| /external/python/cpython3/Modules/_sha3/kcp/ |
| KeccakP-1600-opt64.c | 98 UINT64 lane; local
102 lane = data[0];
104 lane = 0;
105 memcpy(&lane, data, length);
107 lane <<= offset*8;
109 UINT64 lane = 0;
112 lane |= ((UINT64)data[i]) << ((i+offset)*8);
114 ((UINT64*)state)[lanePosition] ^= lane;
164 UINT64 lane = (UINT64)curData[0]
172 ((UINT64*)state)[i] ^= lane;
182 UINT64 lane = byte; local
306 UINT64 lane = ((UINT64*)state)[lanePosition]; local
382 UINT64 lane = ((UINT64*)state)[lanePosition]; local
[all...] |
| /external/tensorflow/tensorflow/core/profiler/internal/ |
| tfprof_timeline.cc | 241 for (const auto& lane : process.second) {
242 for (const auto& node : lane.second) {
248 process.first, lane.first, "Op",
256 process.first, lane.first, flow_id);
350 const auto& lane = p->lanes[i]; local
352 for (auto cur_it = lane.rbegin(); cur_it != lane.rend(); ++cur_it) {
|
| /external/v8/src/compiler/ |
| simd-scalar-lowering.cc | 403 int32_t lane = OpParameter<int32_t>(node); local
405 GetReplacementsWithType(node->InputAt(0), rep_type)[lane], nullptr,
414 int32_t lane = OpParameter<int32_t>(node); local
415 DCHECK(lane >= 0 && lane <= 3);
418 rep_node[lane] = GetReplacements(repNode)[0];
420 rep_node[lane] = repNode;
|
| /external/v8/src/wasm/ |
| function-body-decoder-impl.h | 299 // Operand for SIMD lane operations.
301 uint8_t lane; member in struct:v8::internal::wasm::SimdLaneOperand
305 lane = decoder->checked_read_u8(pc, 2, "lane");
|
| /device/linaro/bootloader/OpenPlatformPkg/Chips/Hisilicon/Pv660/Drivers/PcieInitDxe/ |
| PcieInitLib.c | 35 #define DS_API(lane) ((0x1FF6c + 8*(15-lane))*2)
714 UINT32 lane;
local
725 for (lane = 0; lane < 8; lane++)
726 RegWrite(pcie_serders_base[HostBridgeNum][Port] + (UINT32)DS_API(lane) + 4, 0x3851);
[all...] |
| /external/mesa3d/src/gallium/drivers/swr/rasterizer/core/ |
| pa_avx.cpp | 125 for (uint32_t lane = 0; lane < KNOB_SIMD_WIDTH; ++lane)
127 uint32_t input_cp = lane * TotalControlPoints + cp;
132 vec[lane] = pInputVec[input_lane];
432 // Extract vertex 0 to every lane of first vector
630 int lane = pa.numPrims - pa.numPrimsComplete - 1; local
635 targetVtx[lane] = startVtx[0];
[all...] |
| clip.h | 369 0 * sizeof(simdvertex), // unused lane
379 // @todo dynamic mask based on actual # of verts generated per lane
395 // tranpose clipper output so that each lane's vertices are in SIMD order
551 // step to the lane
557 // gathers a single component for a given attribute for each SIMD lane
572 DWORD lane; local
573 while (_BitScanForward(&lane, mask))
575 mask &= ~(1 << lane);
576 uint8_t* pBuf = (uint8_t*)pBuffer + pOffsets[lane];
577 *(float*)pBuf = pSrc[lane];
[all...] |
| /external/tensorflow/tensorflow/core/kernels/ |
| reduction_gpu_kernels.cu.h | 219 const int lane = threadIdx.x % 32; local
228 int col = lane;
244 if (row < num_rows && lane == 0) out[row] = sum;
256 const int lane = threadIdx.x % 32; local
257 const int lane_row = lane / num_cols;
263 int col = lane % num_cols;
285 if (lane < num_cols) sum = op(sum, tmp);
288 if (lane < num_cols) partial_sums[lane * 33 + threadIdx.y] = sum;
[all...] |
| /external/tensorflow/tensorflow/contrib/lite/kernels/internal/optimized/ |
| optimized_ops.h | 479 int lane = (in + 8 - input_size) % 4; local
484 buf[lane + 4 * k] += filter_val * input_val;
[all...] |
| /external/mesa3d/src/gallium/drivers/swr/rasterizer/jitter/ |
| builder_misc.cpp | 398 /// PRINT("index %d = 0x%p\n",{C(lane), pIndex});
399 /// where C(lane) creates a constant value to print, and pIndex is the Value*
703 /// Byte masks in lower 128 lane of b selects 8 bit values from lower
752 /// @param a - 128bit SIMD lane(16x8bit) of 8bit integer values. Only
769 // Extract 8 values from 128bit lane and sign extend
777 /// @param a - 128bit SIMD lane(8x16bit) of 16bit integer values.
793 // Extract 8 values from 128bit lane and sign extend
802 /// @param a - 256bit SIMD lane(8x32bit) of integer values.
803 /// @param idx - 256bit SIMD lane(8x32bit) of 3 bit lane index value
1233 uint32_t lane = ((i == 0) || (i == 2)) ? 0 : 1; local
1322 uint32_t lane = ((i == 0) || (i == 2)) ? 0 : 1; local
[all...] |
| fetch_jit.cpp | 313 for(uint32_t lane = 0; lane < mVWidth; ++lane)
316 Value* index = VEXTRACT(vCurIndices, C(lane));
331 // We use a full-lane, but don't actually care.
