pop {r4-r10,pc}
.endfunc
+function x264_load_deinterleave_chroma_fdec_neon
+ mov ip, #FDEC_STRIDE/2
+1:
+ vld2.8 {d0-d1}, [r1,:128], r2
+ subs r3, r3, #1
+ pld [r1]
+ vst1.8 {d0}, [r0,:64], ip
+ vst1.8 {d1}, [r0,:64], ip
+ bgt 1b
+
+ bx lr
+.endfunc
+
+function x264_load_deinterleave_chroma_fenc_neon
+ mov ip, #FENC_STRIDE/2
+1:
+ vld2.8 {d0-d1}, [r1,:128], r2
+ subs r3, r3, #1
+ pld [r1]
+ vst1.8 {d0}, [r0,:64], ip
+ vst1.8 {d1}, [r0,:64], ip
+ bgt 1b
+
+ bx lr
+.endfunc
+
function x264_plane_copy_deinterleave_neon
push {r4-r7, lr}
ldrd r6, r7, [sp, #28]
pixel *dstv, intptr_t i_dstv,
pixel *src, intptr_t i_src, int w, int h );
+void x264_load_deinterleave_chroma_fdec_neon( pixel *dst, pixel *src, intptr_t i_src, int height );
+void x264_load_deinterleave_chroma_fenc_neon( pixel *dst, pixel *src, intptr_t i_src, int height );
+
#define MC_WEIGHT(func)\
void x264_mc_weight_w20##func##_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\
void x264_mc_weight_w16##func##_neon( uint8_t *, intptr_t, uint8_t *, intptr_t, const x264_weight_t *, int );\
pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_neon;
+ pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_neon;
+ pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_neon;
+
pf->avg[PIXEL_16x16] = x264_pixel_avg_16x16_neon;
pf->avg[PIXEL_16x8] = x264_pixel_avg_16x8_neon;
pf->avg[PIXEL_8x16] = x264_pixel_avg_8x16_neon;