Lines Matching defs:int8x8_t
48 typedef __attribute__((neon_vector_type(8))) int8_t int8x8_t;
82 int8x8_t val[2];
198 int8x8_t val[3];
314 int8x8_t val[4];
584 __ret = (uint8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
592 __ret = (uint8x8_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
598 __ret = (uint8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
606 __ret = (uint32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t
614 __ret = (uint32x2_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
620 __ret = (uint32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
628 __ret = (uint16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
636 __ret = (uint16x4_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
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) {
649 int8x8_t __ret;
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) {
655 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
656 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
657 int8x8_t __ret;
658 __ret = (int8x8_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
662 __ai int8x8_t __noswap_vabd_s8(int8x8_t __p0, int8x8_t __p1) {
663 int8x8_t __ret;
664 __ret = (int8x8_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
672 __ret = (float32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
680 __ret = (float32x2_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
689 __ret = (int32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
697 __ret = (int32x2_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
703 __ret = (int32x2_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
711 __ret = (int16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
719 __ret = (int16x4_t) __builtin_neon_vabd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
725 __ret = (int16x4_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
795 __ai int8x8_t vabs_s8(int8x8_t __p0) {
796 int8x8_t __ret;
797 __ret = (int8x8_t) __builtin_neon_vabs_v((int8x8_t)__p0, 0);
801 __ai int8x8_t vabs_s8(int8x8_t __p0) {
802 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
803 int8x8_t __ret;
804 __ret = (int8x8_t) __builtin_neon_vabs_v((int8x8_t)__rev0, 0);
813 __ret = (float32x2_t) __builtin_neon_vabs_v((int8x8_t)__p0, 9);
820 __ret = (float32x2_t) __builtin_neon_vabs_v((int8x8_t)__rev0, 9);
829 __ret = (int32x2_t) __builtin_neon_vabs_v((int8x8_t)__p0, 2);
836 __ret = (int32x2_t) __builtin_neon_vabs_v((int8x8_t)__rev0, 2);
845 __ret = (int16x4_t) __builtin_neon_vabs_v((int8x8_t)__p0, 1);
852 __ret = (int16x4_t) __builtin_neon_vabs_v((int8x8_t)__rev0, 1);
1077 __ai int8x8_t vadd_s8(int8x8_t __p0, int8x8_t __p1) {
1078 int8x8_t __ret;
1083 __ai int8x8_t vadd_s8(int8x8_t __p0, int8x8_t __p1) {
1084 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
1085 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1086 int8x8_t __ret;
1269 __ai int8x8_t vaddhn_s16(int16x8_t __p0, int16x8_t __p1) {
1270 int8x8_t __ret;
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) {
1278 int8x8_t __ret;
1279 __ret = (int8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__rev0, (int8x16_t)__rev1, 0);
1283 __ai int8x8_t __noswap_vaddhn_s16(int16x8_t __p0, int16x8_t __p1) {
1284 int8x8_t __ret;
1285 __ret = (int8x8_t) __builtin_neon_vaddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
1492 __ai int8x8_t vand_s8(int8x8_t __p0, int8x8_t __p1) {
1493 int8x8_t __ret;
1498 __ai int8x8_t vand_s8(int8x8_t __p0, int8x8_t __p1) {
1499 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
1500 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1501 int8x8_t __ret;
1758 __ai int8x8_t vbic_s8(int8x8_t __p0, int8x8_t __p1) {
1759 int8x8_t __ret;
1764 __ai int8x8_t vbic_s8(int8x8_t __p0, int8x8_t __p1) {
1765 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
1766 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
1767 int8x8_t __ret;
1825 __ret = (poly8x8_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 4);
1834 __ret = (poly8x8_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 4);
1843 __ret = (poly16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 5);
1852 __ret = (poly16x4_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 5);
2059 __ret = (uint8x8_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 16);
2068 __ret = (uint8x8_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 16);
2077 __ret = (uint32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 18);
2086 __ret = (uint32x2_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 18);
2095 __ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2101 __ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2109 __ret = (uint16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 17);
2118 __ret = (uint16x4_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 17);
2125 __ai int8x8_t vbsl_s8(uint8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
2126 int8x8_t __ret;
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);
2134 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
2135 int8x8_t __ret;
2136 __ret = (int8x8_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 0);
2145 __ret = (float32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
2154 __ret = (float32x2_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 9);
2163 __ret = (int32x2_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 2);
2172 __ret = (int32x2_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 2);
2181 __ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2187 __ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2195 __ret = (int16x4_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 1);
2204 __ret = (int16x4_t) __builtin_neon_vbsl_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 1);
2230 __ret = (uint32x2_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2238 __ret = (uint32x2_t) __builtin_neon_vcage_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
2264 __ret = (uint32x2_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2272 __ret = (uint32x2_t) __builtin_neon_vcagt_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
2298 __ret = (uint32x2_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2306 __ret = (uint32x2_t) __builtin_neon_vcale_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
2332 __ret = (uint32x2_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
2340 __ret = (uint32x2_t) __builtin_neon_vcalt_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
2551 __ai uint8x8_t vceq_s8(int8x8_t __p0, int8x8_t __p1) {
2557 __ai uint8x8_t vceq_s8(int8x8_t __p0, int8x8_t __p1) {
2558 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
2559 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
2789 __ai uint8x8_t vcge_s8(int8x8_t __p0, int8x8_t __p1) {
2795 __ai uint8x8_t vcge_s8(int8x8_t __p0, int8x8_t __p1) {
2796 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
2797 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3027 __ai uint8x8_t vcgt_s8(int8x8_t __p0, int8x8_t __p1) {
3033 __ai uint8x8_t vcgt_s8(int8x8_t __p0, int8x8_t __p1) {
3034 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3035 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3265 __ai uint8x8_t vcle_s8(int8x8_t __p0, int8x8_t __p1) {
3271 __ai uint8x8_t vcle_s8(int8x8_t __p0, int8x8_t __p1) {
3272 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3273 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3381 __ai int8x8_t vcls_s8(int8x8_t __p0) {
3382 int8x8_t __ret;
3383 __ret = (int8x8_t) __builtin_neon_vcls_v((int8x8_t)__p0, 0);
3387 __ai int8x8_t vcls_s8(int8x8_t __p0) {
3388 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3389 int8x8_t __ret;
3390 __ret = (int8x8_t) __builtin_neon_vcls_v((int8x8_t)__rev0, 0);
3399 __ret = (int32x2_t) __builtin_neon_vcls_v((int8x8_t)__p0, 2);
3406 __ret = (int32x2_t) __builtin_neon_vcls_v((int8x8_t)__rev0, 2);
3415 __ret = (int16x4_t) __builtin_neon_vcls_v((int8x8_t)__p0, 1);
3422 __ret = (int16x4_t) __builtin_neon_vcls_v((int8x8_t)__rev0, 1);
3599 __ai uint8x8_t vclt_s8(int8x8_t __p0, int8x8_t __p1) {
3605 __ai uint8x8_t vclt_s8(int8x8_t __p0, int8x8_t __p1) {
3606 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3607 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
3765 __ret = (uint8x8_t) __builtin_neon_vclz_v((int8x8_t)__p0, 16);
3772 __ret = (uint8x8_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 16);
3781 __ret = (uint32x2_t) __builtin_neon_vclz_v((int8x8_t)__p0, 18);
3788 __ret = (uint32x2_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 18);
3797 __ret = (uint16x4_t) __builtin_neon_vclz_v((int8x8_t)__p0, 17);
3804 __ret = (uint16x4_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 17);
3811 __ai int8x8_t vclz_s8(int8x8_t __p0) {
3812 int8x8_t __ret;
3813 __ret = (int8x8_t) __builtin_neon_vclz_v((int8x8_t)__p0, 0);
3817 __ai int8x8_t vclz_s8(int8x8_t __p0) {
3818 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3819 int8x8_t __ret;
3820 __ret = (int8x8_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 0);
3829 __ret = (int32x2_t) __builtin_neon_vclz_v((int8x8_t)__p0, 2);
3836 __ret = (int32x2_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 2);
3845 __ret = (int16x4_t) __builtin_neon_vclz_v((int8x8_t)__p0, 1);
3852 __ret = (int16x4_t) __builtin_neon_vclz_v((int8x8_t)__rev0, 1);
3861 __ret = (poly8x8_t) __builtin_neon_vcnt_v((int8x8_t)__p0, 4);
3868 __ret = (poly8x8_t) __builtin_neon_vcnt_v((int8x8_t)__rev0, 4);
3925 __ret = (uint8x8_t) __builtin_neon_vcnt_v((int8x8_t)__p0, 16);
3932 __ret = (uint8x8_t) __builtin_neon_vcnt_v((int8x8_t)__rev0, 16);
3939 __ai int8x8_t vcnt_s8(int8x8_t __p0) {
3940 int8x8_t __ret;
3941 __ret = (int8x8_t) __builtin_neon_vcnt_v((int8x8_t)__p0, 0);
3945 __ai int8x8_t vcnt_s8(int8x8_t __p0) {
3946 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
3947 int8x8_t __ret;
3948 __ret = (int8x8_t) __builtin_neon_vcnt_v((int8x8_t)__rev0, 0);
4070 __ai int8x16_t vcombine_s8(int8x8_t __p0, int8x8_t __p1) {
4076 __ai int8x16_t vcombine_s8(int8x8_t __p0, int8x8_t __p1) {
4077 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
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) {
4279 __ai int8x8_t vcreate_s8(uint64_t __p0) {
4280 int8x8_t __ret;
4281 __ret = (int8x8_t)(__p0);
4285 __ai int8x8_t vcreate_s8(uint64_t __p0) {
4286 int8x8_t __ret;
4287 __ret = (int8x8_t)(__p0);
4418 __ret = (float32x2_t) __builtin_neon_vcvt_f32_v((int8x8_t)__p0, 18);
4425 __ret = (float32x2_t) __builtin_neon_vcvt_f32_v((int8x8_t)__rev0, 18);
4434 __ret = (float32x2_t) __builtin_neon_vcvt_f32_v((int8x8_t)__p0, 2);
4441 __ret = (float32x2_t) __builtin_neon_vcvt_f32_v((int8x8_t)__rev0, 2);
4450 __ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 41);
4457 __ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__rev0, 41);
4463 __ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 41);
4508 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__s0, __p1, 18); \
4516 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__rev0, __p1, 18); \
4526 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__s0, __p1, 2); \
4534 __ret = (float32x2_t) __builtin_neon_vcvt_n_f32_v((int8x8_t)__rev0, __p1, 2); \
4562 __ret = (int32x2_t) __builtin_neon_vcvt_n_s32_v((int8x8_t)__s0, __p1, 2); \
4570 int8x8_t)__rev0, __p1, 2); \
4598 __ret = (uint32x2_t) __builtin_neon_vcvt_n_u32_v((int8x8_t)__s0, __p1, 18); \
4606 __ret = (uint32x2_t) __builtin_neon_vcvt_n_u32_v((int8x8_t)__rev0, __p1, 18); \
4631 __ret = (int32x2_t) __builtin_neon_vcvt_s32_v((int8x8_t)__p0, 2);
4638 __ret = (int32x2_t) __builtin_neon_vcvt_s32_v((int8x8_t)__rev0, 2);
4663 __ret = (uint32x2_t) __builtin_neon_vcvt_u32_v((int8x8_t)__p0, 18);
4670 __ret = (uint32x2_t) __builtin_neon_vcvt_u32_v((int8x8_t)__rev0, 18);
4821 int8x8_t __s0 = __p0; \
4828 int8x8_t __s0 = __p0; \
4829 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
4980 int8x8_t __s0 = __p0; \
4981 int8x8_t __ret; \
4987 int8x8_t __s0 = __p0; \
4988 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
4989 int8x8_t __ret; \
5338 __ai int8x8_t vdup_n_s8(int8_t __p0) {
5339 int8x8_t __ret;
5340 __ret = (int8x8_t) {__p0, __p0, __p0, __p0, __p0, __p0, __p0, __p0};
5344 __ai int8x8_t vdup_n_s8(int8_t __p0) {
5345 int8x8_t __ret;
5346 __ret = (int8x8_t) {__p0, __p0, __p0, __p0, __p0, __p0, __p0, __p0};
5630 __ai int8x8_t veor_s8(int8x8_t __p0, int8x8_t __p1) {
5631 int8x8_t __ret;
5636 __ai int8x8_t veor_s8(int8x8_t __p0, int8x8_t __p1) {
5637 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
5638 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
5639 int8x8_t __ret;
5699 __ret = (poly8x8_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 4); \
5709 __ret = (poly8x8_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 4); \
5720 __ret = (poly16x4_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 5); \
5730 __ret = (poly16x4_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 5); \
5972 __ret = (uint8x8_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 16); \
5982 __ret = (uint8x8_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 16); \
5993 __ret = (uint32x2_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 18); \
6003 __ret = (uint32x2_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 18); \
6014 __ret = (uint64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
6022 __ret = (uint64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
6032 __ret = (uint16x4_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 17); \
6042 __ret = (uint16x4_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 17); \
6050 int8x8_t __s0 = __p0; \
6051 int8x8_t __s1 = __p1; \
6052 int8x8_t __ret; \
6053 __ret = (int8x8_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 0); \
6058 int8x8_t __s0 = __p0; \
6059 int8x8_t __s1 = __p1; \
6060 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6061 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
6062 int8x8_t __ret; \
6063 __ret = (int8x8_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 0); \
6074 __ret = (float32x2_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 9); \
6084 __ret = (float32x2_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 9); \
6095 __ret = (int32x2_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 2); \
6105 __ret = (int32x2_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 2); \
6116 __ret = (int64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
6124 __ret = (int64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
6134 __ret = (int16x4_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 1); \
6144 __ret = (int16x4_t) __builtin_neon_vext_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 1); \
6176 __ret = (float32x2_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
6185 __ret = (float32x2_t) __builtin_neon_vfma_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 9);
6191 __ret = (float32x2_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
6312 __ai int8x8_t vget_high_s8(int8x16_t __p0) {
6313 int8x8_t __ret;
6318 __ai int8x8_t vget_high_s8(int8x16_t __p0) {
6320 int8x8_t __ret;
6325 __ai int8x8_t __noswap_vget_high_s8(int8x16_t __p0) {
6326 int8x8_t __ret;
6435 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6443 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6449 __ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6458 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6466 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6472 __ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6734 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6742 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6748 __ret = (uint8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6757 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6765 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \
6771 __ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6780 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6787 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6793 __ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6802 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6810 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6816 __ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6823 int8x8_t __s0 = __p0; \
6825 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6830 int8x8_t __s0 = __p0; \
6831 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6833 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \
6837 int8x8_t __s0 = __p0; \
6839 __ret = (int8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \
6848 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \
6856 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__rev0, __p1); \
6862 __ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \
6871 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6879 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \
6885 __ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \
6894 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6901 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6907 __ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6916 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
6924 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \
6930 __ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \
7031 __ai int8x8_t vget_low_s8(int8x16_t __p0) {
7032 int8x8_t __ret;
7037 __ai int8x8_t vget_low_s8(int8x16_t __p0) {
7039 int8x8_t __ret;
7230 __ret = (uint8x8_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
7238 __ret = (uint8x8_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
7247 __ret = (uint32x2_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
7255 __ret = (uint32x2_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
7264 __ret = (uint16x4_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
7272 __ret = (uint16x4_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
7279 __ai int8x8_t vhadd_s8(int8x8_t __p0, int8x8_t __p1) {
7280 int8x8_t __ret;
7281 __ret = (int8x8_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
7285 __ai int8x8_t vhadd_s8(int8x8_t __p0, int8x8_t __p1) {
7286 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
7287 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7288 int8x8_t __ret;
7289 __ret = (int8x8_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
7298 __ret = (int32x2_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
7306 __ret = (int32x2_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
7315 __ret = (int16x4_t) __builtin_neon_vhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
7323 __ret = (int16x4_t) __builtin_neon_vhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
7434 __ret = (uint8x8_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
7442 __ret = (uint8x8_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
7451 __ret = (uint32x2_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
7459 __ret = (uint32x2_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
7468 __ret = (uint16x4_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
7476 __ret = (uint16x4_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
7483 __ai int8x8_t vhsub_s8(int8x8_t __p0, int8x8_t __p1) {
7484 int8x8_t __ret;
7485 __ret = (int8x8_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
7489 __ai int8x8_t vhsub_s8(int8x8_t __p0, int8x8_t __p1) {
7490 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
7491 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
7492 int8x8_t __ret;
7493 __ret = (int8x8_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
7502 __ret = (int32x2_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
7510 __ret = (int32x2_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
7519 __ret = (int16x4_t) __builtin_neon_vhsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
7527 __ret = (int16x4_t) __builtin_neon_vhsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
7804 int8x8_t __ret; \
7805 __ret = (int8x8_t) __builtin_neon_vld1_v(__p0, 0); \
7810 int8x8_t __ret; \
7811 __ret = (int8x8_t) __builtin_neon_vld1_v(__p0, 0); \
8162 int8x8_t __ret; \
8163 __ret = (int8x8_t) __builtin_neon_vld1_dup_v(__p0, 0); \
8168 int8x8_t __ret; \