569 // gather SIMD full pixels per lane then shift/mask to move each component to their
618 // store in simd lane
1343 uint32_t lane = ((i == 0) || (i == 2)) ? 0 : 1; local
1562 uint32_t lane = ((i == 0) || (i == 2)) ? 0 : 1; local
[all...] |
| /external/v8/src/compiler/x64/ |
| instruction-selector-x64.cc | 2284 int32_t lane = OpParameter<int32_t>(node); local
2291 int32_t lane = OpParameter<int32_t>(node); local
[all...] |
| /external/vixl/src/aarch64/ |
| simulator-aarch64.cc | 783 for (int lane = leftmost_lane; lane >= rightmost_lane; lane--) {
785 ? ReadVRegister(code).GetLane<float>(lane)
786 : ReadVRegister(code).GetLane<double>(lane);
899 unsigned lane) {
908 lane);
939 unsigned lane) {
951 PrintVRegisterRawHelper(reg_code, reg_size, lane_size * lane);
953 PrintVRegisterFPHelper(reg_code, lane_size, lane_count, lane);
4223 int lane = instr->GetNEONLSIndex(index_shift); local
[all...] |
| /external/valgrind/VEX/priv/ |
| guest_x86_toIR.c | 513 least significant lane (rightmost in the register). */
8932 Int lane; local
11022 Int lane; local
11043 putXMMRegLane16( gregOfRM(modrm), lane & 7, mkexpr(t4) ); local
[all...] |
| guest_amd64_toIR.c | 14362 Int lane; local
14403 Int lane; local
27896 IRExpr* lane = (laneIs32 ? getYMMRegLane32 : getYMMRegLane64)( rV, i ); local
[all...] |
| guest_arm64_toIR.c | 9068 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I8); local
9075 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I8); local
9082 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I16); local
9089 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I16); local
9096 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I32); local
9103 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I32); local
9110 IRExpr* lane = getQRegLane(nn, laneNo, Ity_I64); local
[all...] |
| /external/vixl/src/aarch32/ |
| disasm-aarch32.cc | 73 DecodeNeon(int lane, SpacingType spacing)
74 : lane_(lane), spacing_(spacing), valid_(true) {}
327 DataTypeValue Dt_U_opc1_opc2_1_Decode(uint32_t value, unsigned* lane) {
329 *lane = value & 7;
333 *lane = (value >> 1) & 3;
337 *lane = value & 7;
341 *lane = (value >> 1) & 3;
345 *lane = (value >> 2) & 1;
348 *lane = -1;
352 DataTypeValue Dt_opc1_opc2_1_Decode(uint32_t value, unsigned* lane) {
829 int lane = (value >> 1) & 0x7; local
835 int lane = (value >> 2) & 0x3; local
841 int lane = (value >> 3) & 0x1; local
861 int lane = (value >> 1) & 0x7; local
874 int lane = (value >> 2) & 0x3; local
887 int lane = (value >> 3) & 0x1; local
908 int lane = (value >> 1) & 0x7; local
921 int lane = (value >> 2) & 0x3; local
934 int lane = (value >> 3) & 0x1; local
955 int lane = (value >> 1) & 0x7; local
968 int lane = (value >> 2) & 0x3; local
983 int lane = (value >> 3) & 0x1; local
14968 int lane = decode_neon.GetLane(); local
14982 lane), local
15010 int lane = decode_neon.GetLane(); local
15024 lane), local
15054 int lane = decode_neon.GetLane(); local
15069 lane), local
15117 int lane = decode_neon.GetLane(); local
15134 lane), local
15162 int lane = decode_neon.GetLane(); local
15179 lane), local
15209 int lane = decode_neon.GetLane(); local
15227 lane), local
15326 int lane = decode_neon.GetLane(); local
15343 lane), local
15370 int lane = decode_neon.GetLane(); local
15387 lane), local
15416 int lane = decode_neon.GetLane(); local
15435 lane), local
15483 int lane = decode_neon.GetLane(); local
15500 lane), local
15528 int lane = decode_neon.GetLane(); local
15545 lane), local
15575 int lane = decode_neon.GetLane(); local
15593 lane), local
15793 int lane = decode_neon.GetLane(); local
15807 lane), local
15835 int lane = decode_neon.GetLane(); local
15849 lane), local
15879 int lane = decode_neon.GetLane(); local
15894 lane), local
16103 int lane = decode_neon.GetLane(); local
16120 lane), local
16148 int lane = decode_neon.GetLane(); local
16165 lane), local
16195 int lane = decode_neon.GetLane(); local
16213 lane), local
16406 int lane = decode_neon.GetLane(); local
16423 lane), local
16446 int lane = decode_neon.GetLane(); local
16463 lane), local
16488 int lane = decode_neon.GetLane(); local
16507 lane), local
16720 int lane = decode_neon.GetLane(); local
16737 lane), local
16765 int lane = decode_neon.GetLane(); local
16782 lane), local
16812 int lane = decode_neon.GetLane(); local
16830 lane), local
25160 unsigned lane; local
25335 unsigned lane; local
28809 unsigned lane; local
28835 unsigned lane; local
29022 int lane; local
29062 int lane; local
29105 int lane; local
29400 int lane; local
29440 int lane; local
29483 int lane; local
29820 int lane; local
29929 int lane; local
29957 int lane; local
29993 int lane; local
30029 int lane; local
43001 unsigned lane; local
43023 unsigned lane; local
43199 int lane; local
43232 int lane; local
43268 int lane; local
43536 int lane; local
43569 int lane; local
43605 int lane; local
43917 int lane; local
44020 int lane; local
44044 int lane; local
44076 int lane; local
44108 int lane; local
51756 int lane = decode_neon.GetLane(); local
51796 int lane = decode_neon.GetLane(); local
51837 int lane = decode_neon.GetLane(); local
51897 int lane = decode_neon.GetLane(); local
51939 int lane = decode_neon.GetLane(); local
51982 int lane = decode_neon.GetLane(); local
52095 int lane = decode_neon.GetLane(); local
52136 int lane = decode_neon.GetLane(); local
52179 int lane = decode_neon.GetLane(); local
52242 int lane = decode_neon.GetLane(); local
52284 int lane = decode_neon.GetLane(); local
52327 int lane = decode_neon.GetLane(); local
54341 int lane = decode_neon.GetLane(); local
54381 int lane = decode_neon.GetLane(); local
54422 int lane = decode_neon.GetLane(); local
54636 int lane = decode_neon.GetLane(); local
54678 int lane = decode_neon.GetLane(); local
54721 int lane = decode_neon.GetLane(); local
54923 int lane = decode_neon.GetLane(); local
54960 int lane = decode_neon.GetLane(); local
54999 int lane = decode_neon.GetLane(); local
55222 int lane = decode_neon.GetLane(); local
55264 int lane = decode_neon.GetLane(); local
55307 int lane = decode_neon.GetLane(); local
67751 unsigned lane; local
67953 unsigned lane; local
[all...] |
| /toolchain/binutils/binutils-2.27/gas/config/ |
| tc-arm.c | 2004 int lane = -1; local
[all...] |
| /prebuilts/gcc/darwin-x86/x86/x86_64-linux-android-4.9/lib/gcc/x86_64-linux-android/4.9.x/include/ |
| arm_neon.h | 415 //Vector add: vadd -> Vr[i]:=Va[i]+Vb[i], Vr, Va, Vb have equal lane sizes.
434 //Vector long add: vaddl -> Vr[i]:=Va[i]+Vb[i], Va, Vb have equal lane sizes, result is a 128 bit vector of lanes that are twice the width.
523 //multiply lane
1212 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1213 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1214 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1215 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
1216 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1217 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1218 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1219 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1220 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1221 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/VLD1.64 {d0}, [r0] variable
1222 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1223 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1224 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1225 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1226 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1227 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1228 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8{d0[0]}, [r0] variable
