Lines Matching refs:lane
1250 …ansfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); //VLD1.8 {d0[0]},…
1251 …ansfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
1252 …ansfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); // VLD1.32 {d0[0]…
1253 …ansfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); // VLD1.64 {d0}, …
1254 …transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); //VLD1.8 {d0[0]},…
1255 …transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); //VLD1.16 {d0[0]}…
1256 …transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); //VLD1.32 {d0[0]}…
1257 …ransfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); //VLD1.16 {d0[0]}…
1258 …sfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); // VLD1.32 {d0[0]…
1259 …transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); //VLD1.64 {d0}, […
1260 …ansfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); //VLD1.8 {d0[0]},…
1261 …ansfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
1262 …transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); //VLD1.8 {d0[0]},…
1263 …ansfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); //VLD1.16 {d0[0]}…
1264 …ansfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); //VLD1.32 {d0[0]}…
1265 …ansfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); //VLD1.64 {d0}, […
1266 …__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); // VLD1.8{d0[0]},…
1267 …transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); //VLD1.16 {d0[0]}…
1268 …transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); //VLD1.32 {d0[0]}…
1269 …ransfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); //VLD1.16 {d0[0]}…
1270 …sfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); // VLD1.32 {d0[0]…
1271 …transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); //VLD1.64 {d0}, […
1272 …transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); //VLD1.8 {d0[0]},…
1273 …ansfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); //VLD1.16 {d0[0]}…
1433 …ersize(2) uint16_t const * ptr, uint16x8x2_t * src, __constrange(0,7) int lane); // VLD2.16 {d0[0]…
1434 …ersize(2) uint32_t const * ptr, uint32x4x2_t * src, __constrange(0,3) int lane); // VLD2.32 {d0[0]…
1435 …sfersize(2) int16_t const * ptr, int16x8x2_t * src, __constrange(0,7) int lane); // VLD2.16 {d0[0]…
1436 …sfersize(2) int32_t const * ptr, int32x4x2_t * src, __constrange(0,3) int lane); // VLD2.32 {d0[0]…
1437 …fersize(2) __fp16 const * ptr, float16x8x2_t * src, __constrange(0,7) int lane); // VLD2.16 {d0[0]…
1438 …size(2) float32_t const * ptr, float32x4x2_t * src, __constrange(0,3) int lane); // VLD2.32 {d0[0]…
1439 …ersize(2) poly16_t const * ptr, poly16x8x2_t * src, __constrange(0,7) int lane); // VLD2.16 {d0[0]…
1440 …ansfersize(2) uint8_t const * ptr, uint8x8x2_t src, __constrange(0,7) int lane); //VLD2.8 {d0[0], …
1441 …sfersize(2) uint16_t const * ptr, uint16x4x2_t src, __constrange(0,3) int lane); // VLD2.16 {d0[0]…
1442 …sfersize(2) uint32_t const * ptr, uint32x2x2_t src, __constrange(0,1) int lane); // VLD2.32 {d0[0]…
1443 …transfersize(2) int8_t const * ptr, int8x8x2_t src, __constrange(0,7) int lane); //VLD2.8 {d0[0], …
1444 …ansfersize(2) int16_t const * ptr, int16x4x2_t src, __constrange(0,3) int lane); //VLD2.16 {d0[0],…
1445 …ansfersize(2) int32_t const * ptr, int32x2x2_t src, __constrange(0,1) int lane); //VLD2.32 {d0[0],…
1447 …rsize(2) float32_t const * ptr, float32x2x2_t src, __constrange(0,1) int lane); // VLD2.32 {d0[0]…
1448 …nsfersize(2) poly8_t const * ptr, poly8x8x2_t src, __constrange(0,7) int lane); //VLD2.8 {d0[0], …
1449 …fersize(2) poly16_t const * ptr, poly16x4x2_t src, __constrange(0,3) int lane); // VLD2.16 {d0[0]…
1450 …ersize(3) uint16_t const * ptr, uint16x8x3_t * src, __constrange(0,7) int lane); // VLD3.16 {d0[0]…
1451 …ersize(3) uint32_t const * ptr, uint32x4x3_t * src, __constrange(0,3) int lane); // VLD3.32 {d0[0]…
1452 …sfersize(3) int16_t const * ptr, int16x8x3_t * src, __constrange(0,7) int lane); // VLD3.16 {d0[0]…
1453 …sfersize(3) int32_t const * ptr, int32x4x3_t * src, __constrange(0,3) int lane); // VLD3.32 {d0[0]…
1454 …fersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); // VLD3.16 {d0[0]…
1455 …size(3) float32_t const * ptr, float32x4x3_t * src, __constrange(0,3) int lane); // VLD3.32 {d0[0]…
1456 …ersize(3) poly16_t const * ptr, poly16x8x3_t * src, __constrange(0,7) int lane); // VLD3.16 {d0[0]…
1457 …ansfersize(3) uint8_t const * ptr, uint8x8x3_t src, __constrange(0,7) int lane); //VLD3.8 {d0[0], …
1458 …sfersize(3) uint16_t const * ptr, uint16x4x3_t src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
1459 …sfersize(3) uint32_t const * ptr, uint32x2x3_t src, __constrange(0,1) int lane); // VLD3.32 {d0[0]…
1460 …transfersize(3) int8_t const * ptr, int8x8x3_t src, __constrange(0,7) int lane); //VLD3.8 {d0[0], …
1461 …ansfersize(3) int16_t const * ptr, int16x4x3_t src, __constrange(0,3) int lane); //VLD3.16 {d0[0],…
1462 …ansfersize(3) int32_t const * ptr, int32x2x3_t src, __constrange(0,1) int lane); //VLD3.32 {d0[0],…
1463 …fersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
1464 …ersize(3) float32_t const * ptr, float32x2x3_t src, __constrange(0,1) int lane); // VLD3.32 {d0[0]…
1465 …ansfersize(3) poly8_t const * ptr, poly8x8x3_t src, __constrange(0,7) int lane); //VLD3.8 {d0[0], …
1466 …sfersize(3) poly16_t const * ptr, poly16x4x3_t src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
1467 …ersize(4) uint16_t const * ptr, uint16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
1468 …ersize(4) uint32_t const * ptr, uint32x4x4_t * src, __constrange(0,3) int lane); // VLD4.32 {d0[0]…
1469 …sfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
1470 …sfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); // VLD4.32 {d0[0]…
1471 …fersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
1472 …size(4) float32_t const * ptr, float32x4x4_t * src, __constrange(0,3) int lane); // VLD4.32 {d0[0]…
1473 …ersize(4) poly16_t const * ptr, poly16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
1474 …ansfersize(4) uint8_t const * ptr, uint8x8x4_t src, __constrange(0,7) int lane); //VLD4.8 {d0[0], …
1475 …sfersize(4) uint16_t const * ptr, uint16x4x4_t src, __constrange(0,3) int lane); // VLD4.16 {d0[0]…
1476 …sfersize(4) uint32_t const * ptr, uint32x2x4_t src, __constrange(0,1) int lane); // VLD4.32 {d0[0]…
1477 …transfersize(4) int8_t const * ptr, int8x8x4_t src, __constrange(0,7) int lane); //VLD4.8 {d0[0], …
1478 …ansfersize(4) int16_t const * ptr, int16x4x4_t src, __constrange(0,3) int lane); //VLD4.16 {d0[0],…
1479 …ansfersize(4) int32_t const * ptr, int32x2x4_t src, __constrange(0,1) int lane); //VLD4.32 {d0[0],…
1480 …fersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); // VLD4.16 {d0[0]…
1481 …ersize(4) float32_t const * ptr, float32x2x4_t src, __constrange(0,1) int lane); // VLD4.32 {d0[0]…
1482 …ansfersize(4) poly8_t const * ptr, poly8x8x4_t src, __constrange(0,7) int lane); //VLD4.8 {d0[0], …
1483 …sfersize(4) poly16_t const * ptr, poly16x4x4_t src, __constrange(0,3) int lane); // VLD4.16 {d0[0]…
1552 …transfersize(2) uint16_t * ptr, uint16x8x2_t * val, __constrange(0,7) int lane); // VST2.16{d0[0],…
1553 …transfersize(2) uint32_t * ptr, uint32x4x2_t * val, __constrange(0,3) int lane); // VST2.32{d0[0],…
1554 …__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); // VST2.16{d0[0],…
1555 …__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); // VST2.32{d0[0],…
1556 …_transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); // VST2.16{d0[0],…
1557 …ansfersize(2) float32_t * ptr, float32x4x2_t * val, __constrange(0,3) int lane); //VST2.32 {d0[0],…
1558 …transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); // VST2.16{d0[0],…
