| arm_neon.h | 324 //Vector add: vadd -> Vr[i]:=Va[i]+Vb[i], Vr, Va, Vb have equal lane sizes.
335 //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.
756 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
757 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
758 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
759 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
760 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
761 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
762 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
763 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
764 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/VLD1.64 {d0}, [r0] variable
765 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
766 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
905 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
906 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
907 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
908 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
909 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
910 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
911 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
912 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
913 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
914 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
915 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
916 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
917 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
919 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
920 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
921 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
922 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
923 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
924 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
925 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
926 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
927 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
928 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
929 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
930 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
931 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
932 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
933 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
934 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
935 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
936 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
937 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
938 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
939 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
940 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
941 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
942 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
943 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
944 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
945 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
946 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
947 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
948 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
949 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
950 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
951 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
952 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
953 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
954 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
955 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
1024 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
1025 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
1026 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
1027 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
1028 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
1029 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
1030 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
1031 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
1032 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
1033 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
1034 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
1035 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
1036 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
1037 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
1038 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
1039 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
1040 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
1041 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
1042 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
1043 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
1044 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
1045 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
1046 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
1047 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
1048 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
1049 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
1050 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
1051 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
1052 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
1053 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
1054 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
1055 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
1056 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
1057 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
1058 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
1059 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
1060 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
1061 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
1062 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
1063 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
1064 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
1065 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
1066 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
1067 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
1068 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
1069 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
1070 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
1071 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
1072 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
1073 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
1074 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
4553 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
4556 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
4559 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