1229 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1230 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1231 float16x4_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1232 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1233 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1234 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1235 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1395 uint16x8x2_t vld2q_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1396 uint32x4x2_t vld2q_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1397 int16x8x2_t vld2q_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1398 int32x4x2_t vld2q_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1399 float16x8x2_t vld2q_lane_f16_ptr(__transfersize(2) __fp16 const * ptr, float16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1400 float32x4x2_t vld2q_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1401 poly16x8x2_t vld2q_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1402 uint8x8x2_t vld2_lane_u8_ptr(__transfersize(2) uint8_t const * ptr, uint8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1403 uint16x4x2_t vld2_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1404 uint32x2x2_t vld2_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1405 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1406 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/VLD2.16 {d0[0], d1[0]}, [r0] variable
1407 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/VLD2.32 {d0[0], d1[0]}, [r0] variable
1409 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1410 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1411 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1412 uint16x8x3_t vld3q_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1413 uint32x4x3_t vld3q_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1414 int16x8x3_t vld3q_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1415 int32x4x3_t vld3q_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1416 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1417 float32x4x3_t vld3q_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1418 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1419 uint8x8x3_t vld3_lane_u8_ptr(__transfersize(3) uint8_t const * ptr, uint8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1420 uint16x4x3_t vld3_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1421 uint32x2x3_t vld3_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1422 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1423 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1424 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1425 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1426 float32x2x3_t vld3_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1427 poly8x8x3_t vld3_lane_p8_ptr(__transfersize(3) poly8_t const * ptr, poly8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1428 poly16x4x3_t vld3_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1429 uint16x8x4_t vld4q_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1430 uint32x4x4_t vld4q_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1431 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1432 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1433 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1434 float32x4x4_t vld4q_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1435 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1436 uint8x8x4_t vld4_lane_u8_ptr(__transfersize(4) uint8_t const * ptr, uint8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1437 uint16x4x4_t vld4_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1438 uint32x2x4_t vld4_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1439 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1440 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); \/\/VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1441 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); \/\/VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1442 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1443 float32x2x4_t vld4_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1444 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1445 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1514 void vst2q_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1515 void vst2q_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1516 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1517 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1518 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1519 void vst2q_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x4x2_t * val, __constrange(0,3) int lane); \/\/VST2.32 {d0[0], d2[0]}, [r0] variable
1520 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1521 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1522 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1523 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1524 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0],d1[0]}, [r0] variable
1525 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1526 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1527 void vst2_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1528 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1529 void vst2_lane_p8_ptr(__transfersize(2) poly8_t * ptr, poly8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1530 void vst2_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1531 void vst3q_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1532 void vst3q_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1533 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1534 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1535 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1536 void vst3q_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x4x3_t * val, __constrange(0,3) int lane); \/\/VST3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1537 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1538 void vst3_lane_u8_ptr(__transfersize(3) uint8_t * ptr, uint8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1539 void vst3_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1540 void vst3_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1541 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8 {d0[0],d1[0], d2[0]}, [r0] variable
1542 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1543 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1544 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1545 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1546 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1547 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1548 void vst4q_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1549 void vst4q_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1550 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1551 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1552 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1553 void vst4q_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x4x4_t * val, __constrange(0,3) int lane); \/\/VST4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1554 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1555 void vst4_lane_u8_ptr(__transfersize(4) uint8_t * ptr, uint8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1556 void vst4_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1557 void vst4_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1558 void vst4_lane_s8_ptr(__transfersize(4) int8_t * ptr, int8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8 {d0[0],d1[0], d2[0], d3[0]}, [r0] variable
1559 void vst4_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1560 void vst4_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1561 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1562 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1563 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1564 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
