float32x2_t __p0, float32x2_t __p1) {
29449 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29460 __ai int32x2x2_t vuzp_s32(int32x2_t __p0, int32x2_t __p1) {
29462 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
29466 __ai int32x2x2_t vuzp_s32(int32x2_t __p0, int32x2_t __p1) {
29468 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29479 __ai int16x4x2_t vuzp_s16(int16x4_t __p0, int16x4_t __p1) {
29481 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
29485 __ai int16x4x2_t vuzp_s16(int16x4_t __p0, int16x4_t __p1) {
29487 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29498 __ai poly8x8x2_t vzip_p8(poly8x8_t __p0, poly8x8_t __p1) {
29500 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
29504 __ai poly8x8x2_t vzip_p8(poly8x8_t __p0, poly8x8_t __p1) {
29506 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29517 __ai poly16x4x2_t vzip_p16(poly16x4_t __p0, poly16x4_t __p1) {
29519 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
29523 __ai poly16x4x2_t vzip_p16(poly16x4_t __p0, poly16x4_t __p1) {
29525 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29536 __ai poly8x16x2_t vzipq_p8(poly8x16_t __p0, poly8x16_t __p1) {
29538 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 36);
29542 __ai poly8x16x2_t vzipq_p8(poly8x16_t __p0, poly8x16_t __p1) {
29544 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29555 __ai poly16x8x2_t vzipq_p16(poly16x8_t __p0, poly16x8_t __p1) {
29557 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 37);
29561 __ai poly16x8x2_t vzipq_p16(poly16x8_t __p0, poly16x8_t __p1) {
29563 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29574 __ai uint8x16x2_t vzipq_u8(uint8x16_t __p0, uint8x16_t __p1) {
29576 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 48);
29580 __ai uint8x16x2_t vzipq_u8(uint8x16_t __p0, uint8x16_t __p1) {
29582 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29593 __ai uint32x4x2_t vzipq_u32(uint32x4_t __p0, uint32x4_t __p1) {
29595 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 50);
29599 __ai uint32x4x2_t vzipq_u32(uint32x4_t __p0, uint32x4_t __p1) {
29601 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29612 __ai uint16x8x2_t vzipq_u16(uint16x8_t __p0, uint16x8_t __p1) {
29614 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 49);
29618 __ai uint16x8x2_t vzipq_u16(uint16x8_t __p0, uint16x8_t __p1) {
29620 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29631 __ai int8x16x2_t vzipq_s8(int8x16_t __p0, int8x16_t __p1) {
29633 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 32);
29637 __ai int8x16x2_t vzipq_s8(int8x16_t __p0, int8x16_t __p1) {
29639 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
29650 __ai float32x4x2_t vzipq_f32(float32x4_t __p0, float32x4_t __p1) {
29652 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 41);
29656 __ai float32x4x2_t vzipq_f32(float32x4_t __p0, float32x4_t __p1) {
29658 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29669 __ai int32x4x2_t vzipq_s32(int32x4_t __p0, int32x4_t __p1) {
29671 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 34);
29675 __ai int32x4x2_t vzipq_s32(int32x4_t __p0, int32x4_t __p1) {
29677 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29688 __ai int16x8x2_t vzipq_s16(int16x8_t __p0, int16x8_t __p1) {
29690 __builtin_neon_vzipq_v(&__ret, (int8x16_t)__p0, (int8x16_t)__p1, 33);
29694 __ai int16x8x2_t vzipq_s16(int16x8_t __p0, int16x8_t __p1) {
29696 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29707 __ai uint8x8x2_t vzip_u8(uint8x8_t __p0, uint8x8_t __p1) {
29709 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
29713 __ai uint8x8x2_t vzip_u8(uint8x8_t __p0, uint8x8_t __p1) {
29715 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29726 __ai uint32x2x2_t vzip_u32(uint32x2_t __p0, uint32x2_t __p1) {
29728 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
29732 __ai uint32x2x2_t vzip_u32(uint32x2_t __p0, uint32x2_t __p1) {
29734 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29745 __ai uint16x4x2_t vzip_u16(uint16x4_t __p0, uint16x4_t __p1) {
29747 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
29751 __ai uint16x4x2_t vzip_u16(uint16x4_t __p0, uint16x4_t __p1) {
29753 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
29764 __ai int8x8x2_t vzip_s8(int8x8_t __p0, int8x8_t __p1) {
29766 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
29770 __ai int8x8x2_t vzip_s8(int8x8_t __p0, int8x8_t __p1) {
29772 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29783 __ai float32x2x2_t vzip_f32(float32x2_t __p0, float32x2_t __p1) {
29785 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
29789 __ai float32x2x2_t vzip_f32(float32x2_t __p0, float32x2_t __p1) {
29791 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29802 __ai int32x2x2_t vzip_s32(int32x2_t __p0, int32x2_t __p1) {
29804 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
29808 __ai int32x2x2_t vzip_s32(int32x2_t __p0, int32x2_t __p1) {
29810 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
29821 __ai int16x4x2_t vzip_s16(int16x4_t __p0, int16x4_t __p1) {
29823 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
29827 __ai int16x4x2_t vzip_s16(int16x4_t __p0, int16x4_t __p1) {
29829 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
34035 __ai float32x4_t vmaxnmq_f32(float32x4_t __p0, float32x4_t __p1) {
34037 __ret = (float32x4_t) __builtin_neon_vmaxnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
34041 __ai float32x4_t vmaxnmq_f32(float32x4_t __p0, float32x4_t __p1) {
34043 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
34052 __ai float32x2_t vmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {
34054 __ret = (float32x2_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
34058 __ai float32x2_t vmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {
34060 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
34069 __ai float32x4_t vminnmq_f32(float32x4_t __p0, float32x4_t __p1) {
34071 __ret = (float32x4_t) __builtin_neon_vminnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
34075 __ai float32x4_t vminnmq_f32(float32x4_t __p0, float32x4_t __p1) {
34077 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
34086 __ai float32x2_t vminnm_f32(float32x2_t __p0, float32x2_t __p1) {
34088 __ret = (float32x2_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
34092 __ai float32x2_t vminnm_f32(float32x2_t __p0, float32x2_t __p1) {
34094 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40079 __ai float64x2_t vmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {
40081 __ret = (float64x2_t) __builtin_neon_vmaxnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
40085 __ai float64x2_t vmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {
40087 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40096 __ai float64x1_t vmaxnm_f64(float64x1_t __p0, float64x1_t __p1) {
40098 __ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40102 __ai float64x1_t vmaxnm_f64(float64x1_t __p0, float64x1_t __p1) {
40104 __ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40110 __ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
40112 __ret = (float64x2_t) __builtin_neon_vminnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
40116 __ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
40118 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40127 __ai float64x1_t vminnm_f64(float64x1_t __p0, float64x1_t __p1) {
40129 __ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40133 __ai float64x1_t vminnm_f64(float64x1_t __p0, float64x1_t __p1) {
40135 __ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40143 __ai uint8x16_t vaesdq_u8(uint8x16_t __p0, uint8x16_t __p1) {
40145 __ret = (uint8x16_t) __builtin_neon_vaesdq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
40149 __ai uint8x16_t vaesdq_u8(uint8x16_t __p0, uint8x16_t __p1) {
40151 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
40160 __ai uint8x16_t vaeseq_u8(uint8x16_t __p0, uint8x16_t __p1) {
40162 __ret = (uint8x16_t) __builtin_neon_vaeseq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
40166 __ai uint8x16_t vaeseq_u8(uint8x16_t __p0, uint8x16_t __p1) {
40168 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
40209 __ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40211 __ret = (uint32x4_t) __builtin_neon_vsha1cq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);
40215 __ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40219 __ret = (uint32x4_t) __builtin_neon_vsha1cq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);
40240 __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40242 __ret = (uint32x4_t) __builtin_neon_vsha1mq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);
40246 __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40250 __ret = (uint32x4_t) __builtin_neon_vsha1mq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);
40257 __ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40259 __ret = (uint32x4_t) __builtin_neon_vsha1pq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);
40263 __ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
40267 __ret = (uint32x4_t) __builtin_neon_vsha1pq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);
40274 __ai uint32x4_t vsha1su0q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40276 __ret = (uint32x4_t) __builtin_neon_vsha1su0q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 50);
40280 __ai uint32x4_t vsha1su0q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40282 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40292 __ai uint32x4_t vsha1su1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
40294 __ret = (uint32x4_t) __builtin_neon_vsha1su1q_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
40298 __ai uint32x4_t vsha1su1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
40300 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40309 __ai uint32x4_t vsha256hq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40311 __ret = (uint32x4_t) __builtin_neon_vsha256hq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 50);
40315 __ai uint32x4_t vsha256hq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40317 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40327 __ai uint32x4_t vsha256h2q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40329 __ret = (uint32x4_t) __builtin_neon_vsha256h2q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 50);
40333 __ai uint32x4_t vsha256h2q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40335 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40345 __ai uint32x4_t vsha256su0q_u32(uint32x4_t __p0, uint32x4_t __p1) {
40347 __ret = (uint32x4_t) __builtin_neon_vsha256su0q_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
40351 __ai uint32x4_t vsha256su0q_u32(uint32x4_t __p0, uint32x4_t __p1) {
40353 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40362 __ai uint32x4_t vsha256su1q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40364 __ret = (uint32x4_t) __builtin_neon_vsha256su1q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 50);
40368 __ai uint32x4_t vsha256su1q_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
40370 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40382 __ai float32x4_t vfmaq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
40384 __ret = (float32x4_t) __builtin_neon_vfmaq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 41);
40388 __ai float32x4_t vfmaq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
40390 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40397 __ai float32x4_t __noswap_vfmaq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
40399 __ret = (float32x4_t) __builtin_neon_vfmaq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 41);
40405 __ai float32x2_t vfma_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
40407 __ret = (float32x2_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
40411 __ai float32x2_t vfma_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
40413 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40420 __ai float32x2_t __noswap_vfma_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
40422 __ret = (float32x2_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
40428 __ai float32x4_t vfmsq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
40430 __ret = vfmaq_f32(__p0, -__p1, __p2);
40434 __ai float32x4_t vfmsq_f32(float32x4_t __p0, float32x4_t __p1, float32x4_t __p2) {
40436 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40446 __ai float32x2_t vfms_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
40448 __ret = vfma_f32(__p0, -__p1, __p2);
40452 __ai float32x2_t vfms_f32(float32x2_t __p0, float32x2_t __p1, float32x2_t __p2) {
40454 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40466 __ai int32x4_t vqrdmlahq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
40468 __ret = vqaddq_s32(__p0, vqrdmulhq_s32(__p1, __p2));
40472 __ai int32x4_t vqrdmlahq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
40474 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40484 __ai int16x8_t vqrdmlahq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
40486 __ret = vqaddq_s16(__p0, vqrdmulhq_s16(__p1, __p2));
40490 __ai int16x8_t vqrdmlahq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
40492 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
40502 __ai int32x2_t vqrdmlah_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
40504 __ret = vqadd_s32(__p0, vqrdmulh_s32(__p1, __p2));
40508 __ai int32x2_t vqrdmlah_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
40510 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40520 __ai int16x4_t vqrdmlah_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
40522 __ret = vqadd_s16(__p0, vqrdmulh_s16(__p1, __p2));
40526 __ai int16x4_t vqrdmlah_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
40528 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40538 #define vqrdmlahq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40540 int32x4_t __s1 = __p1; \
40547 #define vqrdmlahq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40549 int32x4_t __s1 = __p1; \
40562 #define vqrdmlahq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40564 int16x8_t __s1 = __p1; \
40571 #define vqrdmlahq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40573 int16x8_t __s1 = __p1; \
40586 #define vqrdmlah_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40588 int32x2_t __s1 = __p1; \
40595 #define vqrdmlah_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40597 int32x2_t __s1 = __p1; \
40610 #define vqrdmlah_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40612 int16x4_t __s1 = __p1; \
40619 #define vqrdmlah_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40621 int16x4_t __s1 = __p1; \
40634 __ai int32x4_t vqrdmlshq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
40636 __ret = vqsubq_s32(__p0, vqrdmulhq_s32(__p1, __p2));
40640 __ai int32x4_t vqrdmlshq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
40642 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40652 __ai int16x8_t vqrdmlshq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
40654 __ret = vqsubq_s16(__p0, vqrdmulhq_s16(__p1, __p2));
40658 __ai int16x8_t vqrdmlshq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
40660 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
40670 __ai int32x2_t vqrdmlsh_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
40672 __ret = vqsub_s32(__p0, vqrdmulh_s32(__p1, __p2));
40676 __ai int32x2_t vqrdmlsh_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
40678 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
40688 __ai int16x4_t vqrdmlsh_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
40690 __ret = vqsub_s16(__p0, vqrdmulh_s16(__p1, __p2));
40694 __ai int16x4_t vqrdmlsh_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
40696 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
40706 #define vqrdmlshq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40708 int32x4_t __s1 = __p1; \
40715 #define vqrdmlshq_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40717 int32x4_t __s1 = __p1; \
40730 #define vqrdmlshq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40732 int16x8_t __s1 = __p1; \
40739 #define vqrdmlshq_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40741 int16x8_t __s1 = __p1; \
40754 #define vqrdmlsh_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40756 int32x2_t __s1 = __p1; \
40763 #define vqrdmlsh_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40765 int32x2_t __s1 = __p1; \
40778 #define vqrdmlsh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40780 int16x4_t __s1 = __p1; \
40787 #define vqrdmlsh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40789 int16x4_t __s1 = __p1; \
40804 #define vqrdmlahq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40806 int32x4_t __s1 = __p1; \
40813 #define vqrdmlahq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40815 int32x4_t __s1 = __p1; \
40828 #define vqrdmlahq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40830 int16x8_t __s1 = __p1; \
40837 #define vqrdmlahq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40839 int16x8_t __s1 = __p1; \
40852 #define vqrdmlah_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40854 int32x2_t __s1 = __p1; \
40861 #define vqrdmlah_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40863 int32x2_t __s1 = __p1; \
40876 #define vqrdmlah_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40878 int16x4_t __s1 = __p1; \
40885 #define vqrdmlah_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40887 int16x4_t __s1 = __p1; \
40900 #define vqrdmlshq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40902 int32x4_t __s1 = __p1; \
40909 #define vqrdmlshq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40911 int32x4_t __s1 = __p1; \
40924 #define vqrdmlshq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40926 int16x8_t __s1 = __p1; \
40933 #define vqrdmlshq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40935 int16x8_t __s1 = __p1; \
40948 #define vqrdmlsh_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40950 int32x2_t __s1 = __p1; \
40957 #define vqrdmlsh_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
40959 int32x2_t __s1 = __p1; \
40972 #define vqrdmlsh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40974 int16x4_t __s1 = __p1; \
40981 #define vqrdmlsh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
40983 int16x4_t __s1 = __p1; \
40998 __ai float64x2_t vabdq_f64(float64x2_t __p0, float64x2_t __p1) {
41000 __ret = (float64x2_t) __builtin_neon_vabdq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
41004 __ai float64x2_t vabdq_f64(float64x2_t __p0, float64x2_t __p1) {
41006 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41015 __ai float64x1_t vabd_f64(float64x1_t __p0, float64x1_t __p1) {
41017 __ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
41021 __ai float64x1_t vabd_f64(float64x1_t __p0, float64x1_t __p1) {
41023 __ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
41029 __ai float64_t vabdd_f64(float64_t __p0, float64_t __p1) {
41031 __ret = (float64_t) __builtin_neon_vabdd_f64(__p0, __p1);
41035 __ai float64_t vabdd_f64(float64_t __p0, float64_t __p1) {
41037 __ret = (float64_t) __builtin_neon_vabdd_f64(__p0, __p1);
41043 __ai float32_t vabds_f32(float32_t __p0, float32_t __p1) {
41045 __ret = (float32_t) __builtin_neon_vabds_f32(__p0, __p1);
41049 __ai float32_t vabds_f32(float32_t __p0, float32_t __p1) {
41051 __ret = (float32_t) __builtin_neon_vabds_f32(__p0, __p1);
41131 __ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {
41133 __ret = __p0 + __p1;
41137 __ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {
41139 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41148 __ai float64x1_t vadd_f64(float64x1_t __p0, float64x1_t __p1) {
41150 __ret = __p0 + __p1;
41154 __ai float64x1_t vadd_f64(float64x1_t __p0, float64x1_t __p1) {
41156 __ret = __p0 + __p1;
41162 __ai uint64_t vaddd_u64(uint64_t __p0, uint64_t __p1) {
41164 __ret = (uint64_t) __builtin_neon_vaddd_u64(__p0, __p1);
41168 __ai uint64_t vaddd_u64(uint64_t __p0, uint64_t __p1) {
41170 __ret = (uint64_t) __builtin_neon_vaddd_u64(__p0, __p1);
41176 __ai int64_t vaddd_s64(int64_t __p0, int64_t __p1) {
41178 __ret = (int64_t) __builtin_neon_vaddd_s64(__p0, __p1);
41182 __ai int64_t vaddd_s64(int64_t __p0, int64_t __p1) {
41184 __ret = (int64_t) __builtin_neon_vaddd_s64(__p0, __p1);
41190 __ai uint16x8_t vaddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
41192 __ret = vcombine_u16(__p0, vaddhn_u32(__p1, __p2));
41196 __ai uint16x8_t vaddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
41198 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
41208 __ai uint32x4_t vaddhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
41210 __ret = vcombine_u32(__p0, vaddhn_u64(__p1, __p2));
41214 __ai uint32x4_t vaddhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
41216 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41226 __ai uint8x16_t vaddhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
41228 __ret = vcombine_u8(__p0, vaddhn_u16(__p1, __p2));
41232 __ai uint8x16_t vaddhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
41234 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
41244 __ai int16x8_t vaddhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
41246 __ret = vcombine_s16(__p0, vaddhn_s32(__p1, __p2));
41250 __ai int16x8_t vaddhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
41252 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
41262 __ai int32x4_t vaddhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
41264 __ret = vcombine_s32(__p0, vaddhn_s64(__p1, __p2));
41268 __ai int32x4_t vaddhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
41270 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41280 __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
41282 __ret = vcombine_s8(__p0, vaddhn_s16(__p1, __p2));
41286 __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
41288 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
41733 __ai poly64x1_t vbsl_p64(uint64x1_t __p0, poly64x1_t __p1, poly64x1_t __p2) {
41735 __ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
41739 __ai poly64x1_t vbsl_p64(uint64x1_t __p0, poly64x1_t __p1, poly64x1_t __p2) {
41741 __ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
41747 __ai poly64x2_t vbslq_p64(uint64x2_t __p0, poly64x2_t __p1, poly64x2_t __p2) {
41749 __ret = (poly64x2_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 38);
41753 __ai poly64x2_t vbslq_p64(uint64x2_t __p0, poly64x2_t __p1, poly64x2_t __p2) {
41755 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41765 __ai float64x2_t vbslq_f64(uint64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
41767 __ret = (float64x2_t) __builtin_neon_vbslq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 42);
41771 __ai float64x2_t vbslq_f64(uint64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
41773 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41783 __ai float64x1_t vbsl_f64(uint64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
41785 __ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
41789 __ai float64x1_t vbsl_f64(uint64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
41791 __ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
41797 __ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {
41799 __ret = (uint64x2_t) __builtin_neon_vcageq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
41803 __ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {
41805 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41814 __ai uint64x1_t vcage_f64(float64x1_t __p0, float64x1_t __p1) {
41816 __ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41820 __ai uint64x1_t vcage_f64(float64x1_t __p0, float64x1_t __p1) {
41822 __ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41828 __ai uint64_t vcaged_f64(float64_t __p0, float64_t __p1) {
41830 __ret = (uint64_t) __builtin_neon_vcaged_f64(__p0, __p1);
41834 __ai uint64_t vcaged_f64(float64_t __p0, float64_t __p1) {
41836 __ret = (uint64_t) __builtin_neon_vcaged_f64(__p0, __p1);
41842 __ai uint32_t vcages_f32(float32_t __p0, float32_t __p1) {
41844 __ret = (uint32_t) __builtin_neon_vcages_f32(__p0, __p1);
41848 __ai uint32_t vcages_f32(float32_t __p0, float32_t __p1) {
41850 __ret = (uint32_t) __builtin_neon_vcages_f32(__p0, __p1);
41856 __ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {
41858 __ret = (uint64x2_t) __builtin_neon_vcagtq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
41862 __ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {
41864 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41873 __ai uint64x1_t vcagt_f64(float64x1_t __p0, float64x1_t __p1) {
41875 __ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41879 __ai uint64x1_t vcagt_f64(float64x1_t __p0, float64x1_t __p1) {
41881 __ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41887 __ai uint64_t vcagtd_f64(float64_t __p0, float64_t __p1) {
41889 __ret = (uint64_t) __builtin_neon_vcagtd_f64(__p0, __p1);
41893 __ai uint64_t vcagtd_f64(float64_t __p0, float64_t __p1) {
41895 __ret = (uint64_t) __builtin_neon_vcagtd_f64(__p0, __p1);
41901 __ai uint32_t vcagts_f32(float32_t __p0, float32_t __p1) {
41903 __ret = (uint32_t) __builtin_neon_vcagts_f32(__p0, __p1);
41907 __ai uint32_t vcagts_f32(float32_t __p0, float32_t __p1) {
41909 __ret = (uint32_t) __builtin_neon_vcagts_f32(__p0, __p1);
41915 __ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {
41917 __ret = (uint64x2_t) __builtin_neon_vcaleq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
41921 __ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {
41923 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41932 __ai uint64x1_t vcale_f64(float64x1_t __p0, float64x1_t __p1) {
41934 __ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41938 __ai uint64x1_t vcale_f64(float64x1_t __p0, float64x1_t __p1) {
41940 __ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41946 __ai uint64_t vcaled_f64(float64_t __p0, float64_t __p1) {
41948 __ret = (uint64_t) __builtin_neon_vcaled_f64(__p0, __p1);
41952 __ai uint64_t vcaled_f64(float64_t __p0, float64_t __p1) {
41954 __ret = (uint64_t) __builtin_neon_vcaled_f64(__p0, __p1);
41960 __ai uint32_t vcales_f32(float32_t __p0, float32_t __p1) {
41962 __ret = (uint32_t) __builtin_neon_vcales_f32(__p0, __p1);
41966 __ai uint32_t vcales_f32(float32_t __p0, float32_t __p1) {
41968 __ret = (uint32_t) __builtin_neon_vcales_f32(__p0, __p1);
41974 __ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {
41976 __ret = (uint64x2_t) __builtin_neon_vcaltq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
41980 __ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {
41982 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
41991 __ai uint64x1_t vcalt_f64(float64x1_t __p0, float64x1_t __p1) {
41993 __ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41997 __ai uint64x1_t vcalt_f64(float64x1_t __p0, float64x1_t __p1) {
41999 __ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
42005 __ai uint64_t vcaltd_f64(float64_t __p0, float64_t __p1) {
42007 __ret = (uint64_t) __builtin_neon_vcaltd_f64(__p0, __p1);
42011 __ai uint64_t vcaltd_f64(float64_t __p0, float64_t __p1) {
42013 __ret = (uint64_t) __builtin_neon_vcaltd_f64(__p0, __p1);
42019 __ai uint32_t vcalts_f32(float32_t __p0, float32_t __p1) {
42021 __ret = (uint32_t) __builtin_neon_vcalts_f32(__p0, __p1);
42025 __ai uint32_t vcalts_f32(float32_t __p0, float32_t __p1) {
42027 __ret = (uint32_t) __builtin_neon_vcalts_f32(__p0, __p1);
42033 __ai uint64x1_t vceq_p64(poly64x1_t __p0, poly64x1_t __p1) {
42035 __ret = (uint64x1_t)(__p0 == __p1);
42039 __ai uint64x1_t vceq_p64(poly64x1_t __p0, poly64x1_t __p1) {
42041 __ret = (uint64x1_t)(__p0 == __p1);
42047 __ai uint64x2_t vceqq_p64(poly64x2_t __p0, poly64x2_t __p1) {
42049 __ret = (uint64x2_t)(__p0 == __p1);
42053 __ai uint64x2_t vceqq_p64(poly64x2_t __p0, poly64x2_t __p1) {
42055 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42064 __ai uint64x2_t vceqq_u64(uint64x2_t __p0, uint64x2_t __p1) {
42066 __ret = (uint64x2_t)(__p0 == __p1);
42070 __ai uint64x2_t vceqq_u64(uint64x2_t __p0, uint64x2_t __p1) {
42072 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42081 __ai uint64x2_t vceqq_f64(float64x2_t __p0, float64x2_t __p1) {
42083 __ret = (uint64x2_t)(__p0 == __p1);
42087 __ai uint64x2_t vceqq_f64(float64x2_t __p0, float64x2_t __p1) {
42089 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42098 __ai uint64x2_t vceqq_s64(int64x2_t __p0, int64x2_t __p1) {
42100 __ret = (uint64x2_t)(__p0 == __p1);
42104 __ai uint64x2_t vceqq_s64(int64x2_t __p0, int64x2_t __p1) {
42106 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42115 __ai uint64x1_t vceq_u64(uint64x1_t __p0, uint64x1_t __p1) {
42117 __ret = (uint64x1_t)(__p0 == __p1);
42121 __ai uint64x1_t vceq_u64(uint64x1_t __p0, uint64x1_t __p1) {
42123 __ret = (uint64x1_t)(__p0 == __p1);
42129 __ai uint64x1_t vceq_f64(float64x1_t __p0, float64x1_t __p1) {
42131 __ret = (uint64x1_t)(__p0 == __p1);
42135 __ai uint64x1_t vceq_f64(float64x1_t __p0, float64x1_t __p1) {
42137 __ret = (uint64x1_t)(__p0 == __p1);
42143 __ai uint64x1_t vceq_s64(int64x1_t __p0, int64x1_t __p1) {
42145 __ret = (uint64x1_t)(__p0 == __p1);
42149 __ai uint64x1_t vceq_s64(int64x1_t __p0, int64x1_t __p1) {
42151 __ret = (uint64x1_t)(__p0 == __p1);
42157 __ai uint64_t vceqd_u64(uint64_t __p0, uint64_t __p1) {
42159 __ret = (uint64_t) __builtin_neon_vceqd_u64(__p0, __p1);
42163 __ai uint64_t vceqd_u64(uint64_t __p0, uint64_t __p1) {
42165 __ret = (uint64_t) __builtin_neon_vceqd_u64(__p0, __p1);
42171 __ai int64_t vceqd_s64(int64_t __p0, int64_t __p1) {
42173 __ret = (int64_t) __builtin_neon_vceqd_s64(__p0, __p1);
42177 __ai int64_t vceqd_s64(int64_t __p0, int64_t __p1) {
42179 __ret = (int64_t) __builtin_neon_vceqd_s64(__p0, __p1);
42185 __ai uint64_t vceqd_f64(float64_t __p0, float64_t __p1) {
42187 __ret = (uint64_t) __builtin_neon_vceqd_f64(__p0, __p1);
42191 __ai uint64_t vceqd_f64(float64_t __p0, float64_t __p1) {
42193 __ret = (uint64_t) __builtin_neon_vceqd_f64(__p0, __p1);
42199 __ai uint32_t vceqs_f32(float32_t __p0, float32_t __p1) {
42201 __ret = (uint32_t) __builtin_neon_vceqs_f32(__p0, __p1);
42205 __ai uint32_t vceqs_f32(float32_t __p0, float32_t __p1) {
42207 __ret = (uint32_t) __builtin_neon_vceqs_f32(__p0, __p1);
42677 __ai uint64x2_t vcgeq_u64(uint64x2_t __p0, uint64x2_t __p1) {
42679 __ret = (uint64x2_t)(__p0 >= __p1);
42683 __ai uint64x2_t vcgeq_u64(uint64x2_t __p0, uint64x2_t __p1) {
42685 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42694 __ai uint64x2_t vcgeq_f64(float64x2_t __p0, float64x2_t __p1) {
42696 __ret = (uint64x2_t)(__p0 >= __p1);
42700 __ai uint64x2_t vcgeq_f64(float64x2_t __p0, float64x2_t __p1) {
42702 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42711 __ai uint64x2_t vcgeq_s64(int64x2_t __p0, int64x2_t __p1) {
42713 __ret = (uint64x2_t)(__p0 >= __p1);
42717 __ai uint64x2_t vcgeq_s64(int64x2_t __p0, int64x2_t __p1) {
42719 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
42728 __ai uint64x1_t vcge_u64(uint64x1_t __p0, uint64x1_t __p1) {
42730 __ret = (uint64x1_t)(__p0 >= __p1);
42734 __ai uint64x1_t vcge_u64(uint64x1_t __p0, uint64x1_t __p1) {
42736 __ret = (uint64x1_t)(__p0 >= __p1);
42742 __ai uint64x1_t vcge_f64(float64x1_t __p0, float64x1_t __p1) {
42744 __ret = (uint64x1_t)(__p0 >= __p1);
42748 __ai uint64x1_t vcge_f64(float64x1_t __p0, float64x1_t __p1) {
42750 __ret = (uint64x1_t)(__p0 >= __p1);
42756 __ai uint64x1_t vcge_s64(int64x1_t __p0, int64x1_t __p1) {
42758 __ret = (uint64x1_t)(__p0 >= __p1);
42762 __ai uint64x1_t vcge_s64(int64x1_t __p0, int64x1_t __p1) {
42764 __ret = (uint64x1_t)(__p0 >= __p1);
42770 __ai int64_t vcged_s64(int64_t __p0, int64_t __p1) {
42772 __ret = (int64_t) __builtin_neon_vcged_s64(__p0, __p1);
42776 __ai int64_t vcged_s64(int64_t __p0, int64_t __p1) {
42778 __ret = (int64_t) __builtin_neon_vcged_s64(__p0, __p1);
42784 __ai uint64_t vcged_u64(uint64_t __p0, uint64_t __p1) {
42786 __ret = (uint64_t) __builtin_neon_vcged_u64(__p0, __p1);
42790 __ai uint64_t vcged_u64(uint64_t __p0, uint64_t __p1) {
42792 __ret = (uint64_t) __builtin_neon_vcged_u64(__p0, __p1);
42798 __ai uint64_t vcged_f64(float64_t __p0, float64_t __p1) {
42800 __ret = (uint64_t) __builtin_neon_vcged_f64(__p0, __p1);
42804 __ai uint64_t vcged_f64(float64_t __p0, float64_t __p1) {
42806 __ret = (uint64_t) __builtin_neon_vcged_f64(__p0, __p1);
42812 __ai uint32_t vcges_f32(float32_t __p0, float32_t __p1) {
42814 __ret = (uint32_t) __builtin_neon_vcges_f32(__p0, __p1);
42818 __ai uint32_t vcges_f32(float32_t __p0, float32_t __p1) {
42820 __ret = (uint32_t) __builtin_neon_vcges_f32(__p0, __p1);
43056 __ai uint64x2_t vcgtq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43058 __ret = (uint64x2_t)(__p0 > __p1);
43062 __ai uint64x2_t vcgtq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43064 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43073 __ai uint64x2_t vcgtq_f64(float64x2_t __p0, float64x2_t __p1) {
43075 __ret = (uint64x2_t)(__p0 > __p1);
43079 __ai uint64x2_t vcgtq_f64(float64x2_t __p0, float64x2_t __p1) {
43081 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43090 __ai uint64x2_t vcgtq_s64(int64x2_t __p0, int64x2_t __p1) {
43092 __ret = (uint64x2_t)(__p0 > __p1);
43096 __ai uint64x2_t vcgtq_s64(int64x2_t __p0, int64x2_t __p1) {
43098 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43107 __ai uint64x1_t vcgt_u64(uint64x1_t __p0, uint64x1_t __p1) {
43109 __ret = (uint64x1_t)(__p0 > __p1);
43113 __ai uint64x1_t vcgt_u64(uint64x1_t __p0, uint64x1_t __p1) {
43115 __ret = (uint64x1_t)(__p0 > __p1);
43121 __ai uint64x1_t vcgt_f64(float64x1_t __p0, float64x1_t __p1) {
43123 __ret = (uint64x1_t)(__p0 > __p1);
43127 __ai uint64x1_t vcgt_f64(float64x1_t __p0, float64x1_t __p1) {
43129 __ret = (uint64x1_t)(__p0 > __p1);
43135 __ai uint64x1_t vcgt_s64(int64x1_t __p0, int64x1_t __p1) {
43137 __ret = (uint64x1_t)(__p0 > __p1);
43141 __ai uint64x1_t vcgt_s64(int64x1_t __p0, int64x1_t __p1) {
43143 __ret = (uint64x1_t)(__p0 > __p1);
43149 __ai int64_t vcgtd_s64(int64_t __p0, int64_t __p1) {
43151 __ret = (int64_t) __builtin_neon_vcgtd_s64(__p0, __p1);
43155 __ai int64_t vcgtd_s64(int64_t __p0, int64_t __p1) {
43157 __ret = (int64_t) __builtin_neon_vcgtd_s64(__p0, __p1);
43163 __ai uint64_t vcgtd_u64(uint64_t __p0, uint64_t __p1) {
43165 __ret = (uint64_t) __builtin_neon_vcgtd_u64(__p0, __p1);
43169 __ai uint64_t vcgtd_u64(uint64_t __p0, uint64_t __p1) {
43171 __ret = (uint64_t) __builtin_neon_vcgtd_u64(__p0, __p1);
43177 __ai uint64_t vcgtd_f64(float64_t __p0, float64_t __p1) {
43179 __ret = (uint64_t) __builtin_neon_vcgtd_f64(__p0, __p1);
43183 __ai uint64_t vcgtd_f64(float64_t __p0, float64_t __p1) {
43185 __ret = (uint64_t) __builtin_neon_vcgtd_f64(__p0, __p1);
43191 __ai uint32_t vcgts_f32(float32_t __p0, float32_t __p1) {
43193 __ret = (uint32_t) __builtin_neon_vcgts_f32(__p0, __p1);
43197 __ai uint32_t vcgts_f32(float32_t __p0, float32_t __p1) {
43199 __ret = (uint32_t) __builtin_neon_vcgts_f32(__p0, __p1);
43435 __ai uint64x2_t vcleq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43437 __ret = (uint64x2_t)(__p0 <= __p1);
43441 __ai uint64x2_t vcleq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43443 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43452 __ai uint64x2_t vcleq_f64(float64x2_t __p0, float64x2_t __p1) {
43454 __ret = (uint64x2_t)(__p0 <= __p1);
43458 __ai uint64x2_t vcleq_f64(float64x2_t __p0, float64x2_t __p1) {
43460 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43469 __ai uint64x2_t vcleq_s64(int64x2_t __p0, int64x2_t __p1) {
43471 __ret = (uint64x2_t)(__p0 <= __p1);
43475 __ai uint64x2_t vcleq_s64(int64x2_t __p0, int64x2_t __p1) {