8169 __ret = (int8x8_t) __builtin_neon_vld1_dup_v(__p0, 0); \
8253 __ret = (poly8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 4); \
8261 __ret = (poly8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 4); \
8271 __ret = (poly16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 5); \
8279 __ret = (poly16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 5); \
8505 __ret = (uint8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 16); \
8513 __ret = (uint8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 16); \
8523 __ret = (uint32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 18); \
8531 __ret = (uint32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 18); \
8541 __ret = (uint64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
8548 __ret = (uint64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
8557 __ret = (uint16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 17); \
8565 __ret = (uint16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 17); \
8573 int8x8_t __s1 = __p1; \
8574 int8x8_t __ret; \
8575 __ret = (int8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 0); \
8580 int8x8_t __s1 = __p1; \
8581 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
8582 int8x8_t __ret; \
8583 __ret = (int8x8_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 0); \
8593 __ret = (float32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 9); \
8601 __ret = (float32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 9); \
8611 __ret = (float16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 8); \
8619 __ret = (float16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 8); \
8629 __ret = (int32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 2); \
8637 __ret = (int32x2_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 2); \
8647 __ret = (int64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
8654 __ret = (int64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
8663 __ret = (int16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 1); \
8671 __ret = (int16x4_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__rev1, __p2, 1); \
9247 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 4); \
9257 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 4); \
9269 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 5); \
9279 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 5); \
9445 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 16); \
9455 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 16); \
9467 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 18); \
9477 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 18); \
9489 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 17); \
9499 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 17); \
9511 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 0); \
9521 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 0); \
10217 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 4); \
10228 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 4); \
10241 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 5); \
10252 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 5); \
10433 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 16); \
10444 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 16); \
10457 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 18); \
10468 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 18); \
10481 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 17); \
10492 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 17); \
10505 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 0); \
10516 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 0); \
11251 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 4); \
11263 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 4); \
11277 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 5); \
11289 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 5); \
11485 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 16); \
11497 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 16); \
11511 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 18); \
11523 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 18); \
11537 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 17); \
11549 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 17); \
11563 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 0); \
11575 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 0); \
11811 __ret = (uint8x8_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
11819 __ret = (uint8x8_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
11828 __ret = (uint32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
11836 __ret = (uint32x2_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
11845 __ret = (uint16x4_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
11853 __ret = (uint16x4_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
11860 __ai int8x8_t vmax_s8(int8x8_t __p0, int8x8_t __p1) {
11861 int8x8_t __ret;
11862 __ret = (int8x8_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
11866 __ai int8x8_t vmax_s8(int8x8_t __p0, int8x8_t __p1) {
11867 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
11868 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
11869 int8x8_t __ret;
11870 __ret = (int8x8_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
11879 __ret = (float32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
11887 __ret = (float32x2_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
11896 __ret = (int32x2_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
11904 __ret = (int32x2_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
11913 __ret = (int16x4_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
11921 __ret = (int16x4_t) __builtin_neon_vmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
12049 __ret = (uint8x8_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
12057 __ret = (uint8x8_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
12066 __ret = (uint32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
12074 __ret = (uint32x2_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
12083 __ret = (uint16x4_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
12091 __ret = (uint16x4_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
12098 __ai int8x8_t vmin_s8(int8x8_t __p0, int8x8_t __p1) {
12099 int8x8_t __ret;
12100 __ret = (int8x8_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
12104 __ai int8x8_t vmin_s8(int8x8_t __p0, int8x8_t __p1) {
12105 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
12106 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12107 int8x8_t __ret;
12108 __ret = (int8x8_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
12117 __ret = (float32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
12125 __ret = (float32x2_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
12134 __ret = (int32x2_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
12142 __ret = (int32x2_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
12151 __ret = (int16x4_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
12159 __ret = (int16x4_t) __builtin_neon_vmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
12346 __ai int8x8_t vmla_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12347 int8x8_t __ret;
12352 __ai int8x8_t vmla_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
12353 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
12354 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
12355 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
12356 int8x8_t __ret;
13008 __ai int8x8_t vmls_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
13009 int8x8_t __ret;
13014 __ai int8x8_t vmls_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
13015 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
13016 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
13017 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
13018 int8x8_t __ret;
13761 __ai int8x8_t vmov_n_s8(int8_t __p0) {
13762 int8x8_t __ret;
13763 __ret = (int8x8_t) {__p0, __p0, __p0, __p0, __p0, __p0, __p0, __p0};
13767 __ai int8x8_t vmov_n_s8(int8_t __p0) {
13768 int8x8_t __ret;
13769 __ret = (int8x8_t) {__p0, __p0, __p0, __p0, __p0, __p0, __p0, __p0};
13854 __ret = (uint16x8_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 49);
13861 __ret = (uint16x8_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 49);
13867 __ret = (uint16x8_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 49);
13875 __ret = (uint64x2_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 51);
13882 __ret = (uint64x2_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 51);
13888 __ret = (uint64x2_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 51);
13896 __ret = (uint32x4_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 50);
13903 __ret = (uint32x4_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 50);
13909 __ret = (uint32x4_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 50);
13915 __ai int16x8_t vmovl_s8(int8x8_t __p0) {
13917 __ret = (int16x8_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 33);
13921 __ai int16x8_t vmovl_s8(int8x8_t __p0) {
13922 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
13924 __ret = (int16x8_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 33);
13928 __ai int16x8_t __noswap_vmovl_s8(int8x8_t __p0) {
13930 __ret = (int16x8_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 33);
13938 __ret = (int64x2_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 35);
13945 __ret = (int64x2_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 35);
13951 __ret = (int64x2_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 35);
13959 __ret = (int32x4_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 34);
13966 __ret = (int32x4_t) __builtin_neon_vmovl_v((int8x8_t)__rev0, 34);
13972 __ret = (int32x4_t) __builtin_neon_vmovl_v((int8x8_t)__p0, 34);
14083 __ai int8x8_t vmovn_s16(int16x8_t __p0) {
14084 int8x8_t __ret;
14085 __ret = (int8x8_t) __builtin_neon_vmovn_v((int8x16_t)__p0, 0);
14089 __ai int8x8_t vmovn_s16(int16x8_t __p0) {
14091 int8x8_t __ret;
14092 __ret = (int8x8_t) __builtin_neon_vmovn_v((int8x16_t)__rev0, 0);
14096 __ai int8x8_t __noswap_vmovn_s16(int16x8_t __p0) {
14097 int8x8_t __ret;
14098 __ret = (int8x8_t) __builtin_neon_vmovn_v((int8x16_t)__p0, 0);
14274 __ai int8x8_t vmul_s8(int8x8_t __p0, int8x8_t __p1) {
14275 int8x8_t __ret;
14280 __ai int8x8_t vmul_s8(int8x8_t __p0, int8x8_t __p1) {
14281 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
14282 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14283 int8x8_t __ret;
14344 __ret = (poly8x8_t) __builtin_neon_vmul_v((int8x8_t)__p0, (int8x8_t)__p1, 4);
14352 __ret = (poly8x8_t) __builtin_neon_vmul_v((int8x8_t)__rev0, (int8x8_t)__rev1, 4);
14748 __ret = (poly16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 37);
14756 int8x8_t)__rev0, (int8x8_t)__rev1, 37);
14762 __ret = (poly16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 37);
14770 __ret = (uint16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 49);
14778 __ret = (uint16x8_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 49);
14784 __ret = (uint16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 49);
14792 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 51);
14800 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 51);
14806 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 51);
14814 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 50);
14822 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 50);
14828 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 50);
14834 __ai int16x8_t vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14836 __ret = (int16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 33);
14840 __ai int16x8_t vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14841 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
14842 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
14844 __ret = (int16x8_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 33);
14848 __ai int16x8_t __noswap_vmull_s8(int8x8_t __p0, int8x8_t __p1) {
14850 __ret = (int16x8_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 33);
14858 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
14866 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 35);
14872 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
14880 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
14888 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 34);
14894 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
14986 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
14993 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
14999 __ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);
15007 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
15014 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
15020 __ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);
15028 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
15035 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
15041 __ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
15049 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
15056 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
15062 __ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
15244 __ai int8x8_t vmvn_s8(int8x8_t __p0) {
15245 int8x8_t __ret;
15250 __ai int8x8_t vmvn_s8(int8x8_t __p0) {
15251 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
15252 int8x8_t __ret;
15356 __ai int8x8_t vneg_s8(int8x8_t __p0) {
15357 int8x8_t __ret;
15362 __ai int8x8_t vneg_s8(int8x8_t __p0) {
15363 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
15364 int8x8_t __ret;
15621 __ai int8x8_t vorn_s8(int8x8_t __p0, int8x8_t __p1) {
15622 int8x8_t __ret;
15627 __ai int8x8_t vorn_s8(int8x8_t __p0, int8x8_t __p1) {
15628 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
15629 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15630 int8x8_t __ret;
15887 __ai int8x8_t vorr_s8(int8x8_t __p0, int8x8_t __p1) {
15888 int8x8_t __ret;
15893 __ai int8x8_t vorr_s8(int8x8_t __p0, int8x8_t __p1) {
15894 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
15895 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
15896 int8x8_t __ret;
16056 __ret = (uint16x4_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16064 __ret = (uint16x4_t) __builtin_neon_vpadal_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
16073 __ret = (uint64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
16080 __ret = (uint64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__rev1, 19);
16088 __ret = (uint32x2_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16096 __ret = (uint32x2_t) __builtin_neon_vpadal_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
16103 __ai int16x4_t vpadal_s8(int16x4_t __p0, int8x8_t __p1) {
16105 __ret = (int16x4_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16109 __ai int16x4_t vpadal_s8(int16x4_t __p0, int8x8_t __p1) {
16111 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16113 __ret = (int16x4_t) __builtin_neon_vpadal_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
16122 __ret = (int64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
16129 __ret = (int64x1_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__rev1, 3);
16137 __ret = (int32x2_t) __builtin_neon_vpadal_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16145 __ret = (int32x2_t) __builtin_neon_vpadal_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
16154 __ret = (uint8x8_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16162 __ret = (uint8x8_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
16171 __ret = (uint32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16179 __ret = (uint32x2_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
16188 __ret = (uint16x4_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16196 __ret = (uint16x4_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
16203 __ai int8x8_t vpadd_s8(int8x8_t __p0, int8x8_t __p1) {
16204 int8x8_t __ret;
16205 __ret = (int8x8_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16209 __ai int8x8_t vpadd_s8(int8x8_t __p0, int8x8_t __p1) {
16210 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
16211 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16212 int8x8_t __ret;
16213 __ret = (int8x8_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
16222 __ret = (float32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16230 __ret = (float32x2_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
16239 __ret = (int32x2_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16247 __ret = (int32x2_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
16256 __ret = (int16x4_t) __builtin_neon_vpadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16264 __ret = (int16x4_t) __builtin_neon_vpadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
16369 __ret = (uint16x4_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 17);
16376 __ret = (uint16x4_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 17);
16385 __ret = (uint64x1_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 19);
16392 __ret = (uint64x1_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 19);
16400 __ret = (uint32x2_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 18);
16407 __ret = (uint32x2_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 18);
16414 __ai int16x4_t vpaddl_s8(int8x8_t __p0) {
16416 __ret = (int16x4_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 1);
16420 __ai int16x4_t vpaddl_s8(int8x8_t __p0) {
16421 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
16423 __ret = (int16x4_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 1);
16432 __ret = (int64x1_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 3);
16439 __ret = (int64x1_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 3);
16447 __ret = (int32x2_t) __builtin_neon_vpaddl_v((int8x8_t)__p0, 2);
16454 __ret = (int32x2_t) __builtin_neon_vpaddl_v((int8x8_t)__rev0, 2);
16463 __ret = (uint8x8_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16471 __ret = (uint8x8_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
16480 __ret = (uint32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16488 __ret = (uint32x2_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
16497 __ret = (uint16x4_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16505 __ret = (uint16x4_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
16512 __ai int8x8_t vpmax_s8(int8x8_t __p0, int8x8_t __p1) {
16513 int8x8_t __ret;
16514 __ret = (int8x8_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16518 __ai int8x8_t vpmax_s8(int8x8_t __p0, int8x8_t __p1) {
16519 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
16520 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16521 int8x8_t __ret;
16522 __ret = (int8x8_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
16531 __ret = (float32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16539 __ret = (float32x2_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
16548 __ret = (int32x2_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16556 __ret = (int32x2_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
16565 __ret = (int16x4_t) __builtin_neon_vpmax_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16573 __ret = (int16x4_t) __builtin_neon_vpmax_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
16582 __ret = (uint8x8_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16590 __ret = (uint8x8_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
16599 __ret = (uint32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16607 __ret = (uint32x2_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
16616 __ret = (uint16x4_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16624 __ret = (uint16x4_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
16631 __ai int8x8_t vpmin_s8(int8x8_t __p0, int8x8_t __p1) {
16632 int8x8_t __ret;
16633 __ret = (int8x8_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
16637 __ai int8x8_t vpmin_s8(int8x8_t __p0, int8x8_t __p1) {
