pop {r4-r7, pc}
.endfunc
+
+function x264_plane_copy_deinterleave_rgb_neon
+ push {r4-r8, r10, r11, lr}
+ ldrd r4, r5, [sp, #32]
+ ldrd r6, r7, [sp, #40]
+ ldr r8, [sp, #48]
+ ldrd r10, r11, [sp, #52]
+ add lr, r10, #7
+ subs r8, r8, #3
+ bic lr, lr, #7
+ sub r7, r7, lr, lsl #1
+ sub r1, r1, lr
+ sub r3, r3, lr
+ sub r5, r5, lr
+ subne r7, r7, lr, lsl #1
+ subeq r7, r7, lr
+ bne block4
+block3:
+ vld3.8 {d0,d1,d2}, [r6]!
+ subs lr, lr, #8
+ vst1.8 {d0}, [r0]!
+ vst1.8 {d1}, [r2]!
+ vst1.8 {d2}, [r4]!
+ bgt block3
+
+ subs r11, r11, #1
+ add r0, r0, r1
+ add r2, r2, r3
+ add r4, r4, r5
+ add r6, r6, r7
+ mov lr, r10
+ bgt block3
+
+ pop {r4-r8, r10, r11, pc}
+block4:
+ vld4.8 {d0,d1,d2,d3}, [r6]!
+ subs lr, lr, #8
+ vst1.8 {d0}, [r0]!
+ vst1.8 {d1}, [r2]!
+ vst1.8 {d2}, [r4]!
+ bgt block4
+
+ subs r11, r11, #1
+ add r0, r0, r1
+ add r2, r2, r3
+ add r4, r4, r5
+ add r6, r6, r7
+ mov lr, r10
+ bgt block4
+
+ pop {r4-r8, r10, r11, pc}
+.endfunc
void x264_plane_copy_deinterleave_neon( pixel *dstu, intptr_t i_dstu,
pixel *dstv, intptr_t i_dstv,
pixel *src, intptr_t i_src, int w, int h );
+void x264_plane_copy_deinterleave_rgb_neon( pixel *dsta, intptr_t i_dsta,
+ pixel *dstb, intptr_t i_dstb,
+ pixel *dstc, intptr_t i_dstc,
+ pixel *src, intptr_t i_src, int pw, 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 );
pf->copy[PIXEL_4x4] = x264_mc_copy_w4_neon;
pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_neon;
+ pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_neon;
pf->load_deinterleave_chroma_fdec = x264_load_deinterleave_chroma_fdec_neon;
pf->load_deinterleave_chroma_fenc = x264_load_deinterleave_chroma_fenc_neon;