43477 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43486 __ai uint64x1_t vcle_u64(uint64x1_t __p0, uint64x1_t __p1) {
43488 __ret = (uint64x1_t)(__p0 <= __p1);
43492 __ai uint64x1_t vcle_u64(uint64x1_t __p0, uint64x1_t __p1) {
43494 __ret = (uint64x1_t)(__p0 <= __p1);
43500 __ai uint64x1_t vcle_f64(float64x1_t __p0, float64x1_t __p1) {
43502 __ret = (uint64x1_t)(__p0 <= __p1);
43506 __ai uint64x1_t vcle_f64(float64x1_t __p0, float64x1_t __p1) {
43508 __ret = (uint64x1_t)(__p0 <= __p1);
43514 __ai uint64x1_t vcle_s64(int64x1_t __p0, int64x1_t __p1) {
43516 __ret = (uint64x1_t)(__p0 <= __p1);
43520 __ai uint64x1_t vcle_s64(int64x1_t __p0, int64x1_t __p1) {
43522 __ret = (uint64x1_t)(__p0 <= __p1);
43528 __ai uint64_t vcled_u64(uint64_t __p0, uint64_t __p1) {
43530 __ret = (uint64_t) __builtin_neon_vcled_u64(__p0, __p1);
43534 __ai uint64_t vcled_u64(uint64_t __p0, uint64_t __p1) {
43536 __ret = (uint64_t) __builtin_neon_vcled_u64(__p0, __p1);
43542 __ai int64_t vcled_s64(int64_t __p0, int64_t __p1) {
43544 __ret = (int64_t) __builtin_neon_vcled_s64(__p0, __p1);
43548 __ai int64_t vcled_s64(int64_t __p0, int64_t __p1) {
43550 __ret = (int64_t) __builtin_neon_vcled_s64(__p0, __p1);
43556 __ai uint64_t vcled_f64(float64_t __p0, float64_t __p1) {
43558 __ret = (uint64_t) __builtin_neon_vcled_f64(__p0, __p1);
43562 __ai uint64_t vcled_f64(float64_t __p0, float64_t __p1) {
43564 __ret = (uint64_t) __builtin_neon_vcled_f64(__p0, __p1);
43570 __ai uint32_t vcles_f32(float32_t __p0, float32_t __p1) {
43572 __ret = (uint32_t) __builtin_neon_vcles_f32(__p0, __p1);
43576 __ai uint32_t vcles_f32(float32_t __p0, float32_t __p1) {
43578 __ret = (uint32_t) __builtin_neon_vcles_f32(__p0, __p1);
43814 __ai uint64x2_t vcltq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43816 __ret = (uint64x2_t)(__p0 < __p1);
43820 __ai uint64x2_t vcltq_u64(uint64x2_t __p0, uint64x2_t __p1) {
43822 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43831 __ai uint64x2_t vcltq_f64(float64x2_t __p0, float64x2_t __p1) {
43833 __ret = (uint64x2_t)(__p0 < __p1);
43837 __ai uint64x2_t vcltq_f64(float64x2_t __p0, float64x2_t __p1) {
43839 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43848 __ai uint64x2_t vcltq_s64(int64x2_t __p0, int64x2_t __p1) {
43850 __ret = (uint64x2_t)(__p0 < __p1);
43854 __ai uint64x2_t vcltq_s64(int64x2_t __p0, int64x2_t __p1) {
43856 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
43865 __ai uint64x1_t vclt_u64(uint64x1_t __p0, uint64x1_t __p1) {
43867 __ret = (uint64x1_t)(__p0 < __p1);
43871 __ai uint64x1_t vclt_u64(uint64x1_t __p0, uint64x1_t __p1) {
43873 __ret = (uint64x1_t)(__p0 < __p1);
43879 __ai uint64x1_t vclt_f64(float64x1_t __p0, float64x1_t __p1) {
43881 __ret = (uint64x1_t)(__p0 < __p1);
43885 __ai uint64x1_t vclt_f64(float64x1_t __p0, float64x1_t __p1) {
43887 __ret = (uint64x1_t)(__p0 < __p1);
43893 __ai uint64x1_t vclt_s64(int64x1_t __p0, int64x1_t __p1) {
43895 __ret = (uint64x1_t)(__p0 < __p1);
43899 __ai uint64x1_t vclt_s64(int64x1_t __p0, int64x1_t __p1) {
43901 __ret = (uint64x1_t)(__p0 < __p1);
43907 __ai uint64_t vcltd_u64(uint64_t __p0, uint64_t __p1) {
43909 __ret = (uint64_t) __builtin_neon_vcltd_u64(__p0, __p1);
43913 __ai uint64_t vcltd_u64(uint64_t __p0, uint64_t __p1) {
43915 __ret = (uint64_t) __builtin_neon_vcltd_u64(__p0, __p1);
43921 __ai int64_t vcltd_s64(int64_t __p0, int64_t __p1) {
43923 __ret = (int64_t) __builtin_neon_vcltd_s64(__p0, __p1);
43927 __ai int64_t vcltd_s64(int64_t __p0, int64_t __p1) {
43929 __ret = (int64_t) __builtin_neon_vcltd_s64(__p0, __p1);
43935 __ai uint64_t vcltd_f64(float64_t __p0, float64_t __p1) {
43937 __ret = (uint64_t) __builtin_neon_vcltd_f64(__p0, __p1);
43941 __ai uint64_t vcltd_f64(float64_t __p0, float64_t __p1) {
43943 __ret = (uint64_t) __builtin_neon_vcltd_f64(__p0, __p1);
43949 __ai uint32_t vclts_f32(float32_t __p0, float32_t __p1) {
43951 __ret = (uint32_t) __builtin_neon_vclts_f32(__p0, __p1);
43955 __ai uint32_t vclts_f32(float32_t __p0, float32_t __p1) {
43957 __ret = (uint32_t) __builtin_neon_vclts_f32(__p0, __p1);
44193 __ai poly64x2_t vcombine_p64(poly64x1_t __p0, poly64x1_t __p1) {
44195 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
44199 __ai poly64x2_t vcombine_p64(poly64x1_t __p0, poly64x1_t __p1) {
44201 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
44208 __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
44210 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
44214 __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
44216 __ret = __builtin_shufflevector(__p0, __p1, 0, 1);
45321 __ai float16x8_t vcvt_high_f16_f32(float16x4_t __p0, float32x4_t __p1) {
45323 __ret = vcombine_f16(__p0, vcvt_f16_f32(__p1));
45327 __ai float16x8_t vcvt_high_f16_f32(float16x4_t __p0, float32x4_t __p1) {
45329 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
45354 __ai float32x4_t vcvt_high_f32_f64(float32x2_t __p0, float64x2_t __p1) {
45356 __ret = vcombine_f32(__p0, vcvt_f32_f64(__p1));
45360 __ai float32x4_t vcvt_high_f32_f64(float32x2_t __p0, float64x2_t __p1) {
45362 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
45387 #define vcvts_n_f32_u32(__p0, __p1) __extension__ ({ \
45390 __ret = (float32_t) __builtin_neon_vcvts_n_f32_u32(__s0, __p1); \
45394 #define vcvts_n_f32_u32(__p0, __p1) __extension__ ({ \
45397 __ret = (float32_t) __builtin_neon_vcvts_n_f32_u32(__s0, __p1); \
45403 #define vcvts_n_f32_s32(__p0, __p1) __extension__ ({ \
45406 __ret = (float32_t) __builtin_neon_vcvts_n_f32_s32(__s0, __p1); \
45410 #define vcvts_n_f32_s32(__p0, __p1) __extension__ ({ \
45413 __ret = (float32_t) __builtin_neon_vcvts_n_f32_s32(__s0, __p1); \
45419 #define vcvtq_n_f64_u64(__p0, __p1) __extension__ ({ \
45422 __ret = (float64x2_t) __builtin_neon_vcvtq_n_f64_v((int8x16_t)__s0, __p1, 51); \
45426 #define vcvtq_n_f64_u64(__p0, __p1) __extension__ ({ \
45430 __ret = (float64x2_t) __builtin_neon_vcvtq_n_f64_v((int8x16_t)__rev0, __p1, 51); \
45437 #define vcvtq_n_f64_s64(__p0, __p1) __extension__ ({ \
45440 __ret = (float64x2_t) __builtin_neon_vcvtq_n_f64_v((int8x16_t)__s0, __p1, 35); \
45444 #define vcvtq_n_f64_s64(__p0, __p1) __extension__ ({ \
45448 __ret = (float64x2_t) __builtin_neon_vcvtq_n_f64_v((int8x16_t)__rev0, __p1, 35); \
45455 #define vcvt_n_f64_u64(__p0, __p1) __extension__ ({ \
45458 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
45462 #define vcvt_n_f64_u64(__p0, __p1) __extension__ ({ \
45465 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
45471 #define vcvt_n_f64_s64(__p0, __p1) __extension__ ({ \
45474 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
45478 #define vcvt_n_f64_s64(__p0, __p1) __extension__ ({ \
45481 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
45487 #define vcvtd_n_f64_u64(__p0, __p1) __extension__ ({ \
45490 __ret = (float64_t) __builtin_neon_vcvtd_n_f64_u64(__s0, __p1); \
45494 #define vcvtd_n_f64_u64(__p0, __p1) __extension__ ({ \
45497 __ret = (float64_t) __builtin_neon_vcvtd_n_f64_u64(__s0, __p1); \
45503 #define vcvtd_n_f64_s64(__p0, __p1) __extension__ ({ \
45506 __ret = (float64_t) __builtin_neon_vcvtd_n_f64_s64(__s0, __p1); \
45510 #define vcvtd_n_f64_s64(__p0, __p1) __extension__ ({ \
45513 __ret = (float64_t) __builtin_neon_vcvtd_n_f64_s64(__s0, __p1); \
45519 #define vcvts_n_s32_f32(__p0, __p1) __extension__ ({ \
45522 __ret = (int32_t) __builtin_neon_vcvts_n_s32_f32(__s0, __p1); \
45526 #define vcvts_n_s32_f32(__p0, __p1) __extension__ ({ \
45529 __ret = (int32_t) __builtin_neon_vcvts_n_s32_f32(__s0, __p1); \
45535 #define vcvtq_n_s64_f64(__p0, __p1) __extension__ ({ \
45538 __ret = (int64x2_t) __builtin_neon_vcvtq_n_s64_v((int8x16_t)__s0, __p1, 35); \
45542 #define vcvtq_n_s64_f64(__p0, __p1) __extension__ ({ \
45546 __ret = (int64x2_t) __builtin_neon_vcvtq_n_s64_v((int8x16_t)__rev0, __p1, 35); \
45553 #define vcvt_n_s64_f64(__p0, __p1) __extension__ ({ \
45556 __ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
45560 #define vcvt_n_s64_f64(__p0, __p1) __extension__ ({ \
45563 __ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
45569 #define vcvtd_n_s64_f64(__p0, __p1) __extension__ ({ \
45572 __ret = (int64_t) __builtin_neon_vcvtd_n_s64_f64(__s0, __p1); \
45576 #define vcvtd_n_s64_f64(__p0, __p1) __extension__ ({ \
45579 __ret = (int64_t) __builtin_neon_vcvtd_n_s64_f64(__s0, __p1); \
45585 #define vcvts_n_u32_f32(__p0, __p1) __extension__ ({ \
45588 __ret = (uint32_t) __builtin_neon_vcvts_n_u32_f32(__s0, __p1); \
45592 #define vcvts_n_u32_f32(__p0, __p1) __extension__ ({ \
45595 __ret = (uint32_t) __builtin_neon_vcvts_n_u32_f32(__s0, __p1); \
45601 #define vcvtq_n_u64_f64(__p0, __p1) __extension__ ({ \
45604 __ret = (uint64x2_t) __builtin_neon_vcvtq_n_u64_v((int8x16_t)__s0, __p1, 51); \
45608 #define vcvtq_n_u64_f64(__p0, __p1) __extension__ ({ \
45612 __ret = (uint64x2_t) __builtin_neon_vcvtq_n_u64_v((int8x16_t)__rev0, __p1, 51); \
45619 #define vcvt_n_u64_f64(__p0, __p1) __extension__ ({ \
45622 __ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
45626 #define vcvt_n_u64_f64(__p0, __p1) __extension__ ({ \
45629 __ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
45635 #define vcvtd_n_u64_f64(__p0, __p1) __extension__ ({ \
45638 __ret = (uint64_t) __builtin_neon_vcvtd_n_u64_f64(__s0, __p1); \
45642 #define vcvtd_n_u64_f64(__p0, __p1) __extension__ ({ \
45645 __ret = (uint64_t) __builtin_neon_vcvtd_n_u64_f64(__s0, __p1); \
46026 __ai float32x4_t vcvtx_high_f32_f64(float32x2_t __p0, float64x2_t __p1) {
46028 __ret = vcombine_f32(__p0, vcvtx_f32_f64(__p1));
46032 __ai float32x4_t vcvtx_high_f32_f64(float32x2_t __p0, float64x2_t __p1) {
46034 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
46043 __ai float64x2_t vdivq_f64(float64x2_t __p0, float64x2_t __p1) {
46045 __ret = __p0 / __p1;
46049 __ai float64x2_t vdivq_f64(float64x2_t __p0, float64x2_t __p1) {
46051 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
46060 __ai float32x4_t vdivq_f32(float32x4_t __p0, float32x4_t __p1) {
46062 __ret = __p0 / __p1;
46066 __ai float32x4_t vdivq_f32(float32x4_t __p0, float32x4_t __p1) {
46068 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
46077 __ai float64x1_t vdiv_f64(float64x1_t __p0, float64x1_t __p1) {
46079 __ret = __p0 / __p1;
46083 __ai float64x1_t vdiv_f64(float64x1_t __p0, float64x1_t __p1) {
46085 __ret = __p0 / __p1;
46091 __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
46093 __ret = __p0 / __p1;
46097 __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
46099 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
46108 #define vdupb_lane_p8(__p0, __p1) __extension__ ({ \
46111 __ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46115 #define vdupb_lane_p8(__p0, __p1) __extension__ ({ \
46119 __ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46125 #define vduph_lane_p16(__p0, __p1) __extension__ ({ \
46128 __ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46132 #define vduph_lane_p16(__p0, __p1) __extension__ ({ \
46136 __ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46142 #define vdupb_lane_u8(__p0, __p1) __extension__ ({ \
46145 __ret = (uint8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46149 #define vdupb_lane_u8(__p0, __p1) __extension__ ({ \
46153 __ret = (uint8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46159 #define vdups_lane_u32(__p0, __p1) __extension__ ({ \
46162 __ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \
46166 #define vdups_lane_u32(__p0, __p1) __extension__ ({ \
46170 __ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \
46176 #define vdupd_lane_u64(__p0, __p1) __extension__ ({ \
46179 __ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46183 #define vdupd_lane_u64(__p0, __p1) __extension__ ({ \
46186 __ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46192 #define vduph_lane_u16(__p0, __p1) __extension__ ({ \
46195 __ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46199 #define vduph_lane_u16(__p0, __p1) __extension__ ({ \
46203 __ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46209 #define vdupb_lane_s8(__p0, __p1) __extension__ ({ \
46212 __ret = (int8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46216 #define vdupb_lane_s8(__p0, __p1) __extension__ ({ \
46220 __ret = (int8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46226 #define vdupd_lane_f64(__p0, __p1) __extension__ ({ \
46229 __ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \
46233 #define vdupd_lane_f64(__p0, __p1) __extension__ ({ \
46236 __ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \
46242 #define vdups_lane_f32(__p0, __p1) __extension__ ({ \
46245 __ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__s0, __p1); \
46249 #define vdups_lane_f32(__p0, __p1) __extension__ ({ \
46253 __ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__rev0, __p1); \
46259 #define vdups_lane_s32(__p0, __p1) __extension__ ({ \
46262 __ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \
46266 #define vdups_lane_s32(__p0, __p1) __extension__ ({ \
46270 __ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \
46276 #define vdupd_lane_s64(__p0, __p1) __extension__ ({ \
46279 __ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46283 #define vdupd_lane_s64(__p0, __p1) __extension__ ({ \
46286 __ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46292 #define vduph_lane_s16(__p0, __p1) __extension__ ({ \
46295 __ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46299 #define vduph_lane_s16(__p0, __p1) __extension__ ({ \
46303 __ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46309 #define vdup_lane_p64(__p0, __p1) __extension__ ({ \
46312 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46316 #define vdup_lane_p64(__p0, __p1) __extension__ ({ \
46319 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46325 #define vdupq_lane_p64(__p0, __p1) __extension__ ({ \
46328 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46332 #define vdupq_lane_p64(__p0, __p1) __extension__ ({ \
46335 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46342 #define vdupq_lane_f64(__p0, __p1) __extension__ ({ \
46345 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46349 #define vdupq_lane_f64(__p0, __p1) __extension__ ({ \
46352 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46359 #define vdupq_lane_f16(__p0, __p1) __extension__ ({ \
46362 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46366 #define vdupq_lane_f16(__p0, __p1) __extension__ ({ \
46370 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46377 #define vdup_lane_f64(__p0, __p1) __extension__ ({ \
46380 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46384 #define vdup_lane_f64(__p0, __p1) __extension__ ({ \
46387 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46393 #define vdup_lane_f16(__p0, __p1) __extension__ ({ \
46396 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46400 #define vdup_lane_f16(__p0, __p1) __extension__ ({ \
46404 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46411 #define vdupb_laneq_p8(__p0, __p1) __extension__ ({ \
46414 __ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__s0, __p1); \
46418 #define vdupb_laneq_p8(__p0, __p1) __extension__ ({ \
46422 __ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__rev0, __p1); \
46428 #define vduph_laneq_p16(__p0, __p1) __extension__ ({ \
46431 __ret = (poly16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \
46435 #define vduph_laneq_p16(__p0, __p1) __extension__ ({ \
46439 __ret = (poly16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \
46445 #define vdupb_laneq_u8(__p0, __p1) __extension__ ({ \
46448 __ret = (uint8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__s0, __p1); \
46452 #define vdupb_laneq_u8(__p0, __p1) __extension__ ({ \
46456 __ret = (uint8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__rev0, __p1); \
46462 #define vdups_laneq_u32(__p0, __p1) __extension__ ({ \
46465 __ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__s0, __p1); \
46469 #define vdups_laneq_u32(__p0, __p1) __extension__ ({ \
46473 __ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__rev0, __p1); \
46479 #define vdupd_laneq_u64(__p0, __p1) __extension__ ({ \
46482 __ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__s0, __p1); \
46486 #define vdupd_laneq_u64(__p0, __p1) __extension__ ({ \
46490 __ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__rev0, __p1); \
46496 #define vduph_laneq_u16(__p0, __p1) __extension__ ({ \
46499 __ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \
46503 #define vduph_laneq_u16(__p0, __p1) __extension__ ({ \
46507 __ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \
46513 #define vdupb_laneq_s8(__p0, __p1) __extension__ ({ \
46516 __ret = (int8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__s0, __p1); \
46520 #define vdupb_laneq_s8(__p0, __p1) __extension__ ({ \
46524 __ret = (int8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__rev0, __p1); \
46530 #define vdupd_laneq_f64(__p0, __p1) __extension__ ({ \
46533 __ret = (float64_t) __builtin_neon_vdupd_laneq_f64((int8x16_t)__s0, __p1); \
46537 #define vdupd_laneq_f64(__p0, __p1) __extension__ ({ \
46541 __ret = (float64_t) __builtin_neon_vdupd_laneq_f64((int8x16_t)__rev0, __p1); \
46547 #define vdups_laneq_f32(__p0, __p1) __extension__ ({ \
46550 __ret = (float32_t) __builtin_neon_vdups_laneq_f32((int8x16_t)__s0, __p1); \
46554 #define vdups_laneq_f32(__p0, __p1) __extension__ ({ \
46558 __ret = (float32_t) __builtin_neon_vdups_laneq_f32((int8x16_t)__rev0, __p1); \
46564 #define vdups_laneq_s32(__p0, __p1) __extension__ ({ \
46567 __ret = (int32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__s0, __p1); \
46571 #define vdups_laneq_s32(__p0, __p1) __extension__ ({ \
46575 __ret = (int32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__rev0, __p1); \
46581 #define vdupd_laneq_s64(__p0, __p1) __extension__ ({ \
46584 __ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__s0, __p1); \
46588 #define vdupd_laneq_s64(__p0, __p1) __extension__ ({ \
46592 __ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__rev0, __p1); \
46598 #define vduph_laneq_s16(__p0, __p1) __extension__ ({ \
46601 __ret = (int16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \
46605 #define vduph_laneq_s16(__p0, __p1) __extension__ ({ \
46609 __ret = (int16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \
46615 #define vdup_laneq_p8(__p0, __p1) __extension__ ({ \
46618 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46622 #define vdup_laneq_p8(__p0, __p1) __extension__ ({ \
46626 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46633 #define vdup_laneq_p64(__p0, __p1) __extension__ ({ \
46636 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46640 #define vdup_laneq_p64(__p0, __p1) __extension__ ({ \
46644 __ret = __builtin_shufflevector(__rev0, __rev0, __p1); \
46650 #define vdup_laneq_p16(__p0, __p1) __extension__ ({ \
46653 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46657 #define vdup_laneq_p16(__p0, __p1) __extension__ ({ \
46661 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46668 #define vdupq_laneq_p8(__p0, __p1) __extension__ ({ \
46671 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46675 #define vdupq_laneq_p8(__p0, __p1) __extension__ ({ \
46679 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46686 #define vdupq_laneq_p64(__p0, __p1) __extension__ ({ \
46689 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46693 #define vdupq_laneq_p64(__p0, __p1) __extension__ ({ \
46697 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
46704 #define vdupq_laneq_p16(__p0, __p1) __extension__ ({ \
46707 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46711 #define vdupq_laneq_p16(__p0, __p1) __extension__ ({ \
46715 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46722 #define vdupq_laneq_u8(__p0, __p1) __extension__ ({ \
46725 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46729 #define vdupq_laneq_u8(__p0, __p1) __extension__ ({ \
46733 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46740 #define vdupq_laneq_u32(__p0, __p1) __extension__ ({ \
46743 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46747 #define vdupq_laneq_u32(__p0, __p1) __extension__ ({ \
46751 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46758 #define vdupq_laneq_u64(__p0, __p1) __extension__ ({ \
46761 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46765 #define vdupq_laneq_u64(__p0, __p1) __extension__ ({ \
46769 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
46776 #define vdupq_laneq_u16(__p0, __p1) __extension__ ({ \
46779 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46783 #define vdupq_laneq_u16(__p0, __p1) __extension__ ({ \
46787 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46794 #define vdupq_laneq_s8(__p0, __p1) __extension__ ({ \
46797 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46801 #define vdupq_laneq_s8(__p0, __p1) __extension__ ({ \
46805 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46812 #define vdupq_laneq_f64(__p0, __p1) __extension__ ({ \
46815 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46819 #define vdupq_laneq_f64(__p0, __p1) __extension__ ({ \
46823 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
46830 #define vdupq_laneq_f32(__p0, __p1) __extension__ ({ \
46833 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46837 #define vdupq_laneq_f32(__p0, __p1) __extension__ ({ \
46841 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46848 #define vdupq_laneq_f16(__p0, __p1) __extension__ ({ \
46851 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46855 #define vdupq_laneq_f16(__p0, __p1) __extension__ ({ \
46859 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46866 #define vdupq_laneq_s32(__p0, __p1) __extension__ ({ \
46869 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46873 #define vdupq_laneq_s32(__p0, __p1) __extension__ ({ \
46877 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46884 #define vdupq_laneq_s64(__p0, __p1) __extension__ ({ \
46887 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46891 #define vdupq_laneq_s64(__p0, __p1) __extension__ ({ \
46895 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
46902 #define vdupq_laneq_s16(__p0, __p1) __extension__ ({ \
46905 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46909 #define vdupq_laneq_s16(__p0, __p1) __extension__ ({ \
46913 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46920 #define vdup_laneq_u8(__p0, __p1) __extension__ ({ \
46923 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46927 #define vdup_laneq_u8(__p0, __p1) __extension__ ({ \
46931 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46938 #define vdup_laneq_u32(__p0, __p1) __extension__ ({ \
46941 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
46945 #define vdup_laneq_u32(__p0, __p1) __extension__ ({ \
46949 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
46956 #define vdup_laneq_u64(__p0, __p1) __extension__ ({ \
46959 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
46963 #define vdup_laneq_u64(__p0, __p1) __extension__ ({ \
46967 __ret = __builtin_shufflevector(__rev0, __rev0, __p1); \
46973 #define vdup_laneq_u16(__p0, __p1) __extension__ ({ \
46976 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
46980 #define vdup_laneq_u16(__p0, __p1) __extension__ ({ \
46984 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
46991 #define vdup_laneq_s8(__p0, __p1) __extension__ ({ \
46994 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
46998 #define vdup_laneq_s8(__p0, __p1) __extension__ ({ \
47002 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1); \
47009 #define vdup_laneq_f64(__p0, __p1) __extension__ ({ \
47012 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
47016 #define vdup_laneq_f64(__p0, __p1) __extension__ ({ \
47020 __ret = __builtin_shufflevector(__rev0, __rev0, __p1); \
47026 #define vdup_laneq_f32(__p0, __p1) __extension__ ({ \
47029 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
47033 #define vdup_laneq_f32(__p0, __p1) __extension__ ({ \
47037 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
47044 #define vdup_laneq_f16(__p0, __p1) __extension__ ({ \
47047 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
47051 #define vdup_laneq_f16(__p0, __p1) __extension__ ({ \
47055 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
47062 #define vdup_laneq_s32(__p0, __p1) __extension__ ({ \
47065 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1); \
47069 #define vdup_laneq_s32(__p0, __p1) __extension__ ({ \
47073 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1); \
47080 #define vdup_laneq_s64(__p0, __p1) __extension__ ({ \
47083 __ret = __builtin_shufflevector(__s0, __s0, __p1); \
47087 #define vdup_laneq_s64(__p0, __p1) __extension__ ({ \
47091 __ret = __builtin_shufflevector(__rev0, __rev0, __p1); \
47097 #define vdup_laneq_s16(__p0, __p1) __extension__ ({ \
47100 __ret = __builtin_shufflevector(__s0, __s0, __p1, __p1, __p1, __p1); \
47104 #define vdup_laneq_s16(__p0, __p1) __extension__ ({ \
47108 __ret = __builtin_shufflevector(__rev0, __rev0, __p1, __p1, __p1, __p1); \
47173 #define vext_p64(__p0, __p1, __p2) __extension__ ({ \
47175 poly64x1_t __s1 = __p1; \
47181 #define vext_p64(__p0, __p1, __p2) __extension__ ({ \
47183 poly64x1_t __s1 = __p1; \
47191 #define vextq_p64(__p0, __p1, __p2) __extension__ ({ \
47193 poly64x2_t __s1 = __p1; \
47199 #define vextq_p64(__p0, __p1, __p2) __extension__ ({ \
47201 poly64x2_t __s1 = __p1; \
47212 #define vextq_f64(__p0, __p1, __p2) __extension__ ({ \
47214 float64x2_t __s1 = __p1; \
47220 #define vextq_f64(__p0, __p1, __p2) __extension__ ({ \
47222 float64x2_t __s1 = __p1; \
47233 #define vext_f64(__p0, __p1, __p2) __extension__ ({ \
47235 float64x1_t __s1 = __p1; \
47241 #define vext_f64(__p0, __p1, __p2) __extension__ ({ \
47243 float64x1_t __s1 = __p1; \
47251 __ai float64x2_t vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
47253 __ret = (float64x2_t) __builtin_neon_vfmaq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 42);
47257 __ai float64x2_t vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
47259 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
47266 __ai float64x2_t __noswap_vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
47268 __ret = (float64x2_t) __builtin_neon_vfmaq_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 42);
47274 __ai float64x1_t vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
47276 __ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47280 __ai float64x1_t vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
47282 __ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47285 __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
47287 __ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47293 #define vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47295 float64_t __s1 = __p1; \
47302 #define vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47304 float64_t __s1 = __p1; \
47310 #define __noswap_vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47312 float64_t __s1 = __p1; \
47321 #define vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47323 float32_t __s1 = __p1; \
47330 #define vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47332 float32_t __s1 = __p1; \
47339 #define __noswap_vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47341 float32_t __s1 = __p1; \
47350 #define vfmaq_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47352 float64x2_t __s1 = __p1; \
47359 #define vfmaq_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47361 float64x2_t __s1 = __p1; \
47370 #define __noswap_vfmaq_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47372 float64x2_t __s1 = __p1; \
47381 #define vfmaq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47383 float32x4_t __s1 = __p1; \
47390 #define vfmaq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47392 float32x4_t __s1 = __p1; \
47402 #define __noswap_vfmaq_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47404 float32x4_t __s1 = __p1; \
47413 #define vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47415 float64x1_t __s1 = __p1; \
47422 #define vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47424 float64x1_t __s1 = __p1; \
47430 #define __noswap_vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47432 float64x1_t __s1 = __p1; \
47441 #define vfma_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47443 float32x2_t __s1 = __p1; \
47450 #define vfma_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47452 float32x2_t __s1 = __p1; \
47462 #define __noswap_vfma_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47464 float32x2_t __s1 = __p1; \
47473 #define vfmad_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47475 float64_t __s1 = __p1; \
47482 #define vfmad_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47484 float64_t __s1 = __p1; \
47491 #define __noswap_vfmad_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47493 float64_t __s1 = __p1; \
47502 #define vfmas_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47504 float32_t __s1 = __p1; \
47511 #define vfmas_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47513 float32_t __s1 = __p1; \
47520 #define __noswap_vfmas_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47522 float32_t __s1 = __p1; \
47531 #define vfmaq_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47533 float64x2_t __s1 = __p1; \
47540 #define vfmaq_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47542 float64x2_t __s1 = __p1; \
47552 #define __noswap_vfmaq_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47554 float64x2_t __s1 = __p1; \
47563 #define vfmaq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47565 float32x4_t __s1 = __p1; \
47572 #define vfmaq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47574 float32x4_t __s1 = __p1; \
47584 #define __noswap_vfmaq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47586 float32x4_t __s1 = __p1; \
47595 #define vfma_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47597 float64x1_t __s1 = __p1; \
47604 #define vfma_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47606 float64x1_t __s1 = __p1; \
47613 #define __noswap_vfma_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
47615 float64x1_t __s1 = __p1; \
47624 #define vfma_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47626 float32x2_t __s1 = __p1; \
47633 #define vfma_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47635 float32x2_t __s1 = __p1; \
47645 #define __noswap_vfma_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
47647 float32x2_t __s1 = __p1; \
47656 __ai float64x2_t vfmaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
47658 __ret = vfmaq_f64(__p0, __p1, (float64x2_t) {__p2, __p2});
47662 __ai float64x2_t vfmaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
47664 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
47673 __ai float32x4_t vfmaq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
47675 __ret = vfmaq_f32(__p0, __p1, (float32x4_t) {__p2, __p2, __p2, __p2});
47679 __ai float32x4_t vfmaq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
47681 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
47690 __ai float32x2_t vfma_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
47692 __ret = vfma_f32(__p0, __p1, (float32x2_t) {__p2, __p2});
47696 __ai float32x2_t vfma_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
47698 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
47707 __ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
47709 __ret = vfmaq_f64(__p0, -__p1, __p2);
47713 __ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
47715 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
47725 __ai float64x1_t vfms_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
47727 __ret = vfma_f64(__p0, -__p1, __p2);
47731 __ai float64x1_t vfms_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
47733 __ret = __noswap_vfma_f64(__p0, -__p1, __p2);
48006 __ai float64x2_t vfmsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
48008 __ret = vfmaq_f64(__p0, -__p1, (float64x2_t) {__p2, __p2});
48012 __ai float64x2_t vfmsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
48014 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
48023 __ai float32x4_t vfmsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
48025 __ret = vfmaq_f32(__p0, -__p1, (float32x4_t) {__p2, __p2, __p2, __p2});
48029 __ai float32x4_t vfmsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2) {
48031 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
48040 __ai float32x2_t vfms_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
48042 __ret = vfma_f32(__p0, -__p1, (float32x2_t) {__p2, __p2});
48046 __ai float32x2_t vfms_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
48048 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
48092 #define vget_lane_p64(__p0, __p1) __extension__ ({ \
48095 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48099 #define vget_lane_p64(__p0, __p1) __extension__ ({ \
48102 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48105 #define __noswap_vget_lane_p64(__p0, __p1) __extension__ ({ \
48108 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48114 #define vgetq_lane_p64(__p0, __p1) __extension__ ({ \
48117 __ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
48121 #define vgetq_lane_p64(__p0, __p1) __extension__ ({ \
48125 __ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \
48128 #define __noswap_vgetq_lane_p64(__p0, __p1) __extension__ ({ \
48131 __ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \
48137 #define vgetq_lane_f64(__p0, __p1) __extension__ ({ \
48140 __ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__s0, __p1); \
48144 #define vgetq_lane_f64(__p0, __p1) __extension__ ({ \
48148 __ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__rev0, __p1); \
48151 #define __noswap_vgetq_lane_f64(__p0, __p1) __extension__ ({ \
48154 __ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__s0, __p1); \
48160 #define vget_lane_f64(__p0, __p1) __extension__ ({ \
48163 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48167 #define vget_lane_f64(__p0, __p1) __extension__ ({ \
48170 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48173 #define __noswap_vget_lane_f64(__p0, __p1) __extension__ ({ \
48176 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48328 #define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
48329 poly64x1_t __s1 = __p1; \
48335 #define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
48336 poly64x1_t __s1 = __p1; \
48344 #define vld1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
48345 poly64x2_t __s1 = __p1; \
48351 #define vld1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
48352 poly64x2_t __s1 = __p1; \
48362 #define vld1q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
48363 float64x2_t __s1 = __p1; \
48369 #define vld1q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
48370 float64x2_t __s1 = __p1; \
48380 #define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
48381 float64x1_t __s1 = __p1; \
48387 #define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
48388 float64x1_t __s1 = __p1; \
50222 #define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50223 poly64x1x2_t __s1 = __p1; \
50229 #define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50230 poly64x1x2_t __s1 = __p1; \
50238 #define vld2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
50239 poly8x16x2_t __s1 = __p1; \
50245 #define vld2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
50246 poly8x16x2_t __s1 = __p1; \
50260 #define vld2q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50261 poly64x2x2_t __s1 = __p1; \
50267 #define vld2q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50268 poly64x2x2_t __s1 = __p1; \
50282 #define vld2q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