1559 …8(__transfersize(2) uint8_t * ptr, uint8x8x2_t val, __constrange(0,7) int lane); // VST2.8{d0[0], …
1560 …__transfersize(2) uint16_t * ptr, uint16x4x2_t val, __constrange(0,3) int lane); // VST2.16{d0[0],…
1561 …__transfersize(2) uint32_t * ptr, uint32x2x2_t val, __constrange(0,1) int lane); // VST2.32{d0[0],…
1562 …_s8(__transfersize(2) int8_t * ptr, int8x8x2_t val, __constrange(0,7) int lane); // VST2.8 {d0[0],…
1563 …6(__transfersize(2) int16_t * ptr, int16x4x2_t val, __constrange(0,3) int lane); // VST2.16{d0[0],…
1564 …2(__transfersize(2) int32_t * ptr, int32x2x2_t val, __constrange(0,1) int lane); // VST2.32{d0[0],…
1565 …_transfersize(2) __fp16 * ptr, float16x4x2_t * val, __constrange(0,3) int lane); // VST2.16{d0[0],…
1566 …transfersize(2) float32_t * ptr, float32x2x2_t val, __constrange(0,1) int lane); // VST2.32{d0[0],…
1567 …8(__transfersize(2) poly8_t * ptr, poly8x8x2_t val, __constrange(0,7) int lane); // VST2.8{d0[0], …
1568 …__transfersize(2) poly16_t * ptr, poly16x4x2_t val, __constrange(0,3) int lane); // VST2.16{d0[0],…
1569 …transfersize(3) uint16_t * ptr, uint16x8x3_t * val, __constrange(0,7) int lane); // VST3.16{d0[0],…
1570 …transfersize(3) uint32_t * ptr, uint32x4x3_t * val, __constrange(0,3) int lane); // VST3.32{d0[0],…
1571 …__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); // VST3.16{d0[0],…
1572 …__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); // VST3.32{d0[0],…
1573 …_transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); // VST3.16{d0[0],…
1574 …ansfersize(3) float32_t * ptr, float32x4x3_t * val, __constrange(0,3) int lane); //VST3.32 {d0[0],…
1575 …transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); // VST3.16{d0[0],…
1576 …8(__transfersize(3) uint8_t * ptr, uint8x8x3_t val, __constrange(0,7) int lane); // VST3.8{d0[0], …
1577 …__transfersize(3) uint16_t * ptr, uint16x4x3_t val, __constrange(0,3) int lane); // VST3.16{d0[0],…
1578 …__transfersize(3) uint32_t * ptr, uint32x2x3_t val, __constrange(0,1) int lane); // VST3.32{d0[0],…
1579 …_s8(__transfersize(3) int8_t * ptr, int8x8x3_t val, __constrange(0,7) int lane); // VST3.8 {d0[0],…
1580 …6(__transfersize(3) int16_t * ptr, int16x4x3_t val, __constrange(0,3) int lane); // VST3.16{d0[0],…
1581 …2(__transfersize(3) int32_t * ptr, int32x2x3_t val, __constrange(0,1) int lane); // VST3.32{d0[0],…
1582 …_transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); // VST3.16{d0[0],…
1583 …transfersize(3) float32_t * ptr, float32x2x3_t val, __constrange(0,1) int lane); // VST3.32{d0[0],…
1584 …8(__transfersize(3) poly8_t * ptr, poly8x8x3_t val, __constrange(0,7) int lane); // VST3.8{d0[0], …
1585 …__transfersize(3) poly16_t * ptr, poly16x4x3_t val, __constrange(0,3) int lane); // VST3.16{d0[0],…
1586 …transfersize(4) uint16_t * ptr, uint16x8x4_t * val, __constrange(0,7) int lane); // VST4.16{d0[0],…
1587 …transfersize(4) uint32_t * ptr, uint32x4x4_t * val, __constrange(0,3) int lane); // VST4.32{d0[0],…
1588 …__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); // VST4.16{d0[0],…
1589 …__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); // VST4.32{d0[0],…
1590 …_transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); // VST4.16{d0[0],…
1591 …ansfersize(4) float32_t * ptr, float32x4x4_t * val, __constrange(0,3) int lane); //VST4.32 {d0[0],…
1592 …transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); // VST4.16{d0[0],…
1593 …8(__transfersize(4) uint8_t * ptr, uint8x8x4_t val, __constrange(0,7) int lane); // VST4.8{d0[0], …
1594 …__transfersize(4) uint16_t * ptr, uint16x4x4_t val, __constrange(0,3) int lane); // VST4.16{d0[0],…
1595 …__transfersize(4) uint32_t * ptr, uint32x2x4_t val, __constrange(0,1) int lane); // VST4.32{d0[0],…
1596 …_s8(__transfersize(4) int8_t * ptr, int8x8x4_t val, __constrange(0,7) int lane); // VST4.8 {d0[0],…
1597 …6(__transfersize(4) int16_t * ptr, int16x4x4_t val, __constrange(0,3) int lane); // VST4.16{d0[0],…
1598 …2(__transfersize(4) int32_t * ptr, int32x2x4_t val, __constrange(0,1) int lane); // VST4.32{d0[0],…
1599 …_transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); // VST4.16{d0[0],…
1600 …transfersize(4) float32_t * ptr, float32x2x4_t val, __constrange(0,1) int lane); // VST4.32{d0[0],…
1601 …8(__transfersize(4) poly8_t * ptr, poly8x8x4_t val, __constrange(0,7) int lane); // VST4.8{d0[0], …
1602 …__transfersize(4) poly16_t * ptr, poly16x4x4_t val, __constrange(0,3) int lane); // VST4.16{d0[0],…
1604 _NEON2SSESTORAGE uint8_t vget_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VMOV.U8 r0, d0…
1605 _NEON2SSESTORAGE uint16_t vget_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VMOV.U16 r0…
1606 _NEON2SSESTORAGE uint32_t vget_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r0,…
1607 _NEON2SSESTORAGE int8_t vget_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VMOV.S8 r0, d0[0]
1608 _NEON2SSESTORAGE int16_t vget_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VMOV.S16 r0, …
1609 _NEON2SSESTORAGE int32_t vget_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r0, d…
1610 _NEON2SSESTORAGE poly8_t vget_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VMOV.U8 r0, d0…
1611 _NEON2SSESTORAGE poly16_t vget_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VMOV.U16 r0…
1612 _NEON2SSESTORAGE float32_t vget_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r…
1613 _NEON2SSESTORAGE uint8_t vgetq_lane_u8(uint8x16_t vec, __constrange(0,15) int lane); // VMOV.U8 r0,…
1614 _NEON2SSESTORAGE uint16_t vgetq_lane_u16(uint16x8_t vec, __constrange(0,7) int lane); // VMOV.U16 r…
1615 _NEON2SSESTORAGE uint32_t vgetq_lane_u32(uint32x4_t vec, __constrange(0,3) int lane); // VMOV.32 r0…
1616 _NEON2SSESTORAGE int8_t vgetq_lane_s8(int8x16_t vec, __constrange(0,15) int lane); // VMOV.S8 r0, d…
1617 _NEON2SSESTORAGE int16_t vgetq_lane_s16(int16x8_t vec, __constrange(0,7) int lane); // VMOV.S16 r0,…
1618 _NEON2SSESTORAGE int32_t vgetq_lane_s32(int32x4_t vec, __constrange(0,3) int lane); // VMOV.32 r0, …
1619 _NEON2SSESTORAGE poly8_t vgetq_lane_p8(poly8x16_t vec, __constrange(0,15) int lane); // VMOV.U8 r0,…
1620 _NEON2SSESTORAGE poly16_t vgetq_lane_p16(poly16x8_t vec, __constrange(0,7) int lane); // VMOV.U16 r…
1621 _NEON2SSESTORAGE float32_t vgetq_lane_f32(float32x4_t vec, __constrange(0,3) int lane); // VMOV.32 …
1622 _NEON2SSESTORAGE int64_t vget_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV r0,r0,d0
1623 _NEON2SSESTORAGE uint64_t vget_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV r0,r0,…
1624 _NEON2SSESTORAGE int64_t vgetq_lane_s64(int64x2_t vec, __constrange(0,1) int lane); // VMOV r0,r0,d0
1625 _NEON2SSESTORAGE uint64_t vgetq_lane_u64(uint64x2_t vec, __constrange(0,1) int lane); // VMOV r0,r0…
1627 _NEON2SSESTORAGE uint8x8_t vset_lane_u8(uint8_t value, uint8x8_t vec, __constrange(0,7) int lane); …
1628 …6x4_t vset_lane_u16(uint16_t value, uint16x4_t vec, __constrange(0,3) int lane); // VMOV.16 d0[0],…
1629 …2x2_t vset_lane_u32(uint32_t value, uint32x2_t vec, __constrange(0,1) int lane); // VMOV.32 d0[0],…
1630 _NEON2SSESTORAGE int8x8_t vset_lane_s8(int8_t value, int8x8_t vec, __constrange(0,7) int lane); // …
1631 _NEON2SSESTORAGE int16x4_t vset_lane_s16(int16_t value, int16x4_t vec, __constrange(0,3) int lane);…
1632 _NEON2SSESTORAGE int32x2_t vset_lane_s32(int32_t value, int32x2_t vec, __constrange(0,1) int lane);…
1633 _NEON2SSESTORAGE poly8x8_t vset_lane_p8(poly8_t value, poly8x8_t vec, __constrange(0,7) int lane); …
1634 …6x4_t vset_lane_p16(poly16_t value, poly16x4_t vec, __constrange(0,3) int lane); // VMOV.16 d0[0],…
1635 …2_t vset_lane_f32(float32_t value, float32x2_t vec, __constrange(0,1) int lane); // VMOV.32 d0[0],…
1636 …x16_t vsetq_lane_u8(uint8_t value, uint8x16_t vec, __constrange(0,15) int lane); // VMOV.8 d0[0],r0
1637 …x8_t vsetq_lane_u16(uint16_t value, uint16x8_t vec, __constrange(0,7) int lane); // VMOV.16 d0[0],…