9281 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9284 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9287 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9290 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9294 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9297 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9300 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9303 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9306 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9315 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9318 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9321 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9324 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9333 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9342 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9351 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9360 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9363 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9366 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9369 float16x4_t vld1_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9372 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9381 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9384 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9387 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9628 void vst1q_lane_u8(__transfersize(1) uint8_t * ptr, uint8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9631 void vst1q_lane_u16(__transfersize(1) uint16_t * ptr, uint16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9634 void vst1q_lane_u32(__transfersize(1) uint32_t * ptr, uint32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9637 void vst1q_lane_u64(__transfersize(1) uint64_t * ptr, uint64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9640 void vst1q_lane_s8(__transfersize(1) int8_t * ptr, int8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9643 void vst1q_lane_s16(__transfersize(1) int16_t * ptr, int16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9646 void vst1q_lane_s32(__transfersize(1) int32_t * ptr, int32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9649 void vst1q_lane_s64(__transfersize(1) int64_t * ptr, int64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9652 void vst1q_lane_f16(__transfersize(1) __fp16 * ptr, float16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9655 void vst1q_lane_f32(__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9663 void vst1q_lane_p8(__transfersize(1) poly8_t * ptr, poly8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9666 void vst1q_lane_p16(__transfersize(1) poly16_t * ptr, poly16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9669 void vst1_lane_u8(__transfersize(1) uint8_t * ptr, uint8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9675 void vst1_lane_u16(__transfersize(1) uint16_t * ptr, uint16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9681 void vst1_lane_u32(__transfersize(1) uint32_t * ptr, uint32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9687 void vst1_lane_u64(__transfersize(1) uint64_t * ptr, uint64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9693 void vst1_lane_s8(__transfersize(1) int8_t * ptr, int8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9696 void vst1_lane_s16(__transfersize(1) int16_t * ptr, int16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9699 void vst1_lane_s32(__transfersize(1) int32_t * ptr, int32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9703 void vst1_lane_s64(__transfersize(1) int64_t * ptr, int64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9707 void vst1_lane_f16(__transfersize(1) __fp16 * ptr, float16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9710 void vst1_lane_f32(__transfersize(1) float32_t * ptr, float32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9716 void vst1_lane_p8(__transfersize(1) poly8_t * ptr, poly8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9719 void vst1_lane_p16(__transfersize(1) poly16_t * ptr, poly16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
10736 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10740 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10744 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10750 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src,__constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10761 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10765 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10817 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10833 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src,__constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10870 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
10873 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10876 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
10879 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10929 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10933 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10937 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10953 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src,__constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10993 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); variable
10997 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); variable
11001 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); variable
11005 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); variable
11022 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); variable
11026 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); variable
11621 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); variable
11625 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); variable
11629 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); variable
11641 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); variable
11645 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0], d1[0]}, [r0] variable
11654 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16 {d0[0], d1[0]}, [r0] variable
11663 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11672 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); variable
11676 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); variable
11680 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); variable
11686 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11719 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); variable
11723 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); variable
11727 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); variable
11740 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); variable
11771 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); variable
11775 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); variable
11779 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); variable
11783 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); variable
11787 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); variable
11797 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); variable
11801 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); variable
11823 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); variable
11827 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); variable
11831 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); variable
11845 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); variable
11888 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); variable
11891 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
11902 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); variable
11906 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); variable
[all...] |
| /prebuilts/gcc/linux-x86/host/x86_64-linux-glibc2.15-4.8/lib/gcc/x86_64-linux/4.8/include/ |
| arm_neon.h | 415 //Vector add: vadd -> Vr[i]:=Va[i]+Vb[i], Vr, Va, Vb have equal lane sizes.
434 //Vector long add: vaddl -> Vr[i]:=Va[i]+Vb[i], Va, Vb have equal lane sizes, result is a 128 bit vector of lanes that are twice the width.