50283 uint8x16x2_t __s1 = __p1; \
50289 #define vld2q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
50290 uint8x16x2_t __s1 = __p1; \
50304 #define vld2q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50305 uint64x2x2_t __s1 = __p1; \
50311 #define vld2q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50312 uint64x2x2_t __s1 = __p1; \
50326 #define vld2q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
50327 int8x16x2_t __s1 = __p1; \
50333 #define vld2q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
50334 int8x16x2_t __s1 = __p1; \
50348 #define vld2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50349 float64x2x2_t __s1 = __p1; \
50355 #define vld2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50356 float64x2x2_t __s1 = __p1; \
50370 #define vld2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50371 int64x2x2_t __s1 = __p1; \
50377 #define vld2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50378 int64x2x2_t __s1 = __p1; \
50392 #define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50393 uint64x1x2_t __s1 = __p1; \
50399 #define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50400 uint64x1x2_t __s1 = __p1; \
50408 #define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50409 float64x1x2_t __s1 = __p1; \
50415 #define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50416 float64x1x2_t __s1 = __p1; \
50424 #define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50425 int64x1x2_t __s1 = __p1; \
50431 #define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50432 int64x1x2_t __s1 = __p1; \
50820 #define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50821 poly64x1x3_t __s1 = __p1; \
50827 #define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50828 poly64x1x3_t __s1 = __p1; \
50836 #define vld3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
50837 poly8x16x3_t __s1 = __p1; \
50843 #define vld3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
50844 poly8x16x3_t __s1 = __p1; \
50860 #define vld3q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50861 poly64x2x3_t __s1 = __p1; \
50867 #define vld3q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
50868 poly64x2x3_t __s1 = __p1; \
50884 #define vld3q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
50885 uint8x16x3_t __s1 = __p1; \
50891 #define vld3q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
50892 uint8x16x3_t __s1 = __p1; \
50908 #define vld3q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50909 uint64x2x3_t __s1 = __p1; \
50915 #define vld3q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
50916 uint64x2x3_t __s1 = __p1; \
50932 #define vld3q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
50933 int8x16x3_t __s1 = __p1; \
50939 #define vld3q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
50940 int8x16x3_t __s1 = __p1; \
50956 #define vld3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50957 float64x2x3_t __s1 = __p1; \
50963 #define vld3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
50964 float64x2x3_t __s1 = __p1; \
50980 #define vld3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50981 int64x2x3_t __s1 = __p1; \
50987 #define vld3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
50988 int64x2x3_t __s1 = __p1; \
51004 #define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51005 uint64x1x3_t __s1 = __p1; \
51011 #define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51012 uint64x1x3_t __s1 = __p1; \
51020 #define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51021 float64x1x3_t __s1 = __p1; \
51027 #define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51028 float64x1x3_t __s1 = __p1; \
51036 #define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51037 int64x1x3_t __s1 = __p1; \
51043 #define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51044 int64x1x3_t __s1 = __p1; \
51450 #define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
51451 poly64x1x4_t __s1 = __p1; \
51457 #define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
51458 poly64x1x4_t __s1 = __p1; \
51466 #define vld4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
51467 poly8x16x4_t __s1 = __p1; \
51473 #define vld4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
51474 poly8x16x4_t __s1 = __p1; \
51492 #define vld4q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
51493 poly64x2x4_t __s1 = __p1; \
51499 #define vld4q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
51500 poly64x2x4_t __s1 = __p1; \
51518 #define vld4q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
51519 uint8x16x4_t __s1 = __p1; \
51525 #define vld4q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
51526 uint8x16x4_t __s1 = __p1; \
51544 #define vld4q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51545 uint64x2x4_t __s1 = __p1; \
51551 #define vld4q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51552 uint64x2x4_t __s1 = __p1; \
51570 #define vld4q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
51571 int8x16x4_t __s1 = __p1; \
51577 #define vld4q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
51578 int8x16x4_t __s1 = __p1; \
51596 #define vld4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51597 float64x2x4_t __s1 = __p1; \
51603 #define vld4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51604 float64x2x4_t __s1 = __p1; \
51622 #define vld4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51623 int64x2x4_t __s1 = __p1; \
51629 #define vld4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51630 int64x2x4_t __s1 = __p1; \
51648 #define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51649 uint64x1x4_t __s1 = __p1; \
51655 #define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
51656 uint64x1x4_t __s1 = __p1; \
51664 #define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51665 float64x1x4_t __s1 = __p1; \
51671 #define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
51672 float64x1x4_t __s1 = __p1; \
51680 #define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51681 int64x1x4_t __s1 = __p1; \
51687 #define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
51688 int64x1x4_t __s1 = __p1; \
51710 __ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
51712 __ret = (float64x2_t) __builtin_neon_vmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
51716 __ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
51718 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
51727 __ai float64x1_t vmax_f64(float64x1_t __p0, float64x1_t __p1) {
51729 __ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
51733 __ai float64x1_t vmax_f64(float64x1_t __p0, float64x1_t __p1) {
51735 __ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
52011 __ai float64x2_t vminq_f64(float64x2_t __p0, float64x2_t __p1) {
52013 __ret = (float64x2_t) __builtin_neon_vminq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
52017 __ai float64x2_t vminq_f64(float64x2_t __p0, float64x2_t __p1) {
52019 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
52028 __ai float64x1_t vmin_f64(float64x1_t __p0, float64x1_t __p1) {
52030 __ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
52034 __ai float64x1_t vmin_f64(float64x1_t __p0, float64x1_t __p1) {
52036 __ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
52312 __ai float64x2_t vmlaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
52314 __ret = __p0 + __p1 * __p2;
52318 __ai float64x2_t vmlaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
52320 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
52330 __ai float64x1_t vmla_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
52332 __ret = __p0 + __p1 * __p2;
52336 __ai float64x1_t vmla_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
52338 __ret = __p0 + __p1 * __p2;
52344 #define vmlaq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52346 uint32x4_t __s1 = __p1; \
52353 #define vmlaq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52355 uint32x4_t __s1 = __p1; \
52368 #define vmlaq_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52370 uint16x8_t __s1 = __p1; \
52377 #define vmlaq_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52379 uint16x8_t __s1 = __p1; \
52392 #define vmlaq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52394 float32x4_t __s1 = __p1; \
52401 #define vmlaq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52403 float32x4_t __s1 = __p1; \
52416 #define vmlaq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52418 int32x4_t __s1 = __p1; \
52425 #define vmlaq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52427 int32x4_t __s1 = __p1; \
52440 #define vmlaq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52442 int16x8_t __s1 = __p1; \
52449 #define vmlaq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52451 int16x8_t __s1 = __p1; \
52464 #define vmla_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52466 uint32x2_t __s1 = __p1; \
52473 #define vmla_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52475 uint32x2_t __s1 = __p1; \
52488 #define vmla_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52490 uint16x4_t __s1 = __p1; \
52497 #define vmla_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52499 uint16x4_t __s1 = __p1; \
52512 #define vmla_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52514 float32x2_t __s1 = __p1; \
52521 #define vmla_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52523 float32x2_t __s1 = __p1; \
52536 #define vmla_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52538 int32x2_t __s1 = __p1; \
52545 #define vmla_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52547 int32x2_t __s1 = __p1; \
52560 #define vmla_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52562 int16x4_t __s1 = __p1; \
52569 #define vmla_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52571 int16x4_t __s1 = __p1; \
52584 __ai float64x2_t vmlaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
52586 __ret = __p0 + __p1 * (float64x2_t) {__p2, __p2};
52590 __ai float64x2_t vmlaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
52592 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
52601 #define vmlal_high_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52603 uint32x4_t __s1 = __p1; \
52610 #define vmlal_high_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52612 uint32x4_t __s1 = __p1; \
52625 #define vmlal_high_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52627 uint16x8_t __s1 = __p1; \
52634 #define vmlal_high_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52636 uint16x8_t __s1 = __p1; \
52649 #define vmlal_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52651 int32x4_t __s1 = __p1; \
52658 #define vmlal_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52660 int32x4_t __s1 = __p1; \
52673 #define vmlal_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52675 int16x8_t __s1 = __p1; \
52682 #define vmlal_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52684 int16x8_t __s1 = __p1; \
52697 #define vmlal_high_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52699 uint32x4_t __s1 = __p1; \
52706 #define vmlal_high_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52708 uint32x4_t __s1 = __p1; \
52721 #define vmlal_high_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52723 uint16x8_t __s1 = __p1; \
52730 #define vmlal_high_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52732 uint16x8_t __s1 = __p1; \
52745 #define vmlal_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52747 int32x4_t __s1 = __p1; \
52754 #define vmlal_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52756 int32x4_t __s1 = __p1; \
52769 #define vmlal_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52771 int16x8_t __s1 = __p1; \
52778 #define vmlal_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52780 int16x8_t __s1 = __p1; \
52793 #define vmlal_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52795 uint32x2_t __s1 = __p1; \
52802 #define vmlal_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52804 uint32x2_t __s1 = __p1; \
52817 #define vmlal_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52819 uint16x4_t __s1 = __p1; \
52826 #define vmlal_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52828 uint16x4_t __s1 = __p1; \
52841 #define vmlal_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52843 int32x2_t __s1 = __p1; \
52850 #define vmlal_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52852 int32x2_t __s1 = __p1; \
52865 #define vmlal_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52867 int16x4_t __s1 = __p1; \
52874 #define vmlal_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
52876 int16x4_t __s1 = __p1; \
52889 __ai float64x2_t vmlsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
52891 __ret = __p0 - __p1 * __p2;
52895 __ai float64x2_t vmlsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
52897 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
52907 __ai float64x1_t vmls_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
52909 __ret = __p0 - __p1 * __p2;
52913 __ai float64x1_t vmls_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
52915 __ret = __p0 - __p1 * __p2;
52921 #define vmlsq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52923 uint32x4_t __s1 = __p1; \
52930 #define vmlsq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
52932 uint32x4_t __s1 = __p1; \
52945 #define vmlsq_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52947 uint16x8_t __s1 = __p1; \
52954 #define vmlsq_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
52956 uint16x8_t __s1 = __p1; \
52969 #define vmlsq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52971 float32x4_t __s1 = __p1; \
52978 #define vmlsq_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
52980 float32x4_t __s1 = __p1; \
52993 #define vmlsq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
52995 int32x4_t __s1 = __p1; \
53002 #define vmlsq_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53004 int32x4_t __s1 = __p1; \
53017 #define vmlsq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53019 int16x8_t __s1 = __p1; \
53026 #define vmlsq_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53028 int16x8_t __s1 = __p1; \
53041 #define vmls_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53043 uint32x2_t __s1 = __p1; \
53050 #define vmls_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53052 uint32x2_t __s1 = __p1; \
53065 #define vmls_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53067 uint16x4_t __s1 = __p1; \
53074 #define vmls_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53076 uint16x4_t __s1 = __p1; \
53089 #define vmls_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
53091 float32x2_t __s1 = __p1; \
53098 #define vmls_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
53100 float32x2_t __s1 = __p1; \
53113 #define vmls_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53115 int32x2_t __s1 = __p1; \
53122 #define vmls_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53124 int32x2_t __s1 = __p1; \
53137 #define vmls_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53139 int16x4_t __s1 = __p1; \
53146 #define vmls_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53148 int16x4_t __s1 = __p1; \
53161 __ai float64x2_t vmlsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
53163 __ret = __p0 - __p1 * (float64x2_t) {__p2, __p2};
53167 __ai float64x2_t vmlsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
53169 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
53178 #define vmlsl_high_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53180 uint32x4_t __s1 = __p1; \
53187 #define vmlsl_high_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53189 uint32x4_t __s1 = __p1; \
53202 #define vmlsl_high_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53204 uint16x8_t __s1 = __p1; \
53211 #define vmlsl_high_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53213 uint16x8_t __s1 = __p1; \
53226 #define vmlsl_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53228 int32x4_t __s1 = __p1; \
53235 #define vmlsl_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53237 int32x4_t __s1 = __p1; \
53250 #define vmlsl_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53252 int16x8_t __s1 = __p1; \
53259 #define vmlsl_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53261 int16x8_t __s1 = __p1; \
53274 #define vmlsl_high_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53276 uint32x4_t __s1 = __p1; \
53283 #define vmlsl_high_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53285 uint32x4_t __s1 = __p1; \
53298 #define vmlsl_high_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53300 uint16x8_t __s1 = __p1; \
53307 #define vmlsl_high_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53309 uint16x8_t __s1 = __p1; \
53322 #define vmlsl_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53324 int32x4_t __s1 = __p1; \
53331 #define vmlsl_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53333 int32x4_t __s1 = __p1; \
53346 #define vmlsl_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53348 int16x8_t __s1 = __p1; \
53355 #define vmlsl_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53357 int16x8_t __s1 = __p1; \
53370 #define vmlsl_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53372 uint32x2_t __s1 = __p1; \
53379 #define vmlsl_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
53381 uint32x2_t __s1 = __p1; \
53394 #define vmlsl_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53396 uint16x4_t __s1 = __p1; \
53403 #define vmlsl_laneq_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
53405 uint16x4_t __s1 = __p1; \
53418 #define vmlsl_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53420 int32x2_t __s1 = __p1; \
53427 #define vmlsl_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
53429 int32x2_t __s1 = __p1; \
53442 #define vmlsl_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53444 int16x4_t __s1 = __p1; \
53451 #define vmlsl_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
53453 int16x4_t __s1 = __p1; \
53668 __ai uint16x8_t vmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {
53670 __ret = vcombine_u16(__p0, vmovn_u32(__p1));
53674 __ai uint16x8_t vmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {
53676 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
53685 __ai uint32x4_t vmovn_high_u64(uint32x2_t __p0, uint64x2_t __p1) {
53687 __ret = vcombine_u32(__p0, vmovn_u64(__p1));
53691 __ai uint32x4_t vmovn_high_u64(uint32x2_t __p0, uint64x2_t __p1) {
53693 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
53702 __ai uint8x16_t vmovn_high_u16(uint8x8_t __p0, uint16x8_t __p1) {
53704 __ret = vcombine_u8(__p0, vmovn_u16(__p1));
53708 __ai uint8x16_t vmovn_high_u16(uint8x8_t __p0, uint16x8_t __p1) {
53710 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
53719 __ai int16x8_t vmovn_high_s32(int16x4_t __p0, int32x4_t __p1) {
53721 __ret = vcombine_s16(__p0, vmovn_s32(__p1));
53725 __ai int16x8_t vmovn_high_s32(int16x4_t __p0, int32x4_t __p1) {
53727 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
53736 __ai int32x4_t vmovn_high_s64(int32x2_t __p0, int64x2_t __p1) {
53738 __ret = vcombine_s32(__p0, vmovn_s64(__p1));
53742 __ai int32x4_t vmovn_high_s64(int32x2_t __p0, int64x2_t __p1) {
53744 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
53753 __ai int8x16_t vmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
53755 __ret = vcombine_s8(__p0, vmovn_s16(__p1));
53759 __ai int8x16_t vmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
53761 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
53770 __ai float64x2_t vmulq_f64(float64x2_t __p0, float64x2_t __p1) {
53772 __ret = __p0 * __p1;
53776 __ai float64x2_t vmulq_f64(float64x2_t __p0, float64x2_t __p1) {
53778 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
53787 __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
53789 __ret = __p0 * __p1;
53793 __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
53795 __ret = __p0 * __p1;
53838 #define vmul_lane_f64(__p0, __p1, __p2) __extension__ ({ \
53840 float64x1_t __s1 = __p1; \
53846 #define vmul_lane_f64(__p0, __p1, __p2) __extension__ ({ \
53848 float64x1_t __s1 = __p1; \
53856 #define vmulq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
53858 float64x1_t __s1 = __p1; \
53864 #define vmulq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
53866 float64x1_t __s1 = __p1; \
53914 #define vmul_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
53916 float64x2_t __s1 = __p1; \
53922 #define vmul_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
53924 float64x2_t __s1 = __p1; \
53933 #define vmulq_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
53935 uint32x4_t __s1 = __p1; \
53941 #define vmulq_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
53943 uint32x4_t __s1 = __p1; \
53954 #define vmulq_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
53956 uint16x8_t __s1 = __p1; \
53962 #define vmulq_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
53964 uint16x8_t __s1 = __p1; \
53975 #define vmulq_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
53977 float64x2_t __s1 = __p1; \
53983 #define vmulq_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
53985 float64x2_t __s1 = __p1; \
53996 #define vmulq_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
53998 float32x4_t __s1 = __p1; \
54004 #define vmulq_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54006 float32x4_t __s1 = __p1; \
54017 #define vmulq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54019 int32x4_t __s1 = __p1; \
54025 #define vmulq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54027 int32x4_t __s1 = __p1; \
54038 #define vmulq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54040 int16x8_t __s1 = __p1; \
54046 #define vmulq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54048 int16x8_t __s1 = __p1; \
54059 #define vmul_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54061 uint32x4_t __s1 = __p1; \
54067 #define vmul_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54069 uint32x4_t __s1 = __p1; \
54080 #define vmul_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54082 uint16x8_t __s1 = __p1; \
54088 #define vmul_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54090 uint16x8_t __s1 = __p1; \
54101 #define vmul_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54103 float32x4_t __s1 = __p1; \
54109 #define vmul_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54111 float32x4_t __s1 = __p1; \
54122 #define vmul_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54124 int32x4_t __s1 = __p1; \
54130 #define vmul_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54132 int32x4_t __s1 = __p1; \
54143 #define vmul_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54145 int16x8_t __s1 = __p1; \
54151 #define vmul_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54153 int16x8_t __s1 = __p1; \
54164 __ai float64x1_t vmul_n_f64(float64x1_t __p0, float64_t __p1) {
54166 __ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);
54170 __ai float64x1_t vmul_n_f64(float64x1_t __p0, float64_t __p1) {
54172 __ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);
54178 __ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {
54180 __ret = __p0 * (float64x2_t) {__p1, __p1};
54184 __ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {
54187 __ret = __rev0 * (float64x2_t) {__p1, __p1};
54194 __ai poly128_t vmull_p64(poly64_t __p0, poly64_t __p1) {
54196 __ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
54200 __ai poly128_t vmull_p64(poly64_t __p0, poly64_t __p1) {
54202 __ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
54205 __ai poly128_t __noswap_vmull_p64(poly64_t __p0, poly64_t __p1) {
54207 __ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
54213 __ai poly16x8_t vmull_high_p8(poly8x16_t __p0, poly8x16_t __p1) {
54215 __ret = vmull_p8(vget_high_p8(__p0), vget_high_p8(__p1));
54219 __ai poly16x8_t vmull_high_p8(poly8x16_t __p0, poly8x16_t __p1) {
54221 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
54230 __ai uint16x8_t vmull_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
54232 __ret = vmull_u8(vget_high_u8(__p0), vget_high_u8(__p1));
54236 __ai uint16x8_t vmull_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
54238 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
54247 __ai uint64x2_t vmull_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
54249 __ret = vmull_u32(vget_high_u32(__p0), vget_high_u32(__p1));
54253 __ai uint64x2_t vmull_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
54255 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
54264 __ai uint32x4_t vmull_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
54266 __ret = vmull_u16(vget_high_u16(__p0), vget_high_u16(__p1));
54270 __ai uint32x4_t vmull_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
54272 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
54281 __ai int16x8_t vmull_high_s8(int8x16_t __p0, int8x16_t __p1) {
54283 __ret = vmull_s8(vget_high_s8(__p0), vget_high_s8(__p1));
54287 __ai int16x8_t vmull_high_s8(int8x16_t __p0, int8x16_t __p1) {
54289 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
54298 __ai int64x2_t vmull_high_s32(int32x4_t __p0, int32x4_t __p1) {
54300 __ret = vmull_s32(vget_high_s32(__p0), vget_high_s32(__p1));
54304 __ai int64x2_t vmull_high_s32(int32x4_t __p0, int32x4_t __p1) {
54306 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
54315 __ai int32x4_t vmull_high_s16(int16x8_t __p0, int16x8_t __p1) {
54317 __ret = vmull_s16(vget_high_s16(__p0), vget_high_s16(__p1));
54321 __ai int32x4_t vmull_high_s16(int16x8_t __p0, int16x8_t __p1) {
54323 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
54332 __ai poly128_t vmull_high_p64(poly64x2_t __p0, poly64x2_t __p1) {
54334 __ret = vmull_p64((poly64_t)(vget_high_p64(__p0)), (poly64_t)(vget_high_p64(__p1)));
54338 __ai poly128_t vmull_high_p64(poly64x2_t __p0, poly64x2_t __p1) {
54340 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
54348 #define vmull_high_lane_u32(__p0, __p1, __p2) __extension__ ({ \
54350 uint32x2_t __s1 = __p1; \
54356 #define vmull_high_lane_u32(__p0, __p1, __p2) __extension__ ({ \
54358 uint32x2_t __s1 = __p1; \
54369 #define vmull_high_lane_u16(__p0, __p1, __p2) __extension__ ({ \
54371 uint16x4_t __s1 = __p1; \
54377 #define vmull_high_lane_u16(__p0, __p1, __p2) __extension__ ({ \
54379 uint16x4_t __s1 = __p1; \
54390 #define vmull_high_lane_s32(__p0, __p1, __p2) __extension__ ({ \
54392 int32x2_t __s1 = __p1; \
54398 #define vmull_high_lane_s32(__p0, __p1, __p2) __extension__ ({ \
54400 int32x2_t __s1 = __p1; \
54411 #define vmull_high_lane_s16(__p0, __p1, __p2) __extension__ ({ \
54413 int16x4_t __s1 = __p1; \
54419 #define vmull_high_lane_s16(__p0, __p1, __p2) __extension__ ({ \
54421 int16x4_t __s1 = __p1; \
54432 #define vmull_high_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54434 uint32x4_t __s1 = __p1; \
54440 #define vmull_high_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54442 uint32x4_t __s1 = __p1; \
54453 #define vmull_high_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54455 uint16x8_t __s1 = __p1; \
54461 #define vmull_high_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54463 uint16x8_t __s1 = __p1; \
54474 #define vmull_high_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54476 int32x4_t __s1 = __p1; \
54482 #define vmull_high_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54484 int32x4_t __s1 = __p1; \
54495 #define vmull_high_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54497 int16x8_t __s1 = __p1; \
54503 #define vmull_high_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54505 int16x8_t __s1 = __p1; \
54516 __ai uint64x2_t vmull_high_n_u32(uint32x4_t __p0, uint32_t __p1) {
54518 __ret = vmull_n_u32(vget_high_u32(__p0), __p1);
54522 __ai uint64x2_t vmull_high_n_u32(uint32x4_t __p0, uint32_t __p1) {
54525 __ret = __noswap_vmull_n_u32(__noswap_vget_high_u32(__rev0), __p1);
54532 __ai uint32x4_t vmull_high_n_u16(uint16x8_t __p0, uint16_t __p1) {
54534 __ret = vmull_n_u16(vget_high_u16(__p0), __p1);
54538 __ai uint32x4_t vmull_high_n_u16(uint16x8_t __p0, uint16_t __p1) {
54541 __ret = __noswap_vmull_n_u16(__noswap_vget_high_u16(__rev0), __p1);
54548 __ai int64x2_t vmull_high_n_s32(int32x4_t __p0, int32_t __p1) {
54550 __ret = vmull_n_s32(vget_high_s32(__p0), __p1);
54554 __ai int64x2_t vmull_high_n_s32(int32x4_t __p0, int32_t __p1) {
54557 __ret = __noswap_vmull_n_s32(__noswap_vget_high_s32(__rev0), __p1);
54564 __ai int32x4_t vmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
54566 __ret = vmull_n_s16(vget_high_s16(__p0), __p1);
54570 __ai int32x4_t vmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
54573 __ret = __noswap_vmull_n_s16(__noswap_vget_high_s16(__rev0), __p1);
54580 #define vmull_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54582 uint32x4_t __s1 = __p1; \
54588 #define vmull_laneq_u32(__p0, __p1, __p2) __extension__ ({ \
54590 uint32x4_t __s1 = __p1; \
54601 #define vmull_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54603 uint16x8_t __s1 = __p1; \
54609 #define vmull_laneq_u16(__p0, __p1, __p2) __extension__ ({ \
54611 uint16x8_t __s1 = __p1; \
54622 #define vmull_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54624 int32x4_t __s1 = __p1; \
54630 #define vmull_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
54632 int32x4_t __s1 = __p1; \
54643 #define vmull_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54645 int16x8_t __s1 = __p1; \
54651 #define vmull_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
54653 int16x8_t __s1 = __p1; \
54664 __ai float64x2_t vmulxq_f64(float64x2_t __p0, float64x2_t __p1) {
54666 __ret = (float64x2_t) __builtin_neon_vmulxq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
54670 __ai float64x2_t vmulxq_f64(float64x2_t __p0, float64x2_t __p1) {
54672 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
54678 __ai float64x2_t __noswap_vmulxq_f64(float64x2_t __p0, float64x2_t __p1) {
54680 __ret = (float64x2_t) __builtin_neon_vmulxq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
54686 __ai float32x4_t vmulxq_f32(float32x4_t __p0, float32x4_t __p1) {
54688 __ret = (float32x4_t) __builtin_neon_vmulxq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
54692 __ai float32x4_t vmulxq_f32(float32x4_t __p0, float32x4_t __p1) {
54694 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
54700 __ai float32x4_t __noswap_vmulxq_f32(float32x4_t __p0, float32x4_t __p1) {
54702 __ret = (float32x4_t) __builtin_neon_vmulxq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
54708 __ai float64x1_t vmulx_f64(float64x1_t __p0, float64x1_t __p1) {
54710 __ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
54714 __ai float64x1_t vmulx_f64(float64x1_t __p0, float64x1_t __p1) {
54716 __ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
54722 __ai float32x2_t vmulx_f32(float32x2_t __p0, float32x2_t __p1) {
54724 __ret = (float32x2_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
54728 __ai float32x2_t vmulx_f32(float32x2_t __p0, float32x2_t __p1) {
54730 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
54736 __ai float32x2_t __noswap_vmulx_f32(float32x2_t __p0, float32x2_t __p1) {
54738 __ret = (float32x2_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
54744 __ai float64_t vmulxd_f64(float64_t __p0, float64_t __p1) {
54746 __ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
54750 __ai float64_t vmulxd_f64(float64_t __p0, float64_t __p1) {
54752 __ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
54755 __ai float64_t __noswap_vmulxd_f64(float64_t __p0, float64_t __p1) {
54757 __ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
54763 __ai float32_t vmulxs_f32(float32_t __p0, float32_t __p1) {
54765 __ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);
54769 __ai float32_t vmulxs_f32(float32_t __p0, float32_t __p1) {
54771 __ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);
54774 __ai float32_t __noswap_vmulxs_f32(float32_t __p0, float32_t __p1) {
54776 __ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);
54819 #define vmulxq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
54821 float64x1_t __s1 = __p1; \
54827 #define vmulxq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
54829 float64x1_t __s1 = __p1; \
54839 #define vmulxq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
54841 float32x2_t __s1 = __p1; \
54847 #define vmulxq_lane_f32(__p0, __p1, __p2) __extension__ ({ \
54849 float32x2_t __s1 = __p1; \
54860 #define vmulx_lane_f32(__p0, __p1, __p2) __extension__ ({ \
54862 float32x2_t __s1 = __p1; \
54868 #define vmulx_lane_f32(__p0, __p1, __p2) __extension__ ({ \
54870 float32x2_t __s1 = __p1; \
54919 #define vmulxq_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
54921 float64x2_t __s1 = __p1; \
54927 #define vmulxq_laneq_f64(__p0, __p1, __p2) __extension__ ({ \
54929 float64x2_t __s1 = __p1; \
54940 #define vmulxq_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54942 float32x4_t __s1 = __p1; \
54948 #define vmulxq_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54950 float32x4_t __s1 = __p1; \
54961 #define vmulx_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54963 float32x4_t __s1 = __p1; \
54969 #define vmulx_laneq_f32(__p0, __p1, __p2) __extension__ ({ \
54971 float32x4_t __s1 = __p1; \
55056 __ai uint8x16_t vpaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55058 __ret = (uint8x16_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
55062 __ai uint8x16_t vpaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55064 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55073 __ai uint32x4_t vpaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55075 __ret = (uint32x4_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
55079 __ai uint32x4_t vpaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55081 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55090 __ai uint64x2_t vpaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
55092 __ret = (uint64x2_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
55096 __ai uint64x2_t vpaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
55098 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55107 __ai uint16x8_t vpaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55109 __ret = (uint16x8_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
55113 __ai uint16x8_t vpaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55115 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55124 __ai int8x16_t vpaddq_s8(int8x16_t __p0, int8x16_t __p1) {
55126 __ret = (int8x16_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
55130 __ai int8x16_t vpaddq_s8(int8x16_t __p0, int8x16_t __p1) {
55132 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55141 __ai float64x2_t vpaddq_f64(float64x2_t __p0, float64x2_t __p1) {
55143 __ret = (float64x2_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
55147 __ai float64x2_t vpaddq_f64(float64x2_t __p0, float64x2_t __p1) {
55149 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55158 __ai float32x4_t vpaddq_f32(float32x4_t __p0, float32x4_t __p1) {
55160 __ret = (float32x4_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
55164 __ai float32x4_t vpaddq_f32(float32x4_t __p0, float32x4_t __p1) {
55166 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55175 __ai int32x4_t vpaddq_s32(int32x4_t __p0, int32x4_t __p1) {
55177 __ret = (int32x4_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
55181 __ai int32x4_t vpaddq_s32(int32x4_t __p0, int32x4_t __p1) {
55183 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55192 __ai int64x2_t vpaddq_s64(int64x2_t __p0, int64x2_t __p1) {
55194 __ret = (int64x2_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