1638 …x4_t vsetq_lane_u32(uint32_t value, uint32x4_t vec, __constrange(0,3) int lane); // VMOV.32 d0[0],…
1639 _NEON2SSESTORAGE int8x16_t vsetq_lane_s8(int8_t value, int8x16_t vec, __constrange(0,15) int lane);…
1640 _NEON2SSESTORAGE int16x8_t vsetq_lane_s16(int16_t value, int16x8_t vec, __constrange(0,7) int lane)…
1641 _NEON2SSESTORAGE int32x4_t vsetq_lane_s32(int32_t value, int32x4_t vec, __constrange(0,3) int lane)…
1642 …x16_t vsetq_lane_p8(poly8_t value, poly8x16_t vec, __constrange(0,15) int lane); // VMOV.8 d0[0],r0
1643 …x8_t vsetq_lane_p16(poly16_t value, poly16x8_t vec, __constrange(0,7) int lane); // VMOV.16 d0[0],…
1644 …_t vsetq_lane_f32(float32_t value, float32x4_t vec, __constrange(0,3) int lane); // VMOV.32 d0[0],…
1645 _NEON2SSESTORAGE int64x1_t vset_lane_s64(int64_t value, int64x1_t vec, __constrange(0,0) int lane);…
1646 …t64x1_t vset_lane_u64(uint64_t value, uint64x1_t vec, __constrange(0,0) int lane); // VMOV d0,r0,r0
1647 _NEON2SSESTORAGE int64x2_t vsetq_lane_s64(int64_t value, int64x2_t vec, __constrange(0,1) int lane)…
1648 …64x2_t vsetq_lane_u64(uint64_t value, uint64x2_t vec, __constrange(0,1) int lane); // VMOV d0,r0,r0
1709 _NEON2SSESTORAGE uint8x8_t vdup_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0…
1710 _NEON2SSESTORAGE uint16x4_t vdup_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d…
1711 _NEON2SSESTORAGE uint32x2_t vdup_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VDUP.32 d…
1712 _NEON2SSESTORAGE int8x8_t vdup_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0[0]
1713 _NEON2SSESTORAGE int16x4_t vdup_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d0,…
1714 _NEON2SSESTORAGE int32x2_t vdup_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VDUP.32 d0,…
1715 _NEON2SSESTORAGE poly8x8_t vdup_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0…
1716 _NEON2SSESTORAGE poly16x4_t vdup_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d…
1717 _NEON2SSESTORAGE float32x2_t vdup_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VDUP.32…
1718 _NEON2SSESTORAGE uint8x16_t vdupq_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,…
1719 _NEON2SSESTORAGE uint16x8_t vdupq_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VDUP.16 …
1720 _NEON2SSESTORAGE uint32x4_t vdupq_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VDUP.32 …
1721 _NEON2SSESTORAGE int8x16_t vdupq_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,d0…
1722 _NEON2SSESTORAGE int16x8_t vdupq_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VDUP.16 q0…
1723 _NEON2SSESTORAGE int32x4_t vdupq_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VDUP.32 q0…
1724 _NEON2SSESTORAGE poly8x16_t vdupq_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,…
1725 _NEON2SSESTORAGE poly16x8_t vdupq_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VDUP.16 …
1726 _NEON2SSESTORAGE float32x4_t vdupq_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VDUP.3…
1727 _NEON2SSESTORAGE int64x1_t vdup_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV d0,d0
1728 _NEON2SSESTORAGE uint64x1_t vdup_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV d0,d0
1729 _NEON2SSESTORAGE int64x2_t vdupq_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV q0,q0
1730 _NEON2SSESTORAGE uint64x2_t vdupq_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV q0,…
9338 …ansfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); // VLD1.8 {d0[0]}…
9339 #define vld1q_lane_u8(ptr, vec, lane) _MM_INSERT_EPI8(vec, *(ptr), lane) argument
9341 …fersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
9342 #define vld1q_lane_u16(ptr, vec, lane) _MM_INSERT_EPI16(vec, *(ptr), lane) argument
9344 …ansfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); // VLD1.32 {d0[0]…
9345 #define vld1q_lane_u32(ptr, vec, lane) _MM_INSERT_EPI32(vec, *(ptr), lane) argument
9347 …ansfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); // VLD1.64 {d0}, …
9348 #define vld1q_lane_u64(ptr, vec, lane) _MM_INSERT_EPI64(vec, *(ptr), lane); // _p; argument
9351 …transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); // VLD1.8 {d0[0]}…
9352 #define vld1q_lane_s8(ptr, vec, lane) _MM_INSERT_EPI8(vec, *(ptr), lane) argument
9354 …transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
9355 #define vld1q_lane_s16(ptr, vec, lane) _MM_INSERT_EPI16(vec, *(ptr), lane) argument
9357 …transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); // VLD1.32 {d0[0]…
9358 #define vld1q_lane_s32(ptr, vec, lane) _MM_INSERT_EPI32(vec, *(ptr), lane) argument
9360 …ransfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
9363 …sfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); // VLD1.32 {d0[0]…
9364 …ld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane)
9369 return _MM_INSERT_PS(vec, p, _INSERTPS_NDX(0, lane));
9372 …transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); // VLD1.64 {d0}, …
9373 #define vld1q_lane_s64(ptr, vec, lane) _MM_INSERT_EPI64(vec, *(ptr), lane) argument
9375 …ansfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); // VLD1.8 {d0[0]}…
9376 #define vld1q_lane_p8(ptr, vec, lane) _MM_INSERT_EPI8(vec, *(ptr), lane) argument
9378 …ansfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); // VLD1.16 {d0[0]…
9379 #define vld1q_lane_p16(ptr, vec, lane) _MM_INSERT_EPI16(vec, *(ptr), lane) argument
9381 …transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); // VLD1.8 {d0[0]}…
9382 …x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane)
9386 res.m64_u8[lane] = *(ptr);
9390 …ansfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); // VLD1.16 {d0[0]…
9391 …t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane)
9395 res.m64_u16[lane] = *(ptr);
9399 …ansfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); // VLD1.32 {d0[0]…
9400 …t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane)
9404 res.m64_u32[lane] = *(ptr);
9408 …ansfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); // VLD1.64 {d0}, …
9409 …t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane)
9417 …__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); // VLD1.8 {d0[0]}…
9418 #define vld1_lane_s8(ptr, vec, lane) vld1_lane_u8((uint8_t*)ptr, vec, lane) argument
9420 …transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); // VLD1.16 {d0[0]…
9421 #define vld1_lane_s16(ptr, vec, lane) vld1_lane_u16((uint16_t*)ptr, vec, lane) argument
9423 …transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); // VLD1.32 {d0[0]…
9424 #define vld1_lane_s32(ptr, vec, lane) vld1_lane_u32((uint32_t*)ptr, vec, lane) argument
9426 …ransfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); // VLD1.16 {d0[0]…
9429 …sfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); // VLD1.32 {d0[0]…
9430 …vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane)
9434 res.m64_f32[lane] = *(ptr);
9438 …transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); // VLD1.64 {d0}, …
9439 #define vld1_lane_s64(ptr, vec, lane) vld1_lane_u64((uint64_t*)ptr, vec, lane) argument
9441 …transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); // VLD1.8 {d0[0]}…
9444 …ansfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); // VLD1.16 {d0[0]…
9685 …8(__transfersize(1) uint8_t * ptr, uint8x16_t val, __constrange(0,15) int lane); // VST1.8 {d0[0]}…
9686 #define vst1q_lane_u8(ptr, val, lane) *(ptr) = (uint8_t) _MM_EXTRACT_EPI8 (val, lane) argument
9688 …6(__transfersize(1) uint16_t * ptr, uint16x8_t val, __constrange(0,7) int lane); // VST1.16 {d0[0]…
9689 #define vst1q_lane_u16(ptr, val, lane) *(ptr) = (uint16_t) _MM_EXTRACT_EPI16 (val, lane) argument
9691 …2(__transfersize(1) uint32_t * ptr, uint32x4_t val, __constrange(0,3) int lane); // VST1.32 {d0[0]…
9692 #define vst1q_lane_u32(ptr, val, lane) *(ptr) = (uint32_t) _MM_EXTRACT_EPI32 (val, lane) argument
