[FFmpeg-cvslog] swscale/aarch64/rgb2rgb_neon: Implemented {yuyv, uyvy}toyuv{420, 422}
Krzysztof Pyrkosz
git at videolan.org
Mon Feb 17 11:40:08 EET 2025
ffmpeg | branch: master | Krzysztof Pyrkosz <ffmpeg at szaka.eu> | Thu Feb 13 20:02:29 2025 +0100| [b92577405b40b6eb5ecf0036060e34e0219da1e3] | committer: Martin Storsjö
swscale/aarch64/rgb2rgb_neon: Implemented {yuyv, uyvy}toyuv{420, 422}
A78:
uyvytoyuv420_neon: 6112.5 ( 6.96x)
uyvytoyuv422_neon: 6696.0 ( 6.32x)
yuyvtoyuv420_neon: 6113.0 ( 6.95x)
yuyvtoyuv422_neon: 6695.2 ( 6.31x)
A72:
uyvytoyuv420_neon: 9512.1 ( 6.09x)
uyvytoyuv422_neon: 9766.8 ( 6.32x)
yuyvtoyuv420_neon: 9639.1 ( 6.00x)
yuyvtoyuv422_neon: 9779.0 ( 6.03x)
A53:
uyvytoyuv420_neon: 12720.1 ( 9.10x)
uyvytoyuv422_neon: 14282.9 ( 6.71x)
yuyvtoyuv420_neon: 12637.4 ( 9.15x)
yuyvtoyuv422_neon: 14127.6 ( 6.77x)
Signed-off-by: Martin Storsjö <martin at martin.st>
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=b92577405b40b6eb5ecf0036060e34e0219da1e3
---
libswscale/aarch64/rgb2rgb.c | 16 +++
libswscale/aarch64/rgb2rgb_neon.S | 262 ++++++++++++++++++++++++++++++++++++++
2 files changed, 278 insertions(+)
diff --git a/libswscale/aarch64/rgb2rgb.c b/libswscale/aarch64/rgb2rgb.c
index 7e1dba572d..f474228298 100644
--- a/libswscale/aarch64/rgb2rgb.c
+++ b/libswscale/aarch64/rgb2rgb.c
@@ -67,6 +67,18 @@ void ff_shuffle_bytes_2013_neon(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_2130_neon(const uint8_t *src, uint8_t *dst, int src_size);
void ff_shuffle_bytes_1203_neon(const uint8_t *src, uint8_t *dst, int src_size);
+void ff_uyvytoyuv422_neon(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
+ const uint8_t *src, int width, int height,
+ int lumStride, int chromStride, int srcStride);
+void ff_uyvytoyuv420_neon(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
+ const uint8_t *src, int width, int height,
+ int lumStride, int chromStride, int srcStride);
+void ff_yuyvtoyuv420_neon(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
+ const uint8_t *src, int width, int height,
+ int lumStride, int chromStride, int srcStride);
+void ff_yuyvtoyuv422_neon(uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
+ const uint8_t *src, int width, int height,
+ int lumStride, int chromStride, int srcStride);
av_cold void rgb2rgb_init_aarch64(void)
{
int cpu_flags = av_get_cpu_flags();
@@ -84,5 +96,9 @@ av_cold void rgb2rgb_init_aarch64(void)
shuffle_bytes_2013 = ff_shuffle_bytes_2013_neon;
shuffle_bytes_2130 = ff_shuffle_bytes_2130_neon;
shuffle_bytes_1203 = ff_shuffle_bytes_1203_neon;
+ uyvytoyuv422 = ff_uyvytoyuv422_neon;
+ uyvytoyuv420 = ff_uyvytoyuv420_neon;
+ yuyvtoyuv422 = ff_yuyvtoyuv422_neon;
+ yuyvtoyuv420 = ff_yuyvtoyuv420_neon;
}
}