55198 __ai int64x2_t vpaddq_s64(int64x2_t __p0, int64x2_t __p1) {
55200 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55209 __ai int16x8_t vpaddq_s16(int16x8_t __p0, int16x8_t __p1) {
55211 __ret = (int16x8_t) __builtin_neon_vpaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
55215 __ai int16x8_t vpaddq_s16(int16x8_t __p0, int16x8_t __p1) {
55217 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55286 __ai uint8x16_t vpmaxq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55288 __ret = (uint8x16_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
55292 __ai uint8x16_t vpmaxq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55294 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55303 __ai uint32x4_t vpmaxq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55305 __ret = (uint32x4_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
55309 __ai uint32x4_t vpmaxq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55311 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55320 __ai uint16x8_t vpmaxq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55322 __ret = (uint16x8_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
55326 __ai uint16x8_t vpmaxq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55328 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55337 __ai int8x16_t vpmaxq_s8(int8x16_t __p0, int8x16_t __p1) {
55339 __ret = (int8x16_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
55343 __ai int8x16_t vpmaxq_s8(int8x16_t __p0, int8x16_t __p1) {
55345 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55354 __ai float64x2_t vpmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
55356 __ret = (float64x2_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
55360 __ai float64x2_t vpmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
55362 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55371 __ai float32x4_t vpmaxq_f32(float32x4_t __p0, float32x4_t __p1) {
55373 __ret = (float32x4_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
55377 __ai float32x4_t vpmaxq_f32(float32x4_t __p0, float32x4_t __p1) {
55379 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55388 __ai int32x4_t vpmaxq_s32(int32x4_t __p0, int32x4_t __p1) {
55390 __ret = (int32x4_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
55394 __ai int32x4_t vpmaxq_s32(int32x4_t __p0, int32x4_t __p1) {
55396 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55405 __ai int16x8_t vpmaxq_s16(int16x8_t __p0, int16x8_t __p1) {
55407 __ret = (int16x8_t) __builtin_neon_vpmaxq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
55411 __ai int16x8_t vpmaxq_s16(int16x8_t __p0, int16x8_t __p1) {
55413 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55452 __ai float64x2_t vpmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {
55454 __ret = (float64x2_t) __builtin_neon_vpmaxnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
55458 __ai float64x2_t vpmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {
55460 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55469 __ai float32x4_t vpmaxnmq_f32(float32x4_t __p0, float32x4_t __p1) {
55471 __ret = (float32x4_t) __builtin_neon_vpmaxnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
55475 __ai float32x4_t vpmaxnmq_f32(float32x4_t __p0, float32x4_t __p1) {
55477 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55486 __ai float32x2_t vpmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {
55488 __ret = (float32x2_t) __builtin_neon_vpmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
55492 __ai float32x2_t vpmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {
55494 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55533 __ai uint8x16_t vpminq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55535 __ret = (uint8x16_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
55539 __ai uint8x16_t vpminq_u8(uint8x16_t __p0, uint8x16_t __p1) {
55541 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55550 __ai uint32x4_t vpminq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55552 __ret = (uint32x4_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
55556 __ai uint32x4_t vpminq_u32(uint32x4_t __p0, uint32x4_t __p1) {
55558 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55567 __ai uint16x8_t vpminq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55569 __ret = (uint16x8_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
55573 __ai uint16x8_t vpminq_u16(uint16x8_t __p0, uint16x8_t __p1) {
55575 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55584 __ai int8x16_t vpminq_s8(int8x16_t __p0, int8x16_t __p1) {
55586 __ret = (int8x16_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
55590 __ai int8x16_t vpminq_s8(int8x16_t __p0, int8x16_t __p1) {
55592 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
55601 __ai float64x2_t vpminq_f64(float64x2_t __p0, float64x2_t __p1) {
55603 __ret = (float64x2_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
55607 __ai float64x2_t vpminq_f64(float64x2_t __p0, float64x2_t __p1) {
55609 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55618 __ai float32x4_t vpminq_f32(float32x4_t __p0, float32x4_t __p1) {
55620 __ret = (float32x4_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
55624 __ai float32x4_t vpminq_f32(float32x4_t __p0, float32x4_t __p1) {
55626 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55635 __ai int32x4_t vpminq_s32(int32x4_t __p0, int32x4_t __p1) {
55637 __ret = (int32x4_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
55641 __ai int32x4_t vpminq_s32(int32x4_t __p0, int32x4_t __p1) {
55643 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55652 __ai int16x8_t vpminq_s16(int16x8_t __p0, int16x8_t __p1) {
55654 __ret = (int16x8_t) __builtin_neon_vpminq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
55658 __ai int16x8_t vpminq_s16(int16x8_t __p0, int16x8_t __p1) {
55660 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
55699 __ai float64x2_t vpminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
55701 __ret = (float64x2_t) __builtin_neon_vpminnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
55705 __ai float64x2_t vpminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
55707 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55716 __ai float32x4_t vpminnmq_f32(float32x4_t __p0, float32x4_t __p1) {
55718 __ret = (float32x4_t) __builtin_neon_vpminnmq_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
55722 __ai float32x4_t vpminnmq_f32(float32x4_t __p0, float32x4_t __p1) {
55724 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
55733 __ai float32x2_t vpminnm_f32(float32x2_t __p0, float32x2_t __p1) {
55735 __ret = (float32x2_t) __builtin_neon_vpminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
55739 __ai float32x2_t vpminnm_f32(float32x2_t __p0, float32x2_t __p1) {
55741 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
55866 __ai uint8_t vqaddb_u8(uint8_t __p0, uint8_t __p1) {
55868 __ret = (uint8_t) __builtin_neon_vqaddb_u8(__p0, __p1);
55872 __ai uint8_t vqaddb_u8(uint8_t __p0, uint8_t __p1) {
55874 __ret = (uint8_t) __builtin_neon_vqaddb_u8(__p0, __p1);
55880 __ai uint32_t vqadds_u32(uint32_t __p0, uint32_t __p1) {
55882 __ret = (uint32_t) __builtin_neon_vqadds_u32(__p0, __p1);
55886 __ai uint32_t vqadds_u32(uint32_t __p0, uint32_t __p1) {
55888 __ret = (uint32_t) __builtin_neon_vqadds_u32(__p0, __p1);
55894 __ai uint64_t vqaddd_u64(uint64_t __p0, uint64_t __p1) {
55896 __ret = (uint64_t) __builtin_neon_vqaddd_u64(__p0, __p1);
55900 __ai uint64_t vqaddd_u64(uint64_t __p0, uint64_t __p1) {
55902 __ret = (uint64_t) __builtin_neon_vqaddd_u64(__p0, __p1);
55908 __ai uint16_t vqaddh_u16(uint16_t __p0, uint16_t __p1) {
55910 __ret = (uint16_t) __builtin_neon_vqaddh_u16(__p0, __p1);
55914 __ai uint16_t vqaddh_u16(uint16_t __p0, uint16_t __p1) {
55916 __ret = (uint16_t) __builtin_neon_vqaddh_u16(__p0, __p1);
55922 __ai int8_t vqaddb_s8(int8_t __p0, int8_t __p1) {
55924 __ret = (int8_t) __builtin_neon_vqaddb_s8(__p0, __p1);
55928 __ai int8_t vqaddb_s8(int8_t __p0, int8_t __p1) {
55930 __ret = (int8_t) __builtin_neon_vqaddb_s8(__p0, __p1);
55936 __ai int32_t vqadds_s32(int32_t __p0, int32_t __p1) {
55938 __ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
55942 __ai int32_t vqadds_s32(int32_t __p0, int32_t __p1) {
55944 __ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
55947 __ai int32_t __noswap_vqadds_s32(int32_t __p0, int32_t __p1) {
55949 __ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
55955 __ai int64_t vqaddd_s64(int64_t __p0, int64_t __p1) {
55957 __ret = (int64_t) __builtin_neon_vqaddd_s64(__p0, __p1);
55961 __ai int64_t vqaddd_s64(int64_t __p0, int64_t __p1) {
55963 __ret = (int64_t) __builtin_neon_vqaddd_s64(__p0, __p1);
55969 __ai int16_t vqaddh_s16(int16_t __p0, int16_t __p1) {
55971 __ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
55975 __ai int16_t vqaddh_s16(int16_t __p0, int16_t __p1) {
55977 __ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
55980 __ai int16_t __noswap_vqaddh_s16(int16_t __p0, int16_t __p1) {
55982 __ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
55988 __ai int64_t vqdmlals_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
55990 __ret = (int64_t) __builtin_neon_vqdmlals_s32(__p0, __p1, __p2);
55994 __ai int64_t vqdmlals_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
55996 __ret = (int64_t) __builtin_neon_vqdmlals_s32(__p0, __p1, __p2);
56002 __ai int32_t vqdmlalh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
56004 __ret = (int32_t) __builtin_neon_vqdmlalh_s16(__p0, __p1, __p2);
56008 __ai int32_t vqdmlalh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
56010 __ret = (int32_t) __builtin_neon_vqdmlalh_s16(__p0, __p1, __p2);
56016 __ai int64x2_t vqdmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
56018 __ret = vqdmlal_s32(__p0, vget_high_s32(__p1), vget_high_s32(__p2));
56022 __ai int64x2_t vqdmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
56024 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
56034 __ai int32x4_t vqdmlal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
56036 __ret = vqdmlal_s16(__p0, vget_high_s16(__p1), vget_high_s16(__p2));
56040 __ai int32x4_t vqdmlal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
56042 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
56052 #define vqdmlal_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56054 int32x4_t __s1 = __p1; \
56061 #define vqdmlal_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56063 int32x4_t __s1 = __p1; \
56076 #define vqdmlal_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56078 int16x8_t __s1 = __p1; \
56085 #define vqdmlal_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56087 int16x8_t __s1 = __p1; \
56100 #define vqdmlal_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56102 int32x4_t __s1 = __p1; \
56109 #define vqdmlal_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56111 int32x4_t __s1 = __p1; \
56124 #define vqdmlal_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56126 int16x8_t __s1 = __p1; \
56133 #define vqdmlal_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56135 int16x8_t __s1 = __p1; \
56148 __ai int64x2_t vqdmlal_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
56150 __ret = vqdmlal_n_s32(__p0, vget_high_s32(__p1), __p2);
56154 __ai int64x2_t vqdmlal_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
56156 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
56165 __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
56167 __ret = vqdmlal_n_s16(__p0, vget_high_s16(__p1), __p2);
56171 __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
56173 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
56182 #define vqdmlals_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56184 int32_t __s1 = __p1; \
56191 #define vqdmlals_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56193 int32_t __s1 = __p1; \
56203 #define vqdmlalh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56205 int16_t __s1 = __p1; \
56212 #define vqdmlalh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56214 int16_t __s1 = __p1; \
56224 #define vqdmlals_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56226 int32_t __s1 = __p1; \
56233 #define vqdmlals_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56235 int32_t __s1 = __p1; \
56245 #define vqdmlalh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56247 int16_t __s1 = __p1; \
56254 #define vqdmlalh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56256 int16_t __s1 = __p1; \
56266 #define vqdmlal_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56268 int32x2_t __s1 = __p1; \
56275 #define vqdmlal_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56277 int32x2_t __s1 = __p1; \
56290 #define vqdmlal_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56292 int16x4_t __s1 = __p1; \
56299 #define vqdmlal_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56301 int16x4_t __s1 = __p1; \
56314 __ai int64_t vqdmlsls_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
56316 __ret = (int64_t) __builtin_neon_vqdmlsls_s32(__p0, __p1, __p2);
56320 __ai int64_t vqdmlsls_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
56322 __ret = (int64_t) __builtin_neon_vqdmlsls_s32(__p0, __p1, __p2);
56328 __ai int32_t vqdmlslh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
56330 __ret = (int32_t) __builtin_neon_vqdmlslh_s16(__p0, __p1, __p2);
56334 __ai int32_t vqdmlslh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
56336 __ret = (int32_t) __builtin_neon_vqdmlslh_s16(__p0, __p1, __p2);
56342 __ai int64x2_t vqdmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
56344 __ret = vqdmlsl_s32(__p0, vget_high_s32(__p1), vget_high_s32(__p2));
56348 __ai int64x2_t vqdmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
56350 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
56360 __ai int32x4_t vqdmlsl_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
56362 __ret = vqdmlsl_s16(__p0, vget_high_s16(__p1), vget_high_s16(__p2));
56366 __ai int32x4_t vqdmlsl_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
56368 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
56378 #define vqdmlsl_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56380 int32x4_t __s1 = __p1; \
56387 #define vqdmlsl_high_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56389 int32x4_t __s1 = __p1; \
56402 #define vqdmlsl_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56404 int16x8_t __s1 = __p1; \
56411 #define vqdmlsl_high_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56413 int16x8_t __s1 = __p1; \
56426 #define vqdmlsl_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56428 int32x4_t __s1 = __p1; \
56435 #define vqdmlsl_high_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56437 int32x4_t __s1 = __p1; \
56450 #define vqdmlsl_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56452 int16x8_t __s1 = __p1; \
56459 #define vqdmlsl_high_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56461 int16x8_t __s1 = __p1; \
56474 __ai int64x2_t vqdmlsl_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
56476 __ret = vqdmlsl_n_s32(__p0, vget_high_s32(__p1), __p2);
56480 __ai int64x2_t vqdmlsl_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
56482 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
56491 __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
56493 __ret = vqdmlsl_n_s16(__p0, vget_high_s16(__p1), __p2);
56497 __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
56499 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
56508 #define vqdmlsls_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56510 int32_t __s1 = __p1; \
56517 #define vqdmlsls_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56519 int32_t __s1 = __p1; \
56529 #define vqdmlslh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56531 int16_t __s1 = __p1; \
56538 #define vqdmlslh_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56540 int16_t __s1 = __p1; \
56550 #define vqdmlsls_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56552 int32_t __s1 = __p1; \
56559 #define vqdmlsls_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56561 int32_t __s1 = __p1; \
56571 #define vqdmlslh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56573 int16_t __s1 = __p1; \
56580 #define vqdmlslh_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56582 int16_t __s1 = __p1; \
56592 #define vqdmlsl_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56594 int32x2_t __s1 = __p1; \
56601 #define vqdmlsl_laneq_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
56603 int32x2_t __s1 = __p1; \
56616 #define vqdmlsl_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56618 int16x4_t __s1 = __p1; \
56625 #define vqdmlsl_laneq_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
56627 int16x4_t __s1 = __p1; \
56640 __ai int32_t vqdmulhs_s32(int32_t __p0, int32_t __p1) {
56642 __ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
56646 __ai int32_t vqdmulhs_s32(int32_t __p0, int32_t __p1) {
56648 __ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
56651 __ai int32_t __noswap_vqdmulhs_s32(int32_t __p0, int32_t __p1) {
56653 __ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
56659 __ai int16_t vqdmulhh_s16(int16_t __p0, int16_t __p1) {
56661 __ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
56665 __ai int16_t vqdmulhh_s16(int16_t __p0, int16_t __p1) {
56667 __ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
56670 __ai int16_t __noswap_vqdmulhh_s16(int16_t __p0, int16_t __p1) {
56672 __ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
56754 #define vqdmulhq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56756 int32x4_t __s1 = __p1; \
56762 #define vqdmulhq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56764 int32x4_t __s1 = __p1; \
56775 #define vqdmulhq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56777 int16x8_t __s1 = __p1; \
56783 #define vqdmulhq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56785 int16x8_t __s1 = __p1; \
56796 #define vqdmulh_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56798 int32x4_t __s1 = __p1; \
56804 #define vqdmulh_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56806 int32x4_t __s1 = __p1; \
56817 #define vqdmulh_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56819 int16x8_t __s1 = __p1; \
56825 #define vqdmulh_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56827 int16x8_t __s1 = __p1; \
56838 __ai int64_t vqdmulls_s32(int32_t __p0, int32_t __p1) {
56840 __ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
56844 __ai int64_t vqdmulls_s32(int32_t __p0, int32_t __p1) {
56846 __ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
56849 __ai int64_t __noswap_vqdmulls_s32(int32_t __p0, int32_t __p1) {
56851 __ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
56857 __ai int32_t vqdmullh_s16(int16_t __p0, int16_t __p1) {
56859 __ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
56863 __ai int32_t vqdmullh_s16(int16_t __p0, int16_t __p1) {
56865 __ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
56868 __ai int32_t __noswap_vqdmullh_s16(int16_t __p0, int16_t __p1) {
56870 __ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
56876 __ai int64x2_t vqdmull_high_s32(int32x4_t __p0, int32x4_t __p1) {
56878 __ret = vqdmull_s32(vget_high_s32(__p0), vget_high_s32(__p1));
56882 __ai int64x2_t vqdmull_high_s32(int32x4_t __p0, int32x4_t __p1) {
56884 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
56893 __ai int32x4_t vqdmull_high_s16(int16x8_t __p0, int16x8_t __p1) {
56895 __ret = vqdmull_s16(vget_high_s16(__p0), vget_high_s16(__p1));
56899 __ai int32x4_t vqdmull_high_s16(int16x8_t __p0, int16x8_t __p1) {
56901 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
56910 #define vqdmull_high_lane_s32(__p0, __p1, __p2) __extension__ ({ \
56912 int32x2_t __s1 = __p1; \
56918 #define vqdmull_high_lane_s32(__p0, __p1, __p2) __extension__ ({ \
56920 int32x2_t __s1 = __p1; \
56931 #define vqdmull_high_lane_s16(__p0, __p1, __p2) __extension__ ({ \
56933 int16x4_t __s1 = __p1; \
56939 #define vqdmull_high_lane_s16(__p0, __p1, __p2) __extension__ ({ \
56941 int16x4_t __s1 = __p1; \
56952 #define vqdmull_high_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56954 int32x4_t __s1 = __p1; \
56960 #define vqdmull_high_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
56962 int32x4_t __s1 = __p1; \
56973 #define vqdmull_high_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56975 int16x8_t __s1 = __p1; \
56981 #define vqdmull_high_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
56983 int16x8_t __s1 = __p1; \
56994 __ai int64x2_t vqdmull_high_n_s32(int32x4_t __p0, int32_t __p1) {
56996 __ret = vqdmull_n_s32(vget_high_s32(__p0), __p1);
57000 __ai int64x2_t vqdmull_high_n_s32(int32x4_t __p0, int32_t __p1) {
57003 __ret = __noswap_vqdmull_n_s32(__noswap_vget_high_s32(__rev0), __p1);
57010 __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
57012 __ret = vqdmull_n_s16(vget_high_s16(__p0), __p1);
57016 __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
57019 __ret = __noswap_vqdmull_n_s16(__noswap_vget_high_s16(__rev0), __p1);
57102 #define vqdmull_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57104 int32x4_t __s1 = __p1; \
57110 #define vqdmull_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57112 int32x4_t __s1 = __p1; \
57123 #define vqdmull_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57125 int16x8_t __s1 = __p1; \
57131 #define vqdmull_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57133 int16x8_t __s1 = __p1; \
57228 __ai uint16x8_t vqmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {
57230 __ret = vcombine_u16(__p0, vqmovn_u32(__p1));
57234 __ai uint16x8_t vqmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {
57236 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
57245 __ai uint32x4_t vqmovn_high_u64(uint32x2_t __p0, uint64x2_t __p1) {
57247 __ret = vcombine_u32(__p0, vqmovn_u64(__p1));
57251 __ai uint32x4_t vqmovn_high_u64(uint32x2_t __p0, uint64x2_t __p1) {
57253 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
57262 __ai uint8x16_t vqmovn_high_u16(uint8x8_t __p0, uint16x8_t __p1) {
57264 __ret = vcombine_u8(__p0, vqmovn_u16(__p1));
57268 __ai uint8x16_t vqmovn_high_u16(uint8x8_t __p0, uint16x8_t __p1) {
57270 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
57279 __ai int16x8_t vqmovn_high_s32(int16x4_t __p0, int32x4_t __p1) {
57281 __ret = vcombine_s16(__p0, vqmovn_s32(__p1));
57285 __ai int16x8_t vqmovn_high_s32(int16x4_t __p0, int32x4_t __p1) {
57287 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
57296 __ai int32x4_t vqmovn_high_s64(int32x2_t __p0, int64x2_t __p1) {
57298 __ret = vcombine_s32(__p0, vqmovn_s64(__p1));
57302 __ai int32x4_t vqmovn_high_s64(int32x2_t __p0, int64x2_t __p1) {
57304 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
57313 __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
57315 __ret = vcombine_s8(__p0, vqmovn_s16(__p1));
57319 __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
57321 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
57372 __ai uint16x8_t vqmovun_high_s32(int16x4_t __p0, int32x4_t __p1) {
57374 __ret = vcombine_u16((uint16x4_t)(__p0), vqmovun_s32(__p1));
57378 __ai uint16x8_t vqmovun_high_s32(int16x4_t __p0, int32x4_t __p1) {
57380 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
57389 __ai uint32x4_t vqmovun_high_s64(int32x2_t __p0, int64x2_t __p1) {
57391 __ret = vcombine_u32((uint32x2_t)(__p0), vqmovun_s64(__p1));
57395 __ai uint32x4_t vqmovun_high_s64(int32x2_t __p0, int64x2_t __p1) {
57397 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
57406 __ai uint8x16_t vqmovun_high_s16(int8x8_t __p0, int16x8_t __p1) {
57408 __ret = vcombine_u8((uint8x8_t)(__p0), vqmovun_s16(__p1));
57412 __ai uint8x16_t vqmovun_high_s16(int8x8_t __p0, int16x8_t __p1) {
57414 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
57509 __ai int32_t vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
57511 __ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
57515 __ai int32_t vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
57517 __ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
57520 __ai int32_t __noswap_vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
57522 __ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
57528 __ai int16_t vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
57530 __ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
57534 __ai int16_t vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
57536 __ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
57539 __ai int16_t __noswap_vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
57541 __ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
57623 #define vqrdmulhq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57625 int32x4_t __s1 = __p1; \
57631 #define vqrdmulhq_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57633 int32x4_t __s1 = __p1; \
57644 #define vqrdmulhq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57646 int16x8_t __s1 = __p1; \
57652 #define vqrdmulhq_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57654 int16x8_t __s1 = __p1; \
57665 #define vqrdmulh_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57667 int32x4_t __s1 = __p1; \
57673 #define vqrdmulh_laneq_s32(__p0, __p1, __p2) __extension__ ({ \
57675 int32x4_t __s1 = __p1; \
57686 #define vqrdmulh_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57688 int16x8_t __s1 = __p1; \
57694 #define vqrdmulh_laneq_s16(__p0, __p1, __p2) __extension__ ({ \
57696 int16x8_t __s1 = __p1; \
57707 __ai uint8_t vqrshlb_u8(uint8_t __p0, uint8_t __p1) {
57709 __ret = (uint8_t) __builtin_neon_vqrshlb_u8(__p0, __p1);
57713 __ai uint8_t vqrshlb_u8(uint8_t __p0, uint8_t __p1) {
57715 __ret = (uint8_t) __builtin_neon_vqrshlb_u8(__p0, __p1);
57721 __ai uint32_t vqrshls_u32(uint32_t __p0, uint32_t __p1) {
57723 __ret = (uint32_t) __builtin_neon_vqrshls_u32(__p0, __p1);
57727 __ai uint32_t vqrshls_u32(uint32_t __p0, uint32_t __p1) {
57729 __ret = (uint32_t) __builtin_neon_vqrshls_u32(__p0, __p1);
57735 __ai uint64_t vqrshld_u64(uint64_t __p0, uint64_t __p1) {
57737 __ret = (uint64_t) __builtin_neon_vqrshld_u64(__p0, __p1);
57741 __ai uint64_t vqrshld_u64(uint64_t __p0, uint64_t __p1) {
57743 __ret = (uint64_t) __builtin_neon_vqrshld_u64(__p0, __p1);
57749 __ai uint16_t vqrshlh_u16(uint16_t __p0, uint16_t __p1) {
57751 __ret = (uint16_t) __builtin_neon_vqrshlh_u16(__p0, __p1);
57755 __ai uint16_t vqrshlh_u16(uint16_t __p0, uint16_t __p1) {
57757 __ret = (uint16_t) __builtin_neon_vqrshlh_u16(__p0, __p1);
57763 __ai int8_t vqrshlb_s8(int8_t __p0, int8_t __p1) {
57765 __ret = (int8_t) __builtin_neon_vqrshlb_s8(__p0, __p1);
57769 __ai int8_t vqrshlb_s8(int8_t __p0, int8_t __p1) {
57771 __ret = (int8_t) __builtin_neon_vqrshlb_s8(__p0, __p1);
57777 __ai int32_t vqrshls_s32(int32_t __p0, int32_t __p1) {
57779 __ret = (int32_t) __builtin_neon_vqrshls_s32(__p0, __p1);
57783 __ai int32_t vqrshls_s32(int32_t __p0, int32_t __p1) {
57785 __ret = (int32_t) __builtin_neon_vqrshls_s32(__p0, __p1);
57791 __ai int64_t vqrshld_s64(int64_t __p0, int64_t __p1) {
57793 __ret = (int64_t) __builtin_neon_vqrshld_s64(__p0, __p1);
57797 __ai int64_t vqrshld_s64(int64_t __p0, int64_t __p1) {
57799 __ret = (int64_t) __builtin_neon_vqrshld_s64(__p0, __p1);
57805 __ai int16_t vqrshlh_s16(int16_t __p0, int16_t __p1) {
57807 __ret = (int16_t) __builtin_neon_vqrshlh_s16(__p0, __p1);
57811 __ai int16_t vqrshlh_s16(int16_t __p0, int16_t __p1) {
57813 __ret = (int16_t) __builtin_neon_vqrshlh_s16(__p0, __p1);
57945 #define vqrshrns_n_u32(__p0, __p1) __extension__ ({ \
57948 __ret = (uint16_t) __builtin_neon_vqrshrns_n_u32(__s0, __p1); \
57952 #define vqrshrns_n_u32(__p0, __p1) __extension__ ({ \
57955 __ret = (uint16_t) __builtin_neon_vqrshrns_n_u32(__s0, __p1); \
57961 #define vqrshrnd_n_u64(__p0, __p1) __extension__ ({ \
57964 __ret = (uint32_t) __builtin_neon_vqrshrnd_n_u64(__s0, __p1); \
57968 #define vqrshrnd_n_u64(__p0, __p1) __extension__ ({ \
57971 __ret = (uint32_t) __builtin_neon_vqrshrnd_n_u64(__s0, __p1); \
57977 #define vqrshrnh_n_u16(__p0, __p1) __extension__ ({ \
57980 __ret = (uint8_t) __builtin_neon_vqrshrnh_n_u16(__s0, __p1); \
57984 #define vqrshrnh_n_u16(__p0, __p1) __extension__ ({ \
57987 __ret = (uint8_t) __builtin_neon_vqrshrnh_n_u16(__s0, __p1); \
57993 #define vqrshrns_n_s32(__p0, __p1) __extension__ ({ \
57996 __ret = (int16_t) __builtin_neon_vqrshrns_n_s32(__s0, __p1); \
58000 #define vqrshrns_n_s32(__p0, __p1) __extension__ ({ \
58003 __ret = (int16_t) __builtin_neon_vqrshrns_n_s32(__s0, __p1); \
58009 #define vqrshrnd_n_s64(__p0, __p1) __extension__ ({ \
58012 __ret = (int32_t) __builtin_neon_vqrshrnd_n_s64(__s0, __p1); \
58016 #define vqrshrnd_n_s64(__p0, __p1) __extension__ ({ \
58019 __ret = (int32_t) __builtin_neon_vqrshrnd_n_s64(__s0, __p1); \
58025 #define vqrshrnh_n_s16(__p0, __p1) __extension__ ({ \
58028 __ret = (int8_t) __builtin_neon_vqrshrnh_n_s16(__s0, __p1); \
58032 #define vqrshrnh_n_s16(__p0, __p1) __extension__ ({ \
58035 __ret = (int8_t) __builtin_neon_vqrshrnh_n_s16(__s0, __p1); \
58104 #define vqrshruns_n_s32(__p0, __p1) __extension__ ({ \
58107 __ret = (int16_t) __builtin_neon_vqrshruns_n_s32(__s0, __p1); \
58111 #define vqrshruns_n_s32(__p0, __p1) __extension__ ({ \
58114 __ret = (int16_t) __builtin_neon_vqrshruns_n_s32(__s0, __p1); \
58120 #define vqrshrund_n_s64(__p0, __p1) __extension__ ({ \
58123 __ret = (int32_t) __builtin_neon_vqrshrund_n_s64(__s0, __p1); \
58127 #define vqrshrund_n_s64(__p0, __p1) __extension__ ({ \
58130 __ret = (int32_t) __builtin_neon_vqrshrund_n_s64(__s0, __p1); \
58136 #define vqrshrunh_n_s16(__p0, __p1) __extension__ ({ \
58139 __ret = (int8_t) __builtin_neon_vqrshrunh_n_s16(__s0, __p1); \
58143 #define vqrshrunh_n_s16(__p0, __p1) __extension__ ({ \
58146 __ret = (int8_t) __builtin_neon_vqrshrunh_n_s16(__s0, __p1); \
58152 __ai uint8_t vqshlb_u8(uint8_t __p0, uint8_t __p1) {
58154 __ret = (uint8_t) __builtin_neon_vqshlb_u8(__p0, __p1);
58158 __ai uint8_t vqshlb_u8(uint8_t __p0, uint8_t __p1) {
58160 __ret = (uint8_t) __builtin_neon_vqshlb_u8(__p0, __p1);
58166 __ai uint32_t vqshls_u32(uint32_t __p0, uint32_t __p1) {
58168 __ret = (uint32_t) __builtin_neon_vqshls_u32(__p0, __p1);
58172 __ai uint32_t vqshls_u32(uint32_t __p0, uint32_t __p1) {
58174 __ret = (uint32_t) __builtin_neon_vqshls_u32(__p0, __p1);
58180 __ai uint64_t vqshld_u64(uint64_t __p0, uint64_t __p1) {
58182 __ret = (uint64_t) __builtin_neon_vqshld_u64(__p0, __p1);
58186 __ai uint64_t vqshld_u64(uint64_t __p0, uint64_t __p1) {
58188 __ret = (uint64_t) __builtin_neon_vqshld_u64(__p0, __p1);
58194 __ai uint16_t vqshlh_u16(uint16_t __p0, uint16_t __p1) {
58196 __ret = (uint16_t) __builtin_neon_vqshlh_u16(__p0, __p1);
58200 __ai uint16_t vqshlh_u16(uint16_t __p0, uint16_t __p1) {
58202 __ret = (uint16_t) __builtin_neon_vqshlh_u16(__p0, __p1);
58208 __ai int8_t vqshlb_s8(int8_t __p0, int8_t __p1) {
58210 __ret = (int8_t) __builtin_neon_vqshlb_s8(__p0, __p1);
58214 __ai int8_t vqshlb_s8(int8_t __p0, int8_t __p1) {
58216 __ret = (int8_t) __builtin_neon_vqshlb_s8(__p0, __p1);
58222 __ai int32_t vqshls_s32(int32_t __p0, int32_t __p1) {
58224 __ret = (int32_t) __builtin_neon_vqshls_s32(__p0, __p1);
58228 __ai int32_t vqshls_s32(int32_t __p0, int32_t __p1) {
58230 __ret = (int32_t) __builtin_neon_vqshls_s32(__p0, __p1);
58236 __ai int64_t vqshld_s64(int64_t __p0, int64_t __p1) {
58238 __ret = (int64_t) __builtin_neon_vqshld_s64(__p0, __p1);
58242 __ai int64_t vqshld_s64(int64_t __p0, int64_t __p1) {
58244 __ret = (int64_t) __builtin_neon_vqshld_s64(__p0, __p1);
58250 __ai int16_t vqshlh_s16(int16_t __p0, int16_t __p1) {
58252 __ret = (int16_t) __builtin_neon_vqshlh_s16(__p0, __p1);
58256 __ai int16_t vqshlh_s16(int16_t __p0, int16_t __p1) {
58258 __ret = (int16_t) __builtin_neon_vqshlh_s16(__p0, __p1);
58264 #define vqshlb_n_u8(__p0, __p1) __extension__ ({ \
58267 __ret = (uint8_t) __builtin_neon_vqshlb_n_u8(__s0, __p1); \
58271 #define vqshlb_n_u8(__p0, __p1) __extension__ ({ \
58274 __ret = (uint8_t) __builtin_neon_vqshlb_n_u8(__s0, __p1); \
58280 #define vqshls_n_u32(__p0, __p1) __extension__ ({ \
58283 __ret = (uint32_t) __builtin_neon_vqshls_n_u32(__s0, __p1); \
58287 #define vqshls_n_u32(__p0, __p1) __extension__ ({ \
58290 __ret = (uint32_t) __builtin_neon_vqshls_n_u32(__s0, __p1); \
58296 #define vqshld_n_u64(__p0, __p1) __extension__ ({ \
58299 __ret = (uint64_t) __builtin_neon_vqshld_n_u64(__s0, __p1); \
58303 #define vqshld_n_u64(__p0, __p1) __extension__ ({ \
58306 __ret = (uint64_t) __builtin_neon_vqshld_n_u64(__s0, __p1); \
58312 #define vqshlh_n_u16(__p0, __p1) __extension__ ({ \
58315 __ret = (uint16_t) __builtin_neon_vqshlh_n_u16(__s0, __p1); \
58319 #define vqshlh_n_u16(__p0, __p1) __extension__ ({ \
58322 __ret = (uint16_t) __builtin_neon_vqshlh_n_u16(__s0, __p1); \
58328 #define vqshlb_n_s8(__p0, __p1) __extension__ ({ \
58331 __ret = (int8_t) __builtin_neon_vqshlb_n_s8(__s0, __p1); \
58335 #define vqshlb_n_s8(__p0, __p1) __extension__ ({ \
58338 __ret = (int8_t) __builtin_neon_vqshlb_n_s8(__s0, __p1); \
58344 #define vqshls_n_s32(__p0, __p1) __extension__ ({ \
58347 __ret = (int32_t) __builtin_neon_vqshls_n_s32(__s0, __p1); \
58351 #define vqshls_n_s32(__p0, __p1) __extension__ ({ \
58354 __ret = (int32_t) __builtin_neon_vqshls_n_s32(__s0, __p1); \
58360 #define vqshld_n_s64(__p0, __p1) __extension__ ({ \
58363 __ret = (int64_t) __builtin_neon_vqshld_n_s64(__s0, __p1); \
58367 #define vqshld_n_s64(__p0, __p1) __extension__ ({ \
58370 __ret = (int64_t) __builtin_neon_vqshld_n_s64(__s0, __p1); \
58376 #define vqshlh_n_s16(__p0, __p1) __extension__ ({ \
58379 __ret = (int16_t) __builtin_neon_vqshlh_n_s16(__s0, __p1); \
58383 #define vqshlh_n_s16(__p0, __p1) __extension__ ({ \
58386 __ret = (int16_t) __builtin_neon_vqshlh_n_s16(__s0, __p1); \
58392 #define vqshlub_n_s8(__p0, __p1) __extension__ ({ \
58395 __ret = (int8_t) __builtin_neon_vqshlub_n_s8(__s0, __p1); \
58399 #define vqshlub_n_s8(__p0, __p1) __extension__ ({ \
58402 __ret = (int8_t) __builtin_neon_vqshlub_n_s8(__s0, __p1); \
58408 #define vqshlus_n_s32(__p0, __p1) __extension__ ({ \
58411 __ret = (int32_t) __builtin_neon_vqshlus_n_s32(__s0, __p1); \
58415 #define vqshlus_n_s32(__p0, __p1) __extension__ ({ \
58418 __ret = (int32_t) __builtin_neon_vqshlus_n_s32(__s0, __p1); \
58424 #define vqshlud_n_s64(__p0, __p1) __extension__ ({ \
58427 __ret = (int64_t) __builtin_neon_vqshlud_n_s64(__s0, __p1); \
58431 #define vqshlud_n_s64(__p0, __p1) __extension__ ({ \
58434 __ret = (int64_t) __builtin_neon_vqshlud_n_s64(__s0, __p1); \
58440 #define vqshluh_n_s16(__p0, __p1) __extension__ ({ \
58443 __ret = (int16_t) __builtin_neon_vqshluh_n_s16(__s0, __p1); \
58447 #define vqshluh_n_s16(__p0, __p1) __extension__ ({ \
58450 __ret = (int16_t) __builtin_neon_vqshluh_n_s16(__s0, __p1); \
58582 #define vqshrns_n_u32(__p0, __p1) __extension__ ({ \
58585 __ret = (uint16_t) __builtin_neon_vqshrns_n_u32(__s0, __p1); \
58589 #define vqshrns_n_u32(__p0, __p1) __extension__ ({ \
58592 __ret = (uint16_t) __builtin_neon_vqshrns_n_u32(__s0, __p1); \
58598 #define vqshrnd_n_u64(__p0, __p1) __extension__ ({ \
58601 __ret = (uint32_t) __builtin_neon_vqshrnd_n_u64(__s0, __p1); \
58605 #define vqshrnd_n_u64(__p0, __p1) __extension__ ({ \
58608 __ret = (uint32_t) __builtin_neon_vqshrnd_n_u64(__s0, __p1); \
58614 #define vqshrnh_n_u16(__p0, __p1) __extension__ ({ \
58617 __ret = (uint8_t) __builtin_neon_vqshrnh_n_u16(__s0, __p1); \
58621 #define vqshrnh_n_u16(__p0, __p1) __extension__ ({ \
58624 __ret = (uint8_t) __builtin_neon_vqshrnh_n_u16(__s0, __p1); \
58630 #define vqshrns_n_s32(__p0, __p1) __extension__ ({ \
58633 __ret = (int16_t) __builtin_neon_vqshrns_n_s32(__s0, __p1); \
58637 #define vqshrns_n_s32(__p0, __p1) __extension__ ({ \