9694 …4(__transfersize(1) uint64_t * ptr, uint64x2_t val, __constrange(0,1) int lane); // VST1.64 {d0}, …
9695 #define vst1q_lane_u64(ptr, val, lane) *(ptr) = (uint64_t) _MM_EXTRACT_EPI64 (val, lane) argument
9697 …_s8(__transfersize(1) int8_t * ptr, int8x16_t val, __constrange(0,15) int lane); // VST1.8 {d0[0]}…
9698 #define vst1q_lane_s8(ptr, val, lane) *(ptr) = (int8_t) _MM_EXTRACT_EPI8 (val, lane) argument
9700 …s16(__transfersize(1) int16_t * ptr, int16x8_t val, __constrange(0,7) int lane); // VST1.16 {d0[0]…
9701 #define vst1q_lane_s16(ptr, val, lane) *(ptr) = (int16_t) _MM_EXTRACT_EPI16 (val, lane) argument
9703 …s32(__transfersize(1) int32_t * ptr, int32x4_t val, __constrange(0,3) int lane); // VST1.32 {d0[0]…
9704 #define vst1q_lane_s32(ptr, val, lane) *(ptr) = _MM_EXTRACT_EPI32 (val, lane) argument
9706 …s64(__transfersize(1) int64_t * ptr, int64x2_t val, __constrange(0,1) int lane); // VST1.64 {d0}, …
9707 #define vst1q_lane_s64(ptr, val, lane) *(ptr) = _MM_EXTRACT_EPI64 (val, lane) argument
9709 …16(__transfersize(1) __fp16 * ptr, float16x8_t val, __constrange(0,7) int lane); // VST1.16 {d0[0]…
9712 …__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane); // VST1.32 {d0[0]…
9713 …void vst1q_lane_f32(__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane)
9716 ilane = _MM_EXTRACT_PS(val,lane);
9720 …8(__transfersize(1) poly8_t * ptr, poly8x16_t val, __constrange(0,15) int lane); // VST1.8 {d0[0]}…
9723 …6(__transfersize(1) poly16_t * ptr, poly16x8_t val, __constrange(0,7) int lane); // VST1.16 {d0[0]…
9726 …_u8(__transfersize(1) uint8_t * ptr, uint8x8_t val, __constrange(0,7) int lane); // VST1.8 {d0[0]}…
9727 …NLINE void vst1_lane_u8(__transfersize(1) uint8_t * ptr, uint8x8_t val, __constrange(0,7) int lane)
9729 *(ptr) = val.m64_u8[lane];
9732 …6(__transfersize(1) uint16_t * ptr, uint16x4_t val, __constrange(0,3) int lane); // VST1.16 {d0[0]…
9733 …NE void vst1_lane_u16(__transfersize(1) uint16_t * ptr, uint16x4_t val, __constrange(0,3) int lane)
9735 *(ptr) = val.m64_u16[lane];
9738 …2(__transfersize(1) uint32_t * ptr, uint32x2_t val, __constrange(0,1) int lane); // VST1.32 {d0[0]…
9739 …NE void vst1_lane_u32(__transfersize(1) uint32_t * ptr, uint32x2_t val, __constrange(0,1) int lane)
9741 *(ptr) = val.m64_u32[lane];
9744 …4(__transfersize(1) uint64_t * ptr, uint64x1_t val, __constrange(0,0) int lane); // VST1.64 {d0}, …
9745 …NE void vst1_lane_u64(__transfersize(1) uint64_t * ptr, uint64x1_t val, __constrange(0,0) int lane)
9750 …ne_s8(__transfersize(1) int8_t * ptr, int8x8_t val, __constrange(0,7) int lane); // VST1.8 {d0[0]}…
9751 #define vst1_lane_s8(ptr, val, lane) vst1_lane_u8((uint8_t*)ptr, val, lane) argument
9753 …s16(__transfersize(1) int16_t * ptr, int16x4_t val, __constrange(0,3) int lane); // VST1.16 {d0[0]…
9754 #define vst1_lane_s16(ptr, val, lane) vst1_lane_u16((uint16_t*)ptr, val, lane) argument
9756 …s32(__transfersize(1) int32_t * ptr, int32x2_t val, __constrange(0,1) int lane); // VST1.32 {d0[0]…
9757 #define vst1_lane_s32(ptr, val, lane) vst1_lane_u32((uint32_t*)ptr, val, lane) argument
9760 …s64(__transfersize(1) int64_t * ptr, int64x1_t val, __constrange(0,0) int lane); // VST1.64 {d0}, …
9761 #define vst1_lane_s64(ptr, val, lane) vst1_lane_u64((uint64_t*)ptr, val, lane) argument
9764 …16(__transfersize(1) __fp16 * ptr, float16x4_t val, __constrange(0,3) int lane); // VST1.16 {d0[0]…
9767 …__transfersize(1) float32_t * ptr, float32x2_t val, __constrange(0,1) int lane); // VST1.32 {d0[0]…
9768 … void vst1_lane_f32(__transfersize(1) float32_t * ptr, float32x2_t val, __constrange(0,1) int lane)
9770 *(ptr) = val.m64_f32[lane];
9773 …_p8(__transfersize(1) poly8_t * ptr, poly8x8_t val, __constrange(0,7) int lane); // VST1.8 {d0[0]}…
9776 …6(__transfersize(1) poly16_t * ptr, poly16x4_t val, __constrange(0,3) int lane); // VST1.16 {d0[0]…
10705 …sfersize(2) uint16_t const * ptr, uint16x8x2_t* src,__constrange(0,7) int lane) // VLD2.16 {d0[0],…
10708 v.val[0] = vld1q_lane_s16 (ptr, src->val[0], lane);
10709 v.val[1] = vld1q_lane_s16 ((ptr + 1), src->val[1], lane);
10712 #define vld2q_lane_u16(ptr, src, lane) vld2q_lane_u16_ptr(ptr, &src, lane) argument
10715 …sfersize(2) uint32_t const * ptr, uint32x4x2_t* src,__constrange(0,3) int lane) // VLD2.32 {d0[0],…
10718 v.val[0] = _MM_INSERT_EPI32 (src->val[0], ptr[0], lane);
10719 v.val[1] = _MM_INSERT_EPI32 (src->val[1], ptr[1], lane);
10722 #define vld2q_lane_u32(ptr, src, lane) vld2q_lane_u32_ptr(ptr, &src, lane) argument
10725 …q_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x8x2_t* src, __constrange(0,7) int lane)
10728 v.val[0] = vld1q_lane_s16 (ptr, src->val[0], lane);
10729 v.val[1] = vld1q_lane_s16 ((ptr + 1), src->val[1], lane);
10732 #define vld2q_lane_s16(ptr, src, lane) vld2q_lane_s16_ptr(ptr, &src, lane) argument
10735 …q_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x4x2_t* src, __constrange(0,3) int lane)
10738 v.val[0] = _MM_INSERT_EPI32 (src->val[0], ptr[0], lane);
10739 v.val[1] = _MM_INSERT_EPI32 (src->val[1], ptr[1], lane);
10742 #define vld2q_lane_s32(ptr, src, lane) vld2q_lane_s32_ptr(ptr, &src, lane) argument
10748 …ersize(2) float32_t const * ptr, float32x4x2_t* src,__constrange(0,3) int lane) // VLD2.32 {d0[0],…
10751 v.val[0] = vld1q_lane_f32(ptr, src->val[0], lane);
10752 v.val[1] = vld1q_lane_f32((ptr + 1), src->val[1], lane);
10755 #define vld2q_lane_f32(ptr,src,lane) vld2q_lane_f32_ptr(ptr,&src,lane) argument
10760 …ansfersize(2) uint8_t const * ptr, uint8x8x2_t src, __constrange(0,7) int lane);// VLD2.8 {d0[0], …
10761 …ansfersize(2) uint8_t const * ptr, uint8x8x2_t src, __constrange(0,7) int lane) // VLD2.8 {d0[0], …
10764 v.val[0] = vld1_lane_u8(ptr, src.val[0], lane);
10765 v.val[1] = vld1_lane_u8((ptr + 1), src.val[1], lane);
10769 …nsfersize(2) uint16_t const * ptr, uint16x4x2_t src, __constrange(0,3)int lane);// VLD2.16 {d0[0],…
10770 …vld2_lane_u16(__transfersize(2) uint16_t const * ptr, uint16x4x2_t src, __constrange(0,3) int lane)
10773 v.val[0] = vld1_lane_u16(ptr, src.val[0], lane);
10774 v.val[1] = vld1_lane_u16((ptr + 1), src.val[1], lane);
10778 …nsfersize(2) uint32_t const * ptr, uint32x2x2_t src, __constrange(0,1)int lane);// VLD2.32 {d0[0],…
10779 …vld2_lane_u32(__transfersize(2) uint32_t const * ptr, uint32x2x2_t src, __constrange(0,1) int lane)
10782 v.val[0] = vld1_lane_u32(ptr, src.val[0], lane);
10783 v.val[1] = vld1_lane_u32((ptr + 1), src.val[1], lane);
10787 …transfersize(2) int8_t const * ptr, int8x8x2_t src, __constrange(0,7) int lane);// VLD2.8 {d0[0], …
10788 #define vld2_lane_s8(ptr, src, lane) vld2_lane_u8(( uint8_t*) ptr, src, lane) argument
10790 …ansfersize(2) int16_t const * ptr, int16x4x2_t src, __constrange(0,3) int lane);// VLD2.16 {d0[0],…
10791 #define vld2_lane_s16(ptr, src, lane) vld2_lane_u16(( uint16_t*) ptr, src, lane) argument
10793 …ansfersize(2) int32_t const * ptr, int32x2x2_t src, __constrange(0,1) int lane);// VLD2.32 {d0[0],…
10794 #define vld2_lane_s32(ptr, src, lane) vld2_lane_u32(( uint32_t*) ptr, src, lane) argument
10799 …fersize(2) float32_t const * ptr, float32x2x2_t src,__constrange(0,1) int lane); // VLD2.32 {d0[0]…
10800 …d2_lane_f32(__transfersize(2) float32_t const * ptr, float32x2x2_t src,__constrange(0,1) int lane)
10803 v.val[0] = vld1_lane_f32(ptr, src.val[0], lane);
10804 v.val[1] = vld1_lane_f32((ptr + 1), src.val[1], lane);
10809 …sfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); // VLD2.8 {d0[0],…
10813 …ersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); // VLD2.16 {d0[0]…
10822 …sfersize(3) uint16_t const * ptr, uint16x8x3_t* src,__constrange(0,7) int lane) // VLD3.16 {d0[0],…
10825 v.val[0] = _MM_INSERT_EPI16 ( src->val[0], ptr[0], lane);
10826 v.val[1] = _MM_INSERT_EPI16 ( src->val[1], ptr[1], lane);
10827 v.val[2] = _MM_INSERT_EPI16 ( src->val[2], ptr[2], lane);