4562 uint64x2_t vld1q_lane_u64(__transfersize(1) uint64_t const * ptr, uint64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
4565 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
4568 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
4571 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
4576 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
4584 int64x2_t vld1q_lane_s64(__transfersize(1) int64_t const * ptr, int64x2_t vec, __constrange(0,1) int lane); \/\/ VLD1.64 {d0}, [r0] variable
4587 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
4590 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
4695 void vst1q_lane_u8(__transfersize(1) uint8_t * ptr, uint8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
4698 void vst1q_lane_u16(__transfersize(1) uint16_t * ptr, uint16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
4701 void vst1q_lane_u32(__transfersize(1) uint32_t * ptr, uint32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
4704 void vst1q_lane_u64(__transfersize(1) uint64_t * ptr, uint64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
4707 void vst1q_lane_s8(__transfersize(1) int8_t * ptr, int8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
4710 void vst1q_lane_s16(__transfersize(1) int16_t * ptr, int16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
4713 void vst1q_lane_s32(__transfersize(1) int32_t * ptr, int32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
4716 void vst1q_lane_s64(__transfersize(1) int64_t * ptr, int64x2_t val, __constrange(0,1) int lane); \/\/ VST1.64 {d0}, [r0] variable
4719 void vst1q_lane_f16(__transfersize(1) __fp16 * ptr, float16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
4722 void vst1q_lane_f32(__transfersize(1) float32_t * ptr, float32x4_t val, __constrange(0,3) int lane); \/\/ VST1.32 {d0[0]}, [r0] variable
4730 void vst1q_lane_p8(__transfersize(1) poly8_t * ptr, poly8x16_t val, __constrange(0,15) int lane); \/\/ VST1.8 {d0[0]}, [r0] variable
4733 void vst1q_lane_p16(__transfersize(1) poly16_t * ptr, poly16x8_t val, __constrange(0,7) int lane); \/\/ VST1.16 {d0[0]}, [r0] variable
5711 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
5715 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
5719 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
5725 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
5729 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
5733 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
5785 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
5800 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
5836 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
5839 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
5842 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
5845 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
5893 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
5897 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
5901 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
5917 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
5957 int8x8x4_t vld4_lane_s8_ptr(__transfersize(4) int8_t const * ptr, int8x8x4_t * src, __constrange(0,7) int lane); variable
5961 int16x4x4_t vld4_lane_s16_ptr(__transfersize(4) int16_t const * ptr, int16x4x4_t * src, __constrange(0,3) int lane); variable
5965 int32x2x4_t vld4_lane_s32_ptr(__transfersize(4) int32_t const * ptr, int32x2x4_t * src, __constrange(0,1) int lane); variable
5969 float16x4x4_t vld4_lane_f16_ptr(__transfersize(4) __fp16 const * ptr, float16x4x4_t * src, __constrange(0,3) int lane); variable
5981 poly8x8x4_t vld4_lane_p8_ptr(__transfersize(4) poly8_t const * ptr, poly8x8x4_t * src, __constrange(0,7) int lane); variable
5985 poly16x4x4_t vld4_lane_p16_ptr(__transfersize(4) poly16_t const * ptr, poly16x4x4_t * src, __constrange(0,3) int lane); variable
6588 void vst2q_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x8x2_t * val, __constrange(0,7) int lane); variable
6592 void vst2q_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x4x2_t * val, __constrange(0,3) int lane); variable
6596 void vst2q_lane_f16_ptr(__transfersize(2) __fp16 * ptr, float16x8x2_t * val, __constrange(0,7) int lane); variable
6608 void vst2q_lane_p16_ptr(__transfersize(2) poly16_t * ptr, poly16x8x2_t * val, __constrange(0,7) int lane); variable
6612 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
6616 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
6620 void vst2_lane_s8_ptr(__transfersize(2) int8_t * ptr, int8x8x2_t * val, __constrange(0,7) int lane); variable
6624 void vst2_lane_s16_ptr(__transfersize(2) int16_t * ptr, int16x4x2_t * val, __constrange(0,3) int lane); variable
6628 void vst2_lane_s32_ptr(__transfersize(2) int32_t * ptr, int32x2x2_t * val, __constrange(0,1) int lane); variable
6634 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
6662 void vst3q_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x8x3_t * val, __constrange(0,7) int lane); variable
6666 void vst3q_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x4x3_t * val, __constrange(0,3) int lane); variable
6670 void vst3q_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x8x3_t * val, __constrange(0,7) int lane); variable
6683 void vst3_lane_s8_ptr(__transfersize(3) int8_t * ptr, int8x8x3_t * val, __constrange(0,7) int lane); variable
6687 void vst3_lane_s16_ptr(__transfersize(3) int16_t * ptr, int16x4x3_t * val, __constrange(0,3) int lane); variable
6691 void vst3_lane_s32_ptr(__transfersize(3) int32_t * ptr, int32x2x3_t * val, __constrange(0,1) int lane); variable
6695 void vst3_lane_f16_ptr(__transfersize(3) __fp16 * ptr, float16x4x3_t * val, __constrange(0,3) int lane); variable
6699 void vst3_lane_f32_ptr(__transfersize(3) float32_t * ptr, float32x2x3_t * val, __constrange(0,1) int lane); variable
6703 void vst3_lane_p8_ptr(__transfersize(3) poly8_t * ptr, poly8x8x3_t * val, __constrange(0,7) int lane); variable
6707 void vst3_lane_p16_ptr(__transfersize(3) poly16_t * ptr, poly16x4x3_t * val, __constrange(0,3) int lane); variable
6729 void vst4q_lane_s16_ptr(__transfersize(4) int16_t * ptr, int16x8x4_t * val, __constrange(0,7) int lane); variable
6733 void vst4q_lane_s32_ptr(__transfersize(4) int32_t * ptr, int32x4x4_t * val, __constrange(0,3) int lane); variable
6737 void vst4q_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x8x4_t * val, __constrange(0,7) int lane); variable
6751 void vst4q_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x8x4_t * val, __constrange(0,7) int lane); variable
6795 void vst4_lane_f16_ptr(__transfersize(4) __fp16 * ptr, float16x4x4_t * val, __constrange(0,3) int lane); variable
6802 void vst4_lane_p8_ptr(__transfersize(4) poly8_t * ptr, poly8x8x4_t * val, __constrange(0,7) int lane); variable
6806 void vst4_lane_p16_ptr(__transfersize(4) poly16_t * ptr, poly16x4x4_t * val, __constrange(0,3) int lane); variable
[all...] |