58640 __ret = (int16_t) __builtin_neon_vqshrns_n_s32(__s0, __p1); \
58646 #define vqshrnd_n_s64(__p0, __p1) __extension__ ({ \
58649 __ret = (int32_t) __builtin_neon_vqshrnd_n_s64(__s0, __p1); \
58653 #define vqshrnd_n_s64(__p0, __p1) __extension__ ({ \
58656 __ret = (int32_t) __builtin_neon_vqshrnd_n_s64(__s0, __p1); \
58662 #define vqshrnh_n_s16(__p0, __p1) __extension__ ({ \
58665 __ret = (int8_t) __builtin_neon_vqshrnh_n_s16(__s0, __p1); \
58669 #define vqshrnh_n_s16(__p0, __p1) __extension__ ({ \
58672 __ret = (int8_t) __builtin_neon_vqshrnh_n_s16(__s0, __p1); \
58741 #define vqshruns_n_s32(__p0, __p1) __extension__ ({ \
58744 __ret = (int16_t) __builtin_neon_vqshruns_n_s32(__s0, __p1); \
58748 #define vqshruns_n_s32(__p0, __p1) __extension__ ({ \
58751 __ret = (int16_t) __builtin_neon_vqshruns_n_s32(__s0, __p1); \
58757 #define vqshrund_n_s64(__p0, __p1) __extension__ ({ \
58760 __ret = (int32_t) __builtin_neon_vqshrund_n_s64(__s0, __p1); \
58764 #define vqshrund_n_s64(__p0, __p1) __extension__ ({ \
58767 __ret = (int32_t) __builtin_neon_vqshrund_n_s64(__s0, __p1); \
58773 #define vqshrunh_n_s16(__p0, __p1) __extension__ ({ \
58776 __ret = (int8_t) __builtin_neon_vqshrunh_n_s16(__s0, __p1); \
58780 #define vqshrunh_n_s16(__p0, __p1) __extension__ ({ \
58783 __ret = (int8_t) __builtin_neon_vqshrunh_n_s16(__s0, __p1); \
58789 __ai uint8_t vqsubb_u8(uint8_t __p0, uint8_t __p1) {
58791 __ret = (uint8_t) __builtin_neon_vqsubb_u8(__p0, __p1);
58795 __ai uint8_t vqsubb_u8(uint8_t __p0, uint8_t __p1) {
58797 __ret = (uint8_t) __builtin_neon_vqsubb_u8(__p0, __p1);
58803 __ai uint32_t vqsubs_u32(uint32_t __p0, uint32_t __p1) {
58805 __ret = (uint32_t) __builtin_neon_vqsubs_u32(__p0, __p1);
58809 __ai uint32_t vqsubs_u32(uint32_t __p0, uint32_t __p1) {
58811 __ret = (uint32_t) __builtin_neon_vqsubs_u32(__p0, __p1);
58817 __ai uint64_t vqsubd_u64(uint64_t __p0, uint64_t __p1) {
58819 __ret = (uint64_t) __builtin_neon_vqsubd_u64(__p0, __p1);
58823 __ai uint64_t vqsubd_u64(uint64_t __p0, uint64_t __p1) {
58825 __ret = (uint64_t) __builtin_neon_vqsubd_u64(__p0, __p1);
58831 __ai uint16_t vqsubh_u16(uint16_t __p0, uint16_t __p1) {
58833 __ret = (uint16_t) __builtin_neon_vqsubh_u16(__p0, __p1);
58837 __ai uint16_t vqsubh_u16(uint16_t __p0, uint16_t __p1) {
58839 __ret = (uint16_t) __builtin_neon_vqsubh_u16(__p0, __p1);
58845 __ai int8_t vqsubb_s8(int8_t __p0, int8_t __p1) {
58847 __ret = (int8_t) __builtin_neon_vqsubb_s8(__p0, __p1);
58851 __ai int8_t vqsubb_s8(int8_t __p0, int8_t __p1) {
58853 __ret = (int8_t) __builtin_neon_vqsubb_s8(__p0, __p1);
58859 __ai int32_t vqsubs_s32(int32_t __p0, int32_t __p1) {
58861 __ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
58865 __ai int32_t vqsubs_s32(int32_t __p0, int32_t __p1) {
58867 __ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
58870 __ai int32_t __noswap_vqsubs_s32(int32_t __p0, int32_t __p1) {
58872 __ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
58878 __ai int64_t vqsubd_s64(int64_t __p0, int64_t __p1) {
58880 __ret = (int64_t) __builtin_neon_vqsubd_s64(__p0, __p1);
58884 __ai int64_t vqsubd_s64(int64_t __p0, int64_t __p1) {
58886 __ret = (int64_t) __builtin_neon_vqsubd_s64(__p0, __p1);
58892 __ai int16_t vqsubh_s16(int16_t __p0, int16_t __p1) {
58894 __ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
58898 __ai int16_t vqsubh_s16(int16_t __p0, int16_t __p1) {
58900 __ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
58903 __ai int16_t __noswap_vqsubh_s16(int16_t __p0, int16_t __p1) {
58905 __ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
58911 __ai poly8x8_t vqtbl1_p8(poly8x16_t __p0, uint8x8_t __p1) {
58913 __ret = (poly8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 4);
58917 __ai poly8x8_t vqtbl1_p8(poly8x16_t __p0, uint8x8_t __p1) {
58919 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
58928 __ai poly8x16_t vqtbl1q_p8(poly8x16_t __p0, uint8x16_t __p1) {
58930 __ret = (poly8x16_t) __builtin_neon_vqtbl1q_v((int8x16_t)__p0, (int8x16_t)__p1, 36);
58934 __ai poly8x16_t vqtbl1q_p8(poly8x16_t __p0, uint8x16_t __p1) {
58936 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
58945 __ai uint8x16_t vqtbl1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
58947 __ret = (uint8x16_t) __builtin_neon_vqtbl1q_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
58951 __ai uint8x16_t vqtbl1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
58953 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
58962 __ai int8x16_t vqtbl1q_s8(int8x16_t __p0, int8x16_t __p1) {
58964 __ret = (int8x16_t) __builtin_neon_vqtbl1q_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
58968 __ai int8x16_t vqtbl1q_s8(int8x16_t __p0, int8x16_t __p1) {
58970 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
58979 __ai uint8x8_t vqtbl1_u8(uint8x16_t __p0, uint8x8_t __p1) {
58981 __ret = (uint8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 16);
58985 __ai uint8x8_t vqtbl1_u8(uint8x16_t __p0, uint8x8_t __p1) {
58987 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
58996 __ai int8x8_t vqtbl1_s8(int8x16_t __p0, int8x8_t __p1) {
58998 __ret = (int8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 0);
59002 __ai int8x8_t vqtbl1_s8(int8x16_t __p0, int8x8_t __p1) {
59004 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59013 __ai poly8x8_t vqtbl2_p8(poly8x16x2_t __p0, uint8x8_t __p1) {
59015 __ret = (poly8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 4);
59019 __ai poly8x8_t vqtbl2_p8(poly8x16x2_t __p0, uint8x8_t __p1) {
59023 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59032 __ai poly8x16_t vqtbl2q_p8(poly8x16x2_t __p0, uint8x16_t __p1) {
59034 __ret = (poly8x16_t) __builtin_neon_vqtbl2q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p1, 36);
59038 __ai poly8x16_t vqtbl2q_p8(poly8x16x2_t __p0, uint8x16_t __p1) {
59042 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59051 __ai uint8x16_t vqtbl2q_u8(uint8x16x2_t __p0, uint8x16_t __p1) {
59053 __ret = (uint8x16_t) __builtin_neon_vqtbl2q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p1, 48);
59057 __ai uint8x16_t vqtbl2q_u8(uint8x16x2_t __p0, uint8x16_t __p1) {
59061 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59070 __ai int8x16_t vqtbl2q_s8(int8x16x2_t __p0, int8x16_t __p1) {
59072 __ret = (int8x16_t) __builtin_neon_vqtbl2q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p1, 32);
59076 __ai int8x16_t vqtbl2q_s8(int8x16x2_t __p0, int8x16_t __p1) {
59080 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59089 __ai uint8x8_t vqtbl2_u8(uint8x16x2_t __p0, uint8x8_t __p1) {
59091 __ret = (uint8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 16);
59095 __ai uint8x8_t vqtbl2_u8(uint8x16x2_t __p0, uint8x8_t __p1) {
59099 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59108 __ai int8x8_t vqtbl2_s8(int8x16x2_t __p0, int8x8_t __p1) {
59110 __ret = (int8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 0);
59114 __ai int8x8_t vqtbl2_s8(int8x16x2_t __p0, int8x8_t __p1) {
59118 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59127 __ai poly8x8_t vqtbl3_p8(poly8x16x3_t __p0, uint8x8_t __p1) {
59129 __ret = (poly8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x8_t)__p1, 4);
59133 __ai poly8x8_t vqtbl3_p8(poly8x16x3_t __p0, uint8x8_t __p1) {
59138 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59147 __ai poly8x16_t vqtbl3q_p8(poly8x16x3_t __p0, uint8x16_t __p1) {
59149 __ret = (poly8x16_t) __builtin_neon_vqtbl3q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p1, 36);
59153 __ai poly8x16_t vqtbl3q_p8(poly8x16x3_t __p0, uint8x16_t __p1) {
59158 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59167 __ai uint8x16_t vqtbl3q_u8(uint8x16x3_t __p0, uint8x16_t __p1) {
59169 __ret = (uint8x16_t) __builtin_neon_vqtbl3q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p1, 48);
59173 __ai uint8x16_t vqtbl3q_u8(uint8x16x3_t __p0, uint8x16_t __p1) {
59178 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59187 __ai int8x16_t vqtbl3q_s8(int8x16x3_t __p0, int8x16_t __p1) {
59189 __ret = (int8x16_t) __builtin_neon_vqtbl3q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p1, 32);
59193 __ai int8x16_t vqtbl3q_s8(int8x16x3_t __p0, int8x16_t __p1) {
59198 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59207 __ai uint8x8_t vqtbl3_u8(uint8x16x3_t __p0, uint8x8_t __p1) {
59209 __ret = (uint8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x8_t)__p1, 16);
59213 __ai uint8x8_t vqtbl3_u8(uint8x16x3_t __p0, uint8x8_t __p1) {
59218 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59227 __ai int8x8_t vqtbl3_s8(int8x16x3_t __p0, int8x8_t __p1) {
59229 __ret = (int8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x8_t)__p1, 0);
59233 __ai int8x8_t vqtbl3_s8(int8x16x3_t __p0, int8x8_t __p1) {
59238 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59247 __ai poly8x8_t vqtbl4_p8(poly8x16x4_t __p0, uint8x8_t __p1) {
59249 __ret = (poly8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x8_t)__p1, 4);
59253 __ai poly8x8_t vqtbl4_p8(poly8x16x4_t __p0, uint8x8_t __p1) {
59259 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59268 __ai poly8x16_t vqtbl4q_p8(poly8x16x4_t __p0, uint8x16_t __p1) {
59270 __ret = (poly8x16_t) __builtin_neon_vqtbl4q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x16_t)__p1, 36);
59274 __ai poly8x16_t vqtbl4q_p8(poly8x16x4_t __p0, uint8x16_t __p1) {
59280 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59289 __ai uint8x16_t vqtbl4q_u8(uint8x16x4_t __p0, uint8x16_t __p1) {
59291 __ret = (uint8x16_t) __builtin_neon_vqtbl4q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x16_t)__p1, 48);
59295 __ai uint8x16_t vqtbl4q_u8(uint8x16x4_t __p0, uint8x16_t __p1) {
59301 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59310 __ai int8x16_t vqtbl4q_s8(int8x16x4_t __p0, int8x16_t __p1) {
59312 __ret = (int8x16_t) __builtin_neon_vqtbl4q_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x16_t)__p1, 32);
59316 __ai int8x16_t vqtbl4q_s8(int8x16x4_t __p0, int8x16_t __p1) {
59322 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59331 __ai uint8x8_t vqtbl4_u8(uint8x16x4_t __p0, uint8x8_t __p1) {
59333 __ret = (uint8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x8_t)__p1, 16);
59337 __ai uint8x8_t vqtbl4_u8(uint8x16x4_t __p0, uint8x8_t __p1) {
59343 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59352 __ai int8x8_t vqtbl4_s8(int8x16x4_t __p0, int8x8_t __p1) {
59354 __ret = (int8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x16_t)__p0.val[2], (int8x16_t)__p0.val[3], (int8x8_t)__p1, 0);
59358 __ai int8x8_t vqtbl4_s8(int8x16x4_t __p0, int8x8_t __p1) {
59364 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59373 __ai poly8x8_t vqtbx1_p8(poly8x8_t __p0, poly8x16_t __p1, uint8x8_t __p2) {
59375 __ret = (poly8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 4);
59379 __ai poly8x8_t vqtbx1_p8(poly8x8_t __p0, poly8x16_t __p1, uint8x8_t __p2) {
59381 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59391 __ai poly8x16_t vqtbx1q_p8(poly8x16_t __p0, poly8x16_t __p1, uint8x16_t __p2) {
59393 __ret = (poly8x16_t) __builtin_neon_vqtbx1q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 36);
59397 __ai poly8x16_t vqtbx1q_p8(poly8x16_t __p0, poly8x16_t __p1, uint8x16_t __p2) {
59399 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59409 __ai uint8x16_t vqtbx1q_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
59411 __ret = (uint8x16_t) __builtin_neon_vqtbx1q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 48);
59415 __ai uint8x16_t vqtbx1q_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
59417 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59427 __ai int8x16_t vqtbx1q_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
59429 __ret = (int8x16_t) __builtin_neon_vqtbx1q_v((int8x16_t)__p0, (int8x16_t)__p1, (int8x16_t)__p2, 32);
59433 __ai int8x16_t vqtbx1q_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
59435 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59445 __ai uint8x8_t vqtbx1_u8(uint8x8_t __p0, uint8x16_t __p1, uint8x8_t __p2) {
59447 __ret = (uint8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 16);
59451 __ai uint8x8_t vqtbx1_u8(uint8x8_t __p0, uint8x16_t __p1, uint8x8_t __p2) {
59453 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59463 __ai int8x8_t vqtbx1_s8(int8x8_t __p0, int8x16_t __p1, int8x8_t __p2) {
59465 __ret = (int8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 0);
59469 __ai int8x8_t vqtbx1_s8(int8x8_t __p0, int8x16_t __p1, int8x8_t __p2) {
59471 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59481 __ai poly8x8_t vqtbx2_p8(poly8x8_t __p0, poly8x16x2_t __p1, uint8x8_t __p2) {
59483 __ret = (poly8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 4);
59487 __ai poly8x8_t vqtbx2_p8(poly8x8_t __p0, poly8x16x2_t __p1, uint8x8_t __p2) {
59490 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59491 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59501 __ai poly8x16_t vqtbx2q_p8(poly8x16_t __p0, poly8x16x2_t __p1, uint8x16_t __p2) {
59503 __ret = (poly8x16_t) __builtin_neon_vqtbx2q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p2, 36);
59507 __ai poly8x16_t vqtbx2q_p8(poly8x16_t __p0, poly8x16x2_t __p1, uint8x16_t __p2) {
59510 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59511 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59521 __ai uint8x16_t vqtbx2q_u8(uint8x16_t __p0, uint8x16x2_t __p1, uint8x16_t __p2) {
59523 __ret = (uint8x16_t) __builtin_neon_vqtbx2q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p2, 48);
59527 __ai uint8x16_t vqtbx2q_u8(uint8x16_t __p0, uint8x16x2_t __p1, uint8x16_t __p2) {
59530 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59531 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59541 __ai int8x16_t vqtbx2q_s8(int8x16_t __p0, int8x16x2_t __p1, int8x16_t __p2) {
59543 __ret = (int8x16_t) __builtin_neon_vqtbx2q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p2, 32);
59547 __ai int8x16_t vqtbx2q_s8(int8x16_t __p0, int8x16x2_t __p1, int8x16_t __p2) {
59550 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59551 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59561 __ai uint8x8_t vqtbx2_u8(uint8x8_t __p0, uint8x16x2_t __p1, uint8x8_t __p2) {
59563 __ret = (uint8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 16);
59567 __ai uint8x8_t vqtbx2_u8(uint8x8_t __p0, uint8x16x2_t __p1, uint8x8_t __p2) {
59570 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59571 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59581 __ai int8x8_t vqtbx2_s8(int8x8_t __p0, int8x16x2_t __p1, int8x8_t __p2) {
59583 __ret = (int8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 0);
59587 __ai int8x8_t vqtbx2_s8(int8x8_t __p0, int8x16x2_t __p1, int8x8_t __p2) {
59590 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59591 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59601 __ai poly8x8_t vqtbx3_p8(poly8x8_t __p0, poly8x16x3_t __p1, uint8x8_t __p2) {
59603 __ret = (poly8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x8_t)__p2, 4);
59607 __ai poly8x8_t vqtbx3_p8(poly8x8_t __p0, poly8x16x3_t __p1, uint8x8_t __p2) {
59610 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59611 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59612 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59622 __ai poly8x16_t vqtbx3q_p8(poly8x16_t __p0, poly8x16x3_t __p1, uint8x16_t __p2) {
59624 __ret = (poly8x16_t) __builtin_neon_vqtbx3q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p2, 36);
59628 __ai poly8x16_t vqtbx3q_p8(poly8x16_t __p0, poly8x16x3_t __p1, uint8x16_t __p2) {
59631 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59632 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59633 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59643 __ai uint8x16_t vqtbx3q_u8(uint8x16_t __p0, uint8x16x3_t __p1, uint8x16_t __p2) {
59645 __ret = (uint8x16_t) __builtin_neon_vqtbx3q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p2, 48);
59649 __ai uint8x16_t vqtbx3q_u8(uint8x16_t __p0, uint8x16x3_t __p1, uint8x16_t __p2) {
59652 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59653 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59654 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59664 __ai int8x16_t vqtbx3q_s8(int8x16_t __p0, int8x16x3_t __p1, int8x16_t __p2) {
59666 __ret = (int8x16_t) __builtin_neon_vqtbx3q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p2, 32);
59670 __ai int8x16_t vqtbx3q_s8(int8x16_t __p0, int8x16x3_t __p1, int8x16_t __p2) {
59673 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59674 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59675 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59685 __ai uint8x8_t vqtbx3_u8(uint8x8_t __p0, uint8x16x3_t __p1, uint8x8_t __p2) {
59687 __ret = (uint8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x8_t)__p2, 16);
59691 __ai uint8x8_t vqtbx3_u8(uint8x8_t __p0, uint8x16x3_t __p1, uint8x8_t __p2) {
59694 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59695 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59696 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59706 __ai int8x8_t vqtbx3_s8(int8x8_t __p0, int8x16x3_t __p1, int8x8_t __p2) {
59708 __ret = (int8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x8_t)__p2, 0);
59712 __ai int8x8_t vqtbx3_s8(int8x8_t __p0, int8x16x3_t __p1, int8x8_t __p2) {
59715 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59716 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59717 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59727 __ai poly8x8_t vqtbx4_p8(poly8x8_t __p0, poly8x16x4_t __p1, uint8x8_t __p2) {
59729 __ret = (poly8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x8_t)__p2, 4);
59733 __ai poly8x8_t vqtbx4_p8(poly8x8_t __p0, poly8x16x4_t __p1, uint8x8_t __p2) {
59736 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59737 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59738 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59739 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59749 __ai poly8x16_t vqtbx4q_p8(poly8x16_t __p0, poly8x16x4_t __p1, uint8x16_t __p2) {
59751 __ret = (poly8x16_t) __builtin_neon_vqtbx4q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x16_t)__p2, 36);
59755 __ai poly8x16_t vqtbx4q_p8(poly8x16_t __p0, poly8x16x4_t __p1, uint8x16_t __p2) {
59758 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59759 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59760 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59761 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59771 __ai uint8x16_t vqtbx4q_u8(uint8x16_t __p0, uint8x16x4_t __p1, uint8x16_t __p2) {
59773 __ret = (uint8x16_t) __builtin_neon_vqtbx4q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x16_t)__p2, 48);
59777 __ai uint8x16_t vqtbx4q_u8(uint8x16_t __p0, uint8x16x4_t __p1, uint8x16_t __p2) {
59780 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59781 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59782 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59783 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59793 __ai int8x16_t vqtbx4q_s8(int8x16_t __p0, int8x16x4_t __p1, int8x16_t __p2) {
59795 __ret = (int8x16_t) __builtin_neon_vqtbx4q_v((int8x16_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x16_t)__p2, 32);
59799 __ai int8x16_t vqtbx4q_s8(int8x16_t __p0, int8x16x4_t __p1, int8x16_t __p2) {
59802 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59803 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59804 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59805 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59815 __ai uint8x8_t vqtbx4_u8(uint8x8_t __p0, uint8x16x4_t __p1, uint8x8_t __p2) {
59817 __ret = (uint8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x8_t)__p2, 16);
59821 __ai uint8x8_t vqtbx4_u8(uint8x8_t __p0, uint8x16x4_t __p1, uint8x8_t __p2) {
59824 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59825 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59826 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59827 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59837 __ai int8x8_t vqtbx4_s8(int8x8_t __p0, int8x16x4_t __p1, int8x8_t __p2) {
59839 __ret = (int8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x16_t)__p1.val[2], (int8x16_t)__p1.val[3], (int8x8_t)__p2, 0);
59843 __ai int8x8_t vqtbx4_s8(int8x8_t __p0, int8x16x4_t __p1, int8x8_t __p2) {
59846 __rev1.val[0] = __builtin_shufflevector(__p1.val[0], __p1.val[0], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59847 __rev1.val[1] = __builtin_shufflevector(__p1.val[1], __p1.val[1], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59848 __rev1.val[2] = __builtin_shufflevector(__p1.val[2], __p1.val[2], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59849 __rev1.val[3] = __builtin_shufflevector(__p1.val[3], __p1.val[3], 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
59859 __ai uint16x8_t vraddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
59861 __ret = vcombine_u16(__p0, vraddhn_u32(__p1, __p2));
59865 __ai uint16x8_t vraddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
59867 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
59877 __ai uint32x4_t vraddhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
59879 __ret = vcombine_u32(__p0, vraddhn_u64(__p1, __p2));
59883 __ai uint32x4_t vraddhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
59885 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
59895 __ai uint8x16_t vraddhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
59897 __ret = vcombine_u8(__p0, vraddhn_u16(__p1, __p2));
59901 __ai uint8x16_t vraddhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
59903 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59913 __ai int16x8_t vraddhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
59915 __ret = vcombine_s16(__p0, vraddhn_s32(__p1, __p2));
59919 __ai int16x8_t vraddhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
59921 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
59931 __ai int32x4_t vraddhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
59933 __ret = vcombine_s32(__p0, vraddhn_s64(__p1, __p2));
59937 __ai int32x4_t vraddhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
59939 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
59949 __ai int8x16_t vraddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
59951 __ret = vcombine_s8(__p0, vraddhn_s16(__p1, __p2));
59955 __ai int8x16_t vraddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
59957 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
60121 __ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {
60123 __ret = (float64x2_t) __builtin_neon_vrecpsq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
60127 __ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {
60129 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
60138 __ai float64x1_t vrecps_f64(float64x1_t __p0, float64x1_t __p1) {
60140 __ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60144 __ai float64x1_t vrecps_f64(float64x1_t __p0, float64x1_t __p1) {
60146 __ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60152 __ai float64_t vrecpsd_f64(float64_t __p0, float64_t __p1) {
60154 __ret = (float64_t) __builtin_neon_vrecpsd_f64(__p0, __p1);
60158 __ai float64_t vrecpsd_f64(float64_t __p0, float64_t __p1) {
60160 __ret = (float64_t) __builtin_neon_vrecpsd_f64(__p0, __p1);
60166 __ai float32_t vrecpss_f32(float32_t __p0, float32_t __p1) {
60168 __ret = (float32_t) __builtin_neon_vrecpss_f32(__p0, __p1);
60172 __ai float32_t vrecpss_f32(float32_t __p0, float32_t __p1) {
60174 __ret = (float32_t) __builtin_neon_vrecpss_f32(__p0, __p1);
60208 __ai uint64_t vrshld_u64(uint64_t __p0, uint64_t __p1) {
60210 __ret = (uint64_t) __builtin_neon_vrshld_u64(__p0, __p1);
60214 __ai uint64_t vrshld_u64(uint64_t __p0, uint64_t __p1) {
60216 __ret = (uint64_t) __builtin_neon_vrshld_u64(__p0, __p1);
60222 __ai int64_t vrshld_s64(int64_t __p0, int64_t __p1) {
60224 __ret = (int64_t) __builtin_neon_vrshld_s64(__p0, __p1);
60228 __ai int64_t vrshld_s64(int64_t __p0, int64_t __p1) {
60230 __ret = (int64_t) __builtin_neon_vrshld_s64(__p0, __p1);
60236 #define vrshrd_n_u64(__p0, __p1) __extension__ ({ \
60239 __ret = (uint64_t) __builtin_neon_vrshrd_n_u64(__s0, __p1); \
60243 #define vrshrd_n_u64(__p0, __p1) __extension__ ({ \
60246 __ret = (uint64_t) __builtin_neon_vrshrd_n_u64(__s0, __p1); \
60252 #define vrshrd_n_s64(__p0, __p1) __extension__ ({ \
60255 __ret = (int64_t) __builtin_neon_vrshrd_n_s64(__s0, __p1); \
60259 #define vrshrd_n_s64(__p0, __p1) __extension__ ({ \
60262 __ret = (int64_t) __builtin_neon_vrshrd_n_s64(__s0, __p1); \
60452 __ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {
60454 __ret = (float64x2_t) __builtin_neon_vrsqrtsq_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
60458 __ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {
60460 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
60469 __ai float64x1_t vrsqrts_f64(float64x1_t __p0, float64x1_t __p1) {
60471 __ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60475 __ai float64x1_t vrsqrts_f64(float64x1_t __p0, float64x1_t __p1) {
60477 __ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60483 __ai float64_t vrsqrtsd_f64(float64_t __p0, float64_t __p1) {
60485 __ret = (float64_t) __builtin_neon_vrsqrtsd_f64(__p0, __p1);
60489 __ai float64_t vrsqrtsd_f64(float64_t __p0, float64_t __p1) {
60491 __ret = (float64_t) __builtin_neon_vrsqrtsd_f64(__p0, __p1);
60497 __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
60499 __ret = (float32_t) __builtin_neon_vrsqrtss_f32(__p0, __p1);
60503 __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
60505 __ret = (float32_t) __builtin_neon_vrsqrtss_f32(__p0, __p1);
60511 #define vrsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
60513 uint64_t __s1 = __p1; \
60519 #define vrsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
60521 uint64_t __s1 = __p1; \
60529 #define vrsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
60531 int64_t __s1 = __p1; \
60537 #define vrsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
60539 int64_t __s1 = __p1; \
60547 __ai uint16x8_t vrsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
60549 __ret = vcombine_u16(__p0, vrsubhn_u32(__p1, __p2));
60553 __ai uint16x8_t vrsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
60555 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
60565 __ai uint32x4_t vrsubhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
60567 __ret = vcombine_u32(__p0, vrsubhn_u64(__p1, __p2));
60571 __ai uint32x4_t vrsubhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
60573 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
60583 __ai uint8x16_t vrsubhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
60585 __ret = vcombine_u8(__p0, vrsubhn_u16(__p1, __p2));
60589 __ai uint8x16_t vrsubhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
60591 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
60601 __ai int16x8_t vrsubhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
60603 __ret = vcombine_s16(__p0, vrsubhn_s32(__p1, __p2));
60607 __ai int16x8_t vrsubhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
60609 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
60619 __ai int32x4_t vrsubhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
60621 __ret = vcombine_s32(__p0, vrsubhn_s64(__p1, __p2));
60625 __ai int32x4_t vrsubhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
60627 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
60637 __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
60639 __ret = vcombine_s8(__p0, vrsubhn_s16(__p1, __p2));
60643 __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
60645 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
60655 #define vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60657 poly64x1_t __s1 = __p1; \
60663 #define vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60665 poly64x1_t __s1 = __p1; \
60670 #define __noswap_vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60672 poly64x1_t __s1 = __p1; \
60680 #define vsetq_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60682 poly64x2_t __s1 = __p1; \
60688 #define vsetq_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60690 poly64x2_t __s1 = __p1; \
60697 #define __noswap_vsetq_lane_p64(__p0, __p1, __p2) __extension__ ({ \
60699 poly64x2_t __s1 = __p1; \
60707 #define vsetq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60709 float64x2_t __s1 = __p1; \
60715 #define vsetq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60717 float64x2_t __s1 = __p1; \
60724 #define __noswap_vsetq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60726 float64x2_t __s1 = __p1; \
60734 #define vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60736 float64x1_t __s1 = __p1; \
60742 #define vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60744 float64x1_t __s1 = __p1; \
60749 #define __noswap_vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
60751 float64x1_t __s1 = __p1; \
60759 __ai uint64_t vshld_u64(uint64_t __p0, uint64_t __p1) {
60761 __ret = (uint64_t) __builtin_neon_vshld_u64(__p0, __p1);
60765 __ai uint64_t vshld_u64(uint64_t __p0, uint64_t __p1) {
60767 __ret = (uint64_t) __builtin_neon_vshld_u64(__p0, __p1);
60773 __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
60775 __ret = (int64_t) __builtin_neon_vshld_s64(__p0, __p1);
60779 __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
60781 __ret = (int64_t) __builtin_neon_vshld_s64(__p0, __p1);
60787 #define vshld_n_u64(__p0, __p1) __extension__ ({ \
60790 __ret = (uint64_t) __builtin_neon_vshld_n_u64(__s0, __p1); \
60794 #define vshld_n_u64(__p0, __p1) __extension__ ({ \
60797 __ret = (uint64_t) __builtin_neon_vshld_n_u64(__s0, __p1); \
60803 #define vshld_n_s64(__p0, __p1) __extension__ ({ \
60806 __ret = (int64_t) __builtin_neon_vshld_n_s64(__s0, __p1); \
60810 #define vshld_n_s64(__p0, __p1) __extension__ ({ \
60813 __ret = (int64_t) __builtin_neon_vshld_n_s64(__s0, __p1); \
60927 #define vshrd_n_u64(__p0, __p1) __extension__ ({ \
60930 __ret = (uint64_t) __builtin_neon_vshrd_n_u64(__s0, __p1); \
60934 #define vshrd_n_u64(__p0, __p1) __extension__ ({ \
60937 __ret = (uint64_t) __builtin_neon_vshrd_n_u64(__s0, __p1); \
60943 #define vshrd_n_s64(__p0, __p1) __extension__ ({ \
60946 __ret = (int64_t) __builtin_neon_vshrd_n_s64(__s0, __p1); \
60950 #define vshrd_n_s64(__p0, __p1) __extension__ ({ \
60953 __ret = (int64_t) __builtin_neon_vshrd_n_s64(__s0, __p1); \
61085 #define vslid_n_u64(__p0, __p1, __p2) __extension__ ({ \
61087 uint64_t __s1 = __p1; \
61093 #define vslid_n_u64(__p0, __p1, __p2) __extension__ ({ \
61095 uint64_t __s1 = __p1; \
61103 #define vslid_n_s64(__p0, __p1, __p2) __extension__ ({ \
61105 int64_t __s1 = __p1; \
61111 #define vslid_n_s64(__p0, __p1, __p2) __extension__ ({ \
61113 int64_t __s1 = __p1; \
61121 #define vsli_n_p64(__p0, __p1, __p2) __extension__ ({ \
61123 poly64x1_t __s1 = __p1; \
61129 #define vsli_n_p64(__p0, __p1, __p2) __extension__ ({ \
61131 poly64x1_t __s1 = __p1; \
61139 #define vsliq_n_p64(__p0, __p1, __p2) __extension__ ({ \
61141 poly64x2_t __s1 = __p1; \
61147 #define vsliq_n_p64(__p0, __p1, __p2) __extension__ ({ \
61149 poly64x2_t __s1 = __p1; \
61160 __ai uint8_t vsqaddb_u8(uint8_t __p0, uint8_t __p1) {
61162 __ret = (uint8_t) __builtin_neon_vsqaddb_u8(__p0, __p1);
61166 __ai uint8_t vsqaddb_u8(uint8_t __p0, uint8_t __p1) {
61168 __ret = (uint8_t) __builtin_neon_vsqaddb_u8(__p0, __p1);
61174 __ai uint32_t vsqadds_u32(uint32_t __p0, uint32_t __p1) {
61176 __ret = (uint32_t) __builtin_neon_vsqadds_u32(__p0, __p1);
61180 __ai uint32_t vsqadds_u32(uint32_t __p0, uint32_t __p1) {
61182 __ret = (uint32_t) __builtin_neon_vsqadds_u32(__p0, __p1);
61188 __ai uint64_t vsqaddd_u64(uint64_t __p0, uint64_t __p1) {
61190 __ret = (uint64_t) __builtin_neon_vsqaddd_u64(__p0, __p1);
61194 __ai uint64_t vsqaddd_u64(uint64_t __p0, uint64_t __p1) {
61196 __ret = (uint64_t) __builtin_neon_vsqaddd_u64(__p0, __p1);
61202 __ai uint16_t vsqaddh_u16(uint16_t __p0, uint16_t __p1) {
61204 __ret = (uint16_t) __builtin_neon_vsqaddh_u16(__p0, __p1);
61208 __ai uint16_t vsqaddh_u16(uint16_t __p0, uint16_t __p1) {
61210 __ret = (uint16_t) __builtin_neon_vsqaddh_u16(__p0, __p1);
61216 __ai uint8x16_t vsqaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
61218 __ret = (uint8x16_t) __builtin_neon_vsqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 48);
61222 __ai uint8x16_t vsqaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
61224 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
61233 __ai uint32x4_t vsqaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
61235 __ret = (uint32x4_t) __builtin_neon_vsqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 50);
61239 __ai uint32x4_t vsqaddq_u32(uint32x4_t __p0, uint32x4_t __p1) {
61241 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
61250 __ai uint64x2_t vsqaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
61252 __ret = (uint64x2_t) __builtin_neon_vsqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
61256 __ai uint64x2_t vsqaddq_u64(uint64x2_t __p0, uint64x2_t __p1) {
61258 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
61267 __ai uint16x8_t vsqaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
61269 __ret = (uint16x8_t) __builtin_neon_vsqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 49);
61273 __ai uint16x8_t vsqaddq_u16(uint16x8_t __p0, uint16x8_t __p1) {
61275 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
61284 __ai uint8x8_t vsqadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
61286 __ret = (uint8x8_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
61290 __ai uint8x8_t vsqadd_u8(uint8x8_t __p0, uint8x8_t __p1) {
61292 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
61301 __ai uint32x2_t vsqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
61303 __ret = (uint32x2_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
61307 __ai uint32x2_t vsqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
61309 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
61318 __ai uint64x1_t vsqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
61320 __ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
61324 __ai uint64x1_t vsqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
61326 __ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
61332 __ai uint16x4_t vsqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
61334 __ret = (uint16x4_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
61338 __ai uint16x4_t vsqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
61340 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
61411 #define vsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
61413 uint64_t __s1 = __p1; \
61419 #define vsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
61421 uint64_t __s1 = __p1; \
61429 #define vsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
61431 int64_t __s1 = __p1; \
61437 #define vsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
61439 int64_t __s1 = __p1; \
61447 #define vsrid_n_u64(__p0, __p1, __p2) __extension__ ({ \
61449 uint64_t __s1 = __p1; \
61455 #define vsrid_n_u64(__p0, __p1, __p2) __extension__ ({ \
61457 uint64_t __s1 = __p1; \
61465 #define vsrid_n_s64(__p0, __p1, __p2) __extension__ ({ \
61467 int64_t __s1 = __p1; \
61473 #define vsrid_n_s64(__p0, __p1, __p2) __extension__ ({ \
61475 int64_t __s1 = __p1; \
61483 #define vsri_n_p64(__p0, __p1, __p2) __extension__ ({ \
61485 poly64x1_t __s1 = __p1; \
61491 #define vsri_n_p64(__p0, __p1, __p2) __extension__ ({ \
61493 poly64x1_t __s1 = __p1; \
61501 #define vsriq_n_p64(__p0, __p1, __p2) __extension__ ({ \
61503 poly64x2_t __s1 = __p1; \
61509 #define vsriq_n_p64(__p0, __p1, __p2) __extension__ ({ \