16638 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
16639 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
16640 int8x8_t __ret;
16641 __ret = (int8x8_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
16650 __ret = (float32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
16658 __ret = (float32x2_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
16667 __ret = (int32x2_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
16675 __ret = (int32x2_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
16684 __ret = (int16x4_t) __builtin_neon_vpmin_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
16692 __ret = (int16x4_t) __builtin_neon_vpmin_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
16747 __ai int8x8_t vqabs_s8(int8x8_t __p0) {
16748 int8x8_t __ret;
16749 __ret = (int8x8_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 0);
16753 __ai int8x8_t vqabs_s8(int8x8_t __p0) {
16754 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
16755 int8x8_t __ret;
16756 __ret = (int8x8_t) __builtin_neon_vqabs_v((int8x8_t)__rev0, 0);
16765 __ret = (int32x2_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 2);
16772 __ret = (int32x2_t) __builtin_neon_vqabs_v((int8x8_t)__rev0, 2);
16781 __ret = (int16x4_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 1);
16788 __ret = (int16x4_t) __builtin_neon_vqabs_v((int8x8_t)__rev0, 1);
16943 __ret = (uint8x8_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
16951 __ret = (uint8x8_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
16960 __ret = (uint32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
16968 __ret = (uint32x2_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
16977 __ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
16983 __ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
16991 __ret = (uint16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
16999 __ret = (uint16x4_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
17006 __ai int8x8_t vqadd_s8(int8x8_t __p0, int8x8_t __p1) {
17007 int8x8_t __ret;
17008 __ret = (int8x8_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
17012 __ai int8x8_t vqadd_s8(int8x8_t __p0, int8x8_t __p1) {
17013 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
17014 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
17015 int8x8_t __ret;
17016 __ret = (int8x8_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
17025 __ret = (int32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17033 __ret = (int32x2_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
17039 __ret = (int32x2_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17047 __ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
17053 __ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
17061 __ret = (int16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17069 __ret = (int16x4_t) __builtin_neon_vqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
17075 __ret = (int16x4_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17083 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17092 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 35);
17098 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17106 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17115 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 34);
17121 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17177 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17185 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17191 __ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17199 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17207 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17213 __ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17221 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17230 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 35);
17236 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 35);
17244 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17253 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 34);
17259 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 34);
17315 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17323 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17329 __ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);
17337 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17345 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17351 __ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);
17403 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17411 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
17417 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
17425 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17433 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
17439 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
17563 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
17570 __ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
17579 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
17586 __ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
17595 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
17603 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 35);
17609 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 35);
17617 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
17625 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)__rev1, 34);
17631 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)__p1, 34);
17681 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17688 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17694 __ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);
17702 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17709 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17715 __ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);
17826 __ai int8x8_t vqmovn_s16(int16x8_t __p0) {
17827 int8x8_t __ret;
17828 __ret = (int8x8_t) __builtin_neon_vqmovn_v((int8x16_t)__p0, 0);
17832 __ai int8x8_t vqmovn_s16(int16x8_t __p0) {
17834 int8x8_t __ret;
17835 __ret = (int8x8_t) __builtin_neon_vqmovn_v((int8x16_t)__rev0, 0);
17839 __ai int8x8_t __noswap_vqmovn_s16(int16x8_t __p0) {
17840 int8x8_t __ret;
17841 __ret = (int8x8_t) __builtin_neon_vqmovn_v((int8x16_t)__p0, 0);
17958 __ai int8x8_t vqneg_s8(int8x8_t __p0) {
17959 int8x8_t __ret;
17960 __ret = (int8x8_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 0);
17964 __ai int8x8_t vqneg_s8(int8x8_t __p0) {
17965 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
17966 int8x8_t __ret;
17967 __ret = (int8x8_t) __builtin_neon_vqneg_v((int8x8_t)__rev0, 0);
17976 __ret = (int32x2_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 2);
17983 __ret = (int32x2_t) __builtin_neon_vqneg_v((int8x8_t)__rev0, 2);
17992 __ret = (int16x4_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 1);
17999 __ret = (int16x4_t) __builtin_neon_vqneg_v((int8x8_t)__rev0, 1);
18052 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18060 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
18066 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18074 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18082 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
18088 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18212 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
18219 __ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);
18228 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
18235 __ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);
18378 __ai uint8x8_t vqrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18380 __ret = (uint8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
18384 __ai uint8x8_t vqrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18386 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18388 __ret = (uint8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
18397 __ret = (uint32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
18405 __ret = (uint32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
18414 __ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18420 __ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18428 __ret = (uint16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
18436 __ret = (uint16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
18443 __ai int8x8_t vqrshl_s8(int8x8_t __p0, int8x8_t __p1) {
18444 int8x8_t __ret;
18445 __ret = (int8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
18449 __ai int8x8_t vqrshl_s8(int8x8_t __p0, int8x8_t __p1) {
18450 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
18451 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18452 int8x8_t __ret;
18453 __ret = (int8x8_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
18462 __ret = (int32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18470 __ret = (int32x2_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
18479 __ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18485 __ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18493 __ret = (int16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18501 __ret = (int16x4_t) __builtin_neon_vqrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
18630 int8x8_t __ret; \
18631 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 0); \
18638 int8x8_t __ret; \
18639 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__rev0, __p1, 0); \
18645 int8x8_t __ret; \
18646 __ret = (int8x8_t) __builtin_neon_vqrshrn_n_v((int8x16_t)__s0, __p1, 0); \
18860 __ai uint8x8_t vqshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18862 __ret = (uint8x8_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
18866 __ai uint8x8_t vqshl_u8(uint8x8_t __p0, int8x8_t __p1) {
18868 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18870 __ret = (uint8x8_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
18879 __ret = (uint32x2_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
18887 __ret = (uint32x2_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
18896 __ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18902 __ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18910 __ret = (uint16x4_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
18918 __ret = (uint16x4_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
18925 __ai int8x8_t vqshl_s8(int8x8_t __p0, int8x8_t __p1) {
18926 int8x8_t __ret;
18927 __ret = (int8x8_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
18931 __ai int8x8_t vqshl_s8(int8x8_t __p0, int8x8_t __p1) {
18932 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
18933 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
18934 int8x8_t __ret;
18935 __ret = (int8x8_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
18944 __ret = (int32x2_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
18952 __ret = (int32x2_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
18961 __ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18967 __ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18975 __ret = (int16x4_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
18983 __ret = (int16x4_t) __builtin_neon_vqshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
19137 __ret = (uint8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 16); \
19145 __ret = (uint8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 16); \
19155 __ret = (uint32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 18); \
19163 __ret = (uint32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 18); \
19173 __ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
19180 __ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
19189 __ret = (uint16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 17); \
19197 __ret = (uint16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 17); \
19205 int8x8_t __s0 = __p0; \
19206 int8x8_t __ret; \
19207 __ret = (int8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 0); \
19212 int8x8_t __s0 = __p0; \
19213 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
19214 int8x8_t __ret; \
19215 __ret = (int8x8_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 0); \
19225 __ret = (int32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 2); \
19233 __ret = (int32x2_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 2); \
19243 __ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
19250 __ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
19259 __ret = (int16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 1); \
19267 __ret = (int16x4_t) __builtin_neon_vqshl_n_v((int8x8_t)__rev0, __p1, 1); \
19347 int8x8_t __s0 = __p0; \
19349 __ret = (uint8x8_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 16); \
19354 int8x8_t __s0 = __p0; \
19355 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
19357 __ret = (uint8x8_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 16); \
19367 __ret = (uint32x2_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 18); \
19375 __ret = (uint32x2_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 18); \
19385 __ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
19392 __ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
19401 __ret = (uint16x4_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 17); \
19409 __ret = (uint16x4_t) __builtin_neon_vqshlu_n_v((int8x8_t)__rev0, __p1, 17); \
19538 int8x8_t __ret; \
19539 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 0); \
19546 int8x8_t __ret; \
19547 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__rev0, __p1, 0); \
19553 int8x8_t __ret; \
19554 __ret = (int8x8_t) __builtin_neon_vqshrn_n_v((int8x16_t)__s0, __p1, 0); \
19780 __ret = (uint8x8_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
19788 __ret = (uint8x8_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
19797 __ret = (uint32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
19805 __ret = (uint32x2_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
19814 __ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19820 __ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19828 __ret = (uint16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
19836 __ret = (uint16x4_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
19843 __ai int8x8_t vqsub_s8(int8x8_t __p0, int8x8_t __p1) {
19844 int8x8_t __ret;
19845 __ret = (int8x8_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
19849 __ai int8x8_t vqsub_s8(int8x8_t __p0, int8x8_t __p1) {
19850 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
19851 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
19852 int8x8_t __ret;
19853 __ret = (int8x8_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
19862 __ret = (int32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
19870 __ret = (int32x2_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
19876 __ret = (int32x2_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
19884 __ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19890 __ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19898 __ret = (int16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
19906 __ret = (int16x4_t) __builtin_neon_vqsub_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
19912 __ret = (int16x4_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
20028 __ai int8x8_t vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
20029 int8x8_t __ret;
20030 __ret = (int8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
20034 __ai int8x8_t vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
20037 int8x8_t __ret;
20038 __ret = (int8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__rev0, (int8x16_t)__rev1, 0);
20042 __ai int8x8_t __noswap_vraddhn_s16(int16x8_t __p0, int16x8_t __p1) {
20043 int8x8_t __ret;
20044 __ret = (int8x8_t) __builtin_neon_vraddhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
20084 __ret = (uint32x2_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 18);
20091 __ret = (uint32x2_t) __builtin_neon_vrecpe_v((int8x8_t)__rev0, 18);
20100 __ret = (float32x2_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 9);
20107 __ret = (float32x2_t) __builtin_neon_vrecpe_v((int8x8_t)__rev0, 9);
20133 __ret = (float32x2_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
20141 __ret = (float32x2_t) __builtin_neon_vrecps_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
20228 __ai int8x8_t vrev16_s8(int8x8_t __p0) {
20229 int8x8_t __ret;
20234 __ai int8x8_t vrev16_s8(int8x8_t __p0) {
20235 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
20236 int8x8_t __ret;
20404 __ai int8x8_t vrev32_s8(int8x8_t __p0) {
20405 int8x8_t __ret;
20410 __ai int8x8_t vrev32_s8(int8x8_t __p0) {
20411 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
20412 int8x8_t __ret;
20660 __ai int8x8_t vrev64_s8(int8x8_t __p0) {
20661 int8x8_t __ret;
20666 __ai int8x8_t vrev64_s8(int8x8_t __p0) {
20667 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
20668 int8x8_t __ret;
20828 __ret = (uint8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
20836 __ret = (uint8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
20845 __ret = (uint32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
20853 __ret = (uint32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
20862 __ret = (uint16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
20870 __ret = (uint16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
20877 __ai int8x8_t vrhadd_s8(int8x8_t __p0, int8x8_t __p1) {
20878 int8x8_t __ret;
20879 __ret = (int8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
20883 __ai int8x8_t vrhadd_s8(int8x8_t __p0, int8x8_t __p1) {
20884 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
20885 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
20886 int8x8_t __ret;
20887 __ret = (int8x8_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
20896 __ret = (int32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
20904 __ret = (int32x2_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
20913 __ret = (int16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
20921 __ret = (int16x4_t) __builtin_neon_vrhadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
21064 __ai uint8x8_t vrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
21066 __ret = (uint8x8_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
21070 __ai uint8x8_t vrshl_u8(uint8x8_t __p0, int8x8_t __p1) {
21072 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
21074 __ret = (uint8x8_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
21083 __ret = (uint32x2_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
21091 __ret = (uint32x2_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
21100 __ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21106 __ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21114 __ret = (uint16x4_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
21122 __ret = (uint16x4_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
21129 __ai int8x8_t vrshl_s8(int8x8_t __p0, int8x8_t __p1) {
21130 int8x8_t __ret;
21131 __ret = (int8x8_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
21135 __ai int8x8_t vrshl_s8(int8x8_t __p0, int8x8_t __p1) {
21136 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
21137 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
21138 int8x8_t __ret;
21139 __ret = (int8x8_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
21148 __ret = (int32x2_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
21156 __ret = (int32x2_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
21165 __ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21171 __ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21179 __ret = (int16x4_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
21187 __ret = (int16x4_t) __builtin_neon_vrshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
21341 __ret = (uint8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 16); \
21349 __ret = (uint8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 16); \
21359 __ret = (uint32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 18); \
21367 __ret = (uint32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 18); \
21377 __ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