523 //multiply lane
1212 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1213 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1214 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1215 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
1216 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1217 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1218 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1219 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1220 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1221 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/VLD1.64 {d0}, [r0] variable
1222 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1223 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1224 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1225 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1226 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1227 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1228 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8{d0[0]}, [r0] variable
1229 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1230 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1231 float16x4_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1232 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1233 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1234 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1235 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1395 uint16x8x2_t vld2q_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1396 uint32x4x2_t vld2q_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1397 int16x8x2_t vld2q_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1398 int32x4x2_t vld2q_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1399 float16x8x2_t vld2q_lane_f16_ptr(__transfersize(2) __fp16 const * ptr, float16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1400 float32x4x2_t vld2q_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1401 poly16x8x2_t vld2q_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1402 uint8x8x2_t vld2_lane_u8_ptr(__transfersize(2) uint8_t const * ptr, uint8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1403 uint16x4x2_t vld2_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1404 uint32x2x2_t vld2_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1405 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1406 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/VLD2.16 {d0[0], d1[0]}, [r0] variable
1407 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/VLD2.32 {d0[0], d1[0]}, [r0] variable
1409 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1410 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1411 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1412 uint16x8x3_t vld3q_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1413 uint32x4x3_t vld3q_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1414 int16x8x3_t vld3q_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1415 int32x4x3_t vld3q_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1416 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1417 float32x4x3_t vld3q_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1418 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1419 uint8x8x3_t vld3_lane_u8_ptr(__transfersize(3) uint8_t const * ptr, uint8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1420 uint16x4x3_t vld3_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1421 uint32x2x3_t vld3_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1422 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1423 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1424 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1425 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1426 float32x2x3_t vld3_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1427 poly8x8x3_t vld3_lane_p8_ptr(__transfersize(3) poly8_t const * ptr, poly8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1428 poly16x4x3_t vld3_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1429 uint16x8x4_t vld4q_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1430 uint32x4x4_t vld4q_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1431 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1432 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1433 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1434 float32x4x4_t vld4q_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1435 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1436 uint8x8x4_t vld4_lane_u8_ptr(__transfersize(4) uint8_t const * ptr, uint8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1437 uint16x4x4_t vld4_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1438 uint32x2x4_t vld4_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1439 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1440 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); \/\/VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1441 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); \/\/VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1442 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1443 float32x2x4_t vld4_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1444 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1445 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1514 void vst2q_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1515 void vst2q_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1516 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1517 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1518 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1519 void vst2q_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x4x2_t * val, __constrange(0,3) int lane); \/\/VST2.32 {d0[0], d2[0]}, [r0] variable
1520 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1521 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1522 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1523 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1524 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0],d1[0]}, [r0] variable
1525 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1526 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1527 void vst2_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1528 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1529 void vst2_lane_p8_ptr(__transfersize(2) poly8_t * ptr, poly8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1530 void vst2_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1531 void vst3q_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1532 void vst3q_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1533 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1534 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1535 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1536 void vst3q_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x4x3_t * val, __constrange(0,3) int lane); \/\/VST3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1537 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1538 void vst3_lane_u8_ptr(__transfersize(3) uint8_t * ptr, uint8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1539 void vst3_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1540 void vst3_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1541 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8 {d0[0],d1[0], d2[0]}, [r0] variable
1542 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1543 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1544 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1545 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1546 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1547 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1548 void vst4q_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1549 void vst4q_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1550 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1551 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1552 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1553 void vst4q_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x4x4_t * val, __constrange(0,3) int lane); \/\/VST4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1554 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1555 void vst4_lane_u8_ptr(__transfersize(4) uint8_t * ptr, uint8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1556 void vst4_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1557 void vst4_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1558 void vst4_lane_s8_ptr(__transfersize(4) int8_t * ptr, int8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8 {d0[0],d1[0], d2[0], d3[0]}, [r0] variable
1559 void vst4_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1560 void vst4_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1561 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1562 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1563 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1564 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
9281 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9284 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9287 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9290 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9294 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9297 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9300 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9303 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9306 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9315 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9318 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9321 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9324 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9333 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9342 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9351 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9360 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9363 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9366 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9369 float16x4_t vld1_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9372 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9381 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9384 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9387 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9628 void vst1q_lane_u8(__transfersize(1) uint8_t * ptr, uint8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9631 void vst1q_lane_u16(__transfersize(1) uint16_t * ptr, uint16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9634 void vst1q_lane_u32(__transfersize(1) uint32_t * ptr, uint32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9637 void vst1q_lane_u64(__transfersize(1) uint64_t * ptr, uint64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9640 void vst1q_lane_s8(__transfersize(1) int8_t * ptr, int8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9643 void vst1q_lane_s16(__transfersize(1) int16_t * ptr, int16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9646 void vst1q_lane_s32(__transfersize(1) int32_t * ptr, int32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9649 void vst1q_lane_s64(__transfersize(1) int64_t * ptr, int64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9652 void vst1q_lane_f16(__transfersize(1) __fp16 * ptr, float16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9655 void vst1q_lane_f32(__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9663 void vst1q_lane_p8(__transfersize(1) poly8_t * ptr, poly8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9666 void vst1q_lane_p16(__transfersize(1) poly16_t * ptr, poly16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9669 void vst1_lane_u8(__transfersize(1) uint8_t * ptr, uint8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9675 void vst1_lane_u16(__transfersize(1) uint16_t * ptr, uint16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9681 void vst1_lane_u32(__transfersize(1) uint32_t * ptr, uint32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9687 void vst1_lane_u64(__transfersize(1) uint64_t * ptr, uint64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9693 void vst1_lane_s8(__transfersize(1) int8_t * ptr, int8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9696 void vst1_lane_s16(__transfersize(1) int16_t * ptr, int16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9699 void vst1_lane_s32(__transfersize(1) int32_t * ptr, int32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9703 void vst1_lane_s64(__transfersize(1) int64_t * ptr, int64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9707 void vst1_lane_f16(__transfersize(1) __fp16 * ptr, float16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9710 void vst1_lane_f32(__transfersize(1) float32_t * ptr, float32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9716 void vst1_lane_p8(__transfersize(1) poly8_t * ptr, poly8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9719 void vst1_lane_p16(__transfersize(1) poly16_t * ptr, poly16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
10736 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10740 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10744 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10750 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src,__constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10761 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10765 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10817 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10833 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src,__constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10870 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
10873 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10876 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
10879 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10929 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10933 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10937 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10953 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src,__constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10993 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); variable
10997 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); variable
11001 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); variable
11005 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); variable
11022 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); variable
11026 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); variable
11621 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); variable
11625 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); variable
11629 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); variable
11641 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); variable
11645 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0], d1[0]}, [r0] variable
11654 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16 {d0[0], d1[0]}, [r0] variable
11663 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11672 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); variable
11676 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); variable
11680 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); variable
11686 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11719 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); variable
11723 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); variable
11727 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); variable
11740 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); variable
11771 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); variable
11775 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); variable
11779 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); variable
11783 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); variable
11787 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); variable
11797 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); variable
11801 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); variable
11823 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); variable
11827 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); variable
11831 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); variable
11845 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); variable
11888 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); variable
11891 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
11902 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); variable
11906 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); variable
[all...] |
| /prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/lib/gcc/x86_64-linux-android/4.9.x/include/ |
| arm_neon.h | 415 //Vector add: vadd -> Vr[i]:=Va[i]+Vb[i], Vr, Va, Vb have equal lane sizes.