61511 poly64x2_t __s1 = __p1; \
61522 #define vst1_p64(__p0, __p1) __extension__ ({ \
61523 poly64x1_t __s1 = __p1; \
61527 #define vst1_p64(__p0, __p1) __extension__ ({ \
61528 poly64x1_t __s1 = __p1; \
61534 #define vst1q_p64(__p0, __p1) __extension__ ({ \
61535 poly64x2_t __s1 = __p1; \
61539 #define vst1q_p64(__p0, __p1) __extension__ ({ \
61540 poly64x2_t __s1 = __p1; \
61547 #define vst1q_f64(__p0, __p1) __extension__ ({ \
61548 float64x2_t __s1 = __p1; \
61552 #define vst1q_f64(__p0, __p1) __extension__ ({ \
61553 float64x2_t __s1 = __p1; \
61560 #define vst1_f64(__p0, __p1) __extension__ ({ \
61561 float64x1_t __s1 = __p1; \
61565 #define vst1_f64(__p0, __p1) __extension__ ({ \
61566 float64x1_t __s1 = __p1; \
61572 #define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
61573 poly64x1_t __s1 = __p1; \
61577 #define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
61578 poly64x1_t __s1 = __p1; \
61584 #define vst1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
61585 poly64x2_t __s1 = __p1; \
61589 #define vst1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
61590 poly64x2_t __s1 = __p1; \
61597 #define vst1q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
61598 float64x2_t __s1 = __p1; \
61602 #define vst1q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
61603 float64x2_t __s1 = __p1; \
61610 #define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
61611 float64x1_t __s1 = __p1; \
61615 #define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
61616 float64x1_t __s1 = __p1; \
61622 #define vst1_p8_x2(__p0, __p1) __extension__ ({ \
61623 poly8x8x2_t __s1 = __p1; \
61627 #define vst1_p8_x2(__p0, __p1) __extension__ ({ \
61628 poly8x8x2_t __s1 = __p1; \
61637 #define vst1_p64_x2(__p0, __p1) __extension__ ({ \
61638 poly64x1x2_t __s1 = __p1; \
61642 #define vst1_p64_x2(__p0, __p1) __extension__ ({ \
61643 poly64x1x2_t __s1 = __p1; \
61649 #define vst1_p16_x2(__p0, __p1) __extension__ ({ \
61650 poly16x4x2_t __s1 = __p1; \
61654 #define vst1_p16_x2(__p0, __p1) __extension__ ({ \
61655 poly16x4x2_t __s1 = __p1; \
61664 #define vst1q_p8_x2(__p0, __p1) __extension__ ({ \
61665 poly8x16x2_t __s1 = __p1; \
61669 #define vst1q_p8_x2(__p0, __p1) __extension__ ({ \
61670 poly8x16x2_t __s1 = __p1; \
61679 #define vst1q_p64_x2(__p0, __p1) __extension__ ({ \
61680 poly64x2x2_t __s1 = __p1; \
61684 #define vst1q_p64_x2(__p0, __p1) __extension__ ({ \
61685 poly64x2x2_t __s1 = __p1; \
61694 #define vst1q_p16_x2(__p0, __p1) __extension__ ({ \
61695 poly16x8x2_t __s1 = __p1; \
61699 #define vst1q_p16_x2(__p0, __p1) __extension__ ({ \
61700 poly16x8x2_t __s1 = __p1; \
61709 #define vst1q_u8_x2(__p0, __p1) __extension__ ({ \
61710 uint8x16x2_t __s1 = __p1; \
61714 #define vst1q_u8_x2(__p0, __p1) __extension__ ({ \
61715 uint8x16x2_t __s1 = __p1; \
61724 #define vst1q_u32_x2(__p0, __p1) __extension__ ({ \
61725 uint32x4x2_t __s1 = __p1; \
61729 #define vst1q_u32_x2(__p0, __p1) __extension__ ({ \
61730 uint32x4x2_t __s1 = __p1; \
61739 #define vst1q_u64_x2(__p0, __p1) __extension__ ({ \
61740 uint64x2x2_t __s1 = __p1; \
61744 #define vst1q_u64_x2(__p0, __p1) __extension__ ({ \
61745 uint64x2x2_t __s1 = __p1; \
61754 #define vst1q_u16_x2(__p0, __p1) __extension__ ({ \
61755 uint16x8x2_t __s1 = __p1; \
61759 #define vst1q_u16_x2(__p0, __p1) __extension__ ({ \
61760 uint16x8x2_t __s1 = __p1; \
61769 #define vst1q_s8_x2(__p0, __p1) __extension__ ({ \
61770 int8x16x2_t __s1 = __p1; \
61774 #define vst1q_s8_x2(__p0, __p1) __extension__ ({ \
61775 int8x16x2_t __s1 = __p1; \
61784 #define vst1q_f64_x2(__p0, __p1) __extension__ ({ \
61785 float64x2x2_t __s1 = __p1; \
61789 #define vst1q_f64_x2(__p0, __p1) __extension__ ({ \
61790 float64x2x2_t __s1 = __p1; \
61799 #define vst1q_f32_x2(__p0, __p1) __extension__ ({ \
61800 float32x4x2_t __s1 = __p1; \
61804 #define vst1q_f32_x2(__p0, __p1) __extension__ ({ \
61805 float32x4x2_t __s1 = __p1; \
61814 #define vst1q_f16_x2(__p0, __p1) __extension__ ({ \
61815 float16x8x2_t __s1 = __p1; \
61819 #define vst1q_f16_x2(__p0, __p1) __extension__ ({ \
61820 float16x8x2_t __s1 = __p1; \
61829 #define vst1q_s32_x2(__p0, __p1) __extension__ ({ \
61830 int32x4x2_t __s1 = __p1; \
61834 #define vst1q_s32_x2(__p0, __p1) __extension__ ({ \
61835 int32x4x2_t __s1 = __p1; \
61844 #define vst1q_s64_x2(__p0, __p1) __extension__ ({ \
61845 int64x2x2_t __s1 = __p1; \
61849 #define vst1q_s64_x2(__p0, __p1) __extension__ ({ \
61850 int64x2x2_t __s1 = __p1; \
61859 #define vst1q_s16_x2(__p0, __p1) __extension__ ({ \
61860 int16x8x2_t __s1 = __p1; \
61864 #define vst1q_s16_x2(__p0, __p1) __extension__ ({ \
61865 int16x8x2_t __s1 = __p1; \
61874 #define vst1_u8_x2(__p0, __p1) __extension__ ({ \
61875 uint8x8x2_t __s1 = __p1; \
61879 #define vst1_u8_x2(__p0, __p1) __extension__ ({ \
61880 uint8x8x2_t __s1 = __p1; \
61889 #define vst1_u32_x2(__p0, __p1) __extension__ ({ \
61890 uint32x2x2_t __s1 = __p1; \
61894 #define vst1_u32_x2(__p0, __p1) __extension__ ({ \
61895 uint32x2x2_t __s1 = __p1; \
61904 #define vst1_u64_x2(__p0, __p1) __extension__ ({ \
61905 uint64x1x2_t __s1 = __p1; \
61909 #define vst1_u64_x2(__p0, __p1) __extension__ ({ \
61910 uint64x1x2_t __s1 = __p1; \
61916 #define vst1_u16_x2(__p0, __p1) __extension__ ({ \
61917 uint16x4x2_t __s1 = __p1; \
61921 #define vst1_u16_x2(__p0, __p1) __extension__ ({ \
61922 uint16x4x2_t __s1 = __p1; \
61931 #define vst1_s8_x2(__p0, __p1) __extension__ ({ \
61932 int8x8x2_t __s1 = __p1; \
61936 #define vst1_s8_x2(__p0, __p1) __extension__ ({ \
61937 int8x8x2_t __s1 = __p1; \
61946 #define vst1_f64_x2(__p0, __p1) __extension__ ({ \
61947 float64x1x2_t __s1 = __p1; \
61951 #define vst1_f64_x2(__p0, __p1) __extension__ ({ \
61952 float64x1x2_t __s1 = __p1; \
61958 #define vst1_f32_x2(__p0, __p1) __extension__ ({ \
61959 float32x2x2_t __s1 = __p1; \
61963 #define vst1_f32_x2(__p0, __p1) __extension__ ({ \
61964 float32x2x2_t __s1 = __p1; \
61973 #define vst1_f16_x2(__p0, __p1) __extension__ ({ \
61974 float16x4x2_t __s1 = __p1; \
61978 #define vst1_f16_x2(__p0, __p1) __extension__ ({ \
61979 float16x4x2_t __s1 = __p1; \
61988 #define vst1_s32_x2(__p0, __p1) __extension__ ({ \
61989 int32x2x2_t __s1 = __p1; \
61993 #define vst1_s32_x2(__p0, __p1) __extension__ ({ \
61994 int32x2x2_t __s1 = __p1; \
62003 #define vst1_s64_x2(__p0, __p1) __extension__ ({ \
62004 int64x1x2_t __s1 = __p1; \
62008 #define vst1_s64_x2(__p0, __p1) __extension__ ({ \
62009 int64x1x2_t __s1 = __p1; \
62015 #define vst1_s16_x2(__p0, __p1) __extension__ ({ \
62016 int16x4x2_t __s1 = __p1; \
62020 #define vst1_s16_x2(__p0, __p1) __extension__ ({ \
62021 int16x4x2_t __s1 = __p1; \
62030 #define vst1_p8_x3(__p0, __p1) __extension__ ({ \
62031 poly8x8x3_t __s1 = __p1; \
62035 #define vst1_p8_x3(__p0, __p1) __extension__ ({ \
62036 poly8x8x3_t __s1 = __p1; \
62046 #define vst1_p64_x3(__p0, __p1) __extension__ ({ \
62047 poly64x1x3_t __s1 = __p1; \
62051 #define vst1_p64_x3(__p0, __p1) __extension__ ({ \
62052 poly64x1x3_t __s1 = __p1; \
62058 #define vst1_p16_x3(__p0, __p1) __extension__ ({ \
62059 poly16x4x3_t __s1 = __p1; \
62063 #define vst1_p16_x3(__p0, __p1) __extension__ ({ \
62064 poly16x4x3_t __s1 = __p1; \
62074 #define vst1q_p8_x3(__p0, __p1) __extension__ ({ \
62075 poly8x16x3_t __s1 = __p1; \
62079 #define vst1q_p8_x3(__p0, __p1) __extension__ ({ \
62080 poly8x16x3_t __s1 = __p1; \
62090 #define vst1q_p64_x3(__p0, __p1) __extension__ ({ \
62091 poly64x2x3_t __s1 = __p1; \
62095 #define vst1q_p64_x3(__p0, __p1) __extension__ ({ \
62096 poly64x2x3_t __s1 = __p1; \
62106 #define vst1q_p16_x3(__p0, __p1) __extension__ ({ \
62107 poly16x8x3_t __s1 = __p1; \
62111 #define vst1q_p16_x3(__p0, __p1) __extension__ ({ \
62112 poly16x8x3_t __s1 = __p1; \
62122 #define vst1q_u8_x3(__p0, __p1) __extension__ ({ \
62123 uint8x16x3_t __s1 = __p1; \
62127 #define vst1q_u8_x3(__p0, __p1) __extension__ ({ \
62128 uint8x16x3_t __s1 = __p1; \
62138 #define vst1q_u32_x3(__p0, __p1) __extension__ ({ \
62139 uint32x4x3_t __s1 = __p1; \
62143 #define vst1q_u32_x3(__p0, __p1) __extension__ ({ \
62144 uint32x4x3_t __s1 = __p1; \
62154 #define vst1q_u64_x3(__p0, __p1) __extension__ ({ \
62155 uint64x2x3_t __s1 = __p1; \
62159 #define vst1q_u64_x3(__p0, __p1) __extension__ ({ \
62160 uint64x2x3_t __s1 = __p1; \
62170 #define vst1q_u16_x3(__p0, __p1) __extension__ ({ \
62171 uint16x8x3_t __s1 = __p1; \
62175 #define vst1q_u16_x3(__p0, __p1) __extension__ ({ \
62176 uint16x8x3_t __s1 = __p1; \
62186 #define vst1q_s8_x3(__p0, __p1) __extension__ ({ \
62187 int8x16x3_t __s1 = __p1; \
62191 #define vst1q_s8_x3(__p0, __p1) __extension__ ({ \
62192 int8x16x3_t __s1 = __p1; \
62202 #define vst1q_f64_x3(__p0, __p1) __extension__ ({ \
62203 float64x2x3_t __s1 = __p1; \
62207 #define vst1q_f64_x3(__p0, __p1) __extension__ ({ \
62208 float64x2x3_t __s1 = __p1; \
62218 #define vst1q_f32_x3(__p0, __p1) __extension__ ({ \
62219 float32x4x3_t __s1 = __p1; \
62223 #define vst1q_f32_x3(__p0, __p1) __extension__ ({ \
62224 float32x4x3_t __s1 = __p1; \
62234 #define vst1q_f16_x3(__p0, __p1) __extension__ ({ \
62235 float16x8x3_t __s1 = __p1; \
62239 #define vst1q_f16_x3(__p0, __p1) __extension__ ({ \
62240 float16x8x3_t __s1 = __p1; \
62250 #define vst1q_s32_x3(__p0, __p1) __extension__ ({ \
62251 int32x4x3_t __s1 = __p1; \
62255 #define vst1q_s32_x3(__p0, __p1) __extension__ ({ \
62256 int32x4x3_t __s1 = __p1; \
62266 #define vst1q_s64_x3(__p0, __p1) __extension__ ({ \
62267 int64x2x3_t __s1 = __p1; \
62271 #define vst1q_s64_x3(__p0, __p1) __extension__ ({ \
62272 int64x2x3_t __s1 = __p1; \
62282 #define vst1q_s16_x3(__p0, __p1) __extension__ ({ \
62283 int16x8x3_t __s1 = __p1; \
62287 #define vst1q_s16_x3(__p0, __p1) __extension__ ({ \
62288 int16x8x3_t __s1 = __p1; \
62298 #define vst1_u8_x3(__p0, __p1) __extension__ ({ \
62299 uint8x8x3_t __s1 = __p1; \
62303 #define vst1_u8_x3(__p0, __p1) __extension__ ({ \
62304 uint8x8x3_t __s1 = __p1; \
62314 #define vst1_u32_x3(__p0, __p1) __extension__ ({ \
62315 uint32x2x3_t __s1 = __p1; \
62319 #define vst1_u32_x3(__p0, __p1) __extension__ ({ \
62320 uint32x2x3_t __s1 = __p1; \
62330 #define vst1_u64_x3(__p0, __p1) __extension__ ({ \
62331 uint64x1x3_t __s1 = __p1; \
62335 #define vst1_u64_x3(__p0, __p1) __extension__ ({ \
62336 uint64x1x3_t __s1 = __p1; \
62342 #define vst1_u16_x3(__p0, __p1) __extension__ ({ \
62343 uint16x4x3_t __s1 = __p1; \
62347 #define vst1_u16_x3(__p0, __p1) __extension__ ({ \
62348 uint16x4x3_t __s1 = __p1; \
62358 #define vst1_s8_x3(__p0, __p1) __extension__ ({ \
62359 int8x8x3_t __s1 = __p1; \
62363 #define vst1_s8_x3(__p0, __p1) __extension__ ({ \
62364 int8x8x3_t __s1 = __p1; \
62374 #define vst1_f64_x3(__p0, __p1) __extension__ ({ \
62375 float64x1x3_t __s1 = __p1; \
62379 #define vst1_f64_x3(__p0, __p1) __extension__ ({ \
62380 float64x1x3_t __s1 = __p1; \
62386 #define vst1_f32_x3(__p0, __p1) __extension__ ({ \
62387 float32x2x3_t __s1 = __p1; \
62391 #define vst1_f32_x3(__p0, __p1) __extension__ ({ \
62392 float32x2x3_t __s1 = __p1; \
62402 #define vst1_f16_x3(__p0, __p1) __extension__ ({ \
62403 float16x4x3_t __s1 = __p1; \
62407 #define vst1_f16_x3(__p0, __p1) __extension__ ({ \
62408 float16x4x3_t __s1 = __p1; \
62418 #define vst1_s32_x3(__p0, __p1) __extension__ ({ \
62419 int32x2x3_t __s1 = __p1; \
62423 #define vst1_s32_x3(__p0, __p1) __extension__ ({ \
62424 int32x2x3_t __s1 = __p1; \
62434 #define vst1_s64_x3(__p0, __p1) __extension__ ({ \
62435 int64x1x3_t __s1 = __p1; \
62439 #define vst1_s64_x3(__p0, __p1) __extension__ ({ \
62440 int64x1x3_t __s1 = __p1; \
62446 #define vst1_s16_x3(__p0, __p1) __extension__ ({ \
62447 int16x4x3_t __s1 = __p1; \
62451 #define vst1_s16_x3(__p0, __p1) __extension__ ({ \
62452 int16x4x3_t __s1 = __p1; \
62462 #define vst1_p8_x4(__p0, __p1) __extension__ ({ \
62463 poly8x8x4_t __s1 = __p1; \
62467 #define vst1_p8_x4(__p0, __p1) __extension__ ({ \
62468 poly8x8x4_t __s1 = __p1; \
62479 #define vst1_p64_x4(__p0, __p1) __extension__ ({ \
62480 poly64x1x4_t __s1 = __p1; \
62484 #define vst1_p64_x4(__p0, __p1) __extension__ ({ \
62485 poly64x1x4_t __s1 = __p1; \
62491 #define vst1_p16_x4(__p0, __p1) __extension__ ({ \
62492 poly16x4x4_t __s1 = __p1; \
62496 #define vst1_p16_x4(__p0, __p1) __extension__ ({ \
62497 poly16x4x4_t __s1 = __p1; \
62508 #define vst1q_p8_x4(__p0, __p1) __extension__ ({ \
62509 poly8x16x4_t __s1 = __p1; \
62513 #define vst1q_p8_x4(__p0, __p1) __extension__ ({ \
62514 poly8x16x4_t __s1 = __p1; \
62525 #define vst1q_p64_x4(__p0, __p1) __extension__ ({ \
62526 poly64x2x4_t __s1 = __p1; \
62530 #define vst1q_p64_x4(__p0, __p1) __extension__ ({ \
62531 poly64x2x4_t __s1 = __p1; \
62542 #define vst1q_p16_x4(__p0, __p1) __extension__ ({ \
62543 poly16x8x4_t __s1 = __p1; \
62547 #define vst1q_p16_x4(__p0, __p1) __extension__ ({ \
62548 poly16x8x4_t __s1 = __p1; \
62559 #define vst1q_u8_x4(__p0, __p1) __extension__ ({ \
62560 uint8x16x4_t __s1 = __p1; \
62564 #define vst1q_u8_x4(__p0, __p1) __extension__ ({ \
62565 uint8x16x4_t __s1 = __p1; \
62576 #define vst1q_u32_x4(__p0, __p1) __extension__ ({ \
62577 uint32x4x4_t __s1 = __p1; \
62581 #define vst1q_u32_x4(__p0, __p1) __extension__ ({ \
62582 uint32x4x4_t __s1 = __p1; \
62593 #define vst1q_u64_x4(__p0, __p1) __extension__ ({ \
62594 uint64x2x4_t __s1 = __p1; \
62598 #define vst1q_u64_x4(__p0, __p1) __extension__ ({ \
62599 uint64x2x4_t __s1 = __p1; \
62610 #define vst1q_u16_x4(__p0, __p1) __extension__ ({ \
62611 uint16x8x4_t __s1 = __p1; \
62615 #define vst1q_u16_x4(__p0, __p1) __extension__ ({ \
62616 uint16x8x4_t __s1 = __p1; \
62627 #define vst1q_s8_x4(__p0, __p1) __extension__ ({ \
62628 int8x16x4_t __s1 = __p1; \
62632 #define vst1q_s8_x4(__p0, __p1) __extension__ ({ \
62633 int8x16x4_t __s1 = __p1; \
62644 #define vst1q_f64_x4(__p0, __p1) __extension__ ({ \
62645 float64x2x4_t __s1 = __p1; \
62649 #define vst1q_f64_x4(__p0, __p1) __extension__ ({ \
62650 float64x2x4_t __s1 = __p1; \
62661 #define vst1q_f32_x4(__p0, __p1) __extension__ ({ \
62662 float32x4x4_t __s1 = __p1; \
62666 #define vst1q_f32_x4(__p0, __p1) __extension__ ({ \
62667 float32x4x4_t __s1 = __p1; \
62678 #define vst1q_f16_x4(__p0, __p1) __extension__ ({ \
62679 float16x8x4_t __s1 = __p1; \
62683 #define vst1q_f16_x4(__p0, __p1) __extension__ ({ \
62684 float16x8x4_t __s1 = __p1; \
62695 #define vst1q_s32_x4(__p0, __p1) __extension__ ({ \
62696 int32x4x4_t __s1 = __p1; \
62700 #define vst1q_s32_x4(__p0, __p1) __extension__ ({ \
62701 int32x4x4_t __s1 = __p1; \
62712 #define vst1q_s64_x4(__p0, __p1) __extension__ ({ \
62713 int64x2x4_t __s1 = __p1; \
62717 #define vst1q_s64_x4(__p0, __p1) __extension__ ({ \
62718 int64x2x4_t __s1 = __p1; \
62729 #define vst1q_s16_x4(__p0, __p1) __extension__ ({ \
62730 int16x8x4_t __s1 = __p1; \
62734 #define vst1q_s16_x4(__p0, __p1) __extension__ ({ \
62735 int16x8x4_t __s1 = __p1; \
62746 #define vst1_u8_x4(__p0, __p1) __extension__ ({ \
62747 uint8x8x4_t __s1 = __p1; \
62751 #define vst1_u8_x4(__p0, __p1) __extension__ ({ \
62752 uint8x8x4_t __s1 = __p1; \
62763 #define vst1_u32_x4(__p0, __p1) __extension__ ({ \
62764 uint32x2x4_t __s1 = __p1; \
62768 #define vst1_u32_x4(__p0, __p1) __extension__ ({ \
62769 uint32x2x4_t __s1 = __p1; \
62780 #define vst1_u64_x4(__p0, __p1) __extension__ ({ \
62781 uint64x1x4_t __s1 = __p1; \
62785 #define vst1_u64_x4(__p0, __p1) __extension__ ({ \
62786 uint64x1x4_t __s1 = __p1; \
62792 #define vst1_u16_x4(__p0, __p1) __extension__ ({ \
62793 uint16x4x4_t __s1 = __p1; \
62797 #define vst1_u16_x4(__p0, __p1) __extension__ ({ \
62798 uint16x4x4_t __s1 = __p1; \
62809 #define vst1_s8_x4(__p0, __p1) __extension__ ({ \
62810 int8x8x4_t __s1 = __p1; \
62814 #define vst1_s8_x4(__p0, __p1) __extension__ ({ \
62815 int8x8x4_t __s1 = __p1; \
62826 #define vst1_f64_x4(__p0, __p1) __extension__ ({ \
62827 float64x1x4_t __s1 = __p1; \
62831 #define vst1_f64_x4(__p0, __p1) __extension__ ({ \
62832 float64x1x4_t __s1 = __p1; \
62838 #define vst1_f32_x4(__p0, __p1) __extension__ ({ \
62839 float32x2x4_t __s1 = __p1; \
62843 #define vst1_f32_x4(__p0, __p1) __extension__ ({ \
62844 float32x2x4_t __s1 = __p1; \
62855 #define vst1_f16_x4(__p0, __p1) __extension__ ({ \
62856 float16x4x4_t __s1 = __p1; \
62860 #define vst1_f16_x4(__p0, __p1) __extension__ ({ \
62861 float16x4x4_t __s1 = __p1; \
62872 #define vst1_s32_x4(__p0, __p1) __extension__ ({ \
62873 int32x2x4_t __s1 = __p1; \
62877 #define vst1_s32_x4(__p0, __p1) __extension__ ({ \
62878 int32x2x4_t __s1 = __p1; \
62889 #define vst1_s64_x4(__p0, __p1) __extension__ ({ \
62890 int64x1x4_t __s1 = __p1; \
62894 #define vst1_s64_x4(__p0, __p1) __extension__ ({ \
62895 int64x1x4_t __s1 = __p1; \
62901 #define vst1_s16_x4(__p0, __p1) __extension__ ({ \
62902 int16x4x4_t __s1 = __p1; \
62906 #define vst1_s16_x4(__p0, __p1) __extension__ ({ \
62907 int16x4x4_t __s1 = __p1; \
62918 #define vst2_p64(__p0, __p1) __extension__ ({ \
62919 poly64x1x2_t __s1 = __p1; \
62923 #define vst2_p64(__p0, __p1) __extension__ ({ \
62924 poly64x1x2_t __s1 = __p1; \
62930 #define vst2q_p64(__p0, __p1) __extension__ ({ \
62931 poly64x2x2_t __s1 = __p1; \
62935 #define vst2q_p64(__p0, __p1) __extension__ ({ \
62936 poly64x2x2_t __s1 = __p1; \
62945 #define vst2q_u64(__p0, __p1) __extension__ ({ \
62946 uint64x2x2_t __s1 = __p1; \
62950 #define vst2q_u64(__p0, __p1) __extension__ ({ \
62951 uint64x2x2_t __s1 = __p1; \
62960 #define vst2q_f64(__p0, __p1) __extension__ ({ \
62961 float64x2x2_t __s1 = __p1; \
62965 #define vst2q_f64(__p0, __p1) __extension__ ({ \
62966 float64x2x2_t __s1 = __p1; \
62975 #define vst2q_s64(__p0, __p1) __extension__ ({ \
62976 int64x2x2_t __s1 = __p1; \
62980 #define vst2q_s64(__p0, __p1) __extension__ ({ \
62981 int64x2x2_t __s1 = __p1; \
62990 #define vst2_f64(__p0, __p1) __extension__ ({ \
62991 float64x1x2_t __s1 = __p1; \
62995 #define vst2_f64(__p0, __p1) __extension__ ({ \
62996 float64x1x2_t __s1 = __p1; \
63002 #define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63003 poly64x1x2_t __s1 = __p1; \
63007 #define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63008 poly64x1x2_t __s1 = __p1; \
63014 #define vst2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63015 poly8x16x2_t __s1 = __p1; \
63019 #define vst2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63020 poly8x16x2_t __s1 = __p1; \
63029 #define vst2q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63030 poly64x2x2_t __s1 = __p1; \
63034 #define vst2q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63035 poly64x2x2_t __s1 = __p1; \
63044 #define vst2q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63045 uint8x16x2_t __s1 = __p1; \
63049 #define vst2q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63050 uint8x16x2_t __s1 = __p1; \
63059 #define vst2q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63060 uint64x2x2_t __s1 = __p1; \
63064 #define vst2q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63065 uint64x2x2_t __s1 = __p1; \
63074 #define vst2q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63075 int8x16x2_t __s1 = __p1; \
63079 #define vst2q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63080 int8x16x2_t __s1 = __p1; \
63089 #define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63090 float64x2x2_t __s1 = __p1; \
63094 #define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63095 float64x2x2_t __s1 = __p1; \
63104 #define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63105 int64x2x2_t __s1 = __p1; \
63109 #define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63110 int64x2x2_t __s1 = __p1; \
63119 #define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63120 uint64x1x2_t __s1 = __p1; \
63124 #define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63125 uint64x1x2_t __s1 = __p1; \
63131 #define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63132 float64x1x2_t __s1 = __p1; \
63136 #define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63137 float64x1x2_t __s1 = __p1; \
63143 #define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63144 int64x1x2_t __s1 = __p1; \
63148 #define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63149 int64x1x2_t __s1 = __p1; \
63155 #define vst3_p64(__p0, __p1) __extension__ ({ \
63156 poly64x1x3_t __s1 = __p1; \
63160 #define vst3_p64(__p0, __p1) __extension__ ({ \
63161 poly64x1x3_t __s1 = __p1; \
63167 #define vst3q_p64(__p0, __p1) __extension__ ({ \
63168 poly64x2x3_t __s1 = __p1; \
63172 #define vst3q_p64(__p0, __p1) __extension__ ({ \
63173 poly64x2x3_t __s1 = __p1; \
63183 #define vst3q_u64(__p0, __p1) __extension__ ({ \
63184 uint64x2x3_t __s1 = __p1; \
63188 #define vst3q_u64(__p0, __p1) __extension__ ({ \
63189 uint64x2x3_t __s1 = __p1; \
63199 #define vst3q_f64(__p0, __p1) __extension__ ({ \
63200 float64x2x3_t __s1 = __p1; \
63204 #define vst3q_f64(__p0, __p1) __extension__ ({ \
63205 float64x2x3_t __s1 = __p1; \
63215 #define vst3q_s64(__p0, __p1) __extension__ ({ \
63216 int64x2x3_t __s1 = __p1; \
63220 #define vst3q_s64(__p0, __p1) __extension__ ({ \
63221 int64x2x3_t __s1 = __p1; \
63231 #define vst3_f64(__p0, __p1) __extension__ ({ \
63232 float64x1x3_t __s1 = __p1; \
63236 #define vst3_f64(__p0, __p1) __extension__ ({ \
63237 float64x1x3_t __s1 = __p1; \
63243 #define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63244 poly64x1x3_t __s1 = __p1; \
63248 #define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63249 poly64x1x3_t __s1 = __p1; \
63255 #define vst3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63256 poly8x16x3_t __s1 = __p1; \
63260 #define vst3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63261 poly8x16x3_t __s1 = __p1; \
63271 #define vst3q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63272 poly64x2x3_t __s1 = __p1; \
63276 #define vst3q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63277 poly64x2x3_t __s1 = __p1; \
63287 #define vst3q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63288 uint8x16x3_t __s1 = __p1; \
63292 #define vst3q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63293 uint8x16x3_t __s1 = __p1; \
63303 #define vst3q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63304 uint64x2x3_t __s1 = __p1; \
63308 #define vst3q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63309 uint64x2x3_t __s1 = __p1; \
63319 #define vst3q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63320 int8x16x3_t __s1 = __p1; \
63324 #define vst3q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63325 int8x16x3_t __s1 = __p1; \
63335 #define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63336 float64x2x3_t __s1 = __p1; \
63340 #define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63341 float64x2x3_t __s1 = __p1; \
63351 #define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63352 int64x2x3_t __s1 = __p1; \
63356 #define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63357 int64x2x3_t __s1 = __p1; \
63367 #define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63368 uint64x1x3_t __s1 = __p1; \
63372 #define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63373 uint64x1x3_t __s1 = __p1; \
63379 #define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63380 float64x1x3_t __s1 = __p1; \
63384 #define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63385 float64x1x3_t __s1 = __p1; \
63391 #define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63392 int64x1x3_t __s1 = __p1; \
63396 #define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63397 int64x1x3_t __s1 = __p1; \
63403 #define vst4_p64(__p0, __p1) __extension__ ({ \
63404 poly64x1x4_t __s1 = __p1; \
63408 #define vst4_p64(__p0, __p1) __extension__ ({ \
63409 poly64x1x4_t __s1 = __p1; \
63415 #define vst4q_p64(__p0, __p1) __extension__ ({ \
63416 poly64x2x4_t __s1 = __p1; \
63420 #define vst4q_p64(__p0, __p1) __extension__ ({ \
63421 poly64x2x4_t __s1 = __p1; \
63432 #define vst4q_u64(__p0, __p1) __extension__ ({ \
63433 uint64x2x4_t __s1 = __p1; \
63437 #define vst4q_u64(__p0, __p1) __extension__ ({ \
63438 uint64x2x4_t __s1 = __p1; \
63449 #define vst4q_f64(__p0, __p1) __extension__ ({ \
63450 float64x2x4_t __s1 = __p1; \
63454 #define vst4q_f64(__p0, __p1) __extension__ ({ \
63455 float64x2x4_t __s1 = __p1; \
63466 #define vst4q_s64(__p0, __p1) __extension__ ({ \
63467 int64x2x4_t __s1 = __p1; \
63471 #define vst4q_s64(__p0, __p1) __extension__ ({ \
63472 int64x2x4_t __s1 = __p1; \
63483 #define vst4_f64(__p0, __p1) __extension__ ({ \
63484 float64x1x4_t __s1 = __p1; \
63488 #define vst4_f64(__p0, __p1) __extension__ ({ \
63489 float64x1x4_t __s1 = __p1; \
63495 #define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63496 poly64x1x4_t __s1 = __p1; \
63500 #define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63501 poly64x1x4_t __s1 = __p1; \
63507 #define vst4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63508 poly8x16x4_t __s1 = __p1; \
63512 #define vst4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
63513 poly8x16x4_t __s1 = __p1; \
63524 #define vst4q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63525 poly64x2x4_t __s1 = __p1; \
63529 #define vst4q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
63530 poly64x2x4_t __s1 = __p1; \
63541 #define vst4q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63542 uint8x16x4_t __s1 = __p1; \
63546 #define vst4q_lane_u8(__p0, __p1, __p2) __extension__ ({ \
63547 uint8x16x4_t __s1 = __p1; \
63558 #define vst4q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63559 uint64x2x4_t __s1 = __p1; \
63563 #define vst4q_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63564 uint64x2x4_t __s1 = __p1; \
63575 #define vst4q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63576 int8x16x4_t __s1 = __p1; \
63580 #define vst4q_lane_s8(__p0, __p1, __p2) __extension__ ({ \
63581 int8x16x4_t __s1 = __p1; \
63592 #define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63593 float64x2x4_t __s1 = __p1; \
63597 #define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63598 float64x2x4_t __s1 = __p1; \
63609 #define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63610 int64x2x4_t __s1 = __p1; \
63614 #define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63615 int64x2x4_t __s1 = __p1; \
63626 #define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63627 uint64x1x4_t __s1 = __p1; \
63631 #define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
63632 uint64x1x4_t __s1 = __p1; \
63638 #define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63639 float64x1x4_t __s1 = __p1; \
63643 #define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
63644 float64x1x4_t __s1 = __p1; \
63650 #define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63651 int64x1x4_t __s1 = __p1; \
63655 #define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
63656 int64x1x4_t __s1 = __p1; \
63662 #define vstrq_p128(__p0, __p1) __extension__ ({ \
63663 poly128_t __s1 = __p1; \
63667 #define vstrq_p128(__p0, __p1) __extension__ ({ \
63668 poly128_t __s1 = __p1; \
63674 __ai uint64_t vsubd_u64(uint64_t __p0, uint64_t __p1) {
63676 __ret = (uint64_t) __builtin_neon_vsubd_u64(__p0, __p1);
63680 __ai uint64_t vsubd_u64(uint64_t __p0, uint64_t __p1) {
63682 __ret = (uint64_t) __builtin_neon_vsubd_u64(__p0, __p1);
63688 __ai int64_t vsubd_s64(int64_t __p0, int64_t __p1) {
63690 __ret = (int64_t) __builtin_neon_vsubd_s64(__p0, __p1);
63694 __ai int64_t vsubd_s64(int64_t __p0, int64_t __p1) {
63696 __ret = (int64_t) __builtin_neon_vsubd_s64(__p0, __p1);
63702 __ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {
63704 __ret = __p0 - __p1;
63708 __ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {
63710 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
63719 __ai float64x1_t vsub_f64(float64x1_t __p0, float64x1_t __p1) {
63721 __ret = __p0 - __p1;
63725 __ai float64x1_t vsub_f64(float64x1_t __p0, float64x1_t __p1) {
63727 __ret = __p0 - __p1;
63733 __ai uint16x8_t vsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
63735 __ret = vcombine_u16(__p0, vsubhn_u32(__p1, __p2));
63739 __ai uint16x8_t vsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
63741 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
63751 __ai uint32x4_t vsubhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
63753 __ret = vcombine_u32(__p0, vsubhn_u64(__p1, __p2));
63757 __ai uint32x4_t vsubhn_high_u64(uint32x2_t __p0, uint64x2_t __p1, uint64x2_t __p2) {
63759 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
63769 __ai uint8x16_t vsubhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
63771 __ret = vcombine_u8(__p0, vsubhn_u16(__p1, __p2));
63775 __ai uint8x16_t vsubhn_high_u16(uint8x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
63777 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
63787 __ai int16x8_t vsubhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
63789 __ret = vcombine_s16(__p0, vsubhn_s32(__p1, __p2));
63793 __ai int16x8_t vsubhn_high_s32(int16x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
63795 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
63805 __ai int32x4_t vsubhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
63807 __ret = vcombine_s32(__p0, vsubhn_s64(__p1, __p2));
63811 __ai int32x4_t vsubhn_high_s64(int32x2_t __p0, int64x2_t __p1, int64x2_t __p2) {
63813 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
63823 __ai int8x16_t vsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
63825 __ret = vcombine_s8(__p0, vsubhn_s16(__p1, __p2));
63829 __ai int8x16_t vsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
63831 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
63841 __ai uint16x8_t vsubl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
63843 __ret = vmovl_high_u8(__p0) - vmovl_high_u8(__p1);
63847 __ai uint16x8_t vsubl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
63849 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
63858 __ai uint64x2_t vsubl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
63860 __ret = vmovl_high_u32(__p0) - vmovl_high_u32(__p1);
63864 __ai uint64x2_t vsubl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
63866 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
63875 __ai uint32x4_t vsubl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
63877 __ret = vmovl_high_u16(__p0) - vmovl_high_u16(__p1);
63881 __ai uint32x4_t vsubl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
63883 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
63892 __ai int16x8_t vsubl_high_s8(int8x16_t __p0, int8x16_t __p1) {
63894 __ret = vmovl_high_s8(__p0) - vmovl_high_s8(__p1);
63898 __ai int16x8_t vsubl_high_s8(int8x16_t __p0, int8x16_t __p1) {
63900 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
63909 __ai int64x2_t vsubl_high_s32(int32x4_t __p0, int32x4_t __p1) {
63911 __ret = vmovl_high_s32(__p0) - vmovl_high_s32(__p1);
63915 __ai int64x2_t vsubl_high_s32(int32x4_t __p0, int32x4_t __p1) {
63917 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
63926 __ai int32x4_t vsubl_high_s16(int16x8_t __p0, int16x8_t __p1) {
63928 __ret = vmovl_high_s16(__p0) - vmovl_high_s16(__p1);
63932 __ai int32x4_t vsubl_high_s16(int16x8_t __p0, int16x8_t __p1) {
63934 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
63943 __ai uint16x8_t vsubw_high_u8(uint16x8_t __p0, uint8x16_t __p1) {
63945 __ret = __p0 - vmovl_high_u8(__p1);
63949 __ai uint16x8_t vsubw_high_u8(uint16x8_t __p0, uint8x16_t __p1) {
63951 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
63960 __ai uint64x2_t vsubw_high_u32(uint64x2_t __p0, uint32x4_t __p1) {
63962 __ret = __p0 - vmovl_high_u32(__p1);
63966 __ai uint64x2_t vsubw_high_u32(uint64x2_t __p0, uint32x4_t __p1) {
63968 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
63977 __ai uint32x4_t vsubw_high_u16(uint32x4_t __p0, uint16x8_t __p1) {
63979 __ret = __p0 - vmovl_high_u16(__p1);
63983 __ai uint32x4_t vsubw_high_u16(uint32x4_t __p0, uint16x8_t __p1) {
63985 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
63994 __ai int16x8_t vsubw_high_s8(int16x8_t __p0, int8x16_t __p1) {
63996 __ret = __p0 - vmovl_high_s8(__p1);
64000 __ai int16x8_t vsubw_high_s8(int16x8_t __p0, int8x16_t __p1) {
64002 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64011 __ai int64x2_t vsubw_high_s32(int64x2_t __p0, int32x4_t __p1) {
64013 __ret = __p0 - vmovl_high_s32(__p1);
64017 __ai int64x2_t vsubw_high_s32(int64x2_t __p0, int32x4_t __p1) {
64019 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64028 __ai int32x4_t vsubw_high_s16(int32x4_t __p0, int16x8_t __p1) {
64030 __ret = __p0 - vmovl_high_s16(__p1);
64034 __ai int32x4_t vsubw_high_s16(int32x4_t __p0, int16x8_t __p1) {
64036 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64045 __ai poly8x8_t vtrn1_p8(poly8x8_t __p0, poly8x8_t __p1) {
64047 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64051 __ai poly8x8_t vtrn1_p8(poly8x8_t __p0, poly8x8_t __p1) {
64053 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64062 __ai poly16x4_t vtrn1_p16(poly16x4_t __p0, poly16x4_t __p1) {
64064 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64068 __ai poly16x4_t vtrn1_p16(poly16x4_t __p0, poly16x4_t __p1) {
64070 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64079 __ai poly8x16_t vtrn1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
64081 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30);
64085 __ai poly8x16_t vtrn1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
64087 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64096 __ai poly64x2_t vtrn1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
64098 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64102 __ai poly64x2_t vtrn1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
64104 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64113 __ai poly16x8_t vtrn1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
64115 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64119 __ai poly16x8_t vtrn1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
64121 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64130 __ai uint8x16_t vtrn1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
64132 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30);
64136 __ai uint8x16_t vtrn1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
64138 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64147 __ai uint32x4_t vtrn1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
64149 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64153 __ai uint32x4_t vtrn1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
64155 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64164 __ai uint64x2_t vtrn1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
64166 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64170 __ai uint64x2_t vtrn1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
64172 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64181 __ai uint16x8_t vtrn1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
64183 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64187 __ai uint16x8_t vtrn1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
64189 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64198 __ai int8x16_t vtrn1q_s8(int8x16_t __p0, int8x16_t __p1) {
64200 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30);
64204 __ai int8x16_t vtrn1q_s8(int8x16_t __p0, int8x16_t __p1) {
64206 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64215 __ai float64x2_t vtrn1q_f64(float64x2_t __p0, float64x2_t __p1) {
64217 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64221 __ai float64x2_t vtrn1q_f64(float64x2_t __p0, float64x2_t __p1) {
64223 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64232 __ai float32x4_t vtrn1q_f32(float32x4_t __p0, float32x4_t __p1) {
64234 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64238 __ai float32x4_t vtrn1q_f32(float32x4_t __p0, float32x4_t __p1) {