21384 __ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
21393 __ret = (uint16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 17); \
21401 __ret = (uint16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 17); \
21409 int8x8_t __s0 = __p0; \
21410 int8x8_t __ret; \
21411 __ret = (int8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 0); \
21416 int8x8_t __s0 = __p0; \
21417 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
21418 int8x8_t __ret; \
21419 __ret = (int8x8_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 0); \
21429 __ret = (int32x2_t) __builtin_neon_vrshr_n_v((int8x8_t
21437 __ret = (int32x2_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 2); \
21447 __ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
21454 __ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
21463 __ret = (int16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 1); \
21471 __ret = (int16x4_t) __builtin_neon_vrshr_n_v((int8x8_t)__rev0, __p1, 1); \
21600 int8x8_t __ret; \
21601 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 0); \
21608 int8x8_t __ret; \
21609 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__rev0, __p1, 0); \
21615 int8x8_t __ret; \
21616 __ret = (int8x8_t) __builtin_neon_vrshrn_n_v((int8x16_t)__s0, __p1, 0); \
21656 __ret = (uint32x2_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 18);
21663 __ret = (uint32x2_t) __builtin_neon_vrsqrte_v((int8x8_t)__rev0, 18);
21672 __ret = (float32x2_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 9);
21679 __ret = (float32x2_t) __builtin_neon_vrsqrte_v((int8x8_t)__rev0, 9);
21705 __ret = (float32x2_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
21713 __ret = (float32x2_t) __builtin_neon_vrsqrts_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
21892 __ret = (uint8x8_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 16); \
21902 __ret = (uint8x8_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 16); \
21913 __ret = (uint32x2_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 18); \
21923 __ret = (uint32x2_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 18); \
21934 __ret = (uint64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
21942 __ret = (uint64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
21952 __ret = (uint16x4_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 17); \
21962 __ret = (uint16x4_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 17); \
21970 int8x8_t __s0 = __p0; \
21971 int8x8_t __s1 = __p1; \
21972 int8x8_t __ret; \
21973 __ret = (int8x8_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 0); \
21978 int8x8_t __s0 = __p0; \
21979 int8x8_t __s1 = __p1; \
21980 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
21981 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
21982 int8x8_t __ret; \
21983 __ret = (int8x8_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 0); \
21994 __ret = (int32x2_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 2); \
22004 __ret = (int32x2_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 2); \
22015 __ret = (int64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
22023 __ret = (int64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
22033 __ret = (int16x4_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 1); \
22043 __ret = (int16x4_t) __builtin_neon_vrsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 1); \
22160 __ai int8x8_t vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22161 int8x8_t __ret;
22162 __ret = (int8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
22166 __ai int8x8_t vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22169 int8x8_t __ret;
22170 __ret = (int8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__rev0, (int8x16_t)__rev1, 0);
22174 __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
22175 int8x8_t __ret;
22176 __ret = (int8x8_t) __builtin_neon_vrsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
22186 __ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22195 __ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__rev1, __p2); \
22203 __ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22213 __ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22222 __ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \
22230 __ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22537 __ret = (uint8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22546 __ret = (uint8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__rev1, __p2); \
22554 __ret = (uint8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22564 __ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \
22573 __ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__rev1, __p2); \
22581 __ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \
22591 __ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22599 __ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22606 __ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22616 __ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22625 __ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \
22633 __ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22641 int8x8_t __s1 = __p1; \
22642 int8x8_t __ret; \
22643 __ret = (int8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22649 int8x8_t __s1 = __p1; \
22650 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
22651 int8x8_t __ret; \
22652 __ret = (int8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__rev1, __p2); \
22658 int8x8_t __s1 = __p1; \
22659 int8x8_t __ret; \
22660 __ret = (int8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \
22670 __ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__s1, __p2); \
22679 __ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__rev1, __p2); \
22687 __ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__s1, __p2); \
22697 __ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \
22706 __ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__rev1, __p2); \
22714 __ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \
22724 __ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22732 __ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22739 __ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
22749 __ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22758 __ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \
22766 __ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \
22908 __ai uint8x8_t vshl_u8(uint8x8_t __p0, int8x8_t __p1) {
22910 __ret = (uint8x8_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
22914 __ai uint8x8_t vshl_u8(uint8x8_t __p0, int8x8_t __p1) {
22916 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22918 __ret = (uint8x8_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
22927 __ret = (uint32x2_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
22935 __ret = (uint32x2_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
22944 __ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22950 __ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22958 __ret = (uint16x4_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
22966 __ret = (uint16x4_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
22973 __ai int8x8_t vshl_s8(int8x8_t __p0, int8x8_t __p1) {
22974 int8x8_t __ret;
22975 __ret = (int8x8_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
22979 __ai int8x8_t vshl_s8(int8x8_t __p0, int8x8_t __p1) {
22980 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
22981 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
22982 int8x8_t __ret;
22983 __ret = (int8x8_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
22992 __ret = (int32x2_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
23000 __ret = (int32x2_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
23009 __ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
23015 __ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
23023 __ret = (int16x4_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
23031 __ret = (int16x4_t) __builtin_neon_vshl_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
23185 __ret = (uint8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 16); \
23193 __ret = (uint8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 16); \
23203 __ret = (uint32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 18); \
23211 __ret = (uint32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 18); \
23221 __ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
23228 __ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
23237 __ret = (uint16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 17); \
23245 __ret = (uint16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 17); \
23253 int8x8_t __s0 = __p0; \
23254 int8x8_t __ret; \
23255 __ret = (int8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 0); \
23260 int8x8_t __s0 = __p0; \
23261 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
23262 int8x8_t __ret; \
23263 __ret = (int8x8_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 0); \
23273 __ret = (int32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 2); \
23281 __ret = (int32x2_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 2); \
23291 __ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
23298 __ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
23307 __ret = (int16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 1); \
23315 __ret = (int16x4_t) __builtin_neon_vshl_n_v((int8x8_t)__rev0, __p1, 1); \
23325 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 49); \
23333 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 49); \
23340 __ret = (uint16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 49); \
23349 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 51); \
23357 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 51); \
23364 __ret = (uint64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 51); \
23373 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 50); \
23381 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 50); \
23388 __ret = (uint32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 50); \
23395 int8x8_t __s0 = __p0; \
23397 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 33); \
23402 int8x8_t __s0 = __p0; \
23403 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
23405 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 33); \
23410 int8x8_t __s0 = __p0; \
23412 __ret = (int16x8_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 33); \
23421 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 35); \
23429 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 35); \
23436 __ret = (int64x2_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 35); \
23445 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 34); \
23453 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__rev0, __p1, 34); \
23460 __ret = (int32x4_t) __builtin_neon_vshll_n_v((int8x8_t)__s0, __p1, 34); \
23613 __ret = (uint8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 16); \
23621 __ret = (uint8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 16); \
23631 __ret = (uint32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 18); \
23639 __ret = (uint32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 18); \
23649 __ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
23656 __ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
23665 __ret = (uint16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 17); \
23673 __ret = (uint16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 17); \
23681 int8x8_t __s0 = __p0; \
23682 int8x8_t __ret; \
23683 __ret = (int8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 0); \
23688 int8x8_t __s0 = __p0; \
23689 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
23690 int8x8_t __ret; \
23691 __ret = (int8x8_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 0); \
23701 __ret = (int32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 2); \
23709 __ret = (int32x2_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 2); \
23719 __ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
23726 __ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
23735 __ret = (int16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 1); \
23743 __ret = (int16x4_t) __builtin_neon_vshr_n_v((int8x8_t)__rev0, __p1, 1); \
23872 int8x8_t __ret; \
23873 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 0); \
23880 int8x8_t __ret; \
23881 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__rev0, __p1, 0); \
23887 int8x8_t __ret; \
23888 __ret = (int8x8_t) __builtin_neon_vshrn_n_v((int8x16_t)__s0, __p1, 0); \
23898 __ret = (poly8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 4); \
23908 __ret = (poly8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 4); \
23919 __ret = (poly16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 5); \
23929 __ret = (poly16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 5); \
24150 __ret = (uint8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 16); \
24160 __ret = (uint8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 16); \
24171 __ret = (uint32x2_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 18); \
24181 __ret = (uint32x2_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 18); \
24192 __ret = (uint64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24200 __ret = (uint64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24210 __ret = (uint16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 17); \
24220 __ret = (uint16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 17); \
24228 int8x8_t __s0 = __p0; \
24229 int8x8_t __s1 = __p1; \
24230 int8x8_t __ret; \
24231 __ret = (int8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 0); \
24236 int8x8_t __s0 = __p0; \
24237 int8x8_t __s1 = __p1; \
24238 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
24239 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
24240 int8x8_t __ret; \
24241 __ret = (int8x8_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 0); \
24252 __ret = (int32x2_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 2); \
24262 __ret = (int32x2_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 2); \
24273 __ret = (int64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
24281 __ret = (int64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
24291 __ret = (int16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 1); \
24301 __ret = (int16x4_t) __builtin_neon_vsli_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 1); \
24480 __ret = (uint8x8_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 16); \
24490 __ret = (uint8x8_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 16); \
24501 __ret = (uint32x2_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 18); \
24511 __ret = (uint32x2_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 18); \
24522 __ret = (uint64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24530 __ret = (uint64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24540 __ret = (uint16x4_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 17); \
24550 __ret = (uint16x4_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 17); \
24558 int8x8_t __s0 = __p0; \
24559 int8x8_t __s1 = __p1; \
24560 int8x8_t __ret; \
24561 __ret = (int8x8_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 0); \
24566 int8x8_t __s0 = __p0; \
24567 int8x8_t __s1 = __p1; \
24568 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
24569 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
24570 int8x8_t __ret; \
24571 __ret = (int8x8_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 0); \
24582 __ret = (int32x2_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 2); \
24592 __ret = (int32x2_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 2); \
24603 __ret = (int64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
24611 __ret = (int64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
24621 __ret = (int16x4_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 1); \
24631 __ret = (int16x4_t) __builtin_neon_vsra_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 1); \
24642 __ret = (poly8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 4); \
24652 __ret = (poly8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 4); \
24663 __ret = (poly16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 5); \
24673 __ret = (poly16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 5); \
24894 __ret = (uint8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 16); \
24904 __ret = (uint8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 16); \
24915 __ret = (uint32x2_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 18); \
24925 __ret = (uint32x2_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 18); \
24936 __ret = (uint64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24944 __ret = (uint64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
24954 __ret = (uint16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 17); \
24964 __ret = (uint16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 17); \
24972 int8x8_t __s0 = __p0; \
24973 int8x8_t __s1 = __p1; \
24974 int8x8_t __ret; \
24975 __ret = (int8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 0); \
24980 int8x8_t __s0 = __p0; \
24981 int8x8_t __s1 = __p1; \
24982 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
24983 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
24984 int8x8_t __ret; \
24985 __ret = (int8x8_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 0); \
24996 __ret = (int32x2_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 2); \
25006 __ret = (int32x2_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 2); \
25017 __ret = (int64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25025 __ret = (int64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25035 __ret = (int16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 1); \
25045 __ret = (int16x4_t) __builtin_neon_vsri_n_v((int8x8_t)__rev0, (int8x8_t)__rev1, __p2, 1); \
25054 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 4); \
25060 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 4); \
25067 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 5); \
25073 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 5); \
25236 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 16); \
25242 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 16); \
25249 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 18); \
25255 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 18); \
25262 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 19); \
25267 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 19); \
25274 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 17); \
25280 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 17); \
25286 int8x8_t __s1 = __p1; \
25287 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 0); \
25291 int8x8_t __s1 = __p1; \
25292 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
25293 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 0); \
25300 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 9); \
25306 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 9); \
25313 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 8); \
25319 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 8); \
25326 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 2); \
25332 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 2); \
25339 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 3); \
25344 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 3); \
25351 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 1); \
25357 __builtin_neon_vst1_v(__p0, (int8x8_t)__rev1, 1); \
25364 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 4); \
25370 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 4); \
25377 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 5); \
25383 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 5); \
25546 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 16); \
25552 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 16); \
25559 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 18); \