434 //Vector long add: vaddl -> Vr[i]:=Va[i]+Vb[i], Va, Vb have equal lane sizes, result is a 128 bit vector of lanes that are twice the width.
523 //multiply lane
1212 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1213 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1214 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1215 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
1216 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1217 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1218 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1219 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1220 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1221 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/VLD1.64 {d0}, [r0] variable
1222 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1223 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
1224 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1225 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1226 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1227 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1228 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8{d0[0]}, [r0] variable
1229 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1230 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/VLD1.32 {d0[0]}, [r0] variable
1231 float16x4_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1232 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
1233 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/VLD1.64 {d0}, [r0] variable
1234 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/VLD1.8 {d0[0]}, [r0] variable
1235 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/VLD1.16 {d0[0]}, [r0] variable
1395 uint16x8x2_t vld2q_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1396 uint32x4x2_t vld2q_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1397 int16x8x2_t vld2q_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1398 int32x4x2_t vld2q_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1399 float16x8x2_t vld2q_lane_f16_ptr(__transfersize(2) __fp16 const * ptr, float16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1400 float32x4x2_t vld2q_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.32 {d0[0], d2[0]}, [r0] variable
1401 poly16x8x2_t vld2q_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.16 {d0[0], d2[0]}, [r0] variable
1402 uint8x8x2_t vld2_lane_u8_ptr(__transfersize(2) uint8_t const * ptr, uint8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1403 uint16x4x2_t vld2_lane_u16_ptr(__transfersize(2) uint16_t const * ptr, uint16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1404 uint32x2x2_t vld2_lane_u32_ptr(__transfersize(2) uint32_t const * ptr, uint32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1405 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1406 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/VLD2.16 {d0[0], d1[0]}, [r0] variable
1407 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/VLD2.32 {d0[0], d1[0]}, [r0] variable
1409 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
1410 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/VLD2.8 {d0[0], d1[0]}, [r0] variable
1411 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
1412 uint16x8x3_t vld3q_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1413 uint32x4x3_t vld3q_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1414 int16x8x3_t vld3q_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1415 int32x4x3_t vld3q_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1416 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1417 float32x4x3_t vld3q_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1418 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
1419 uint8x8x3_t vld3_lane_u8_ptr(__transfersize(3) uint8_t const * ptr, uint8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1420 uint16x4x3_t vld3_lane_u16_ptr(__transfersize(3) uint16_t const * ptr, uint16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1421 uint32x2x3_t vld3_lane_u32_ptr(__transfersize(3) uint32_t const * ptr, uint32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1422 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1423 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1424 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1425 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1426 float32x2x3_t vld3_lane_f32_ptr(__transfersize(3) float32_t const * ptr, float32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
1427 poly8x8x3_t vld3_lane_p8_ptr(__transfersize(3) poly8_t const * ptr, poly8x8x3_t * src, __constrange(0,7) int lane); \/\/VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
1428 poly16x4x3_t vld3_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
1429 uint16x8x4_t vld4q_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1430 uint32x4x4_t vld4q_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1431 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1432 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1433 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1434 float32x4x4_t vld4q_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1435 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1436 uint8x8x4_t vld4_lane_u8_ptr(__transfersize(4) uint8_t const * ptr, uint8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1437 uint16x4x4_t vld4_lane_u16_ptr(__transfersize(4) uint16_t const * ptr, uint16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1438 uint32x2x4_t vld4_lane_u32_ptr(__transfersize(4) uint32_t const * ptr, uint32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1439 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1440 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); \/\/VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1441 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); \/\/VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1442 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1443 float32x2x4_t vld4_lane_f32_ptr(__transfersize(4) float32_t const * ptr, float32x2x4_t * src, __constrange(0,1) int lane); \/\/ VLD4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1444 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); \/\/VLD4.8 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1445 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.16 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1514 void vst2q_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1515 void vst2q_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1516 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1517 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.32{d0[0], d2[0]}, [r0] variable
1518 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1519 void vst2q_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x4x2_t * val, __constrange(0,3) int lane); \/\/VST2.32 {d0[0], d2[0]}, [r0] variable
1520 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.16{d0[0], d2[0]}, [r0] variable
1521 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1522 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1523 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1524 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0],d1[0]}, [r0] variable