64240 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64249 __ai int32x4_t vtrn1q_s32(int32x4_t __p0, int32x4_t __p1) {
64251 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64255 __ai int32x4_t vtrn1q_s32(int32x4_t __p0, int32x4_t __p1) {
64257 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64266 __ai int64x2_t vtrn1q_s64(int64x2_t __p0, int64x2_t __p1) {
64268 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64272 __ai int64x2_t vtrn1q_s64(int64x2_t __p0, int64x2_t __p1) {
64274 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64283 __ai int16x8_t vtrn1q_s16(int16x8_t __p0, int16x8_t __p1) {
64285 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64289 __ai int16x8_t vtrn1q_s16(int16x8_t __p0, int16x8_t __p1) {
64291 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64300 __ai uint8x8_t vtrn1_u8(uint8x8_t __p0, uint8x8_t __p1) {
64302 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64306 __ai uint8x8_t vtrn1_u8(uint8x8_t __p0, uint8x8_t __p1) {
64308 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64317 __ai uint32x2_t vtrn1_u32(uint32x2_t __p0, uint32x2_t __p1) {
64319 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64323 __ai uint32x2_t vtrn1_u32(uint32x2_t __p0, uint32x2_t __p1) {
64325 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64334 __ai uint16x4_t vtrn1_u16(uint16x4_t __p0, uint16x4_t __p1) {
64336 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64340 __ai uint16x4_t vtrn1_u16(uint16x4_t __p0, uint16x4_t __p1) {
64342 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64351 __ai int8x8_t vtrn1_s8(int8x8_t __p0, int8x8_t __p1) {
64353 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 2, 10, 4, 12, 6, 14);
64357 __ai int8x8_t vtrn1_s8(int8x8_t __p0, int8x8_t __p1) {
64359 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64368 __ai float32x2_t vtrn1_f32(float32x2_t __p0, float32x2_t __p1) {
64370 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64374 __ai float32x2_t vtrn1_f32(float32x2_t __p0, float32x2_t __p1) {
64376 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64385 __ai int32x2_t vtrn1_s32(int32x2_t __p0, int32x2_t __p1) {
64387 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
64391 __ai int32x2_t vtrn1_s32(int32x2_t __p0, int32x2_t __p1) {
64393 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64402 __ai int16x4_t vtrn1_s16(int16x4_t __p0, int16x4_t __p1) {
64404 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 2, 6);
64408 __ai int16x4_t vtrn1_s16(int16x4_t __p0, int16x4_t __p1) {
64410 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64419 __ai poly8x8_t vtrn2_p8(poly8x8_t __p0, poly8x8_t __p1) {
64421 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64425 __ai poly8x8_t vtrn2_p8(poly8x8_t __p0, poly8x8_t __p1) {
64427 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64436 __ai poly16x4_t vtrn2_p16(poly16x4_t __p0, poly16x4_t __p1) {
64438 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64442 __ai poly16x4_t vtrn2_p16(poly16x4_t __p0, poly16x4_t __p1) {
64444 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64453 __ai poly8x16_t vtrn2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
64455 __ret = __builtin_shufflevector(__p0, __p1, 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31);
64459 __ai poly8x16_t vtrn2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
64461 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64470 __ai poly64x2_t vtrn2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
64472 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64476 __ai poly64x2_t vtrn2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
64478 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64487 __ai poly16x8_t vtrn2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
64489 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64493 __ai poly16x8_t vtrn2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
64495 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64504 __ai uint8x16_t vtrn2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
64506 __ret = __builtin_shufflevector(__p0, __p1, 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31);
64510 __ai uint8x16_t vtrn2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
64512 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64521 __ai uint32x4_t vtrn2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
64523 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64527 __ai uint32x4_t vtrn2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
64529 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64538 __ai uint64x2_t vtrn2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
64540 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64544 __ai uint64x2_t vtrn2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
64546 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64555 __ai uint16x8_t vtrn2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
64557 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64561 __ai uint16x8_t vtrn2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
64563 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64572 __ai int8x16_t vtrn2q_s8(int8x16_t __p0, int8x16_t __p1) {
64574 __ret = __builtin_shufflevector(__p0, __p1, 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31);
64578 __ai int8x16_t vtrn2q_s8(int8x16_t __p0, int8x16_t __p1) {
64580 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64589 __ai float64x2_t vtrn2q_f64(float64x2_t __p0, float64x2_t __p1) {
64591 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64595 __ai float64x2_t vtrn2q_f64(float64x2_t __p0, float64x2_t __p1) {
64597 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64606 __ai float32x4_t vtrn2q_f32(float32x4_t __p0, float32x4_t __p1) {
64608 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64612 __ai float32x4_t vtrn2q_f32(float32x4_t __p0, float32x4_t __p1) {
64614 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64623 __ai int32x4_t vtrn2q_s32(int32x4_t __p0, int32x4_t __p1) {
64625 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64629 __ai int32x4_t vtrn2q_s32(int32x4_t __p0, int32x4_t __p1) {
64631 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64640 __ai int64x2_t vtrn2q_s64(int64x2_t __p0, int64x2_t __p1) {
64642 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64646 __ai int64x2_t vtrn2q_s64(int64x2_t __p0, int64x2_t __p1) {
64648 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64657 __ai int16x8_t vtrn2q_s16(int16x8_t __p0, int16x8_t __p1) {
64659 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64663 __ai int16x8_t vtrn2q_s16(int16x8_t __p0, int16x8_t __p1) {
64665 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64674 __ai uint8x8_t vtrn2_u8(uint8x8_t __p0, uint8x8_t __p1) {
64676 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64680 __ai uint8x8_t vtrn2_u8(uint8x8_t __p0, uint8x8_t __p1) {
64682 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64691 __ai uint32x2_t vtrn2_u32(uint32x2_t __p0, uint32x2_t __p1) {
64693 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64697 __ai uint32x2_t vtrn2_u32(uint32x2_t __p0, uint32x2_t __p1) {
64699 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64708 __ai uint16x4_t vtrn2_u16(uint16x4_t __p0, uint16x4_t __p1) {
64710 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64714 __ai uint16x4_t vtrn2_u16(uint16x4_t __p0, uint16x4_t __p1) {
64716 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64725 __ai int8x8_t vtrn2_s8(int8x8_t __p0, int8x8_t __p1) {
64727 __ret = __builtin_shufflevector(__p0, __p1, 1, 9, 3, 11, 5, 13, 7, 15);
64731 __ai int8x8_t vtrn2_s8(int8x8_t __p0, int8x8_t __p1) {
64733 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64742 __ai float32x2_t vtrn2_f32(float32x2_t __p0, float32x2_t __p1) {
64744 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64748 __ai float32x2_t vtrn2_f32(float32x2_t __p0, float32x2_t __p1) {
64750 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64759 __ai int32x2_t vtrn2_s32(int32x2_t __p0, int32x2_t __p1) {
64761 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
64765 __ai int32x2_t vtrn2_s32(int32x2_t __p0, int32x2_t __p1) {
64767 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64776 __ai int16x4_t vtrn2_s16(int16x4_t __p0, int16x4_t __p1) {
64778 __ret = __builtin_shufflevector(__p0, __p1, 1, 5, 3, 7);
64782 __ai int16x4_t vtrn2_s16(int16x4_t __p0, int16x4_t __p1) {
64784 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
64793 __ai uint64x1_t vtst_p64(poly64x1_t __p0, poly64x1_t __p1) {
64795 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64799 __ai uint64x1_t vtst_p64(poly64x1_t __p0, poly64x1_t __p1) {
64801 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64807 __ai uint64x2_t vtstq_p64(poly64x2_t __p0, poly64x2_t __p1) {
64809 __ret = (uint64x2_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
64813 __ai uint64x2_t vtstq_p64(poly64x2_t __p0, poly64x2_t __p1) {
64815 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64824 __ai uint64x2_t vtstq_u64(uint64x2_t __p0, uint64x2_t __p1) {
64826 __ret = (uint64x2_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
64830 __ai uint64x2_t vtstq_u64(uint64x2_t __p0, uint64x2_t __p1) {
64832 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64841 __ai uint64x2_t vtstq_s64(int64x2_t __p0, int64x2_t __p1) {
64843 __ret = (uint64x2_t) __builtin_neon_vtstq_v((int8x16_t)__p0, (int8x16_t)__p1, 51);
64847 __ai uint64x2_t vtstq_s64(int64x2_t __p0, int64x2_t __p1) {
64849 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
64858 __ai uint64x1_t vtst_u64(uint64x1_t __p0, uint64x1_t __p1) {
64860 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64864 __ai uint64x1_t vtst_u64(uint64x1_t __p0, uint64x1_t __p1) {
64866 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64872 __ai uint64x1_t vtst_s64(int64x1_t __p0, int64x1_t __p1) {
64874 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64878 __ai uint64x1_t vtst_s64(int64x1_t __p0, int64x1_t __p1) {
64880 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64886 __ai uint64_t vtstd_u64(uint64_t __p0, uint64_t __p1) {
64888 __ret = (uint64_t) __builtin_neon_vtstd_u64(__p0, __p1);
64892 __ai uint64_t vtstd_u64(uint64_t __p0, uint64_t __p1) {
64894 __ret = (uint64_t) __builtin_neon_vtstd_u64(__p0, __p1);
64900 __ai int64_t vtstd_s64(int64_t __p0, int64_t __p1) {
64902 __ret = (int64_t) __builtin_neon_vtstd_s64(__p0, __p1);
64906 __ai int64_t vtstd_s64(int64_t __p0, int64_t __p1) {
64908 __ret = (int64_t) __builtin_neon_vtstd_s64(__p0, __p1);
64914 __ai int8_t vuqaddb_s8(int8_t __p0, int8_t __p1) {
64916 __ret = (int8_t) __builtin_neon_vuqaddb_s8(__p0, __p1);
64920 __ai int8_t vuqaddb_s8(int8_t __p0, int8_t __p1) {
64922 __ret = (int8_t) __builtin_neon_vuqaddb_s8(__p0, __p1);
64928 __ai int32_t vuqadds_s32(int32_t __p0, int32_t __p1) {
64930 __ret = (int32_t) __builtin_neon_vuqadds_s32(__p0, __p1);
64934 __ai int32_t vuqadds_s32(int32_t __p0, int32_t __p1) {
64936 __ret = (int32_t) __builtin_neon_vuqadds_s32(__p0, __p1);
64942 __ai int64_t vuqaddd_s64(int64_t __p0, int64_t __p1) {
64944 __ret = (int64_t) __builtin_neon_vuqaddd_s64(__p0, __p1);
64948 __ai int64_t vuqaddd_s64(int64_t __p0, int64_t __p1) {
64950 __ret = (int64_t) __builtin_neon_vuqaddd_s64(__p0, __p1);
64956 __ai int16_t vuqaddh_s16(int16_t __p0, int16_t __p1) {
64958 __ret = (int16_t) __builtin_neon_vuqaddh_s16(__p0, __p1);
64962 __ai int16_t vuqaddh_s16(int16_t __p0, int16_t __p1) {
64964 __ret = (int16_t) __builtin_neon_vuqaddh_s16(__p0, __p1);
64970 __ai int8x16_t vuqaddq_s8(int8x16_t __p0, int8x16_t __p1) {
64972 __ret = (int8x16_t) __builtin_neon_vuqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 32);
64976 __ai int8x16_t vuqaddq_s8(int8x16_t __p0, int8x16_t __p1) {
64978 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
64987 __ai int32x4_t vuqaddq_s32(int32x4_t __p0, int32x4_t __p1) {
64989 __ret = (int32x4_t) __builtin_neon_vuqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 34);
64993 __ai int32x4_t vuqaddq_s32(int32x4_t __p0, int32x4_t __p1) {
64995 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65004 __ai int64x2_t vuqaddq_s64(int64x2_t __p0, int64x2_t __p1) {
65006 __ret = (int64x2_t) __builtin_neon_vuqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 35);
65010 __ai int64x2_t vuqaddq_s64(int64x2_t __p0, int64x2_t __p1) {
65012 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65021 __ai int16x8_t vuqaddq_s16(int16x8_t __p0, int16x8_t __p1) {
65023 __ret = (int16x8_t) __builtin_neon_vuqaddq_v((int8x16_t)__p0, (int8x16_t)__p1, 33);
65027 __ai int16x8_t vuqaddq_s16(int16x8_t __p0, int16x8_t __p1) {
65029 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65038 __ai int8x8_t vuqadd_s8(int8x8_t __p0, int8x8_t __p1) {
65040 __ret = (int8x8_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
65044 __ai int8x8_t vuqadd_s8(int8x8_t __p0, int8x8_t __p1) {
65046 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65055 __ai int32x2_t vuqadd_s32(int32x2_t __p0, int32x2_t __p1) {
65057 __ret = (int32x2_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
65061 __ai int32x2_t vuqadd_s32(int32x2_t __p0, int32x2_t __p1) {
65063 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65072 __ai int64x1_t vuqadd_s64(int64x1_t __p0, int64x1_t __p1) {
65074 __ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
65078 __ai int64x1_t vuqadd_s64(int64x1_t __p0, int64x1_t __p1) {
65080 __ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
65086 __ai int16x4_t vuqadd_s16(int16x4_t __p0, int16x4_t __p1) {
65088 __ret = (int16x4_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
65092 __ai int16x4_t vuqadd_s16(int16x4_t __p0, int16x4_t __p1) {
65094 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65103 __ai poly8x8_t vuzp1_p8(poly8x8_t __p0, poly8x8_t __p1) {
65105 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65109 __ai poly8x8_t vuzp1_p8(poly8x8_t __p0, poly8x8_t __p1) {
65111 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65120 __ai poly16x4_t vuzp1_p16(poly16x4_t __p0, poly16x4_t __p1) {
65122 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65126 __ai poly16x4_t vuzp1_p16(poly16x4_t __p0, poly16x4_t __p1) {
65128 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65137 __ai poly8x16_t vuzp1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65139 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30);
65143 __ai poly8x16_t vuzp1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65145 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65154 __ai poly64x2_t vuzp1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65156 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65160 __ai poly64x2_t vuzp1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65162 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65171 __ai poly16x8_t vuzp1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65173 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65177 __ai poly16x8_t vuzp1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65179 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65188 __ai uint8x16_t vuzp1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65190 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30);
65194 __ai uint8x16_t vuzp1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65196 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65205 __ai uint32x4_t vuzp1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65207 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65211 __ai uint32x4_t vuzp1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65213 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65222 __ai uint64x2_t vuzp1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65224 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65228 __ai uint64x2_t vuzp1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65230 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65239 __ai uint16x8_t vuzp1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65241 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65245 __ai uint16x8_t vuzp1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65247 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65256 __ai int8x16_t vuzp1q_s8(int8x16_t __p0, int8x16_t __p1) {
65258 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30);
65262 __ai int8x16_t vuzp1q_s8(int8x16_t __p0, int8x16_t __p1) {
65264 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65273 __ai float64x2_t vuzp1q_f64(float64x2_t __p0, float64x2_t __p1) {
65275 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65279 __ai float64x2_t vuzp1q_f64(float64x2_t __p0, float64x2_t __p1) {
65281 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65290 __ai float32x4_t vuzp1q_f32(float32x4_t __p0, float32x4_t __p1) {
65292 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65296 __ai float32x4_t vuzp1q_f32(float32x4_t __p0, float32x4_t __p1) {
65298 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65307 __ai int32x4_t vuzp1q_s32(int32x4_t __p0, int32x4_t __p1) {
65309 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65313 __ai int32x4_t vuzp1q_s32(int32x4_t __p0, int32x4_t __p1) {
65315 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65324 __ai int64x2_t vuzp1q_s64(int64x2_t __p0, int64x2_t __p1) {
65326 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65330 __ai int64x2_t vuzp1q_s64(int64x2_t __p0, int64x2_t __p1) {
65332 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65341 __ai int16x8_t vuzp1q_s16(int16x8_t __p0, int16x8_t __p1) {
65343 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65347 __ai int16x8_t vuzp1q_s16(int16x8_t __p0, int16x8_t __p1) {
65349 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65358 __ai uint8x8_t vuzp1_u8(uint8x8_t __p0, uint8x8_t __p1) {
65360 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65364 __ai uint8x8_t vuzp1_u8(uint8x8_t __p0, uint8x8_t __p1) {
65366 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65375 __ai uint32x2_t vuzp1_u32(uint32x2_t __p0, uint32x2_t __p1) {
65377 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65381 __ai uint32x2_t vuzp1_u32(uint32x2_t __p0, uint32x2_t __p1) {
65383 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65392 __ai uint16x4_t vuzp1_u16(uint16x4_t __p0, uint16x4_t __p1) {
65394 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65398 __ai uint16x4_t vuzp1_u16(uint16x4_t __p0, uint16x4_t __p1) {
65400 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65409 __ai int8x8_t vuzp1_s8(int8x8_t __p0, int8x8_t __p1) {
65411 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6, 8, 10, 12, 14);
65415 __ai int8x8_t vuzp1_s8(int8x8_t __p0, int8x8_t __p1) {
65417 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65426 __ai float32x2_t vuzp1_f32(float32x2_t __p0, float32x2_t __p1) {
65428 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65432 __ai float32x2_t vuzp1_f32(float32x2_t __p0, float32x2_t __p1) {
65434 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65443 __ai int32x2_t vuzp1_s32(int32x2_t __p0, int32x2_t __p1) {
65445 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65449 __ai int32x2_t vuzp1_s32(int32x2_t __p0, int32x2_t __p1) {
65451 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65460 __ai int16x4_t vuzp1_s16(int16x4_t __p0, int16x4_t __p1) {
65462 __ret = __builtin_shufflevector(__p0, __p1, 0, 2, 4, 6);
65466 __ai int16x4_t vuzp1_s16(int16x4_t __p0, int16x4_t __p1) {
65468 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65477 __ai poly8x8_t vuzp2_p8(poly8x8_t __p0, poly8x8_t __p1) {
65479 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65483 __ai poly8x8_t vuzp2_p8(poly8x8_t __p0, poly8x8_t __p1) {
65485 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65494 __ai poly16x4_t vuzp2_p16(poly16x4_t __p0, poly16x4_t __p1) {
65496 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65500 __ai poly16x4_t vuzp2_p16(poly16x4_t __p0, poly16x4_t __p1) {
65502 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65511 __ai poly8x16_t vuzp2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65513 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31);
65517 __ai poly8x16_t vuzp2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65519 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65528 __ai poly64x2_t vuzp2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65530 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65534 __ai poly64x2_t vuzp2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65536 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65545 __ai poly16x8_t vuzp2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65547 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65551 __ai poly16x8_t vuzp2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65553 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65562 __ai uint8x16_t vuzp2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65564 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31);
65568 __ai uint8x16_t vuzp2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65570 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65579 __ai uint32x4_t vuzp2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65581 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65585 __ai uint32x4_t vuzp2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65587 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65596 __ai uint64x2_t vuzp2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65598 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65602 __ai uint64x2_t vuzp2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65604 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65613 __ai uint16x8_t vuzp2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65615 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65619 __ai uint16x8_t vuzp2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65621 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65630 __ai int8x16_t vuzp2q_s8(int8x16_t __p0, int8x16_t __p1) {
65632 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31);
65636 __ai int8x16_t vuzp2q_s8(int8x16_t __p0, int8x16_t __p1) {
65638 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65647 __ai float64x2_t vuzp2q_f64(float64x2_t __p0, float64x2_t __p1) {
65649 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65653 __ai float64x2_t vuzp2q_f64(float64x2_t __p0, float64x2_t __p1) {
65655 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65664 __ai float32x4_t vuzp2q_f32(float32x4_t __p0, float32x4_t __p1) {
65666 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65670 __ai float32x4_t vuzp2q_f32(float32x4_t __p0, float32x4_t __p1) {
65672 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65681 __ai int32x4_t vuzp2q_s32(int32x4_t __p0, int32x4_t __p1) {
65683 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65687 __ai int32x4_t vuzp2q_s32(int32x4_t __p0, int32x4_t __p1) {
65689 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65698 __ai int64x2_t vuzp2q_s64(int64x2_t __p0, int64x2_t __p1) {
65700 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65704 __ai int64x2_t vuzp2q_s64(int64x2_t __p0, int64x2_t __p1) {
65706 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65715 __ai int16x8_t vuzp2q_s16(int16x8_t __p0, int16x8_t __p1) {
65717 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65721 __ai int16x8_t vuzp2q_s16(int16x8_t __p0, int16x8_t __p1) {
65723 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65732 __ai uint8x8_t vuzp2_u8(uint8x8_t __p0, uint8x8_t __p1) {
65734 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65738 __ai uint8x8_t vuzp2_u8(uint8x8_t __p0, uint8x8_t __p1) {
65740 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65749 __ai uint32x2_t vuzp2_u32(uint32x2_t __p0, uint32x2_t __p1) {
65751 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65755 __ai uint32x2_t vuzp2_u32(uint32x2_t __p0, uint32x2_t __p1) {
65757 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65766 __ai uint16x4_t vuzp2_u16(uint16x4_t __p0, uint16x4_t __p1) {
65768 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65772 __ai uint16x4_t vuzp2_u16(uint16x4_t __p0, uint16x4_t __p1) {
65774 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65783 __ai int8x8_t vuzp2_s8(int8x8_t __p0, int8x8_t __p1) {
65785 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7, 9, 11, 13, 15);
65789 __ai int8x8_t vuzp2_s8(int8x8_t __p0, int8x8_t __p1) {
65791 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65800 __ai float32x2_t vuzp2_f32(float32x2_t __p0, float32x2_t __p1) {
65802 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65806 __ai float32x2_t vuzp2_f32(float32x2_t __p0, float32x2_t __p1) {
65808 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65817 __ai int32x2_t vuzp2_s32(int32x2_t __p0, int32x2_t __p1) {
65819 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
65823 __ai int32x2_t vuzp2_s32(int32x2_t __p0, int32x2_t __p1) {
65825 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65834 __ai int16x4_t vuzp2_s16(int16x4_t __p0, int16x4_t __p1) {
65836 __ret = __builtin_shufflevector(__p0, __p1, 1, 3, 5, 7);
65840 __ai int16x4_t vuzp2_s16(int16x4_t __p0, int16x4_t __p1) {
65842 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65851 __ai poly8x8_t vzip1_p8(poly8x8_t __p0, poly8x8_t __p1) {
65853 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
65857 __ai poly8x8_t vzip1_p8(poly8x8_t __p0, poly8x8_t __p1) {
65859 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65868 __ai poly16x4_t vzip1_p16(poly16x4_t __p0, poly16x4_t __p1) {
65870 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
65874 __ai poly16x4_t vzip1_p16(poly16x4_t __p0, poly16x4_t __p1) {
65876 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65885 __ai poly8x16_t vzip1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65887 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23);
65891 __ai poly8x16_t vzip1q_p8(poly8x16_t __p0, poly8x16_t __p1) {
65893 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65902 __ai poly64x2_t vzip1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65904 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65908 __ai poly64x2_t vzip1q_p64(poly64x2_t __p0, poly64x2_t __p1) {
65910 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65919 __ai poly16x8_t vzip1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65921 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
65925 __ai poly16x8_t vzip1q_p16(poly16x8_t __p0, poly16x8_t __p1) {
65927 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65936 __ai uint8x16_t vzip1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65938 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23);
65942 __ai uint8x16_t vzip1q_u8(uint8x16_t __p0, uint8x16_t __p1) {
65944 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
65953 __ai uint32x4_t vzip1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65955 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
65959 __ai uint32x4_t vzip1q_u32(uint32x4_t __p0, uint32x4_t __p1) {
65961 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
65970 __ai uint64x2_t vzip1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65972 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
65976 __ai uint64x2_t vzip1q_u64(uint64x2_t __p0, uint64x2_t __p1) {
65978 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
65987 __ai uint16x8_t vzip1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65989 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
65993 __ai uint16x8_t vzip1q_u16(uint16x8_t __p0, uint16x8_t __p1) {
65995 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66004 __ai int8x16_t vzip1q_s8(int8x16_t __p0, int8x16_t __p1) {
66006 __ret = __builtin_shufflevector(__p0, __p1, 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23);
66010 __ai int8x16_t vzip1q_s8(int8x16_t __p0, int8x16_t __p1) {
66012 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66021 __ai float64x2_t vzip1q_f64(float64x2_t __p0, float64x2_t __p1) {
66023 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
66027 __ai float64x2_t vzip1q_f64(float64x2_t __p0, float64x2_t __p1) {
66029 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66038 __ai float32x4_t vzip1q_f32(float32x4_t __p0, float32x4_t __p1) {
66040 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
66044 __ai float32x4_t vzip1q_f32(float32x4_t __p0, float32x4_t __p1) {
66046 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66055 __ai int32x4_t vzip1q_s32(int32x4_t __p0, int32x4_t __p1) {
66057 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
66061 __ai int32x4_t vzip1q_s32(int32x4_t __p0, int32x4_t __p1) {
66063 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66072 __ai int64x2_t vzip1q_s64(int64x2_t __p0, int64x2_t __p1) {
66074 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
66078 __ai int64x2_t vzip1q_s64(int64x2_t __p0, int64x2_t __p1) {
66080 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66089 __ai int16x8_t vzip1q_s16(int16x8_t __p0, int16x8_t __p1) {
66091 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
66095 __ai int16x8_t vzip1q_s16(int16x8_t __p0, int16x8_t __p1) {
66097 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66106 __ai uint8x8_t vzip1_u8(uint8x8_t __p0, uint8x8_t __p1) {
66108 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
66112 __ai uint8x8_t vzip1_u8(uint8x8_t __p0, uint8x8_t __p1) {
66114 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66123 __ai uint32x2_t vzip1_u32(uint32x2_t __p0, uint32x2_t __p1) {
66125 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
66129 __ai uint32x2_t vzip1_u32(uint32x2_t __p0, uint32x2_t __p1) {
66131 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66140 __ai uint16x4_t vzip1_u16(uint16x4_t __p0, uint16x4_t __p1) {
66142 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
66146 __ai uint16x4_t vzip1_u16(uint16x4_t __p0, uint16x4_t __p1) {
66148 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66157 __ai int8x8_t vzip1_s8(int8x8_t __p0, int8x8_t __p1) {
66159 __ret = __builtin_shufflevector(__p0, __p1, 0, 8, 1, 9, 2, 10, 3, 11);
66163 __ai int8x8_t vzip1_s8(int8x8_t __p0, int8x8_t __p1) {
66165 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66174 __ai float32x2_t vzip1_f32(float32x2_t __p0, float32x2_t __p1) {
66176 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
66180 __ai float32x2_t vzip1_f32(float32x2_t __p0, float32x2_t __p1) {
66182 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66191 __ai int32x2_t vzip1_s32(int32x2_t __p0, int32x2_t __p1) {
66193 __ret = __builtin_shufflevector(__p0, __p1, 0, 2);
66197 __ai int32x2_t vzip1_s32(int32x2_t __p0, int32x2_t __p1) {
66199 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66208 __ai int16x4_t vzip1_s16(int16x4_t __p0, int16x4_t __p1) {
66210 __ret = __builtin_shufflevector(__p0, __p1, 0, 4, 1, 5);
66214 __ai int16x4_t vzip1_s16(int16x4_t __p0, int16x4_t __p1) {
66216 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66225 __ai poly8x8_t vzip2_p8(poly8x8_t __p0, poly8x8_t __p1) {
66227 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66231 __ai poly8x8_t vzip2_p8(poly8x8_t __p0, poly8x8_t __p1) {
66233 poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66242 __ai poly16x4_t vzip2_p16(poly16x4_t __p0, poly16x4_t __p1) {
66244 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66248 __ai poly16x4_t vzip2_p16(poly16x4_t __p0, poly16x4_t __p1) {
66250 poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66259 __ai poly8x16_t vzip2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
66261 __ret = __builtin_shufflevector(__p0, __p1, 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31);
66265 __ai poly8x16_t vzip2q_p8(poly8x16_t __p0, poly8x16_t __p1) {
66267 poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66276 __ai poly64x2_t vzip2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
66278 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66282 __ai poly64x2_t vzip2q_p64(poly64x2_t __p0, poly64x2_t __p1) {
66284 poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66293 __ai poly16x8_t vzip2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
66295 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66299 __ai poly16x8_t vzip2q_p16(poly16x8_t __p0, poly16x8_t __p1) {
66301 poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66310 __ai uint8x16_t vzip2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
66312 __ret = __builtin_shufflevector(__p0, __p1, 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31);
66316 __ai uint8x16_t vzip2q_u8(uint8x16_t __p0, uint8x16_t __p1) {
66318 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66327 __ai uint32x4_t vzip2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
66329 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66333 __ai uint32x4_t vzip2q_u32(uint32x4_t __p0, uint32x4_t __p1) {
66335 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66344 __ai uint64x2_t vzip2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
66346 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66350 __ai uint64x2_t vzip2q_u64(uint64x2_t __p0, uint64x2_t __p1) {
66352 uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66361 __ai uint16x8_t vzip2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
66363 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66367 __ai uint16x8_t vzip2q_u16(uint16x8_t __p0, uint16x8_t __p1) {
66369 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66378 __ai int8x16_t vzip2q_s8(int8x16_t __p0, int8x16_t __p1) {
66380 __ret = __builtin_shufflevector(__p0, __p1, 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31);
66384 __ai int8x16_t vzip2q_s8(int8x16_t __p0, int8x16_t __p1) {
66386 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66395 __ai float64x2_t vzip2q_f64(float64x2_t __p0, float64x2_t __p1) {
66397 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66401 __ai float64x2_t vzip2q_f64(float64x2_t __p0, float64x2_t __p1) {
66403 float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66412 __ai float32x4_t vzip2q_f32(float32x4_t __p0, float32x4_t __p1) {
66414 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66418 __ai float32x4_t vzip2q_f32(float32x4_t __p0, float32x4_t __p1) {
66420 float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66429 __ai int32x4_t vzip2q_s32(int32x4_t __p0, int32x4_t __p1) {
66431 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66435 __ai int32x4_t vzip2q_s32(int32x4_t __p0, int32x4_t __p1) {
66437 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66446 __ai int64x2_t vzip2q_s64(int64x2_t __p0, int64x2_t __p1) {
66448 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66452 __ai int64x2_t vzip2q_s64(int64x2_t __p0, int64x2_t __p1) {
66454 int64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66463 __ai int16x8_t vzip2q_s16(int16x8_t __p0, int16x8_t __p1) {
66465 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66469 __ai int16x8_t vzip2q_s16(int16x8_t __p0, int16x8_t __p1) {
66471 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66480 __ai uint8x8_t vzip2_u8(uint8x8_t __p0, uint8x8_t __p1) {
66482 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66486 __ai uint8x8_t vzip2_u8(uint8x8_t __p0, uint8x8_t __p1) {
66488 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66497 __ai uint32x2_t vzip2_u32(uint32x2_t __p0, uint32x2_t __p1) {
66499 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66503 __ai uint32x2_t vzip2_u32(uint32x2_t __p0, uint32x2_t __p1) {
66505 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66514 __ai uint16x4_t vzip2_u16(uint16x4_t __p0, uint16x4_t __p1) {
66516 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66520 __ai uint16x4_t vzip2_u16(uint16x4_t __p0, uint16x4_t __p1) {