10830 #define vld3q_lane_u16(ptr, src, lane) vld3q_lane_u16_ptr(ptr, &src, lane) argument
10833 …sfersize(3) uint32_t const * ptr, uint32x4x3_t* src,__constrange(0,3) int lane) // VLD3.32 {d0[0],…
10836 v.val[0] = _MM_INSERT_EPI32 ( src->val[0], ptr[0], lane);
10837 v.val[1] = _MM_INSERT_EPI32 ( src->val[1], ptr[1], lane);
10838 v.val[2] = _MM_INSERT_EPI32 ( src->val[2], ptr[2], lane);
10841 #define vld3q_lane_u32(ptr, src, lane) vld3q_lane_u32_ptr(ptr, &src, lane) argument
10844 …nsfersize(3) int16_t const * ptr, int16x8x3_t* src, __constrange(0,7) int lane) // VLD3.16 {d0[0],…
10847 v.val[0] = _MM_INSERT_EPI16 ( src->val[0], ptr[0], lane);
10848 v.val[1] = _MM_INSERT_EPI16 ( src->val[1], ptr[1], lane);
10849 v.val[2] = _MM_INSERT_EPI16 ( src->val[2], ptr[2], lane);
10852 #define vld3q_lane_s16(ptr, src, lane) vld3q_lane_s16_ptr(ptr, &src, lane) argument
10855 …nsfersize(3) int32_t const * ptr, int32x4x3_t* src, __constrange(0,3) int lane) // VLD3.32 {d0[0],…
10858 v.val[0] = _MM_INSERT_EPI32 ( src->val[0], ptr[0], lane);
10859 v.val[1] = _MM_INSERT_EPI32 ( src->val[1], ptr[1], lane);
10860 v.val[2] = _MM_INSERT_EPI32 ( src->val[2], ptr[2], lane);
10863 #define vld3q_lane_s32(ptr, src, lane) vld3q_lane_s32_ptr(ptr, &src, lane) argument
10865 …fersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); // VLD3.16 {d0[0]…
10867 #define vld3q_lane_f16(ptr, src, lane) vld3q_lane_f16_ptr(ptr, &src, lane) argument
10871 …ersize(3) float32_t const * ptr, float32x4x3_t* src,__constrange(0,3) int lane) // VLD3.32 {d0[0],…
10874 v.val[0] = vld1q_lane_f32(&ptr[0], src->val[0], lane);
10875 v.val[1] = vld1q_lane_f32(&ptr[1], src->val[1], lane);
10876 v.val[2] = vld1q_lane_f32(&ptr[2], src->val[2], lane);
10879 #define vld3q_lane_f32(ptr,src,lane) vld3q_lane_f32_ptr(ptr,&src,lane) argument
10881 …fersize(3) poly16_t const * ptr, poly16x8x3_t * src,__constrange(0,7) int lane); // VLD3.16 {d0[0]…
10884 …ansfersize(3) uint8_t const * ptr, uint8x8x3_t src, __constrange(0,7) int lane);// VLD3.8 {d0[0], …
10885 …ansfersize(3) uint8_t const * ptr, uint8x8x3_t src, __constrange(0,7) int lane) // VLD3.8 {d0[0], …
10888 v.val[0] = vld1_lane_u8(ptr, src.val[0], lane);
10889 v.val[1] = vld1_lane_u8((ptr + 1), src.val[1], lane);
10890 v.val[2] = vld1_lane_u8((ptr + 2), src.val[2], lane);
10894 …fersize(3) uint16_t const * ptr, uint16x4x3_t src, __constrange(0,3)int lane);// VLD3.16 {d0[0],…
10895 …sfersize(3) uint16_t const * ptr, uint16x4x3_t src, __constrange(0,3) int lane) // VLD3.16 {d0[0],…
10898 v.val[0] = vld1_lane_u16(ptr, src.val[0], lane);
10899 v.val[1] = vld1_lane_u16((ptr + 1), src.val[1], lane);
10900 v.val[2] = vld1_lane_u16((ptr + 2), src.val[2], lane);
10904 …nsfersize(3) uint32_t const * ptr, uint32x2x3_t src, __constrange(0,1)int lane);// VLD3.32 {d0[0],…
10905 …sfersize(3) uint32_t const * ptr, uint32x2x3_t src, __constrange(0,1) int lane) // VLD3.32 {d0[0],…
10909 v.val[0] = vld1_lane_u32(ptr, src.val[0], lane);;
10910 v.val[1] = vld1_lane_u32((ptr + 1), src.val[1], lane);;
10911 v.val[2] = vld1_lane_u32((ptr + 2), src.val[2], lane);;
10915 …ransfersize(3) int8_t const * ptr, int8x8x3_t src, __constrange(0,7) int lane); // VLD3.8 {d0[0],…
10916 #define vld3_lane_s8(ptr, src, lane) vld3_lane_u8(( uint8_t*) ptr, src, lane) argument
10918 …nsfersize(3) int16_t const * ptr, int16x4x3_t src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
10919 #define vld3_lane_s16(ptr, src, lane) vld3_lane_u16(( uint16_t*) ptr, src, lane) argument
10921 …nsfersize(3) int32_t const * ptr, int32x2x3_t src, __constrange(0,1) int lane); // VLD3.32 {d0[0]…
10922 #define vld3_lane_s32(ptr, src, lane) vld3_lane_u32(( uint32_t*) ptr, src, lane) argument
10924 …fersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
10927 …fersize(3) float32_t const * ptr, float32x2x3_t src,__constrange(0,1) int lane);// VLD3.32 {d0[0],…
10928 …fersize(3) float32_t const * ptr, float32x2x3_t src,__constrange(0,1) int lane) // VLD3.32 {d0[0],…
10931 v.val[0] = vld1_lane_f32(ptr, src.val[0], lane);
10932 v.val[1] = vld1_lane_f32((ptr + 1), src.val[1], lane);
10933 v.val[2] = vld1_lane_f32((ptr + 2), src.val[2], lane);
10937 …ansfersize(3) poly8_t const * ptr, poly8x8x3_t src, __constrange(0,7) int lane); // VLD3.8 {d0[0],…
10940 …sfersize(3) poly16_t const * ptr, poly16x4x3_t src, __constrange(0,3) int lane); // VLD3.16 {d0[0]…
10949 …_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x8x4_t* src,__constrange(0,7) int lane)
10952 v.val[0] = _MM_INSERT_EPI16 ( src->val[0], ptr[0], lane);
10953 v.val[1] = _MM_INSERT_EPI16 ( src->val[1], ptr[1], lane);
10954 v.val[2] = _MM_INSERT_EPI16 ( src->val[2], ptr[2], lane);
10955 v.val[3] = _MM_INSERT_EPI16 ( src->val[3], ptr[3], lane);
10958 #define vld4q_lane_u16(ptr, src, lane) vld4q_lane_u16_ptr(ptr, &src, lane) argument
10961 …_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x4x4_t* src,__constrange(0,3) int lane)
10964 v.val[0] = _MM_INSERT_EPI32 ( src->val[0], ptr[0], lane);
10965 v.val[1] = _MM_INSERT_EPI32 ( src->val[1], ptr[1], lane);
10966 v.val[2] = _MM_INSERT_EPI32 ( src->val[2], ptr[2], lane);
10967 v.val[3] = _MM_INSERT_EPI32 ( src->val[3], ptr[3], lane);
10970 #define vld4q_lane_u32(ptr, src, lane) vld4q_lane_u32_ptr(ptr, &src, lane) argument
10973 …sfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
10974 #define vld4q_lane_s16(ptr, src, lane) vld4q_lane_u16(( uint16_t*) ptr, src, lane) argument
10977 …sfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); // VLD4.32 {d0[0]…
10978 #define vld4q_lane_s32(ptr, src, lane) vld4q_lane_u32(( uint32_t*) ptr, src, lane) argument
10981 …fersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); // VLD4.16 {d0[0]…
10985 …ane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x4x4_t* src,__constrange(0,3) int lane)
10988 v.val[0] = vld1q_lane_f32(&ptr[0], src->val[0], lane);
10989 v.val[1] = vld1q_lane_f32(&ptr[1], src->val[1], lane);
10990 v.val[2] = vld1q_lane_f32(&ptr[2], src->val[2], lane);
10991 v.val[3] = vld1q_lane_f32(&ptr[3], src->val[3], lane);
10994 #define vld4q_lane_f32(ptr,val,lane) vld4q_lane_f32_ptr(ptr,&val,lane) argument
10997 …fersize(4) poly16_t const * ptr, poly16x8x4_t * src,__constrange(0,7) int lane); // VLD4.16 {d0[0]…
11000 …ansfersize(4) uint8_t const * ptr, uint8x8x4_t src, __constrange(0,7) int lane);// VLD4.8 {d0[0], …
11001 …_t vld4_lane_u8(__transfersize(4) uint8_t const * ptr, uint8x8x4_t src, __constrange(0,7) int lane)
11004 v.val[0] = vld1_lane_u8(ptr, src.val[0], lane);
11005 v.val[1] = vld1_lane_u8((ptr + 1), src.val[1], lane);
11006 v.val[2] = vld1_lane_u8((ptr + 2), src.val[2], lane);
11007 v.val[3] = vld1_lane_u8((ptr + 3), src.val[3], lane);
11011 …nsfersize(4) uint16_t const * ptr, uint16x4x4_t src, __constrange(0,3)int lane);// VLD4.16 {d0[0],…
11012 …vld4_lane_u16(__transfersize(4) uint16_t const * ptr, uint16x4x4_t src, __constrange(0,3) int lane)
11015 v.val[0] = vld1_lane_u16(ptr, src.val[0], lane);
11016 v.val[1] = vld1_lane_u16((ptr + 1), src.val[1], lane);
11017 v.val[2] = vld1_lane_u16((ptr + 2), src.val[2], lane);
11018 v.val[3] = vld1_lane_u16((ptr + 3), src.val[3], lane);
11022 …nsfersize(4) uint32_t const * ptr, uint32x2x4_t src, __constrange(0,1)int lane);// VLD4.32 {d0[0],…
11023 …vld4_lane_u32(__transfersize(4) uint32_t const * ptr, uint32x2x4_t src, __constrange(0,1) int lane)
11026 v.val[0] = vld1_lane_u32(ptr, src.val[0], lane);
11027 v.val[1] = vld1_lane_u32((ptr + 1), src.val[1], lane);
11028 v.val[2] = vld1_lane_u32((ptr + 2), src.val[2], lane);
11029 v.val[3] = vld1_lane_u32((ptr + 3), src.val[3], lane);
11033 …transfersize(4) int8_t const * ptr, int8x8x4_t src, __constrange(0,7) int lane);// VLD4.8 {d0[0], …
11034 #define vld4_lane_s8(ptr,src,lane) vld4_lane_u8((uint8_t*)ptr,src,lane) argument
11036 …ansfersize(4) int16_t const * ptr, int16x4x4_t src, __constrange(0,3) int lane);// VLD4.16 {d0[0],…