25565 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 18); \
25572 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
25577 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
25584 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 17); \
25590 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 17); \
25596 int8x8_t __s1 = __p1; \
25597 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 0); \
25601 int8x8_t __s1 = __p1; \
25602 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
25603 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 0); \
25610 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 9); \
25616 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 9); \
25623 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 8); \
25629 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 8); \
25636 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 2); \
25642 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 2); \
25649 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
25654 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
25661 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 1); \
25667 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__rev1, __p2, 1); \
25674 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 4); \
25682 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 4); \
25689 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 5); \
25697 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 5); \
25854 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 16); \
25862 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 16); \
25869 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 18); \
25877 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 18); \
25884 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
25889 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
25896 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 17); \
25904 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 17); \
25911 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 0); \
25919 __builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 0); \
25998 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 4); \
26006 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 4); \
26013 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 5); \
26021 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 5); \
26133 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 16); \
26141 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 16); \
26148 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 18); \
26156 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 18); \
26163 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 17); \
26171 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 17); \
26178 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 0); \
26186 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 0); \
26253 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 4); \
26262 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 4); \
26269 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 5); \
26278 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 5); \
26445 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 16); \
26454 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 16); \
26461 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 18); \
26470 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 18); \
26477 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
26482 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
26489 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 17); \
26498 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 17); \
26505 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 0); \
26514 __builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 0); \
26597 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 4); \
26606 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 4); \
26613 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 5); \
26622 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 5); \
26741 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 16); \
26750 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 16); \
26757 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 18); \
26766 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 18); \
26773 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 17); \
26782 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 17); \
26789 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 0); \
26798 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 0); \
26869 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 4); \
26879 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 4); \
26886 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 5); \
26896 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 5); \
27073 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 16); \
27083 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 16); \
27090 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 18); \
27100 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 18); \
27107 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
27112 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
27119 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 17); \
27129 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 17); \
27136 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 0); \
27146 __builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 0); \
27233 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 4); \
27243 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 4); \
27250 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 5); \
27260 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 5); \
27386 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 16); \
27396 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 16); \
27403 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 18); \
27413 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 18); \
27420 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 17); \
27430 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 17); \
27437 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 0); \
27447 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 0); \
27738 __ai int8x8_t vsub_s8(int8x8_t __p0, int8x8_t __p1) {
27739 int8x8_t __ret;
27744 __ai int8x8_t vsub_s8(int8x8_t __p0, int8x8_t __p1) {
27745 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
27746 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
27747 int8x8_t __ret;
27930 __ai int8x8_t vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27931 int8x8_t __ret;
27932 __ret = (int8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
27936 __ai int8x8_t vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27939 int8x8_t __ret;
27940 __ret = (int8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__rev0, (int8x16_t)__rev1, 0);
27944 __ai int8x8_t __noswap_vsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
27945 int8x8_t __ret;
27946 __ret = (int8x8_t) __builtin_neon_vsubhn_v((int8x16_t)__p0, (int8x16_t)__p1, 0);
28003 __ai int16x8_t vsubl_s8(int8x8_t __p0, int8x8_t __p1) {
28009 __ai int16x8_t vsubl_s8(int8x8_t __p0, int8x8_t __p1) {
28010 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28011 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28105 __ai int16x8_t vsubw_s8(int16x8_t __p0, int8x8_t __p1) {
28111 __ai int16x8_t vsubw_s8(int16x8_t __p0, int8x8_t __p1) {
28113 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28158 __ret = (poly8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 4);
28166 __ret = (poly8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__rev0, (int8x8_t)__rev1, 4);
28175 __ret = (uint8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
28183 __ret = (uint8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
28190 __ai int8x8_t vtbl1_s8(int8x8_t __p0, int8x8_t __p1) {
28191 int8x8_t __ret;
28192 __ret = (int8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
28196 __ai int8x8_t vtbl1_s8(int8x8_t __p0, int8x8_t __p1) {
28197 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28198 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28199 int8x8_t __ret;
28200 __ret = (int8x8_t) __builtin_neon_vtbl1_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
28209 __ret = (poly8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 4);
28219 __ret = (poly8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev1, 4);
28228 __ret = (uint8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 16);
28238 __ret = (uint8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev1, 16);
28245 __ai int8x8_t vtbl2_s8(int8x8x2_t __p0, int8x8_t __p1) {
28246 int8x8_t __ret;
28247 __ret = (int8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__p0.val[0], (int8x8_t)__p0.val[1], (int8x8_t)__p1, 0);
28251 __ai int8x8_t vtbl2_s8(int8x8x2_t __p0, int8x8_t __p1) {
28255 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28256 int8x8_t __ret;
28257 __ret = (int8x8_t) __builtin_neon_vtbl2_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev1, 0);
28266 __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);
28277 __ret = (poly8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev1, 4);
28286 __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);
28297 __ret = (uint8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev1, 16);
28304 __ai int8x8_t vtbl3_s8(int8x8x3_t __p0, int8x8_t __p1) {
28305 int8x8_t __ret;
28306 __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);
28310 __ai int8x8_t vtbl3_s8(int8x8x3_t __p0, int8x8_t __p1) {
28315 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28316 int8x8_t __ret;
28317 __ret = (int8x8_t) __builtin_neon_vtbl3_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev1, 0);
28326 __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);
28338 __ret = (poly8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev0.val[3], (int8x8_t)__rev1, 4);
28347 __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);
28359 __ret = (uint8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev0.val[3], (int8x8_t)__rev1, 16);
28366 __ai int8x8_t vtbl4_s8(int8x8x4_t __p0, int8x8_t __p1) {
28367 int8x8_t __ret;
28368 __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);
28372 __ai int8x8_t vtbl4_s8(int8x8x4_t __p0, int8x8_t __p1) {
28378 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28379 int8x8_t __ret;
28380 __ret = (int8x8_t) __builtin_neon_vtbl4_v((int8x8_t)__rev0.val[0], (int8x8_t)__rev0.val[1], (int8x8_t)__rev0.val[2], (int8x8_t)__rev0.val[3], (int8x8_t)__rev1, 0);
28389 __ret = (poly8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 4);
28398 __ret = (poly8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 4);
28407 __ret = (uint8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 16);
28416 __ret = (uint8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 16);
28423 __ai int8x8_t vtbx1_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
28424 int8x8_t __ret;
28425 __ret = (int8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 0);
28429 __ai int8x8_t vtbx1_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
28430 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28431 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28432 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
28433 int8x8_t __ret;
28434 __ret = (int8x8_t) __builtin_neon_vtbx1_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 0);
28443 __ret = (poly8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 4);
28454 __ret = (poly8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev2, 4);
28463 __ret = (uint8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 16);
28474 __ret = (uint8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev2, 16);
28481 __ai int8x8_t vtbx2_s8(int8x8_t __p0, int8x8x2_t __p1, int8x8_t __p2) {
28482 int8x8_t __ret;
28483 __ret = (int8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__p0, (int8x8_t)__p1.val[0], (int8x8_t)__p1.val[1], (int8x8_t)__p2, 0);
28487 __ai int8x8_t vtbx2_s8(int8x8_t __p0, int8x8x2_t __p1, int8x8_t __p2) {
28488 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28492 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
28493 int8x8_t __ret;
28494 __ret = (int8x8_t) __builtin_neon_vtbx2_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev2, 0);
28503 __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);
28515 __ret = (poly8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev2, 4);
28524 __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);
28536 __ret = (uint8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev2, 16);
28543 __ai int8x8_t vtbx3_s8(int8x8_t __p0, int8x8x3_t __p1, int8x8_t __p2) {
28544 int8x8_t __ret;
28545 __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);
28549 __ai int8x8_t vtbx3_s8(int8x8_t __p0, int8x8x3_t __p1, int8x8_t __p2) {
28550 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28555 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
28556 int8x8_t __ret;
28557 __ret = (int8x8_t) __builtin_neon_vtbx3_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev2, 0);
28566 __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);
28579 __ret = (poly8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], (int8x8_t)__rev2, 4);
28588 __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);
28601 __ret = (uint8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], (int8x8_t)__rev2, 16);
28608 __ai int8x8_t vtbx4_s8(int8x8_t __p0, int8x8x4_t __p1, int8x8_t __p2) {
28609 int8x8_t __ret;
28610 __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);
28614 __ai int8x8_t vtbx4_s8(int8x8_t __p0, int8x8x4_t __p1, int8x8_t __p2) {
28615 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28621 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
28622 int8x8_t __ret;
28623 __ret = (int8x8_t) __builtin_neon_vtbx4_v((int8x8_t)__rev0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], (int8x8_t)__rev2, 0);
28632 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
28640 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 4);
28651 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
28659 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 5);
28841 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
28849 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 16);
28860 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
28868 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 18);
28879 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
28887 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 17);
28896 __ai int8x8x2_t vtrn_s8(int8x8_t __p0, int8x8_t __p1) {
28898 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
28902 __ai int8x8x2_t vtrn_s8(int8x8_t __p0, int8x8_t __p1) {
28903 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
28904 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
28906 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 0);
28917 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
28925 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 9);
28936 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
28944 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 2);
28955 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
28963 __builtin_neon_vtrn_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 1);
28974 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
28982 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
28991 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
28999 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
29144 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
29152 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
29161 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
29169 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
29178 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
29186 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
29193 __ai uint8x8_t vtst_s8(int8x8_t __p0, int8x8_t __p1) {
29195 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
29199 __ai uint8x8_t vtst_s8(int8x8_t __p0, int8x8_t __p1) {
29200 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
29201 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29203 __ret = (uint8x8_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
29212 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
29220 __ret = (uint32x2_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
29229 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
29237 __ret = (uint16x4_t) __builtin_neon_vtst_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
29246 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
29254 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 4);
29265 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
29273 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 5);
29455 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
29463 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 16);
29474 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
29482 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 18);
29493 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
29501 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 17);
29510 __ai int8x8x2_t vuzp_s8(int8x8_t __p0, int8x8_t __p1) {
29512 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
29516 __ai int8x8x2_t vuzp_s8(int8x8_t __p0, int8x8_t __p1) {
29517 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
29518 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29520 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 0);
29531 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
29539 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 9);
29550 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
29558 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 2);
29569 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
29577 __builtin_neon_vuzp_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 1);
29588 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 4);
29596 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 4);
29607 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 5);
29615 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 5);
29797 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 16);
29805 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 16);
29816 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 18);
29824 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 18);
29835 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 17);
29843 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 17);
29852 __ai int8x8x2_t vzip_s8(int8x8_t __p0, int8x8_t __p1) {
29854 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 0);
29858 __ai int8x8x2_t vzip_s8(int8x8_t __p0, int8x8_t __p1) {
29859 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
29860 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
29862 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 0);
29873 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 9);
29881 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 9);
29892 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 2);
29900 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 2);
29911 __builtin_neon_vzip_v(&__ret, (int8x8_t)__p0, (int8x8_t)__p1, 1);
29919 __builtin_neon_vzip_v(&__ret, (int8x8_t)__rev0, (int8x8_t)__rev1, 1);
29999 __ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
30005 __ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
30153 __ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
30159 __ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
32155 __ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
32161 __ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
32309 __ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
32315 __ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
32463 __ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