1525 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1526 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1527 void vst2_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1528 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32{d0[0], d1[0]}, [r0] variable
1529 void vst2_lane_p8_ptr(__transfersize(2) poly8_t * ptr, poly8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8{d0[0], d1[0]}, [r0] variable
1530 void vst2_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16{d0[0], d1[0]}, [r0] variable
1531 void vst3q_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1532 void vst3q_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1533 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1534 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.32{d0[0], d2[0], d4[0]}, [r0] variable
1535 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1536 void vst3q_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x4x3_t * val, __constrange(0,3) int lane); \/\/VST3.32 {d0[0], d2[0], d4[0]}, [r0] variable
1537 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.16{d0[0], d2[0], d4[0]}, [r0] variable
1538 void vst3_lane_u8_ptr(__transfersize(3) uint8_t * ptr, uint8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1539 void vst3_lane_u16_ptr(__transfersize(3) uint16_t * ptr, uint16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1540 void vst3_lane_u32_ptr(__transfersize(3) uint32_t * ptr, uint32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1541 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8 {d0[0],d1[0], d2[0]}, [r0] variable
1542 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1543 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1544 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1545 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); \/\/ VST3.32{d0[0], d1[0], d2[0]}, [r0] variable
1546 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); \/\/ VST3.8{d0[0], d1[0], d2[0]}, [r0] variable
1547 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); \/\/ VST3.16{d0[0], d1[0], d2[0]}, [r0] variable
1548 void vst4q_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1549 void vst4q_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1550 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1551 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.32{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1552 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1553 void vst4q_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x4x4_t * val, __constrange(0,3) int lane); \/\/VST4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1554 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.16{d0[0], d2[0], d4[0], d6[0]}, [r0] variable
1555 void vst4_lane_u8_ptr(__transfersize(4) uint8_t * ptr, uint8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1556 void vst4_lane_u16_ptr(__transfersize(4) uint16_t * ptr, uint16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1557 void vst4_lane_u32_ptr(__transfersize(4) uint32_t * ptr, uint32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1558 void vst4_lane_s8_ptr(__transfersize(4) int8_t * ptr, int8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8 {d0[0],d1[0], d2[0], d3[0]}, [r0] variable
1559 void vst4_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1560 void vst4_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1561 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1562 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1563 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); \/\/ VST4.8{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
1564 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); \/\/ VST4.16{d0[0], d1[0], d2[0], d3[0]}, [r0] variable
9281 uint8x16_t vld1q_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9284 uint16x8_t vld1q_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9287 uint32x4_t vld1q_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9290 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9294 int8x16_t vld1q_lane_s8(__transfersize(1) int8_t const * ptr, int8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9297 int16x8_t vld1q_lane_s16(__transfersize(1) int16_t const * ptr, int16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9300 int32x4_t vld1q_lane_s32(__transfersize(1) int32_t const * ptr, int32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9303 float16x8_t vld1q_lane_f16(__transfersize(1) __fp16 const * ptr, float16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9306 float32x4_t vld1q_lane_f32(__transfersize(1) float32_t const * ptr, float32x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9315 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9318 poly8x16_t vld1q_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x16_t vec, __constrange(0,15) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9321 poly16x8_t vld1q_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9324 uint8x8_t vld1_lane_u8(__transfersize(1) uint8_t const * ptr, uint8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9333 uint16x4_t vld1_lane_u16(__transfersize(1) uint16_t const * ptr, uint16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9342 uint32x2_t vld1_lane_u32(__transfersize(1) uint32_t const * ptr, uint32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9351 uint64x1_t vld1_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9360 int8x8_t vld1_lane_s8(__transfersize(1) int8_t const * ptr, int8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9363 int16x4_t vld1_lane_s16(__transfersize(1) int16_t const * ptr, int16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9366 int32x2_t vld1_lane_s32(__transfersize(1) int32_t const * ptr, int32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9369 float16x4_t vld1_lane_f16(__transfersize(1) __fp16 const * ptr, float16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9372 float32x2_t vld1_lane_f32(__transfersize(1) float32_t const * ptr, float32x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.32 {d0[0]}, [r0] variable
9381 int64x1_t vld1_lane_s64(__transfersize(1) int64_t const * ptr, int64x1_t vec, __constrange(0,0) int lane); \/\/ VLD1.64 {d0}, [r0] variable
9384 poly8x8_t vld1_lane_p8(__transfersize(1) poly8_t const * ptr, poly8x8_t vec, __constrange(0,7) int lane); \/\/ VLD1.8 {d0[0]}, [r0] variable
9387 poly16x4_t vld1_lane_p16(__transfersize(1) poly16_t const * ptr, poly16x4_t vec, __constrange(0,3) int lane); \/\/ VLD1.16 {d0[0]}, [r0] variable
9628 void vst1q_lane_u8(__transfersize(1) uint8_t * ptr, uint8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9631 void vst1q_lane_u16(__transfersize(1) uint16_t * ptr, uint16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9634 void vst1q_lane_u32(__transfersize(1) uint32_t * ptr, uint32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9637 void vst1q_lane_u64(__transfersize(1) uint64_t * ptr, uint64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9640 void vst1q_lane_s8(__transfersize(1) int8_t * ptr, int8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9643 void vst1q_lane_s16(__transfersize(1) int16_t * ptr, int16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9646 void vst1q_lane_s32(__transfersize(1) int32_t * ptr, int32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9649 void vst1q_lane_s64(__transfersize(1) int64_t * ptr, int64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