11037 #define vld4_lane_s16(ptr,src,lane) vld4_lane_u16((uint16_t*)ptr,src,lane) argument
11039 …ansfersize(4) int32_t const * ptr, int32x2x4_t src, __constrange(0,1) int lane);// VLD4.32 {d0[0],…
11040 #define vld4_lane_s32(ptr,src,lane) vld4_lane_u32((uint32_t*)ptr,src,lane) argument
11043 …ane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane);
11046 …fersize(4) float32_t const * ptr, float32x2x4_t src,__constrange(0,1) int lane);// VLD4.32 {d0[0],…
11047 …ld4_lane_f32(__transfersize(4) float32_t const * ptr, float32x2x4_t src,__constrange(0,1) int lane)
11051 v.val[0] = vld1_lane_f32(ptr, src.val[0], lane);
11052 v.val[1] = vld1_lane_f32((ptr + 1), src.val[1], lane);
11053 v.val[2] = vld1_lane_f32((ptr + 2), src.val[2], lane);
11054 v.val[3] = vld1_lane_f32((ptr + 3), src.val[3], lane);
11058 …ansfersize(4) poly8_t const * ptr, poly8x8x4_t src, __constrange(0,7) int lane);// VLD4.8 {d0[0], …
11061 …nsfersize(4) poly16_t const * ptr, poly16x4x4_t src, __constrange(0,3)int lane);// VLD4.16 {d0[0],…
11617 …vst2q_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x8x2_t* val, __constrange(0,7) int lane)
11619 vst1q_lane_s16(ptr, val->val[0], lane);
11620 vst1q_lane_s16((ptr + 1), val->val[1], lane);
11622 #define vst2q_lane_u16(ptr, val, lane) vst2q_lane_u16_ptr(ptr, &val, lane) argument
11625 … vst2q_lane_u32_ptr(__transfersize(2) uint32_t* ptr, uint32x4x2_t* val, __constrange(0,3) int lane)
11627 vst1q_lane_u32(ptr, val->val[0], lane);
11628 vst1q_lane_u32((ptr + 1), val->val[1], lane);
11630 #define vst2q_lane_u32(ptr, val, lane) vst2q_lane_u32_ptr(ptr, &val, lane) argument
11633 …vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane);
11634 #define vst2q_lane_s16(ptr, val, lane) vst2q_lane_u16((uint16_t*)ptr, val, lane) argument
11637 …vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane);
11638 #define vst2q_lane_s32(ptr, val, lane) vst2q_lane_u32((uint32_t*)ptr, val, lane) argument
11641 …st2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane);
11645 …st2q_lane_f32_ptr(__transfersize(2) float32_t* ptr, float32x4x2_t* val, __constrange(0,3) int lane)
11647 vst1q_lane_f32(ptr, val->val[0], lane);
11648 vst1q_lane_f32((ptr + 1), val->val[1], lane);
11650 #define vst2q_lane_f32(ptr,src,lane) vst2q_lane_f32_ptr(ptr,&src,lane) argument
11653 …t2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane);
11656 …8(__transfersize(2) uint8_t * ptr, uint8x8x2_t val, __constrange(0,7) int lane);// VST2.8 {d0[0], …
11657 …8(__transfersize(2) uint8_t * ptr, uint8x8x2_t val, __constrange(0,7) int lane) // VST2.8 {d0[0], …
11659 *(ptr) = val.val[0].m64_u8[lane];
11660 *(ptr + 1) = val.val[1].m64_u8[lane];
11663 …__transfersize(2) uint16_t * ptr, uint16x4x2_t val, __constrange(0,3) int lane);// VST2.16 {d0[0],…
11664 … void vst2_lane_u16(__transfersize(2) uint16_t * ptr, uint16x4x2_t val, __constrange(0,3) int lane)
11666 *(ptr) = val.val[0].m64_u16[lane];
11667 *(ptr + 1) = val.val[1].m64_u16[lane];
11670 …__transfersize(2) uint32_t * ptr, uint32x2x2_t val, __constrange(0,1) int lane);// VST2.32 {d0[0],…
11671 … void vst2_lane_u32(__transfersize(2) uint32_t * ptr, uint32x2x2_t val, __constrange(0,1) int lane)
11673 *(ptr) = val.val[0].m64_u32[lane];
11674 *(ptr + 1) = val.val[1].m64_u32[lane];
11677 …_s8(__transfersize(2) int8_t * ptr, int8x8x2_t val, __constrange(0,7) int lane);// VST2.8 {d0[0], …
11678 #define vst2_lane_s8(ptr, val, lane) vst2_lane_u8((uint8_t*)ptr, val, lane) argument
11680 …6(__transfersize(2) int16_t * ptr, int16x4x2_t val, __constrange(0,3) int lane);// VST2.16 {d0[0],…
11681 #define vst2_lane_s16(ptr, val, lane) vst2_lane_u16((uint16_t*)ptr, val, lane) argument
11683 …2(__transfersize(2) int32_t * ptr, int32x2x2_t val, __constrange(0,1) int lane);// VST2.32 {d0[0],…
11684 #define vst2_lane_s32(ptr, val, lane) vst2_lane_u32((uint32_t*)ptr, val, lane) argument
11689 …transfersize(2) float32_t * ptr, float32x2x2_t val, __constrange(0,1) int lane); // VST2.32 {d0[0]…
11690 …oid vst2_lane_f32(__transfersize(2) float32_t * ptr, float32x2x2_t val, __constrange(0,1) int lane)
11692 *(ptr) = val.val[0].m64_f32[lane];
11693 *(ptr + 1) = val.val[1].m64_f32[lane];
11696 …8(__transfersize(2) poly8_t * ptr, poly8x8x2_t val, __constrange(0,7) int lane);// VST2.8 {d0[0], …
11699 …__transfersize(2) poly16_t * ptr, poly16x4x2_t val, __constrange(0,3) int lane);// VST2.16 {d0[0],…
11705 …vst3q_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x8x3_t* val, __constrange(0,7) int lane)
11707 vst2q_lane_u16_ptr(ptr, (uint16x8x2_t*)val, lane);
11708 vst1q_lane_u16((ptr + 2), val->val[2], lane);
11710 #define vst3q_lane_u16(ptr, val, lane) vst3q_lane_u16_ptr(ptr, &val, lane) argument
11713 …vst3q_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x4x3_t* val, __constrange(0,3) int lane)
11715 vst2q_lane_u32_ptr(ptr, (uint32x4x2_t*)val, lane);
11716 vst1q_lane_u32((ptr + 2), val->val[2], lane);
11718 #define vst3q_lane_u32(ptr, val, lane) vst3q_lane_u32_ptr(ptr, &val, lane) argument
11721 …vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane);
11722 #define vst3q_lane_s16(ptr, val, lane) vst3q_lane_u16((uint16_t *)ptr, val, lane) argument
11725 …vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane);
11726 #define vst3q_lane_s32(ptr, val, lane) vst3q_lane_u32((uint32_t *)ptr, val, lane) argument
11729 …st3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane);
11733 …t3q_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x4x3_t* val, __constrange(0,3) int lane)
11735 vst1q_lane_f32(ptr, val->val[0], lane);
11736 vst1q_lane_f32((ptr + 1), val->val[1], lane);
11737 vst1q_lane_f32((ptr + 2), val->val[2], lane);
11739 #define vst3q_lane_f32(ptr,val,lane) vst3q_lane_f32_ptr(ptr,&val,lane) argument
11742 …t3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane);
11745 …8(__transfersize(3) uint8_t * ptr, uint8x8x3_t val, __constrange(0,7) int lane);// VST3.8 {d0[0], …
11746 …INE void vst3_lane_u8(__transfersize(3) uint8_t * ptr, uint8x8x3_t val, __constrange(0,7) int lane)
11748 *(ptr) = val.val[0].m64_u8[lane];
11749 *(ptr + 1) = val.val[1].m64_u8[lane];
11750 *(ptr + 2) = val.val[2].m64_u8[lane];
11753 …__transfersize(3) uint16_t * ptr, uint16x4x3_t val, __constrange(0,3) int lane);// VST3.16 {d0[0],…
11754 … void vst3_lane_u16(__transfersize(3) uint16_t * ptr, uint16x4x3_t val, __constrange(0,3) int lane)
11756 *(ptr) = val.val[0].m64_u16[lane];
11757 *(ptr + 1) = val.val[1].m64_u16[lane];
11758 *(ptr + 2) = val.val[2].m64_u16[lane];
11761 …__transfersize(3) uint32_t * ptr, uint32x2x3_t val, __constrange(0,1) int lane);// VST3.32 {d0[0],…
11762 … void vst3_lane_u32(__transfersize(3) uint32_t * ptr, uint32x2x3_t val, __constrange(0,1) int lane)
11764 *(ptr) = val.val[0].m64_u32[lane];
11765 *(ptr + 1) = val.val[1].m64_u32[lane];
11766 *(ptr + 2) = val.val[2].m64_u32[lane];
11769 …_s8(__transfersize(3) int8_t * ptr, int8x8x3_t val, __constrange(0,7) int lane);// VST3.8 {d0[0], …
11770 #define vst3_lane_s8(ptr, val, lane) vst3_lane_u8((uint8_t *)ptr, val, lane) argument
11772 …6(__transfersize(3) int16_t * ptr, int16x4x3_t val, __constrange(0,3) int lane);// VST3.16 {d0[0],…
11773 #define vst3_lane_s16(ptr, val, lane) vst3_lane_u16((uint16_t *)ptr, val, lane) argument
11775 …2(__transfersize(3) int32_t * ptr, int32x2x3_t val, __constrange(0,1) int lane);// VST3.32 {d0[0],…
11776 #define vst3_lane_s32(ptr, val, lane) vst3_lane_u32((uint32_t *)ptr, val, lane) argument
11779 …vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane);
11782 …transfersize(3) float32_t * ptr, float32x2x3_t val, __constrange(0,1) int lane);// VST3.32 {d0[0],…
11783 …oid vst3_lane_f32(__transfersize(3) float32_t * ptr, float32x2x3_t val, __constrange(0,1) int lane)
11785 *(ptr) = val.val[0].m64_f32[lane];
11786 *(ptr + 1) = val.val[1].m64_f32[lane];