32469 __ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
32617 __ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
32623 __ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
32701 __ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
32702 int8x8_t __ret;
32703 __ret = (int8x8_t
32707 __ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
32708 int8x8_t __ret;
32709 __ret = (int8x8_t)(__p0);
32715 __ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
32716 int8x8_t __ret;
32717 __ret = (int8x8_t)(__p0);
32721 __ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
32722 int8x8_t __ret;
32723 __ret = (int8x8_t)(__p0);
32729 __ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
32730 int8x8_t __ret;
32731 __ret = (int8x8_t)(__p0);
32735 __ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
32736 int8x8_t __ret;
32737 __ret = (int8x8_t)(__p0);
32743 __ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
32744 int8x8_t __ret;
32745 __ret = (int8x8_t)(__p0);
32749 __ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
32750 int8x8_t __ret;
32751 __ret = (int8x8_t)(__p0);
32757 __ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
32758 int8x8_t __ret;
32759 __ret = (int8x8_t)(__p0);
32763 __ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
32764 int8x8_t __ret;
32765 __ret = (int8x8_t)(__p0);
32771 __ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
32772 int8x8_t __ret;
32773 __ret = (int8x8_t)(__p0);
32777 __ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
32778 int8x8_t __ret;
32779 __ret = (int8x8_t)(__p0);
32785 __ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
32786 int8x8_t __ret;
32787 __ret = (int8x8_t)(__p0);
32791 __ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
32792 int8x8_t __ret;
32793 __ret = (int8x8_t)(__p0);
32799 __ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
32800 int8x8_t __ret;
32801 __ret = (int8x8_t)(__p0);
32805 __ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
32806 int8x8_t __ret;
32807 __ret = (int8x8_t)(__p0);
32813 __ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
32814 int8x8_t __ret;
32815 __ret = (int8x8_t)(__p0);
32819 __ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
32820 int8x8_t __ret;
32821 __ret = (int8x8_t)(__p0);
32827 __ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
32828 int8x8_t __ret;
32829 __ret = (int8x8_t)(__p0);
32833 __ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
32834 int8x8_t __ret;
32835 __ret = (int8x8_t)(__p0);
32841 __ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
32842 int8x8_t __ret;
32843 __ret = (int8x8_t)(__p0);
32847 __ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
32848 int8x8_t __ret;
32849 __ret = (int8x8_t)(__p0);
32939 __ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
32945 __ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
33093 __ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
33099 __ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
33247 __ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
33253 __ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
33401 __ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
33407 __ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
33555 __ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
33561 __ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
33645 __ret = (int32x2_t) __builtin_neon_vcvta_s32_v((int8x8_t)__p0, 2);
33652 __ret = (int32x2_t) __builtin_neon_vcvta_s32_v((int8x8_t)__rev0, 2);
33677 __ret = (uint32x2_t) __builtin_neon_vcvta_u32_v((int8x8_t)__p0, 18);
33684 __ret = (uint32x2_t) __builtin_neon_vcvta_u32_v((int8x8_t)__rev0, 18);
33709 __ret = (int32x2_t) __builtin_neon_vcvtm_s32_v((int8x8_t)__p0, 2);
33716 __ret = (int32x2_t) __builtin_neon_vcvtm_s32_v((int8x8_t)__rev0, 2);
33741 __ret = (uint32x2_t) __builtin_neon_vcvtm_u32_v((int8x8_t)__p0, 18);
33748 __ret = (uint32x2_t) __builtin_neon_vcvtm_u32_v((int8x8_t)__rev0, 18);
33773 __ret = (int32x2_t) __builtin_neon_vcvtn_s32_v((int8x8_t)__p0, 2);
33780 __ret = (int32x2_t) __builtin_neon_vcvtn_s32_v((int8x8_t)__rev0, 2);
33805 __ret = (uint32x2_t) __builtin_neon_vcvtn_u32_v((int8x8_t)__p0, 18);
33812 __ret = (uint32x2_t) __builtin_neon_vcvtn_u32_v((int8x8_t)__rev0, 18);
33837 __ret = (int32x2_t) __builtin_neon_vcvtp_s32_v((int8x8_t)__p0, 2);
33844 __ret = (int32x2_t) __builtin_neon_vcvtp_s32_v((int8x8_t)__rev0, 2);
33869 __ret = (uint32x2_t) __builtin_neon_vcvtp_u32_v((int8x8_t)__p0, 18);
33876 __ret = (uint32x2_t) __builtin_neon_vcvtp_u32_v((int8x8_t)__rev0, 18);
33903 __ret = (float32x2_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 9);
33910 __ret = (float32x2_t) __builtin_neon_vrnd_v((int8x8_t)__rev0, 9);
33935 __ret = (float32x2_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 9);
33942 __ret = (float32x2_t) __builtin_neon_vrnda_v((int8x8_t)__rev0, 9);
33967 __ret = (float32x2_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 9);
33974 __ret = (float32x2_t) __builtin_neon_vrndm_v((int8x8_t)__rev0, 9);
33999 __ret = (float32x2_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 9);
34006 __ret = (float32x2_t) __builtin_neon_vrndn_v((int8x8_t)__rev0, 9);
34031 __ret = (float32x2_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 9);
34038 __ret = (float32x2_t) __builtin_neon_vrndp_v((int8x8_t)__rev0, 9);
34063 __ret = (float32x2_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 9);
34070 __ret = (float32x2_t) __builtin_neon_vrndx_v((int8x8_t)__rev0, 9);
34098 __ret = (float32x2_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
34106 __ret = (float32x2_t) __builtin_neon_vmaxnm_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
34132 __ret = (float32x2_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
34140 __ret = (float32x2_t) __builtin_neon_vminnm_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
34167 __ret = (int64x1_t) __builtin_neon_vcvta_s64_v((int8x8_t)__p0, 3);
34173 __ret = (int64x1_t) __builtin_neon_vcvta_s64_v((int8x8_t)__p0, 3);
34197 __ret = (uint64x1_t) __builtin_neon_vcvta_u64_v((int8x8_t)__p0, 19);
34203 __ret = (uint64x1_t) __builtin_neon_vcvta_u64_v((int8x8_t)__p0, 19);
34227 __ret = (int64x1_t) __builtin_neon_vcvtm_s64_v((int8x8_t)__p0, 3);
34233 __ret = (int64x1_t) __builtin_neon_vcvtm_s64_v((int8x8_t)__p0, 3);
34257 __ret = (uint64x1_t) __builtin_neon_vcvtm_u64_v((int8x8_t)__p0, 19);
34263 __ret = (uint64x1_t) __builtin_neon_vcvtm_u64_v((int8x8_t)__p0, 19);
34287 __ret = (int64x1_t) __builtin_neon_vcvtn_s64_v((int8x8_t)__p0, 3);
34293 __ret = (int64x1_t) __builtin_neon_vcvtn_s64_v((int8x8_t)__p0, 3);
34317 __ret = (uint64x1_t) __builtin_neon_vcvtn_u64_v((int8x8_t)__p0, 19);
34323 __ret = (uint64x1_t) __builtin_neon_vcvtn_u64_v((int8x8_t)__p0, 19);
34347 __ret = (int64x1_t) __builtin_neon_vcvtp_s64_v((int8x8_t)__p0, 3);
34353 __ret = (int64x1_t) __builtin_neon_vcvtp_s64_v((int8x8_t)__p0, 3);
34377 __ret = (uint64x1_t) __builtin_neon_vcvtp_u64_v((int8x8_t)__p0, 19);
34383 __ret = (uint64x1_t) __builtin_neon_vcvtp_u64_v((int8x8_t)__p0, 19);
34473 __ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
34479 __ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
34655 __ai poly64x1_t vreinterpret_p64_s8(int8x8_t __p0) {
34661 __ai poly64x1_t vreinterpret_p64_s8(int8x8_t __p0) {
34837 __ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
34843 __ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
37959 __ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
37965 __ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
38141 __ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
38147 __ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
38323 __ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
38329 __ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
38505 __ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
38511 __ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
38603 __ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
38604 int8x8_t __ret;
38605 __ret = (int8x8_t)(__p0);
38609 __ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
38610 int8x8_t __ret;
38611 __ret = (int8x8_t)(__p0);
38617 __ai int8x8_t vreinterpret_s8_p64(poly64x1_t __p0) {
38618 int8x8_t __ret;
38619 __ret = (int8x8_t)(__p0);
38623 __ai int8x8_t vreinterpret_s8_p64(poly64x1_t __p0) {
38624 int8x8_t __ret;
38625 __ret = (int8x8_t)(__p0);
38631 __ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
38632 int8x8_t __ret;
38633 __ret = (int8x8_t)(__p0);
38637 __ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
38638 int8x8_t __ret;
38639 __ret = (int8x8_t)(__p0);
38645 __ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
38646 int8x8_t __ret;
38647 __ret = (int8x8_t)(__p0);
38651 __ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
38652 int8x8_t __ret;
38653 __ret = (int8x8_t)(__p0);
38659 __ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
38660 int8x8_t __ret;
38661 __ret = (int8x8_t)(__p0);
38665 __ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
38666 int8x8_t __ret;
38667 __ret = (int8x8_t)(__p0);
38673 __ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
38674 int8x8_t __ret;
38675 __ret = (int8x8_t)(__p0);
38679 __ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
38680 int8x8_t __ret;
38681 __ret = (int8x8_t)(__p0);
38687 __ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
38688 int8x8_t __ret;
38689 __ret = (int8x8_t)(__p0);
38693 __ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
38694 int8x8_t __ret;
38695 __ret = (int8x8_t)(__p0);
38701 __ai int8x8_t vreinterpret_s8_f64(float64x1_t __p0) {
38702 int8x8_t __ret;
38703 __ret = (int8x8_t)(__p0);
38707 __ai int8x8_t vreinterpret_s8_f64(float64x1_t __p0) {
38708 int8x8_t __ret;
38709 __ret = (int8x8_t)(__p0);
38715 __ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
38716 int8x8_t __ret;
38717 __ret = (int8x8_t)(__p0);
38721 __ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
38722 int8x8_t __ret;
38723 __ret = (int8x8_t)(__p0);
38729 __ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
38730 int8x8_t __ret;
38731 __ret = (int8x8_t)(__p0);
38735 __ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
38736 int8x8_t __ret;
38737 __ret = (int8x8_t)(__p0);
38743 __ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
38744 int8x8_t __ret;
38745 __ret = (int8x8_t)(__p0);
38749 __ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
38750 int8x8_t __ret;
38751 __ret = (int8x8_t)(__p0);
38757 __ai int8x8_t
38758 int8x8_t __ret;
38759 __ret = (int8x8_t)(__p0);
38763 __ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
38764 int8x8_t __ret;
38765 __ret = (int8x8_t)(__p0);
38771 __ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
38772 int8x8_t __ret;
38773 __ret = (int8x8_t)(__p0);
38777 __ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
38778 int8x8_t __ret;
38779 __ret = (int8x8_t)(__p0);
38883 __ai float64x1_t vreinterpret_f64_s8(int8x8_t __p0) {
38889 __ai float64x1_t vreinterpret_f64_s8(int8x8_t __p0) {
39065 __ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
39071 __ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
39247 __ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
39253 __ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
39429 __ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
39435 __ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
39611 __ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
39617 __ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
39793 __ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
39799 __ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
39897 __ret = (float64x1_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 10);
39903 __ret = (float64x1_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 10);
39927 __ret = (float64x1_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 10);
39933 __ret = (float64x1_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 10);
39973 __ret = (float64x1_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 10);
39979 __ret = (float64x1_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 10);
39987 __ret = (float32x2_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 9);
39994 __ret = (float32x2_t) __builtin_neon_vrndi_v((int8x8_t)__rev0, 9);
40019 __ret = (float64x1_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 10);
40025 __ret = (float64x1_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 10);
40049 __ret = (float64x1_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 10);
40055 __ret = (float64x1_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 10);
40079 __ret = (float64x1_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 10);
40085 __ret = (float64x1_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 10);
40109 __ret = (float64x1_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 10);
40115 __ret = (float64x1_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 10);
40142 __ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40148 __ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40173 __ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40179 __ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40977 __ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
40983 __ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
41051 __ret = (float64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 10);
41057 __ret = (float64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 10);
41065 __ret = (int64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 3);
41071 __ret = (int64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 3);
41240 __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
41246 __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
41247 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
41350 __ret = (uint16_t) __builtin_neon_vaddlv_u8((int8x8_t)__p0);
41357 __ret = (uint16_t) __builtin_neon_vaddlv_u8((int8x8_t)__rev0);
41365 __ret = (uint64_t) __builtin_neon_vaddlv_u32((int8x8_t)__p0);
41372 __ret = (uint64_t) __builtin_neon_vaddlv_u32((int8x8_t)__rev0);
41380 __ret = (uint32_t) __builtin_neon_vaddlv_u16((int8x8_t)__p0);
41387 __ret = (uint32_t) __builtin_neon_vaddlv_u16((int8x8_t)__rev0);
41393 __ai int16_t vaddlv_s8(int8x8_t __p0) {
41395 __ret = (int16_t) __builtin_neon_vaddlv_s8((int8x8_t)__p0);
41399 __ai int16_t vaddlv_s8(int8x8_t __p0) {
41400 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
41402 __ret = (int16_t) __builtin_neon_vaddlv_s8((int8x8_t)__rev0);
41410 __ret = (int64_t) __builtin_neon_vaddlv_s32((int8x8_t)__p0);
41417 __ret = (int64_t) __builtin_neon_vaddlv_s32((int8x8_t)__rev0);
41425 __ret = (int32_t) __builtin_neon_vaddlv_s16((int8x8_t)__p0);
41432 __ret = (int32_t) __builtin_neon_vaddlv_s16((int8x8_t)__rev0);
41590 __ret = (uint8_t) __builtin_neon_vaddv_u8((int8x8_t)__p0);
41597 int8x8_t)__rev0);
41605 __ret = (uint32_t) __builtin_neon_vaddv_u32((int8x8_t)__p0);
41612 __ret = (uint32_t) __builtin_neon_vaddv_u32((int8x8_t)__rev0);
41620 __ret = (uint16_t) __builtin_neon_vaddv_u16((int8x8_t)__p0);
41627 __ret = (uint16_t) __builtin_neon_vaddv_u16((int8x8_t)__rev0);
41633 __ai int8_t vaddv_s8(int8x8_t __p0) {
41635 __ret = (int8_t) __builtin_neon_vaddv_s8((int8x8_t)__p0);
41639 __ai int8_t vaddv_s8(int8x8_t __p0) {
41640 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
41642 __ret = (int8_t) __builtin_neon_vaddv_s8((int8x8_t)__rev0);
41650 __ret = (float32_t) __builtin_neon_vaddv_f32((int8x8_t)__p0);
41657 __ret = (float32_t) __builtin_neon_vaddv_f32((int8x8_t)__rev0);
41665 __ret = (int32_t) __builtin_neon_vaddv_s32((int8x8_t)__p0);
41672 __ret = (int32_t) __builtin_neon_vaddv_s32((int8x8_t)__rev0);
41680 __ret = (int16_t) __builtin_neon_vaddv_s16((int8x8_t)__p0);
41687 __ret = (int16_t) __builtin_neon_vaddv_s16((int8x8_t)__rev0);
41695 __ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
41701 __ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
41745 __ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
41751 __ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
41776 __ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41782 __ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41835 __ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41841 __ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41894 __ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41900 __ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41953 __ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
41959 __ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
42175 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 16);
42182 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 16);
42191 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42197 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42205 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 17);
42212 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 17);
42429 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 16);
42436 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 16);
42445 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 18);
42452 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 18);
42461 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42467 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42475 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 17);
42482 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 17);
42489 __ai uint8x8_t vceqz_s8(int8x8_t __p0) {
42491 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 16);
42495 __ai uint8x8_t vceqz_s8(int8x8_t __p0) {
42496 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
42498 __ret = (uint8x8_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 16);
42507 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42513 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42521 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 18);
42528 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 18);
42537 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 18);
42544 __ret = (uint32x2_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 18);
42553 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42559 __ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
42567 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 17);
42574 __ret = (uint16x4_t) __builtin_neon_vceqz_v((int8x8_t)__rev0, 17);
42882 __ai uint8x8_t vcgez_s8(int8x8_t __p0) {
42884 __ret = (uint8x8_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 16);
42888 __ai uint8x8_t vcgez_s8(int8x8_t __p0) {
42889 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
42891 __ret = (uint8x8_t) __builtin_neon_vcgez_v((int8x8_t)__rev0, 16);
42900 __ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
42906 __ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
42914 __ret = (uint32x2_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 18);
42921 __ret = (uint32x2_t) __builtin_neon_vcgez_v((int8x8_t)__rev0, 18);
42930 __ret = (uint32x2_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 18);
42937 __ret = (uint32x2_t) __builtin_neon_vcgez_v((int8x8_t)__rev0, 18);
42946 __ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
42952 __ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
42960 __ret = (uint16x4_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 17);
42967 __ret = (uint16x4_t) __builtin_neon_vcgez_v((int8x8_t)__rev0, 17);
43261 __ai uint8x8_t vcgtz_s8(int8x8_t __p0) {
43263 __ret = (uint8x8_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 16);
43267 __ai uint8x8_t vcgtz_s8(int8x8_t __p0) {
43268 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
43270 __ret = (uint8x8_t) __builtin_neon_vcgtz_v((int8x8_t)__rev0, 16);
43279 __ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
43285 __ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
43293 __ret = (uint32x2_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 18);
43300 __ret = (uint32x2_t) __builtin_neon_vcgtz_v((int8x8_t)__rev0, 18);
43309 __ret = (uint32x2_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 18);
43316 __ret = (uint32x2_t) __builtin_neon_vcgtz_v((int8x8_t)__rev0, 18);