66522 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66531 __ai int8x8_t vzip2_s8(int8x8_t __p0, int8x8_t __p1) {
66533 __ret = __builtin_shufflevector(__p0, __p1, 4, 12, 5, 13, 6, 14, 7, 15);
66537 __ai int8x8_t vzip2_s8(int8x8_t __p0, int8x8_t __p1) {
66539 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66548 __ai float32x2_t vzip2_f32(float32x2_t __p0, float32x2_t __p1) {
66550 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66554 __ai float32x2_t vzip2_f32(float32x2_t __p0, float32x2_t __p1) {
66556 float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66565 __ai int32x2_t vzip2_s32(int32x2_t __p0, int32x2_t __p1) {
66567 __ret = __builtin_shufflevector(__p0, __p1, 1, 3);
66571 __ai int32x2_t vzip2_s32(int32x2_t __p0, int32x2_t __p1) {
66573 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66582 __ai int16x4_t vzip2_s16(int16x4_t __p0, int16x4_t __p1) {
66584 __ret = __builtin_shufflevector(__p0, __p1, 2, 6, 3, 7);
66588 __ai int16x4_t vzip2_s16(int16x4_t __p0, int16x4_t __p1) {
66590 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66600 __ai uint8x16_t vabaq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
66602 __ret = __p0 + vabdq_u8(__p1, __p2);
66606 __ai uint8x16_t vabaq_u8(uint8x16_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
66608 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66618 __ai uint32x4_t vabaq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
66620 __ret = __p0 + vabdq_u32(__p1, __p2);
66624 __ai uint32x4_t vabaq_u32(uint32x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
66626 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66636 __ai uint16x8_t vabaq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
66638 __ret = __p0 + vabdq_u16(__p1, __p2);
66642 __ai uint16x8_t vabaq_u16(uint16x8_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
66644 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66654 __ai int8x16_t vabaq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
66656 __ret = __p0 + vabdq_s8(__p1, __p2);
66660 __ai int8x16_t vabaq_s8(int8x16_t __p0, int8x16_t __p1, int8x16_t __p2) {
66662 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
66672 __ai int32x4_t vabaq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
66674 __ret = __p0 + vabdq_s32(__p1, __p2);
66678 __ai int32x4_t vabaq_s32(int32x4_t __p0, int32x4_t __p1, int32x4_t __p2) {
66680 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66690 __ai int16x8_t vabaq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
66692 __ret = __p0 + vabdq_s16(__p1, __p2);
66696 __ai int16x8_t vabaq_s16(int16x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
66698 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66708 __ai uint8x8_t vaba_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
66710 __ret = __p0 + vabd_u8(__p1, __p2);
66714 __ai uint8x8_t vaba_u8(uint8x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
66716 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66726 __ai uint32x2_t vaba_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
66728 __ret = __p0 + vabd_u32(__p1, __p2);
66732 __ai uint32x2_t vaba_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
66734 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66744 __ai uint16x4_t vaba_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
66746 __ret = __p0 + vabd_u16(__p1, __p2);
66750 __ai uint16x4_t vaba_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
66752 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66762 __ai int8x8_t vaba_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
66764 __ret = __p0 + vabd_s8(__p1, __p2);
66768 __ai int8x8_t vaba_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
66770 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66780 __ai int32x2_t vaba_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
66782 __ret = __p0 + vabd_s32(__p1, __p2);
66786 __ai int32x2_t vaba_s32(int32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
66788 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66798 __ai int16x4_t vaba_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
66800 __ret = __p0 + vabd_s16(__p1, __p2);
66804 __ai int16x4_t vaba_s16(int16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
66806 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66816 __ai uint16x8_t vabdl_u8(uint8x8_t __p0, uint8x8_t __p1) {
66818 __ret = (uint16x8_t)(vmovl_u8((uint8x8_t)(vabd_u8(__p0, __p1))));
66822 __ai uint16x8_t vabdl_u8(uint8x8_t __p0, uint8x8_t __p1) {
66824 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66830 __ai uint16x8_t __noswap_vabdl_u8(uint8x8_t __p0, uint8x8_t __p1) {
66832 __ret = (uint16x8_t)(__noswap_vmovl_u8((uint8x8_t)(__noswap_vabd_u8(__p0, __p1))));
66838 __ai uint64x2_t vabdl_u32(uint32x2_t __p0, uint32x2_t __p1) {
66840 __ret = (uint64x2_t)(vmovl_u32((uint32x2_t)(vabd_u32(__p0, __p1))));
66844 __ai uint64x2_t vabdl_u32(uint32x2_t __p0, uint32x2_t __p1) {
66846 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66852 __ai uint64x2_t __noswap_vabdl_u32(uint32x2_t __p0, uint32x2_t __p1) {
66854 __ret = (uint64x2_t)(__noswap_vmovl_u32((uint32x2_t)(__noswap_vabd_u32(__p0, __p1))));
66860 __ai uint32x4_t vabdl_u16(uint16x4_t __p0, uint16x4_t __p1) {
66862 __ret = (uint32x4_t)(vmovl_u16((uint16x4_t)(vabd_u16(__p0, __p1))));
66866 __ai uint32x4_t vabdl_u16(uint16x4_t __p0, uint16x4_t __p1) {
66868 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66874 __ai uint32x4_t __noswap_vabdl_u16(uint16x4_t __p0, uint16x4_t __p1) {
66876 __ret = (uint32x4_t)(__noswap_vmovl_u16((uint16x4_t)(__noswap_vabd_u16(__p0, __p1))));
66882 __ai int16x8_t vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
66884 __ret = (int16x8_t)(vmovl_u8((uint8x8_t)(vabd_s8(__p0, __p1))));
66888 __ai int16x8_t vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
66890 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66896 __ai int16x8_t __noswap_vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
66898 __ret = (int16x8_t)(__noswap_vmovl_u8((uint8x8_t)(__noswap_vabd_s8(__p0, __p1))));
66904 __ai int64x2_t vabdl_s32(int32x2_t __p0, int32x2_t __p1) {
66906 __ret = (int64x2_t)(vmovl_u32((uint32x2_t)(vabd_s32(__p0, __p1))));
66910 __ai int64x2_t vabdl_s32(int32x2_t __p0, int32x2_t __p1) {
66912 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66918 __ai int64x2_t __noswap_vabdl_s32(int32x2_t __p0, int32x2_t __p1) {
66920 __ret = (int64x2_t)(__noswap_vmovl_u32((uint32x2_t)(__noswap_vabd_s32(__p0, __p1))));
66926 __ai int32x4_t vabdl_s16(int16x4_t __p0, int16x4_t __p1) {
66928 __ret = (int32x4_t)(vmovl_u16((uint16x4_t)(vabd_s16(__p0, __p1))));
66932 __ai int32x4_t vabdl_s16(int16x4_t __p0, int16x4_t __p1) {
66934 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66940 __ai int32x4_t __noswap_vabdl_s16(int16x4_t __p0, int16x4_t __p1) {
66942 __ret = (int32x4_t)(__noswap_vmovl_u16((uint16x4_t)(__noswap_vabd_s16(__p0, __p1))));
66948 __ai uint16x8_t vaddl_u8(uint8x8_t __p0, uint8x8_t __p1) {
66950 __ret = vmovl_u8(__p0) + vmovl_u8(__p1);
66954 __ai uint16x8_t vaddl_u8(uint8x8_t __p0, uint8x8_t __p1) {
66956 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66965 __ai uint64x2_t vaddl_u32(uint32x2_t __p0, uint32x2_t __p1) {
66967 __ret = vmovl_u32(__p0) + vmovl_u32(__p1);
66971 __ai uint64x2_t vaddl_u32(uint32x2_t __p0, uint32x2_t __p1) {
66973 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
66982 __ai uint32x4_t vaddl_u16(uint16x4_t __p0, uint16x4_t __p1) {
66984 __ret = vmovl_u16(__p0) + vmovl_u16(__p1);
66988 __ai uint32x4_t vaddl_u16(uint16x4_t __p0, uint16x4_t __p1) {
66990 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
66999 __ai int16x8_t vaddl_s8(int8x8_t __p0, int8x8_t __p1) {
67001 __ret = vmovl_s8(__p0) + vmovl_s8(__p1);
67005 __ai int16x8_t vaddl_s8(int8x8_t __p0, int8x8_t __p1) {
67007 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67016 __ai int64x2_t vaddl_s32(int32x2_t __p0, int32x2_t __p1) {
67018 __ret = vmovl_s32(__p0) + vmovl_s32(__p1);
67022 __ai int64x2_t vaddl_s32(int32x2_t __p0, int32x2_t __p1) {
67024 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67033 __ai int32x4_t vaddl_s16(int16x4_t __p0, int16x4_t __p1) {
67035 __ret = vmovl_s16(__p0) + vmovl_s16(__p1);
67039 __ai int32x4_t vaddl_s16(int16x4_t __p0, int16x4_t __p1) {
67041 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67050 __ai uint16x8_t vaddw_u8(uint16x8_t __p0, uint8x8_t __p1) {
67052 __ret = __p0 + vmovl_u8(__p1);
67056 __ai uint16x8_t vaddw_u8(uint16x8_t __p0, uint8x8_t __p1) {
67058 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67067 __ai uint64x2_t vaddw_u32(uint64x2_t __p0, uint32x2_t __p1) {
67069 __ret = __p0 + vmovl_u32(__p1);
67073 __ai uint64x2_t vaddw_u32(uint64x2_t __p0, uint32x2_t __p1) {
67075 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67084 __ai uint32x4_t vaddw_u16(uint32x4_t __p0, uint16x4_t __p1) {
67086 __ret = __p0 + vmovl_u16(__p1);
67090 __ai uint32x4_t vaddw_u16(uint32x4_t __p0, uint16x4_t __p1) {
67092 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67101 __ai int16x8_t vaddw_s8(int16x8_t __p0, int8x8_t __p1) {
67103 __ret = __p0 + vmovl_s8(__p1);
67107 __ai int16x8_t vaddw_s8(int16x8_t __p0, int8x8_t __p1) {
67109 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67118 __ai int64x2_t vaddw_s32(int64x2_t __p0, int32x2_t __p1) {
67120 __ret = __p0 + vmovl_s32(__p1);
67124 __ai int64x2_t vaddw_s32(int64x2_t __p0, int32x2_t __p1) {
67126 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67135 __ai int32x4_t vaddw_s16(int32x4_t __p0, int16x4_t __p1) {
67137 __ret = __p0 + vmovl_s16(__p1);
67141 __ai int32x4_t vaddw_s16(int32x4_t __p0, int16x4_t __p1) {
67143 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67194 __ai uint16x8_t vmlal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67196 __ret = __p0 + vmull_u8(__p1, __p2);
67200 __ai uint16x8_t vmlal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67202 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67209 __ai uint16x8_t __noswap_vmlal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67211 __ret = __p0 + __noswap_vmull_u8(__p1, __p2);
67217 __ai uint64x2_t vmlal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67219 __ret = __p0 + vmull_u32(__p1, __p2);
67223 __ai uint64x2_t vmlal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67225 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67232 __ai uint64x2_t __noswap_vmlal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67234 __ret = __p0 + __noswap_vmull_u32(__p1, __p2);
67240 __ai uint32x4_t vmlal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67242 __ret = __p0 + vmull_u16(__p1, __p2);
67246 __ai uint32x4_t vmlal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67248 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67255 __ai uint32x4_t __noswap_vmlal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67257 __ret = __p0 + __noswap_vmull_u16(__p1, __p2);
67263 __ai int16x8_t vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67265 __ret = __p0 + vmull_s8(__p1, __p2);
67269 __ai int16x8_t vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67271 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67278 __ai int16x8_t __noswap_vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67280 __ret = __p0 + __noswap_vmull_s8(__p1, __p2);
67286 __ai int64x2_t vmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67288 __ret = __p0 + vmull_s32(__p1, __p2);
67292 __ai int64x2_t vmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67294 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67301 __ai int64x2_t __noswap_vmlal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67303 __ret = __p0 + __noswap_vmull_s32(__p1, __p2);
67309 __ai int32x4_t vmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67311 __ret = __p0 + vmull_s16(__p1, __p2);
67315 __ai int32x4_t vmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67317 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67324 __ai int32x4_t __noswap_vmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67326 __ret = __p0 + __noswap_vmull_s16(__p1, __p2);
67332 #define vmlal_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
67334 uint32x2_t __s1 = __p1; \
67341 #define vmlal_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
67343 uint32x2_t __s1 = __p1; \
67356 #define vmlal_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
67358 uint16x4_t __s1 = __p1; \
67365 #define vmlal_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
67367 uint16x4_t __s1 = __p1; \
67380 #define vmlal_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
67382 int32x2_t __s1 = __p1; \
67389 #define vmlal_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
67391 int32x2_t __s1 = __p1; \
67404 #define vmlal_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
67406 int16x4_t __s1 = __p1; \
67413 #define vmlal_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
67415 int16x4_t __s1 = __p1; \
67428 __ai uint64x2_t vmlal_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67430 __ret = __p0 + vmull_u32(__p1, (uint32x2_t) {__p2, __p2});
67434 __ai uint64x2_t vmlal_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67436 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67442 __ai uint64x2_t __noswap_vmlal_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67444 __ret = __p0 + __noswap_vmull_u32(__p1, (uint32x2_t) {__p2, __p2});
67450 __ai uint32x4_t vmlal_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67452 __ret = __p0 + vmull_u16(__p1, (uint16x4_t) {__p2, __p2, __p2, __p2});
67456 __ai uint32x4_t vmlal_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67458 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67464 __ai uint32x4_t __noswap_vmlal_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67466 __ret = __p0 + __noswap_vmull_u16(__p1, (uint16x4_t) {__p2, __p2, __p2, __p2});
67472 __ai int64x2_t vmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67474 __ret = __p0 + vmull_s32(__p1, (int32x2_t) {__p2, __p2});
67478 __ai int64x2_t vmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67480 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67486 __ai int64x2_t __noswap_vmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67488 __ret = __p0 + __noswap_vmull_s32(__p1, (int32x2_t) {__p2, __p2});
67494 __ai int32x4_t vmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67496 __ret = __p0 + vmull_s16(__p1, (int16x4_t) {__p2, __p2, __p2, __p2});
67500 __ai int32x4_t vmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67502 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67508 __ai int32x4_t __noswap_vmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67510 __ret = __p0 + __noswap_vmull_s16(__p1, (int16x4_t) {__p2, __p2, __p2, __p2});
67516 __ai uint16x8_t vmlsl_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67518 __ret = __p0 - vmull_u8(__p1, __p2);
67522 __ai uint16x8_t vmlsl_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67524 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67531 __ai uint16x8_t __noswap_vmlsl_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
67533 __ret = __p0 - __noswap_vmull_u8(__p1, __p2);
67539 __ai uint64x2_t vmlsl_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67541 __ret = __p0 - vmull_u32(__p1, __p2);
67545 __ai uint64x2_t vmlsl_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67547 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67554 __ai uint64x2_t __noswap_vmlsl_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
67556 __ret = __p0 - __noswap_vmull_u32(__p1, __p2);
67562 __ai uint32x4_t vmlsl_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67564 __ret = __p0 - vmull_u16(__p1, __p2);
67568 __ai uint32x4_t vmlsl_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67570 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67577 __ai uint32x4_t __noswap_vmlsl_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
67579 __ret = __p0 - __noswap_vmull_u16(__p1, __p2);
67585 __ai int16x8_t vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67587 __ret = __p0 - vmull_s8(__p1, __p2);
67591 __ai int16x8_t vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67593 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67600 __ai int16x8_t __noswap_vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67602 __ret = __p0 - __noswap_vmull_s8(__p1, __p2);
67608 __ai int64x2_t vmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67610 __ret = __p0 - vmull_s32(__p1, __p2);
67614 __ai int64x2_t vmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67616 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67623 __ai int64x2_t __noswap_vmlsl_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
67625 __ret = __p0 - __noswap_vmull_s32(__p1, __p2);
67631 __ai int32x4_t vmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67633 __ret = __p0 - vmull_s16(__p1, __p2);
67637 __ai int32x4_t vmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67639 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67646 __ai int32x4_t __noswap_vmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
67648 __ret = __p0 - __noswap_vmull_s16(__p1, __p2);
67654 #define vmlsl_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
67656 uint32x2_t __s1 = __p1; \
67663 #define vmlsl_lane_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
67665 uint32x2_t __s1 = __p1; \
67678 #define vmlsl_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
67680 uint16x4_t __s1 = __p1; \
67687 #define vmlsl_lane_u16(__p0, __p1, __p2, __p3) __extension__ ({ \
67689 uint16x4_t __s1 = __p1; \
67702 #define vmlsl_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
67704 int32x2_t __s1 = __p1; \
67711 #define vmlsl_lane_s32(__p0, __p1, __p2, __p3) __extension__ ({ \
67713 int32x2_t __s1 = __p1; \
67726 #define vmlsl_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
67728 int16x4_t __s1 = __p1; \
67735 #define vmlsl_lane_s16(__p0, __p1, __p2, __p3) __extension__ ({ \
67737 int16x4_t __s1 = __p1; \
67750 __ai uint64x2_t vmlsl_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67752 __ret = __p0 - vmull_u32(__p1, (uint32x2_t) {__p2, __p2});
67756 __ai uint64x2_t vmlsl_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67758 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67764 __ai uint64x2_t __noswap_vmlsl_n_u32(uint64x2_t __p0, uint32x2_t __p1, uint32_t __p2) {
67766 __ret = __p0 - __noswap_vmull_u32(__p1, (uint32x2_t) {__p2, __p2});
67772 __ai uint32x4_t vmlsl_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67774 __ret = __p0 - vmull_u16(__p1, (uint16x4_t) {__p2, __p2, __p2, __p2});
67778 __ai uint32x4_t vmlsl_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67780 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67786 __ai uint32x4_t __noswap_vmlsl_n_u16(uint32x4_t __p0, uint16x4_t __p1, uint16_t __p2) {
67788 __ret = __p0 - __noswap_vmull_u16(__p1, (uint16x4_t) {__p2, __p2, __p2, __p2});
67794 __ai int64x2_t vmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67796 __ret = __p0 - vmull_s32(__p1, (int32x2_t) {__p2, __p2});
67800 __ai int64x2_t vmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67802 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
67808 __ai int64x2_t __noswap_vmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
67810 __ret = __p0 - __noswap_vmull_s32(__p1, (int32x2_t) {__p2, __p2});
67816 __ai int32x4_t vmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67818 __ret = __p0 - vmull_s16(__p1, (int16x4_t) {__p2, __p2, __p2, __p2});
67822 __ai int32x4_t vmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67824 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
67830 __ai int32x4_t __noswap_vmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
67832 __ret = __p0 - __noswap_vmull_s16(__p1, (int16x4_t) {__p2, __p2, __p2, __p2});
67891 __ai int32_t vqrdmlahs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
67893 __ret = vqadds_s32(__p0, vqrdmulhs_s32(__p1, __p2));
67897 __ai int32_t vqrdmlahs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
67899 __ret = __noswap_vqadds_s32(__p0, __noswap_vqrdmulhs_s32(__p1, __p2));
67905 __ai int16_t vqrdmlahh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
67907 __ret = vqaddh_s16(__p0, vqrdmulhh_s16(__p1, __p2));
67911 __ai int16_t vqrdmlahh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
67913 __ret = __noswap_vqaddh_s16(__p0, __noswap_vqrdmulhh_s16(__p1, __p2));
68003 __ai int32_t vqrdmlshs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
68005 __ret = vqsubs_s32(__p0, vqrdmulhs_s32(__p1, __p2));
68009 __ai int32_t vqrdmlshs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
68011 __ret = __noswap_vqsubs_s32(__p0, __noswap_vqrdmulhs_s32(__p1, __p2));
68017 __ai int16_t vqrdmlshh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
68019 __ret = vqsubh_s16(__p0, vqrdmulhh_s16(__p1, __p2));
68023 __ai int16_t vqrdmlshh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
68025 __ret = __noswap_vqsubh_s16(__p0, __noswap_vqrdmulhh_s16(__p1, __p2));
68117 __ai uint16x8_t vabdl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
68119 __ret = vabdl_u8(vget_high_u8(__p0), vget_high_u8(__p1));
68123 __ai uint16x8_t vabdl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
68125 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68134 __ai uint64x2_t vabdl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
68136 __ret = vabdl_u32(vget_high_u32(__p0), vget_high_u32(__p1));
68140 __ai uint64x2_t vabdl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
68142 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68151 __ai uint32x4_t vabdl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
68153 __ret = vabdl_u16(vget_high_u16(__p0), vget_high_u16(__p1));
68157 __ai uint32x4_t vabdl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
68159 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68168 __ai int16x8_t vabdl_high_s8(int8x16_t __p0, int8x16_t __p1) {
68170 __ret = vabdl_s8(vget_high_s8(__p0), vget_high_s8(__p1));
68174 __ai int16x8_t vabdl_high_s8(int8x16_t __p0, int8x16_t __p1) {
68176 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68185 __ai int64x2_t vabdl_high_s32(int32x4_t __p0, int32x4_t __p1) {
68187 __ret = vabdl_s32(vget_high_s32(__p0), vget_high_s32(__p1));
68191 __ai int64x2_t vabdl_high_s32(int32x4_t __p0, int32x4_t __p1) {
68193 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68202 __ai int32x4_t vabdl_high_s16(int16x8_t __p0, int16x8_t __p1) {
68204 __ret = vabdl_s16(vget_high_s16(__p0), vget_high_s16(__p1));
68208 __ai int32x4_t vabdl_high_s16(int16x8_t __p0, int16x8_t __p1) {
68210 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68219 __ai uint16x8_t vaddl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
68221 __ret = vmovl_high_u8(__p0) + vmovl_high_u8(__p1);
68225 __ai uint16x8_t vaddl_high_u8(uint8x16_t __p0, uint8x16_t __p1) {
68227 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68236 __ai uint64x2_t vaddl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
68238 __ret = vmovl_high_u32(__p0) + vmovl_high_u32(__p1);
68242 __ai uint64x2_t vaddl_high_u32(uint32x4_t __p0, uint32x4_t __p1) {
68244 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68253 __ai uint32x4_t vaddl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
68255 __ret = vmovl_high_u16(__p0) + vmovl_high_u16(__p1);
68259 __ai uint32x4_t vaddl_high_u16(uint16x8_t __p0, uint16x8_t __p1) {
68261 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68270 __ai int16x8_t vaddl_high_s8(int8x16_t __p0, int8x16_t __p1) {
68272 __ret = vmovl_high_s8(__p0) + vmovl_high_s8(__p1);
68276 __ai int16x8_t vaddl_high_s8(int8x16_t __p0, int8x16_t __p1) {
68278 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68287 __ai int64x2_t vaddl_high_s32(int32x4_t __p0, int32x4_t __p1) {
68289 __ret = vmovl_high_s32(__p0) + vmovl_high_s32(__p1);
68293 __ai int64x2_t vaddl_high_s32(int32x4_t __p0, int32x4_t __p1) {
68295 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68304 __ai int32x4_t vaddl_high_s16(int16x8_t __p0, int16x8_t __p1) {
68306 __ret = vmovl_high_s16(__p0) + vmovl_high_s16(__p1);
68310 __ai int32x4_t vaddl_high_s16(int16x8_t __p0, int16x8_t __p1) {
68312 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68321 __ai uint16x8_t vaddw_high_u8(uint16x8_t __p0, uint8x16_t __p1) {
68323 __ret = __p0 + vmovl_high_u8(__p1);
68327 __ai uint16x8_t vaddw_high_u8(uint16x8_t __p0, uint8x16_t __p1) {
68329 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68338 __ai uint64x2_t vaddw_high_u32(uint64x2_t __p0, uint32x4_t __p1) {
68340 __ret = __p0 + vmovl_high_u32(__p1);
68344 __ai uint64x2_t vaddw_high_u32(uint64x2_t __p0, uint32x4_t __p1) {
68346 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68355 __ai uint32x4_t vaddw_high_u16(uint32x4_t __p0, uint16x8_t __p1) {
68357 __ret = __p0 + vmovl_high_u16(__p1);
68361 __ai uint32x4_t vaddw_high_u16(uint32x4_t __p0, uint16x8_t __p1) {
68363 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68372 __ai int16x8_t vaddw_high_s8(int16x8_t __p0, int8x16_t __p1) {
68374 __ret = __p0 + vmovl_high_s8(__p1);
68378 __ai int16x8_t vaddw_high_s8(int16x8_t __p0, int8x16_t __p1) {
68380 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68389 __ai int64x2_t vaddw_high_s32(int64x2_t __p0, int32x4_t __p1) {
68391 __ret = __p0 + vmovl_high_s32(__p1);
68395 __ai int64x2_t vaddw_high_s32(int64x2_t __p0, int32x4_t __p1) {
68397 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68406 __ai int32x4_t vaddw_high_s16(int32x4_t __p0, int16x8_t __p1) {
68408 __ret = __p0 + vmovl_high_s16(__p1);
68412 __ai int32x4_t vaddw_high_s16(int32x4_t __p0, int16x8_t __p1) {
68414 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68579 __ai uint16x8_t vmlal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
68581 __ret = vmlal_u8(__p0, vget_high_u8(__p1), vget_high_u8(__p2));
68585 __ai uint16x8_t vmlal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
68587 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68597 __ai uint64x2_t vmlal_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
68599 __ret = vmlal_u32(__p0, vget_high_u32(__p1), vget_high_u32(__p2));
68603 __ai uint64x2_t vmlal_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
68605 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68615 __ai uint32x4_t vmlal_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
68617 __ret = vmlal_u16(__p0, vget_high_u16(__p1), vget_high_u16(__p2));
68621 __ai uint32x4_t vmlal_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
68623 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68633 __ai int16x8_t vmlal_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
68635 __ret = vmlal_s8(__p0, vget_high_s8(__p1), vget_high_s8(__p2));
68639 __ai int16x8_t vmlal_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
68641 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68651 __ai int64x2_t vmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
68653 __ret = vmlal_s32(__p0, vget_high_s32(__p1), vget_high_s32(__p2));
68657 __ai int64x2_t vmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
68659 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68669 __ai int32x4_t vmlal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
68671 __ret = vmlal_s16(__p0, vget_high_s16(__p1), vget_high_s16(__p2));
68675 __ai int32x4_t vmlal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
68677 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68687 __ai uint64x2_t vmlal_high_n_u32(uint64x2_t __p0, uint32x4_t __p1, uint32_t __p2) {
68689 __ret = vmlal_n_u32(__p0, vget_high_u32(__p1), __p2);
68693 __ai uint64x2_t vmlal_high_n_u32(uint64x2_t __p0, uint32x4_t __p1, uint32_t __p2) {
68695 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68704 __ai uint32x4_t vmlal_high_n_u16(uint32x4_t __p0, uint16x8_t __p1, uint16_t __p2) {
68706 __ret = vmlal_n_u16(__p0, vget_high_u16(__p1), __p2);
68710 __ai uint32x4_t vmlal_high_n_u16(uint32x4_t __p0, uint16x8_t __p1, uint16_t __p2) {
68712 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68721 __ai int64x2_t vmlal_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
68723 __ret = vmlal_n_s32(__p0, vget_high_s32(__p1), __p2);
68727 __ai int64x2_t vmlal_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
68729 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68738 __ai int32x4_t vmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
68740 __ret = vmlal_n_s16(__p0, vget_high_s16(__p1), __p2);
68744 __ai int32x4_t vmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
68746 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68755 __ai uint16x8_t vmlsl_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
68757 __ret = vmlsl_u8(__p0, vget_high_u8(__p1), vget_high_u8(__p2));
68761 __ai uint16x8_t vmlsl_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
68763 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68773 __ai uint64x2_t vmlsl_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
68775 __ret = vmlsl_u32(__p0, vget_high_u32(__p1), vget_high_u32(__p2));
68779 __ai uint64x2_t vmlsl_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
68781 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68791 __ai uint32x4_t vmlsl_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
68793 __ret = vmlsl_u16(__p0, vget_high_u16(__p1), vget_high_u16(__p2));
68797 __ai uint32x4_t vmlsl_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
68799 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68809 __ai int16x8_t vmlsl_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
68811 __ret = vmlsl_s8(__p0, vget_high_s8(__p1), vget_high_s8(__p2));
68815 __ai int16x8_t vmlsl_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
68817 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
68827 __ai int64x2_t vmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
68829 __ret = vmlsl_s32(__p0, vget_high_s32(__p1), vget_high_s32(__p2));
68833 __ai int64x2_t vmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
68835 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68845 __ai int32x4_t vmlsl_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
68847 __ret = vmlsl_s16(__p0, vget_high_s16(__p1), vget_high_s16(__p2));
68851 __ai int32x4_t vmlsl_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
68853 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68863 __ai uint64x2_t vmlsl_high_n_u32(uint64x2_t __p0, uint32x4_t __p1, uint32_t __p2) {
68865 __ret = vmlsl_n_u32(__p0, vget_high_u32(__p1), __p2);
68869 __ai uint64x2_t vmlsl_high_n_u32(uint64x2_t __p0, uint32x4_t __p1, uint32_t __p2) {
68871 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68880 __ai uint32x4_t vmlsl_high_n_u16(uint32x4_t __p0, uint16x8_t __p1, uint16_t __p2) {
68882 __ret = vmlsl_n_u16(__p0, vget_high_u16(__p1), __p2);
68886 __ai uint32x4_t vmlsl_high_n_u16(uint32x4_t __p0, uint16x8_t __p1, uint16_t __p2) {
68888 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68897 __ai int64x2_t vmlsl_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
68899 __ret = vmlsl_n_s32(__p0, vget_high_s32(__p1), __p2);
68903 __ai int64x2_t vmlsl_high_n_s32(int64x2_t __p0, int32x4_t __p1, int32_t __p2) {
68905 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
68914 __ai int32x4_t vmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
68916 __ret = vmlsl_n_s16(__p0, vget_high_s16(__p1), __p2);
68920 __ai int32x4_t vmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
68922 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68981 __ai uint16x8_t vabal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
68983 __ret = __p0 + vabdl_u8(__p1, __p2);
68987 __ai uint16x8_t vabal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
68989 uint8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
68996 __ai uint16x8_t __noswap_vabal_u8(uint16x8_t __p0, uint8x8_t __p1, uint8x8_t __p2) {
68998 __ret = __p0 + __noswap_vabdl_u8(__p1, __p2);
69004 __ai uint64x2_t vabal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
69006 __ret = __p0 + vabdl_u32(__p1, __p2);
69010 __ai uint64x2_t vabal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
69012 uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
69019 __ai uint64x2_t __noswap_vabal_u32(uint64x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
69021 __ret = __p0 + __noswap_vabdl_u32(__p1, __p2);
69027 __ai uint32x4_t vabal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
69029 __ret = __p0 + vabdl_u16(__p1, __p2);
69033 __ai uint32x4_t vabal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
69035 uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
69042 __ai uint32x4_t __noswap_vabal_u16(uint32x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
69044 __ret = __p0 + __noswap_vabdl_u16(__p1, __p2);
69050 __ai int16x8_t vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69052 __ret = __p0 + vabdl_s8(__p1, __p2);
69056 __ai int16x8_t vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69058 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
69065 __ai int16x8_t __noswap_vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69067 __ret = __p0 + __noswap_vabdl_s8(__p1, __p2);
69073 __ai int64x2_t vabal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
69075 __ret = __p0 + vabdl_s32(__p1, __p2);
69079 __ai int64x2_t vabal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
69081 int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
69088 __ai int64x2_t __noswap_vabal_s32(int64x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
69090 __ret = __p0 + __noswap_vabdl_s32(__p1, __p2);
69096 __ai int32x4_t vabal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
69098 __ret = __p0 + vabdl_s16(__p1, __p2);
69102 __ai int32x4_t vabal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
69104 int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
69111 __ai int32x4_t __noswap_vabal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
69113 __ret = __p0 + __noswap_vabdl_s16(__p1, __p2);
69120 __ai uint16x8_t vabal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
69122 __ret = vabal_u8(__p0, vget_high_u8(__p1), vget_high_u8(__p2));
69126 __ai uint16x8_t vabal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
69128 uint8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
69138 __ai uint64x2_t vabal_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
69140 __ret = vabal_u32(__p0, vget_high_u32(__p1), vget_high_u32(__p2));
69144 __ai uint64x2_t vabal_high_u32(uint64x2_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
69146 uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
69156 __ai uint32x4_t vabal_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
69158 __ret = vabal_u16(__p0, vget_high_u16(__p1), vget_high_u16(__p2));
69162 __ai uint32x4_t vabal_high_u16(uint32x4_t __p0, uint16x8_t __p1, uint16x8_t __p2) {
69164 uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
69174 __ai int16x8_t vabal_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
69176 __ret = vabal_s8(__p0, vget_high_s8(__p1), vget_high_s8(__p2));
69180 __ai int16x8_t vabal_high_s8(int16x8_t __p0, int8x16_t __p1, int8x16_t __p2) {
69182 int8x16_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
69192 __ai int64x2_t vabal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
69194 __ret = vabal_s32(__p0, vget_high_s32(__p1), vget_high_s32(__p2));
69198 __ai int64x2_t vabal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
69200 int32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
69210 __ai int32x4_t vabal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
69212 __ret = vabal_s16(__p0, vget_high_s16(__p1), vget_high_s16(__p2));
69216 __ai int32x4_t vabal_high_s16(int32x4_t __p0, int16x8_t __p1, int16x8_t __p2) {
69218 int16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);