11787 *(ptr + 2) = val.val[2].m64_f32[lane];
11790 …8(__transfersize(3) poly8_t * ptr, poly8x8x3_t val, __constrange(0,7) int lane);// VST3.8 {d0[0], …
11793 …__transfersize(3) poly16_t * ptr, poly16x4x3_t val, __constrange(0,3) int lane);// VST3.16 {d0[0],…
11799 …st4q_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x8x4_t* val4, __constrange(0,7) int lane)
11801 vst2q_lane_u16_ptr(ptr, (uint16x8x2_t*)val4->val, lane);
11802 vst2q_lane_u16_ptr((ptr + 2),((uint16x8x2_t*)val4->val + 1), lane);
11804 #define vst4q_lane_u16(ptr, val, lane) vst4q_lane_u16_ptr(ptr, &val, lane) argument
11807 …st4q_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x4x4_t* val4, __constrange(0,3) int lane)
11809 vst2q_lane_u32_ptr(ptr, (uint32x4x2_t*)val4->val, lane);
11810 vst2q_lane_u32_ptr((ptr + 2), ((uint32x4x2_t*)val4->val + 1), lane);
11812 #define vst4q_lane_u32(ptr, val, lane) vst4q_lane_u32_ptr(ptr, &val, lane) argument
11815 …vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane);
11816 #define vst4q_lane_s16(ptr,val,lane) vst4q_lane_u16((uint16_t *)ptr,val,lane) argument
11819 …vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane);
11820 #define vst4q_lane_s32(ptr,val,lane) vst4q_lane_u32((uint32_t *)ptr,val,lane) argument
11823 …st4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane);
11827 …t4q_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x4x4_t* val, __constrange(0,3) int lane)
11829 vst1q_lane_f32(ptr, val->val[0], lane);
11830 vst1q_lane_f32((ptr + 1), val->val[1], lane);
11831 vst1q_lane_f32((ptr + 2), val->val[2], lane);
11832 vst1q_lane_f32((ptr + 3), val->val[3], lane);
11834 #define vst4q_lane_f32(ptr,val,lane) vst4q_lane_f32_ptr(ptr,&val,lane) argument
11837 …t4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane);
11840 …8(__transfersize(4) uint8_t * ptr, uint8x8x4_t val, __constrange(0,7) int lane);// VST4.8 {d0[0], …
11841 …INE void vst4_lane_u8(__transfersize(4) uint8_t * ptr, uint8x8x4_t val, __constrange(0,7) int lane)
11843 *(ptr) = val.val[0].m64_u8[lane];
11844 *(ptr + 1) = val.val[1].m64_u8[lane];
11845 *(ptr + 2) = val.val[2].m64_u8[lane];
11846 *(ptr + 3) = val.val[3].m64_u8[lane];
11849 …__transfersize(4) uint16_t * ptr, uint16x4x4_t val, __constrange(0,3) int lane);// VST4.16 {d0[0],…
11850 … void vst4_lane_u16(__transfersize(4) uint16_t * ptr, uint16x4x4_t val, __constrange(0,3) int lane)
11852 *(ptr) = val.val[0].m64_u16[lane];
11853 *(ptr + 1) = val.val[1].m64_u16[lane];
11854 *(ptr + 2) = val.val[2].m64_u16[lane];
11855 *(ptr + 3) = val.val[3].m64_u16[lane];
11858 …__transfersize(4) uint32_t * ptr, uint32x2x4_t val, __constrange(0,1) int lane);// VST4.32 {d0[0],…
11859 … void vst4_lane_u32(__transfersize(4) uint32_t * ptr, uint32x2x4_t val, __constrange(0,1) int lane)
11861 *(ptr) = val.val[0].m64_u32[lane];
11862 *(ptr + 1) = val.val[1].m64_u32[lane];
11863 *(ptr + 2) = val.val[2].m64_u32[lane];
11864 *(ptr + 3) = val.val[3].m64_u32[lane];
11867 …_s8(__transfersize(4) int8_t * ptr, int8x8x4_t val, __constrange(0,7) int lane);// VST4.8 {d0[0], …
11868 #define vst4_lane_s8(ptr, val, lane) vst4_lane_u8((uint8_t*)ptr, val, lane) argument
11870 …6(__transfersize(4) int16_t * ptr, int16x4x4_t val, __constrange(0,3) int lane);// VST4.16 {d0[0],…
11871 #define vst4_lane_s16(ptr, val, lane) vst4_lane_u16((uint16_t*)ptr, val, lane) argument
11873 …2(__transfersize(4) int32_t * ptr, int32x2x4_t val, __constrange(0,1) int lane);// VST4.32 {d0[0],…
11874 #define vst4_lane_s32(ptr, val, lane) vst4_lane_u32((uint32_t*)ptr, val, lane) argument
11877 …vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane);
11880 …ransfersize(4) float32_t * ptr, float32x2x4_t val, __constrange(0,1) int lane); // VST4.32 {d0[0]…
11881 …oid vst4_lane_f32(__transfersize(4) float32_t * ptr, float32x2x4_t val, __constrange(0,1) int lane)
11883 *(ptr) = val.val[0].m64_f32[lane];
11884 *(ptr + 1) = val.val[1].m64_f32[lane];
11885 *(ptr + 2) = val.val[2].m64_f32[lane];
11886 *(ptr + 3) = val.val[3].m64_f32[lane];
11889 …8(__transfersize(4) poly8_t * ptr, poly8x8x4_t val, __constrange(0,7) int lane);// VST4.8 {d0[0], …
11892 …__transfersize(4) poly16_t * ptr, poly16x4x4_t val, __constrange(0,3) int lane);// VST4.16 {d0[0],…
11899 _NEON2SSESTORAGE uint8_t vget_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VMOV.U8 r0, d0…
11900 #define vget_lane_u8(vec, lane) vec.m64_u8[lane] argument
11902 _NEON2SSESTORAGE uint16_t vget_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VMOV.s16 r0…
11903 #define vget_lane_u16(vec, lane) vec.m64_u16[lane] argument
11906 _NEON2SSESTORAGE uint32_t vget_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r0,…
11907 #define vget_lane_u32(vec, lane) vec.m64_u32[lane] argument
11909 _NEON2SSESTORAGE int8_t vget_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VMOV.S8 r0, d0[0]
11910 #define vget_lane_s8(vec, lane) vec.m64_i8[lane] argument
11912 _NEON2SSESTORAGE int16_t vget_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VMOV.S16 r0, …
11913 #define vget_lane_s16(vec, lane) vec.m64_i16[lane] argument
11915 _NEON2SSESTORAGE int32_t vget_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r0, d…
11916 #define vget_lane_s32(vec, lane) vec.m64_i32[lane] argument
11918 _NEON2SSESTORAGE poly8_t vget_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VMOV.U8 r0, d0…
11921 _NEON2SSESTORAGE poly16_t vget_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VMOV.s16 r0…
11924 _NEON2SSESTORAGE float32_t vget_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VMOV.32 r…
11925 #define vget_lane_f32(vec, lane) vec.m64_f32[lane] argument
11927 _NEON2SSESTORAGE uint8_t vgetq_lane_u8(uint8x16_t vec, __constrange(0,15) int lane); // VMOV.U8 r0,…
11930 _NEON2SSESTORAGE uint16_t vgetq_lane_u16(uint16x8_t vec, __constrange(0,7) int lane); // VMOV.s16 r…
11933 _NEON2SSESTORAGE uint32_t vgetq_lane_u32(uint32x4_t vec, __constrange(0,3) int lane); // VMOV.32 r0…
11936 _NEON2SSESTORAGE int8_t vgetq_lane_s8(int8x16_t vec, __constrange(0,15) int lane); // VMOV.S8 r0, d…
11939 _NEON2SSESTORAGE int16_t vgetq_lane_s16(int16x8_t vec, __constrange(0,7) int lane); // VMOV.S16 r0,…
11942 _NEON2SSESTORAGE int32_t vgetq_lane_s32(int32x4_t vec, __constrange(0,3) int lane); // VMOV.32 r0, …
11945 _NEON2SSESTORAGE poly8_t vgetq_lane_p8(poly8x16_t vec, __constrange(0,15) int lane); // VMOV.U8 r0,…
11948 _NEON2SSESTORAGE poly16_t vgetq_lane_p16(poly16x8_t vec, __constrange(0,7) int lane); // VMOV.s16 r…
11951 _NEON2SSESTORAGE float32_t vgetq_lane_f32(float32x4_t vec, __constrange(0,3) int lane); // VMOV.32 …
11952 _NEON2SSE_INLINE float32_t vgetq_lane_f32(float32x4_t vec, __constrange(0,3) int lane)
11955 ilane = _MM_EXTRACT_PS(vec,lane);
11959 _NEON2SSESTORAGE int64_t vget_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV r0,r0,d0
11960 #define vget_lane_s64(vec, lane) vec.m64_i64[0] argument
11962 _NEON2SSESTORAGE uint64_t vget_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV r0,r0,…
11963 #define vget_lane_u64(vec, lane) vec.m64_u64[0] argument
11966 _NEON2SSESTORAGE int64_t vgetq_lane_s64(int64x2_t vec, __constrange(0,1) int lane); // VMOV r0,r0,d0
11969 _NEON2SSESTORAGE uint64_t vgetq_lane_u64(uint64x2_t vec, __constrange(0,1) int lane); // VMOV r0,r0…
11977 _NEON2SSESTORAGE uint8x8_t vset_lane_u8(uint8_t value, uint8x8_t vec, __constrange(0,7) int lane); …
11978 _NEON2SSE_INLINE uint8x8_t vset_lane_u8(uint8_t value, uint8x8_t vec, __constrange(0,7) int lane)
11982 return vld1_lane_u8(&val, vec, lane);
11985 …6x4_t vset_lane_u16(uint16_t value, uint16x4_t vec, __constrange(0,3) int lane); // VMOV.16 d0[0],…
11986 …EON2SSE_INLINE uint16x4_t vset_lane_u16(uint16_t value, uint16x4_t vec, __constrange(0,3) int lane)
11990 return vld1_lane_u16(&val, vec, lane);
11993 …2x2_t vset_lane_u32(uint32_t value, uint32x2_t vec, __constrange(0,1) int lane); // VMOV.32 d0[0],…