43325 int8x8_t)__p0, 19);
43331 __ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
43339 __ret = (uint16x4_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 17);
43346 __ret = (uint16x4_t) __builtin_neon_vcgtz_v((int8x8_t)__rev0, 17);
43640 __ai uint8x8_t vclez_s8(int8x8_t __p0) {
43642 __ret = (uint8x8_t) __builtin_neon_vclez_v((int8x8_t)__p0, 16);
43646 __ai uint8x8_t vclez_s8(int8x8_t __p0) {
43647 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
43649 __ret = (uint8x8_t) __builtin_neon_vclez_v((int8x8_t)__rev0, 16);
43658 __ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
43664 __ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
43672 __ret = (uint32x2_t) __builtin_neon_vclez_v((int8x8_t)__p0, 18);
43679 __ret = (uint32x2_t) __builtin_neon_vclez_v((int8x8_t)__rev0, 18);
43688 __ret = (uint32x2_t) __builtin_neon_vclez_v((int8x8_t)__p0, 18);
43695 __ret = (uint32x2_t) __builtin_neon_vclez_v((int8x8_t)__rev0, 18);
43704 __ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
43710 __ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
43718 __ret = (uint16x4_t) __builtin_neon_vclez_v((int8x8_t)__p0, 17);
43725 __ret = (uint16x4_t) __builtin_neon_vclez_v((int8x8_t)__rev0, 17);
44019 __ai uint8x8_t vcltz_s8(int8x8_t __p0) {
44021 __ret = (uint8x8_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 16);
44025 __ai uint8x8_t vcltz_s8(int8x8_t __p0) {
44026 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
44028 __ret = (uint8x8_t) __builtin_neon_vcltz_v((int8x8_t)__rev0, 16);
44037 __ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
44043 __ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
44051 __ret = (uint32x2_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 18);
44058 __ret = (uint32x2_t) __builtin_neon_vcltz_v((int8x8_t)__rev0, 18);
44067 __ret = (uint32x2_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 18);
44074 __ret = (uint32x2_t) __builtin_neon_vcltz_v((int8x8_t)__rev0, 18);
44083 __ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
44089 __ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
44097 __ret = (uint16x4_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 17);
44104 __ret = (uint16x4_t) __builtin_neon_vcltz_v((int8x8_t)__rev0, 17);
44310 int8x8_t __s2_12 = __p2_12; \
44318 int8x8_t __s2_13 = __p2_13; \
44320 int8x8_t __rev2_13; __rev2_13 = __builtin_shufflevector(__s2_13, __s2_13, 7, 6, 5, 4, 3, 2, 1, 0); \
44536 int8x8_t __s0_34 = __p0_34; \
44537 int8x8_t __s2_34 = __p2_34; \
44538 int8x8_t __ret_34; \
44544 int8x8_t __s0_35 = __p0_35; \
44545 int8x8_t __s2_35 = __p2_35; \
44546 int8x8_t __rev0_35; __rev0_35 = __builtin_shufflevector(__s0_35, __s0_35, 7, 6, 5, 4, 3, 2, 1, 0); \
44547 int8x8_t __rev2_35; __rev2_35 = __builtin_shufflevector(__s2_35, __s2_35, 7, 6, 5, 4, 3, 2, 1, 0); \
44548 int8x8_t __ret_35; \
44993 int8x8_t __s0_78 = __p0_78; \
44995 int8x8_t __ret_78; \
45001 int8x8_t __s0_79 = __p0_79; \
45003 int8x8_t __rev0_79; __rev0_79 = __builtin_shufflevector(__s0_79, __s0_79, 7, 6, 5, 4, 3, 2, 1, 0); \
45005 int8x8_t __ret_79; \
45234 __ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 19);
45240 __ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 19);
45248 __ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 3);
45254 __ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 3);
45262 __ret = (float64x2_t) __builtin_neon_vcvt_f64_f32((int8x8_t)__p0, 42);
45269 __ret = (float64x2_t) __builtin_neon_vcvt_f64_f32((int8x8_t)__rev0, 42);
45275 __ret = (float64x2_t) __builtin_neon_vcvt_f64_f32((int8x8_t)__p0, 42);
45418 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
45425 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
45434 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
45441 __ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
45516 __ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
45523 __ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
45582 __ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
45589 __ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
45657 __ret = (int64x1_t) __builtin_neon_vcvt_s64_v((int8x8_t)__p0, 3);
45663 __ret = (int64x1_t) __builtin_neon_vcvt_s64_v((int8x8_t)__p0, 3);
45715 __ret = (uint64x1_t) __builtin_neon_vcvt_u64_v((int8x8_t)__p0, 19);
45721 __ret = (uint64x1_t) __builtin_neon_vcvt_u64_v((int8x8_t)__p0, 19);
46071 __ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46079 __ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46088 __ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46096 __ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46105 __ret = (uint8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46113 __ret = (uint8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46122 __ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \
46130 __ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \
46139 __ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46146 __ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46155 __ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46163 __ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46170 int8x8_t __s0 = __p0; \
46172 __ret = (int8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \
46177 int8x8_t __s0 = __p0; \
46178 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
46180 __ret = (int8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \
46189 __ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \
46196 __ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \
46205 __ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__s0, __p1); \
46213 __ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__rev0, __p1); \
46222 __ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \
46230 __ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \
46239 __ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46246 __ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
46255 __ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \
46263 __ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \
46953 int8x8_t __ret; \
46961 int8x8_t __ret; \
47137 __ret = (poly64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
47145 __ret = (poly64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
47197 __ret = (float64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
47205 __ret = (float64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
47236 __ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47242 __ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47253 __ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \
47262 __ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \
47270 __ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \
47281 __ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__s2, __p3); \
47291 __ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__rev2, __p3); \
47299 __ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__s2, __p3); \
47310 __ret = (float64x2_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__s0, (int8x16_t)__s1, (int8x8_t)__s2, __p3, 42); \
47321 __ret = (float64x2_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__rev0, (int8x16_t)__rev1, (int8x8_t)__s2, __p3, 42); \
47330 __ret = (float64x2_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__s0, (int8x16_t)__s1, (int8x8_t)__s2, __p3, 42); \
47341 __ret = (float32x4_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__s0, (int8x16_t)__s1, (int8x8_t)__s2, __p3, 41); \
47353 __ret = (float32x4_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__rev0, (int8x16_t)__rev1, (int8x8_t)__rev2, __p3, 41); \
47362 __ret = (float32x4_t) __builtin_neon_vfmaq_lane_v((int8x16_t)__s0, (int8x16_t)__s1, (int8x8_t)__s2, __p3, 41); \
47373 __ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
47382 __ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
47390 __ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
47401 __ret = (float32x2_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 9); \
47413 __ret = (float32x2_t) __builtin_neon_vfma_lane_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, __p3, 9); \
47422 __ret = (float32x2_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 9); \
47555 __ret = (float64x1_t) __builtin_neon_vfma_laneq_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x16_t)__s2, __p3, 10); \
47565 __ret = (float64x1_t) __builtin_neon_vfma_laneq_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x16_t)__rev2, __p3, 10); \
47573 __ret = (float64x1_t) __builtin_neon_vfma_laneq_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x16_t)__s2, __p3, 10); \
47584 __ret = (float32x2_t) __builtin_neon_vfma_laneq_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x16_t)__s2, __p3, 9); \
47596 __ret = (float32x2_t) __builtin_neon_vfma_laneq_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x16_t)__rev2, __p3, 9); \
47605 __ret = (float32x2_t) __builtin_neon_vfma_laneq_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x16_t)__s2, __p3, 9); \
47710 __ret = (float64x1_t) __builtin_neon_vfms_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47716 __ret = (float64x1_t) __builtin_neon_vfms_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
47724 __ret = (float32x2_t) __builtin_neon_vfms_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
47733 __ret = (float32x2_t) __builtin_neon_vfms_v((int8x8_t)__rev0, (int8x8_t)__rev1, (int8x8_t)__rev2, 9);
47739 __ret = (float32x2_t) __builtin_neon_vfms_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 9);
48101 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48108 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48114 __ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
48169 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48176 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48182 __ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
48337 __ret = (poly64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
48344 __ret = (poly64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
48389 __ret = (float64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
48396 __ret = (float64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
50231 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
50238 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
50401 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
50408 __builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
50829 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
50836 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
51013 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
51020 __builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
51459 int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
51466 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
51657 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
51664 __builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
51735 __ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
51741 __ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
51779 __ret = (float32_t) __builtin_neon_vmaxnmv_f32((int8x8_t)__p0);
51786 __ret = (float32_t) __builtin_neon_vmaxnmv_f32((int8x8_t)__rev0);
51914 __ret = (uint8_t) __builtin_neon_vmaxv_u8((int8x8_t)__p0);
51921 __ret = (uint8_t) __builtin_neon_vmaxv_u8((int8x8_t)__rev0);
51929 __ret = (uint32_t) __builtin_neon_vmaxv_u32((int8x8_t)__p0);
51936 __ret = (uint32_t) __builtin_neon_vmaxv_u32((int8x8_t)__rev0);
51944 __ret = (uint16_t) __builtin_neon_vmaxv_u16((int8x8_t)__p0);
51951 __ret = (uint16_t) __builtin_neon_vmaxv_u16((int8x8_t)__rev0);
51957 __ai int8_t vmaxv_s8(int8x8_t __p0) {
51959 __ret = (int8_t) __builtin_neon_vmaxv_s8((int8x8_t)__p0);
51963 __ai int8_t vmaxv_s8(int8x8_t __p0) {
51964 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
51966 __ret = (int8_t) __builtin_neon_vmaxv_s8((int8x8_t)__rev0);
51974 __ret = (float32_t) __builtin_neon_vmaxv_f32((int8x8_t)__p0);
51981 __ret = (float32_t) __builtin_neon_vmaxv_f32((int8x8_t)__rev0);
51989 __ret = (int32_t) __builtin_neon_vmaxv_s32((int8x8_t)__p0);
51996 __ret = (int32_t) __builtin_neon_vmaxv_s32((int8x8_t)__rev0);
52004 __ret = (int16_t) __builtin_neon_vmaxv_s16((int8x8_t)__p0);
52011 __ret = (int16_t) __builtin_neon_vmaxv_s16((int8x8_t)__rev0);
52036 __ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
52042 __ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
52080 __ret = (float32_t) __builtin_neon_vminnmv_f32((int8x8_t)__p0);
52087 __ret = (float32_t) __builtin_neon_vminnmv_f32((int8x8_t)__rev0);
52215 __ret = (uint8_t) __builtin_neon_vminv_u8((int8x8_t)__p0);
52222 __ret = (uint8_t) __builtin_neon_vminv_u8((int8x8_t)__rev0);
52230 __ret = (uint32_t) __builtin_neon_vminv_u32((int8x8_t)__p0);
52237 __ret = (uint32_t) __builtin_neon_vminv_u32((int8x8_t)__rev0);
52245 __ret = (uint16_t) __builtin_neon_vminv_u16((int8x8_t)__p0);
52252 __ret = (uint16_t) __builtin_neon_vminv_u16((int8x8_t)__rev0);
52258 __ai int8_t vminv_s8(int8x8_t __p0) {
52260 __ret = (int8_t) __builtin_neon_vminv_s8((int8x8_t)__p0);
52264 __ai int8_t vminv_s8(int8x8_t __p0) {
52265 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
52267 __ret = (int8_t) __builtin_neon_vminv_s8((int8x8_t)__rev0);
52275 __ret = (float32_t) __builtin_neon_vminv_f32((int8x8_t)__p0);
52282 __ret = (float32_t) __builtin_neon_vminv_f32((int8x8_t)__rev0);
52290 __ret = (int32_t) __builtin_neon_vminv_s32((int8x8_t)__p0);
52297 __ret = (int32_t) __builtin_neon_vminv_s32((int8x8_t)__rev0);
52305 __ret = (int16_t) __builtin_neon_vminv_s16((int8x8_t)__p0);
52312 __ret = (int16_t) __builtin_neon_vminv_s16((int8x8_t)__rev0);
53604 int8x8_t __a1_121 = vget_high_s8(__p0_121);
53612 int8x8_t __a1_122 = __noswap_vget_high_s8(__rev0_122);
53619 int8x8_t __a1_123 = __noswap_vget_high_s8(__p0_123);
53759 __ai int8x16_t vmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
53765 __ai int8x16_t vmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
53766 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
53848 __ret = (float64x1_t) __builtin_neon_vmul_lane_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
53856 __ret = (float64x1_t) __builtin_neon_vmul_lane_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
53924 __ret = (float64x1_t) __builtin_neon_vmul_laneq_v((int8x8_t)__s0, (int8x16_t)__s1, __p2, 10); \
53933 __ret = (float64x1_t) __builtin_neon_vmul_laneq_v((int8x8_t)__s0, (int8x16_t)__rev1, __p2, 10); \
54172 __ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);
54178 __ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);
54716 __ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
54722 __ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
54730 __ret = (float32x2_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
54738 __ret = (float32x2_t) __builtin_neon_vmulx_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
54744 __ret = (float32x2_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
55279 __ret = (float32_t) __builtin_neon_vpadds_f32((int8x8_t)__p0);
55286 __ret = (float32_t) __builtin_neon_vpadds_f32((int8x8_t)__rev0);
55445 __ret = (float32_t) __builtin_neon_vpmaxs_f32((int8x8_t)__p0);
55452 __ret = (float32_t) __builtin_neon_vpmaxs_f32((int8x8_t)__rev0);
55494 __ret = (float32x2_t) __builtin_neon_vpmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
55502 __ret = (float32x2_t) __builtin_neon_vpmaxnm_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
55526 __ret = (float32_t) __builtin_neon_vpmaxnms_f32((int8x8_t)__p0);
55533 __ret = (float32_t) __builtin_neon_vpmaxnms_f32((int8x8_t)__rev0);
55692 __ret = (float32_t) __builtin_neon_vpmins_f32((int8x8_t)__p0);
55699 __ret = (float32_t) __builtin_neon_vpmins_f32((int8x8_t)__rev0);
55741 __ret = (float32x2_t) __builtin_neon_vpminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
55749 __ret = (float32x2_t) __builtin_neon_vpminnm_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
55773 __ret = (float32_t) __builtin_neon_vpminnms_f32((int8x8_t)__p0);
55780 __ret = (float32_t) __builtin_neon_vpminnms_f32((int8x8_t)__rev0);
55804 __ret = (int64x1_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 3);
55810 __ret = (int64x1_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 3);
56193 __ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, (int8x8_t)__s2, __p3); \
56203 __ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, (int8x8_t)__rev2, __p3); \
56214 __ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, (int8x8_t)__s2, __p3); \
56224 __ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, (int8x8_t)__rev2, __p3); \
56519 __ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, (int8x8_t)__s2, __p3); \
56529 __ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, (int8x8_t)__rev2, __p3); \
56540 __ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, (int8x8_t)__s2, __p3); \
56550 __ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, (int8x8_t)__rev2, __p3); \
57319 __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
57325 __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
57326 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57412 __ai int8x16_t vqmovun_high_s16(int8x8_t __p0, int16x8_t __p1) {
57418 __ai int8x16_t vqmovun_high_s16(int8x8_t __p0, int16x8_t __p1) {
57419 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57447 __ret = (int64x1_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 3);
57453 __ret = (int64x1_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 3);
57931 int8x8_t __s0_180 = __p0_180; \
57934 __ret_180 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_180), (int8x8_t)(vqrshrn_n_s16(__s1_180, __p2_180)))); \
57939 int8x8_t __s0_181 = __p0_181; \
57941 int8x8_t __rev0_181; __rev0_181 = __builtin_shufflevector(__s0_181, __s0_181, 7, 6, 5, 4, 3, 2, 1, 0); \
57944 __ret_181 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_181), (int8x8_t)(__noswap_vqrshrn_n_s16(__rev1_181, __p2_181)))); \
58090 int8x8_t __s0_186 = __p0_186; \
58093 __ret_186 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_186), (int8x8_t)(vqrshrun_n_s16(__s1_186, __p2_186)))); \
58098 int8x8_t __s0_187 = __p0_187; \
58100 int8x8_t __rev0_187; __rev0_187 = __builtin_shufflevector(__s0_187, __s0_187, 7, 6, 5, 4, 3, 2, 1, 0); \
58103 __ret_187 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_187), (int8x8_t)(__noswap_vqrshrun_n_s16(__rev1_187, __p2_187)))); \
58568 int8x8_t __s0_198 = __p0_198; \
58571 __ret_198 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_198), (int8x8_t)(vqshrn_n_s16(__s1_198, __p2_198)))); \
58576 int8x8_t __s0_199 = __p0_199; \
58578 int8x8_t __rev0_199; __rev0_199 = __builtin_shufflevector(__s0_199, __s0_199, 7, 6, 5, 4, 3, 2, 1, 0); \
58581 __ret_199 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_199), (int8x8_t)(__noswap_vqshrn_n_s16(__rev1_199, __p2_199)))); \
58727 int8x8_t __s0_204 = __p0_204; \
58730 __ret_204 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_204), (int8x8_t)(vqshrun_n_s16(__s1_204, __p2_204)))); \
58735 int8x8_t __s0_205 = __p0_205; \
58737 int8x8_t __rev0_205; __rev0_205 = __builtin_shufflevector(__s0_205, __s0_205, 7, 6, 5, 4, 3, 2, 1, 0); \
58740 __ret_205 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_205), (int8x8_t)(__noswap_vqshrun_n_s16(__rev1_205, __p2_205)))); \
58919 __ret = (poly8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 4);
58927 __ret = (poly8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__rev0, (int8x8_t)__rev1, 4);
58987 __ret = (uint8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 16);
58995 __ret = (uint8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__rev0, (int8x8_t)__rev1, 16);
59002 __ai int8x8_t vqtbl1_s8(int8x16_t __p0, int8x8_t __p1) {
59003 int8x8_t __ret;
59004 __ret = (int8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__p0, (int8x8_t)__p1, 0);
59008 __ai int8x8_t vqtbl1_s8(int8x16_t __p0, int8x8_t __p1) {
59010 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59011 int8x8_t __ret;
59012 __ret = (int8x8_t) __builtin_neon_vqtbl1_v((int8x16_t)__rev0, (int8x8_t)__rev1, 0);
59021 __ret = (poly8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 4);
59031 __ret = (poly8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x8_t)__rev1, 4);