9652 void vst1q_lane_f16(__transfersize(1) __fp16 * ptr, float16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9655 void vst1q_lane_f32(__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9663 void vst1q_lane_p8(__transfersize(1) poly8_t * ptr, poly8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9666 void vst1q_lane_p16(__transfersize(1) poly16_t * ptr, poly16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9669 void vst1_lane_u8(__transfersize(1) uint8_t * ptr, uint8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9675 void vst1_lane_u16(__transfersize(1) uint16_t * ptr, uint16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9681 void vst1_lane_u32(__transfersize(1) uint32_t * ptr, uint32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9687 void vst1_lane_u64(__transfersize(1) uint64_t * ptr, uint64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9693 void vst1_lane_s8(__transfersize(1) int8_t * ptr, int8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9696 void vst1_lane_s16(__transfersize(1) int16_t * ptr, int16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9699 void vst1_lane_s32(__transfersize(1) int32_t * ptr, int32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9703 void vst1_lane_s64(__transfersize(1) int64_t * ptr, int64x1_t val, __constrange(0,0) int lane); \/\/ VST1.64 {d0}, [r0] variable
9707 void vst1_lane_f16(__transfersize(1) __fp16 * ptr, float16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
9710 void vst1_lane_f32(__transfersize(1) float32_t * ptr, float32x2_t val, __constrange(0,1) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
9716 void vst1_lane_p8(__transfersize(1) poly8_t * ptr, poly8x8_t val, __constrange(0,7) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
9719 void vst1_lane_p16(__transfersize(1) poly16_t * ptr, poly16x4_t val, __constrange(0,3) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
10736 int8x8x2_t vld2_lane_s8_ptr(__transfersize(2) int8_t const * ptr, int8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10740 int16x4x2_t vld2_lane_s16_ptr(__transfersize(2) int16_t const * ptr, int16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10744 int32x2x2_t vld2_lane_s32_ptr(__transfersize(2) int32_t const * ptr, int32x2x2_t * src, __constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10750 float32x2x2_t vld2_lane_f32_ptr(__transfersize(2) float32_t const * ptr, float32x2x2_t * src,__constrange(0,1) int lane); \/\/ VLD2.32 {d0[0], d1[0]}, [r0] variable
10761 poly8x8x2_t vld2_lane_p8_ptr(__transfersize(2) poly8_t const * ptr, poly8x8x2_t * src, __constrange(0,7) int lane); \/\/ VLD2.8 {d0[0], d1[0]}, [r0] variable
10765 poly16x4x2_t vld2_lane_p16_ptr(__transfersize(2) poly16_t const * ptr, poly16x4x2_t * src, __constrange(0,3) int lane); \/\/ VLD2.16 {d0[0], d1[0]}, [r0] variable
10817 float16x8x3_t vld3q_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10833 poly16x8x3_t vld3q_lane_p16_ptr(__transfersize(3) poly16_t const * ptr, poly16x8x3_t * src,__constrange(0,7) int lane); \/\/ VLD3.16 {d0[0], d2[0], d4[0]}, [r0] variable
10870 int8x8x3_t vld3_lane_s8_ptr(__transfersize(3) int8_t const * ptr, int8x8x3_t * src, __constrange(0,7) int lane); \/\/ VLD3.8 {d0[0], d1[0], d2[0]}, [r0] variable
10873 int16x4x3_t vld3_lane_s16_ptr(__transfersize(3) int16_t const * ptr, int16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10876 int32x2x3_t vld3_lane_s32_ptr(__transfersize(3) int32_t const * ptr, int32x2x3_t * src, __constrange(0,1) int lane); \/\/ VLD3.32 {d0[0], d1[0], d2[0]}, [r0] variable
10879 float16x4x3_t vld3_lane_f16_ptr(__transfersize(3) __fp16 const * ptr, float16x4x3_t * src, __constrange(0,3) int lane); \/\/ VLD3.16 {d0[0], d1[0], d2[0]}, [r0] variable
10929 int16x8x4_t vld4q_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10933 int32x4x4_t vld4q_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x4x4_t * src, __constrange(0,3) int lane); \/\/ VLD4.32 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10937 float16x8x4_t vld4q_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x8x4_t * src, __constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10953 poly16x8x4_t vld4q_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x8x4_t * src,__constrange(0,7) int lane); \/\/ VLD4.16 {d0[0], d2[0], d4[0], d6[0]}, [r0] variable
10993 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); variable
10997 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); variable
11001 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); variable
11005 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); variable
11022 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); variable
11026 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); variable
11621 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); variable
11625 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); variable
11629 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); variable
11641 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); variable
11645 void vst2_lane_u8_ptr(__transfersize(2) uint8_t * ptr, uint8x8x2_t * val, __constrange(0,7) int lane); \/\/ VST2.8 {d0[0], d1[0]}, [r0] variable
11654 void vst2_lane_u16_ptr(__transfersize(2) uint16_t * ptr, uint16x4x2_t * val, __constrange(0,3) int lane); \/\/ VST2.16 {d0[0], d1[0]}, [r0] variable
11663 void vst2_lane_u32_ptr(__transfersize(2) uint32_t * ptr, uint32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11672 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); variable
11676 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); variable
11680 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); variable
11686 void vst2_lane_f32_ptr(__transfersize(2) float32_t * ptr, float32x2x2_t * val, __constrange(0,1) int lane); \/\/ VST2.32 {d0[0], d1[0]}, [r0] variable
11719 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); variable
11723 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); variable
11727 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); variable
11740 void vst3q_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x8x3_t * val, __constrange(0,7) int lane); variable
11771 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); variable
11775 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); variable
11779 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); variable
11783 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); variable
11787 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); variable
11797 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); variable
11801 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); variable
11823 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); variable
11827 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); variable
11831 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); variable
11845 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); variable
11888 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); variable
11891 void vst4_lane_f32_ptr(__transfersize(4) float32_t * ptr, float32x2x4_t * val, __constrange(0,1) int lane); \/\/ VST4.32 {d0[0], d1[0], d2[0], d3[0]}, [r0] variable
11902 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); variable
11906 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); variable
[all...] |