11994 …EON2SSE_INLINE uint32x2_t vset_lane_u32(uint32_t value, uint32x2_t vec, __constrange(0,1) int lane)
11998 return vld1_lane_u32(&val, vec, lane);
12001 _NEON2SSESTORAGE int8x8_t vset_lane_s8(int8_t value, int8x8_t vec, __constrange(0,7) int lane); // …
12002 _NEON2SSE_INLINE int8x8_t vset_lane_s8(int8_t value, int8x8_t vec, __constrange(0,7) int lane)
12006 return vld1_lane_s8(&val, vec, lane);
12009 _NEON2SSESTORAGE int16x4_t vset_lane_s16(int16_t value, int16x4_t vec, __constrange(0,3) int lane);…
12010 _NEON2SSE_INLINE int16x4_t vset_lane_s16(int16_t value, int16x4_t vec, __constrange(0,3) int lane)
12014 return vld1_lane_s16(&val, vec, lane);
12017 _NEON2SSESTORAGE int32x2_t vset_lane_s32(int32_t value, int32x2_t vec, __constrange(0,1) int lane);…
12018 _NEON2SSE_INLINE int32x2_t vset_lane_s32(int32_t value, int32x2_t vec, __constrange(0,1) int lane)
12022 return vld1_lane_s32(&val, vec, lane);
12025 _NEON2SSESTORAGE poly8x8_t vset_lane_p8(poly8_t value, poly8x8_t vec, __constrange(0,7) int lane); …
12028 …6x4_t vset_lane_p16(poly16_t value, poly16x4_t vec, __constrange(0,3) int lane); // VMOV.16 d0[0],…
12031 …2_t vset_lane_f32(float32_t value, float32x2_t vec, __constrange(0,1) int lane); // VMOV.32 d0[0],…
12032 …2SSE_INLINE float32x2_t vset_lane_f32(float32_t value, float32x2_t vec, __constrange(0,1) int lane)
12036 return vld1_lane_f32(&val, vec, lane);
12039 …x16_t vsetq_lane_u8(uint8_t value, uint8x16_t vec, __constrange(0,15) int lane); // VMOV.8 d0[0],r0
12040 …EON2SSE_INLINE uint8x16_t vsetq_lane_u8(uint8_t value, uint8x16_t vec, __constrange(0,15) int lane)
12044 return vld1q_lane_u8(&val, vec, lane);
12047 …x8_t vsetq_lane_u16(uint16_t value, uint16x8_t vec, __constrange(0,7) int lane); // VMOV.16 d0[0],…
12048 …ON2SSE_INLINE uint16x8_t vsetq_lane_u16(uint16_t value, uint16x8_t vec, __constrange(0,7) int lane)
12052 return vld1q_lane_u16(&val, vec, lane);
12055 …x4_t vsetq_lane_u32(uint32_t value, uint32x4_t vec, __constrange(0,3) int lane); // VMOV.32 d0[0],…
12056 …ON2SSE_INLINE uint32x4_t vsetq_lane_u32(uint32_t value, uint32x4_t vec, __constrange(0,3) int lane)
12060 return vld1q_lane_u32(&val, vec, lane);
12063 _NEON2SSESTORAGE int8x16_t vsetq_lane_s8(int8_t value, int8x16_t vec, __constrange(0,15) int lane);…
12064 _NEON2SSE_INLINE int8x16_t vsetq_lane_s8(int8_t value, int8x16_t vec, __constrange(0,15) int lane)
12068 return vld1q_lane_s8(&val, vec, lane);
12071 _NEON2SSESTORAGE int16x8_t vsetq_lane_s16(int16_t value, int16x8_t vec, __constrange(0,7) int lane)…
12072 _NEON2SSE_INLINE int16x8_t vsetq_lane_s16(int16_t value, int16x8_t vec, __constrange(0,7) int lane)
12076 return vld1q_lane_s16(&val, vec, lane);
12079 _NEON2SSESTORAGE int32x4_t vsetq_lane_s32(int32_t value, int32x4_t vec, __constrange(0,3) int lane)…
12080 _NEON2SSE_INLINE int32x4_t vsetq_lane_s32(int32_t value, int32x4_t vec, __constrange(0,3) int lane)
12084 return vld1q_lane_s32(&val, vec, lane);
12087 …x16_t vsetq_lane_p8(poly8_t value, poly8x16_t vec, __constrange(0,15) int lane); // VMOV.8 d0[0],r0
12090 …x8_t vsetq_lane_p16(poly16_t value, poly16x8_t vec, __constrange(0,7) int lane); // VMOV.16 d0[0],…
12093 …_t vsetq_lane_f32(float32_t value, float32x4_t vec, __constrange(0,3) int lane); // VMOV.32 d0[0],…
12094 …SSE_INLINE float32x4_t vsetq_lane_f32(float32_t value, float32x4_t vec, __constrange(0,3) int lane)
12098 return vld1q_lane_f32(&val, vec, lane);
12101 _NEON2SSESTORAGE int64x1_t vset_lane_s64(int64_t value, int64x1_t vec, __constrange(0,0) int lane);…
12102 _NEON2SSE_INLINE int64x1_t vset_lane_s64(int64_t value, int64x1_t vec, __constrange(0,0) int lane)
12106 return vld1_lane_s64(&val, vec, lane);
12109 …t64x1_t vset_lane_u64(uint64_t value, uint64x1_t vec, __constrange(0,0) int lane); // VMOV d0,r0,r0
12110 …EON2SSE_INLINE uint64x1_t vset_lane_u64(uint64_t value, uint64x1_t vec, __constrange(0,0) int lane)
12114 return vld1_lane_u64(&val, vec, lane);
12117 _NEON2SSESTORAGE int64x2_t vsetq_lane_s64(int64_t value, int64x2_t vec, __constrange(0,1) int lane)…
12118 _NEON2SSE_INLINE int64x2_t vsetq_lane_s64(int64_t value, int64x2_t vec, __constrange(0,1) int lane)
12122 return vld1q_lane_s64(&val, vec, lane);
12125 …64x2_t vsetq_lane_u64(uint64_t value, uint64x2_t vec, __constrange(0,1) int lane); // VMOV d0,r0,r0
12384 _NEON2SSESTORAGE uint8x8_t vdup_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0…
12385 _NEON2SSE_INLINE uint8x8_t vdup_lane_u8(uint8x8_t vec, __constrange(0,7) int lane)
12390 valane = vec.m64_u8[lane];
12397 _NEON2SSESTORAGE uint16x4_t vdup_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d…
12398 _NEON2SSE_INLINE uint16x4_t vdup_lane_u16(uint16x4_t vec, __constrange(0,3) int lane)
12402 valane = vec.m64_u16[lane];
12410 _NEON2SSESTORAGE uint32x2_t vdup_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VDUP.32 d…
12411 _NEON2SSE_INLINE uint32x2_t vdup_lane_u32(uint32x2_t vec, __constrange(0,1) int lane)
12414 res.m64_u32[0] = vec.m64_u32[lane];
12419 _NEON2SSESTORAGE int8x8_t vdup_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0[…
12422 _NEON2SSESTORAGE int16x4_t vdup_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d0…
12425 _NEON2SSESTORAGE int32x2_t vdup_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VDUP.32 d0…
12428 _NEON2SSESTORAGE poly8x8_t vdup_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VDUP.8 d0,d0…
12431 _NEON2SSESTORAGE poly16x4_t vdup_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VDUP.16 d…
12434 _NEON2SSESTORAGE float32x2_t vdup_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VDUP.32…
12435 _NEON2SSE_INLINE float32x2_t vdup_lane_f32(float32x2_t vec, __constrange(0,1) int lane)
12438 res.m64_f32[0] = vec.m64_f32[lane];
12443 _NEON2SSESTORAGE uint8x16_t vdupq_lane_u8(uint8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,…
12444 _NEON2SSE_INLINE uint8x16_t vdupq_lane_u8(uint8x8_t vec, __constrange(0,7) int lane) // VDUP.8 q0,d…
12446 const int8_t lane8 = (int8_t) lane;
12451 _NEON2SSESTORAGE uint16x8_t vdupq_lane_u16(uint16x4_t vec, __constrange(0,3) int lane); // VDUP.16 …
12452 _NEON2SSE_INLINE uint16x8_t vdupq_lane_u16(uint16x4_t vec, __constrange(0,3) int lane) // VDUP.16 q…
12455 const int8_t lane16 = ((int8_t) lane) << 1;
12462 _NEON2SSESTORAGE uint32x4_t vdupq_lane_u32(uint32x2_t vec, __constrange(0,1) int lane); // VDUP.32 …
12463 _NEON2SSE_INLINE uint32x4_t vdupq_lane_u32(uint32x2_t vec, __constrange(0,1) int lane)
12466 if (lane == 1)
12472 _NEON2SSESTORAGE int8x16_t vdupq_lane_s8(int8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,d0…
12475 _NEON2SSESTORAGE int16x8_t vdupq_lane_s16(int16x4_t vec, __constrange(0,3) int lane); // VDUP.16 q0…
12478 _NEON2SSESTORAGE int32x4_t vdupq_lane_s32(int32x2_t vec, __constrange(0,1) int lane); // VDUP.32 q0…
12481 _NEON2SSESTORAGE poly8x16_t vdupq_lane_p8(poly8x8_t vec, __constrange(0,7) int lane); // VDUP.8 q0,…
12484 _NEON2SSESTORAGE poly16x8_t vdupq_lane_p16(poly16x4_t vec, __constrange(0,3) int lane); // VDUP.16 …
12487 _NEON2SSESTORAGE float32x4_t vdupq_lane_f32(float32x2_t vec, __constrange(0,1) int lane); // VDUP.3…
12488 #define vdupq_lane_f32(vec, lane) _mm_load1_ps((vec.m64_f32 + lane)) argument
12490 _NEON2SSESTORAGE int64x1_t vdup_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV d0,d0
12491 #define vdup_lane_s64(vec,lane) vec argument
12493 _NEON2SSESTORAGE uint64x1_t vdup_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV d0,d0
12494 #define vdup_lane_u64(vec,lane) vec argument
12496 _NEON2SSESTORAGE int64x2_t vdupq_lane_s64(int64x1_t vec, __constrange(0,0) int lane); // VMOV q0,q0
12497 _NEON2SSE_INLINE int64x2_t vdupq_lane_s64(int64x1_t vec, __constrange(0,0) int lane)
12504 _NEON2SSESTORAGE uint64x2_t vdupq_lane_u64(uint64x1_t vec, __constrange(0,0) int lane); // VMOV q0,…