59097 __ret = (uint8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 16);
59107 __ret = (uint8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x8_t)__rev1, 16);
59114 __ai int8x8_t vqtbl2_s8(int8x16x2_t __p0, int8x8_t __p1) {
59115 int8x8_t __ret;
59116 __ret = (int8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__p0.val[0], (int8x16_t)__p0.val[1], (int8x8_t)__p1, 0);
59120 __ai int8x8_t vqtbl2_s8(int8x16x2_t __p0, int8x8_t __p1) {
59124 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59125 int8x8_t __ret;
59126 __ret = (int8x8_t) __builtin_neon_vqtbl2_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x8_t)__rev1, 0);
59135 __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);
59146 __ret = (poly8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x8_t)__rev1, 4);
59215 __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);
59226 __ret = (uint8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x8_t)__rev1, 16);
59233 __ai int8x8_t vqtbl3_s8(int8x16x3_t __p0, int8x8_t __p1) {
59234 int8x8_t __ret;
59235 __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);
59239 __ai int8x8_t vqtbl3_s8(int8x16x3_t __p0, int8x8_t __p1) {
59244 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59245 int8x8_t __ret;
59246 __ret = (int8x8_t) __builtin_neon_vqtbl3_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x8_t)__rev1, 0);
59255 __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);
59267 __ret = (poly8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x16_t)__rev0.val[3], (int8x8_t)__rev1, 4);
59339 __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);
59351 __ret = (uint8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x16_t)__rev0.val[3], (int8x8_t)__rev1, 16);
59358 __ai int8x8_t vqtbl4_s8(int8x16x4_t __p0, int8x8_t __p1) {
59359 int8x8_t __ret;
59360 __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);
59364 __ai int8x8_t vqtbl4_s8(int8x16x4_t __p0, int8x8_t __p1) {
59370 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
59371 int8x8_t __ret;
59372 __ret = (int8x8_t) __builtin_neon_vqtbl4_v((int8x16_t)__rev0.val[0], (int8x16_t)__rev0.val[1], (int8x16_t)__rev0.val[2], (int8x16_t)__rev0.val[3], (int8x8_t)__rev1, 0);
59381 __ret = (poly8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 4);
59390 __ret = (poly8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__rev0, (int8x16_t)__rev1, (int8x8_t)__rev2, 4);
59453 __ret = (uint8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 16);
59462 __ret = (uint8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__rev0, (int8x16_t)__rev1, (int8x8_t)__rev2, 16);
59469 __ai int8x8_t vqtbx1_s8(int8x8_t __p0, int8x16_t __p1, int8x8_t __p2) {
59470 int8x8_t __ret;
59471 __ret = (int8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__p0, (int8x16_t)__p1, (int8x8_t)__p2, 0);
59475 __ai int8x8_t vqtbx1_s8(int8x8_t __p0, int8x16_t __p1, int8x8_t __p2) {
59476 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
59478 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
59479 int8x8_t __ret;
59480 __ret = (int8x8_t) __builtin_neon_vqtbx1_v((int8x8_t)__rev0, (int8x16_t)__rev1, (int8x8_t)__rev2, 0);
59489 __ret = (poly8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 4);
59500 __ret = (poly8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x8_t)__rev2, 4);
59569 __ret = (uint8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 16);
59580 __ret = (uint8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x8_t)__rev2, 16);
59587 __ai int8x8_t vqtbx2_s8(int8x8_t __p0, int8x16x2_t __p1, int8x8_t __p2) {
59588 int8x8_t __ret;
59589 __ret = (int8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__p0, (int8x16_t)__p1.val[0], (int8x16_t)__p1.val[1], (int8x8_t)__p2, 0);
59593 __ai int8x8_t vqtbx2_s8(int8x8_t __p0, int8x16x2_t __p1, int8x8_t __p2) {
59594 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
59598 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
59599 int8x8_t __ret;
59600 __ret = (int8x8_t) __builtin_neon_vqtbx2_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x8_t)__rev2, 0);
59609 __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);
59621 __ret = (poly8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x8_t)__rev2, 4);
59693 __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);
59705 __ret = (uint8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x8_t)__rev2, 16);
59712 __ai int8x8_t vqtbx3_s8(int8x8_t __p0, int8x16x3_t __p1, int8x8_t __p2) {
59713 int8x8_t __ret;
59714 __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);
59718 __ai int8x8_t vqtbx3_s8(int8x8_t __p0, int8x16x3_t __p1, int8x8_t __p2) {
59719 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
59724 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
59725 int8x8_t __ret;
59726 __ret = (int8x8_t) __builtin_neon_vqtbx3_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x8_t)__rev2, 0);
59735 __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);
59748 __ret = (poly8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], (int8x8_t)__rev2, 4);
59823 __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);
59836 __ret = (uint8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], (int8x8_t)__rev2, 16);
59843 __ai int8x8_t vqtbx4_s8(int8x8_t __p0, int8x16x4_t __p1, int8x8_t __p2) {
59844 int8x8_t __ret;
59845 __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);
59849 __ai int8x8_t vqtbx4_s8(int8x8_t __p0, int8x16x4_t __p1, int8x8_t __p2) {
59850 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
59856 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
59857 int8x8_t __ret;
59858 __ret = (int8x8_t) __builtin_neon_vqtbx4_v((int8x8_t)__rev0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], (int8x8_t)__rev2, 0);
59955 __ai int8x16_t vraddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
59961 __ai int8x16_t vraddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
59962 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
59975 __ret = (poly8x8_t) __builtin_neon_vrbit_v((int8x8_t)__p0, 4);
59982 __ret = (poly8x8_t) __builtin_neon_vrbit_v((int8x8_t)__rev0, 4);
60039 __ret = (uint8x8_t) __builtin_neon_vrbit_v((int8x8_t)__p0, 16);
60046 __ret = (uint8x8_t) __builtin_neon_vrbit_v((int8x8_t)__rev0, 16);
60053 __ai int8x8_t vrbit_s8(int8x8_t __p0) {
60054 int8x8_t __ret;
60055 __ret = (int8x8_t) __builtin_neon_vrbit_v((int8x8_t)__p0, 0);
60059 __ai int8x8_t vrbit_s8(int8x8_t __p0) {
60060 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
60061 int8x8_t __ret;
60062 __ret = (int8x8_t) __builtin_neon_vrbit_v((int8x8_t)__rev0, 0);
60087 __ret = (float64x1_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 10);
60093 __ret = (float64x1_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 10);
60146 __ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60152 __ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60380 int8x8_t __s0_216 = __p0_216; \
60383 __ret_216 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_216), (int8x8_t)(vrshrn_n_s16(__s1_216, __p2_216)))); \
60388 int8x8_t __s0_217 = __p0_217; \
60390 int8x8_t __rev0_217; __rev0_217 = __builtin_shufflevector(__s0_217, __s0_217, 7, 6, 5, 4, 3, 2, 1, 0); \
60393 __ret_217 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_217), (int8x8_t)(__noswap_vrshrn_n_s16(__rev1_217, __p2_217)))); \
60418 __ret = (float64x1_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 10);
60424 __ret = (float64x1_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 10);
60477 __ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60483 __ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
60643 __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
60649 __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
60650 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
60665 __ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
60673 __ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
60680 __ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
60744 __ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \
60752 __ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \
60759 __ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \
61071 int8x8_t __s0_240 = __p0_240; \
61074 __ret_240 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_240), (int8x8_t)(vshrn_n_s16(__s1_240, __p2_240)))); \
61079 int8x8_t __s0_241 = __p0_241; \
61081 int8x8_t __rev0_241; __rev0_241 = __builtin_shufflevector(__s0_241, __s0_241, 7, 6, 5, 4, 3, 2, 1, 0); \
61084 __ret_241 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_241), (int8x8_t)(__noswap_vshrn_n_s16(__rev1_241, __p2_241)))); \
61131 __ret = (poly64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
61139 __ret = (poly64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
61292 __ret = (uint8x8_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 16);
61300 __ret = (uint8x8_t) __builtin_neon_vsqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 16);
61309 __ret = (uint32x2_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 18);
61317 __ret = (uint32x2_t) __builtin_neon_vsqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 18);
61326 __ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
61332 __ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
61340 __ret = (uint16x4_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 17);
61348 __ret = (uint16x4_t) __builtin_neon_vsqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 17);
61389 __ret = (float64x1_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 10);
61395 __ret = (float64x1_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 10);
61403 __ret = (float32x2_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 9);
61410 __ret = (float32x2_t) __builtin_neon_vsqrt_v((int8x8_t)__rev0, 9);
61493 __ret = (poly64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
61501 __ret = (poly64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
61530 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 6); \
61535 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 6); \
61568 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 10); \
61573 __builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 10); \
61580 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
61585 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
61618 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
61623 __builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
61630 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 4); \
61638 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 4); \
61645 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
61650 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
61657 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 5); \
61665 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 5); \
61882 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 16); \
61890 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 16); \
61897 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 18); \
61905 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 18); \
61912 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
61917 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
61924 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 17); \
61932 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 17); \
61939 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 0); \
61947 __builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 0); \
62038 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 4); \
62047 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 4); \
62054 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
62059 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
62066 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 5); \
62075 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 5); \
62306 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 16); \
62315 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 16); \
62322 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 18); \
62331 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 18); \
62338 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
62343 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
62350 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 17); \
62359 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 17); \
62366 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 0); \
62375 __builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 0); \
62470 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 4); \
62480 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 4); \
62487 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
62492 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
62499 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 5); \
62509 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 5); \
62754 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 16); \
62764 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 16); \
62771 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 18); \
62781 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 18); \
62788 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
62793 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
62800 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 17); \
62810 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 17); \
62817 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 0); \
62827 __builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 0); \
62926 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
62931 __builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
63010 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
63015 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
63127 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
63132 __builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
63163 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
63168 __builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
63251 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
63256 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
63375 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
63380 __builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
63411 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
63416 __builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
63503 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
63508 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
63634 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
63639 __builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
63829 __ai int8x16_t vsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
63835 __ai int8x16_t vsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
63836 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
64357 __ai int8x8_t vtrn1_s8(int8x8_t __p0, int8x8_t __p1) {
64358 int8x8_t __ret;
64363 __ai int8x8_t vtrn1_s8(int8x8_t __p0, int8x8_t __p1) {
64364 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
64365 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64366 int8x8_t __ret;
64731 __ai int8x8_t vtrn2_s8(int8x8_t __p0, int8x8_t __p1) {
64732 int8x8_t __ret;
64737 __ai int8x8_t vtrn2_s8(int8x8_t __p0, int8x8_t __p1) {
64738 int8x8_t
64739 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
64740 int8x8_t __ret;
64801 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64807 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64866 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64872 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64880 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
64886 __ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
65044 __ai int8x8_t vuqadd_s8(int8x8_t __p0, int8x8_t __p1) {
65045 int8x8_t __ret;
65046 __ret = (int8x8_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 0);
65050 __ai int8x8_t vuqadd_s8(int8x8_t __p0, int8x8_t __p1) {
65051 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
65052 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65053 int8x8_t __ret;
65054 __ret = (int8x8_t) __builtin_neon_vuqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 0);
65063 __ret = (int32x2_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 2);
65071 __ret = (int32x2_t) __builtin_neon_vuqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 2);
65080 __ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
65086 __ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
65094 __ret = (int16x4_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 1);
65102 __ret = (int16x4_t) __builtin_neon_vuqadd_v((int8x8_t)__rev0, (int8x8_t)__rev1, 1);
65415 __ai int8x8_t vuzp1_s8(int8x8_t __p0, int8x8_t __p1) {
65416 int8x8_t __ret;
65421 __ai int8x8_t vuzp1_s8(int8x8_t __p0, int8x8_t __p1) {
65422 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
65423 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65424 int8x8_t __ret;
65789 __ai int8x8_t vuzp2_s8(int8x8_t __p0, int8x8_t __p1) {
65790 int8x8_t __ret;
65795 __ai int8x8_t vuzp2_s8(int8x8_t __p0, int8x8_t __p1) {
65796 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
65797 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
65798 int8x8_t __ret;
66163 __ai int8x8_t vzip1_s8(int8x8_t __p0, int8x8_t __p1) {
66164 int8x8_t __ret;
66169 __ai int8x8_t vzip1_s8(int8x8_t __p0, int8x8_t __p1) {
66170 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
66171 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66172 int8x8_t __ret;
66537 __ai int8x8_t vzip2_s8(int8x8_t __p0, int8x8_t __p1) {
66538 int8x8_t __ret;
66543 __ai int8x8_t vzip2_s8(int8x8_t __p0, int8x8_t __p1) {
66544 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
66545 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66546 int8x8_t __ret;
66768 __ai int8x8_t vaba_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
66769 int8x8_t __ret;
66774 __ai int8x8_t vaba_s8(int8x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
66775 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
66776 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66777 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
66778 int8x8_t __ret;
66888 __ai int16x8_t vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
66894 __ai int16x8_t vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
66895 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
66896 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
66902 __ai int16x8_t __noswap_vabdl_s8(int8x8_t __p0, int8x8_t __p1) {
67005 __ai int16x8_t vaddl_s8(int8x8_t __p0, int8x8_t __p1) {
67011 __ai int16x8_t vaddl_s8(int8x8_t __p0, int8x8_t __p1) {
67012 int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
67013 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67107 __ai int16x8_t vaddw_s8(int16x8_t __p0, int8x8_t __p1) {
67113 __ai int16x8_t vaddw_s8(int16x8_t __p0, int8x8_t __p1) {
67115 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67269 __ai int16x8_t vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67275 __ai int16x8_t vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67277 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67278 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
67284 __ai int16x8_t __noswap_vmlal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67591 __ai int16x8_t vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67597 __ai int16x8_t vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
67599 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
67600 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
67606 __ai int16x8_t __noswap_vmlsl_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69056 __ai int16x8_t vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69062 __ai int16x8_t vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
69064 int8x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
69065 int8x8_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 7, 6, 5, 4, 3, 2, 1, 0);
69071 __ai int16x8_t __noswap_vabal_s8(int16x8_t __p0, int8x8_t __p1, int8x8_t __p2) {