diff --git a/libswscale/aarch64/rgb2rgb_neon.S b/libswscale/aarch64/rgb2rgb_neon.S
index 97dd781378..f6d625f11f 100644
--- a/libswscale/aarch64/rgb2rgb_neon.S
+++ b/libswscale/aarch64/rgb2rgb_neon.S
@@ -425,3 +425,265 @@ neon_shuf 2013
neon_shuf 1203
neon_shuf 2130
neon_shuf 3210
+
+/*
+v0-v7 - two consecutive lines
+x0 - upper Y destination
+x1 - U destination
+x2 - V destination
+x3 - upper src line
+w5 - width/iteration counter - count of line pairs for yuv420, of single lines for 422
+x6 - lum padding
+x7 - chrom padding
+x8 - src padding
+w9 - number of bytes remaining in the tail
+x10 - lower Y destination
+w12 - tmp
+x13 - lower src line
+w14 - tmp
+w17 - set to 1 if last line has to be handled separately (odd height)
+*/
+
+// one fast path iteration processes 16 uyvy tuples
+// is_line_tail is set to 1 when final 16 tuples are being processed
+// skip_storing_chroma is set to 1 when final line is processed and the height is odd
+.macro fastpath_iteration src_fmt, dst_fmt, is_line_tail, skip_storing_chroma
+ ld4 {v0.16b - v3.16b}, [x3], #64
+.if ! \is_line_tail
+ subs w14, w14, #32
+.endif
+
+.if ! \skip_storing_chroma
+.ifc \dst_fmt, yuv420
+ ld4 {v4.16b - v7.16b}, [x13], #64
+.endif
+
+.ifc \dst_fmt, yuv420 // store UV
+.ifc \src_fmt, uyvy
+ uhadd v0.16b, v4.16b, v0.16b // halving sum of U
+ uhadd v2.16b, v6.16b, v2.16b // halving sum of V
+.else
+ uhadd v1.16b, v5.16b, v1.16b // halving sum of U
+ uhadd v3.16b, v7.16b, v3.16b // halving sum of V
+.endif
+.endif
+
+.ifc \src_fmt, uyvy
+ st1 {v2.16b}, [x2], #16
+ st1 {v0.16b}, [x1], #16
+.else
+ st1 {v3.16b}, [x2], #16
+ st1 {v1.16b}, [x1], #16
+.endif
+
+.ifc \dst_fmt, yuv420 // store_y
+.ifc \src_fmt, uyvy
+ mov v6.16b, v5.16b
+ st2 {v6.16b,v7.16b}, [x10], #32
+.else
+ mov v5.16b, v4.16b
+ st2 {v5.16b,v6.16b}, [x10], #32
+.endif
+.endif
+
+.endif // ! \skip_storing_chroma
+
+.ifc \src_fmt, uyvy
+ mov v2.16b, v1.16b
+ st2 {v2.16b,v3.16b}, [x0], #32
+.else
+ mov v1.16b, v0.16b
+ st2 {v1.16b,v2.16b}, [x0], #32
+.endif
+.endm
+
+// shift pointers back to width - 32 to process the tail of the line
+// if the height is odd, processing the final line is simplified
+.macro fastpath_shift_back_pointers src_fmt, dst_fmt, is_final_odd_line
+ add x3, x3, w9, sxtw #1
+ sub x3, x3, #64
+.if ! \is_final_odd_line
+.ifc \dst_fmt, yuv420
+ add x13, x13, w9, sxtw #1
+ sub x13, x13, #64
+ add x10, x10, w9, sxtw
+ sub x10, x10, #32
+.endif
+.endif
+ add x0, x0, w9, sxtw
+ sub x0, x0, #32
+.if ! \is_final_odd_line
+ asr w14, w9, #1
+ add x1, x1, w14, sxtw
+ sub x1, x1, #16
+ add x2, x2, w14, sxtw
+ sub x2, x2, #16
+.endif
+.endm
+
+.macro slowpath_iteration src_fmt, dst_fmt, skip_storing_chroma
+.ifc \dst_fmt, yuv422
+.ifc \src_fmt, uyvy
+ ldrb w12, [x3], #1
+ ldrb w14, [x3], #1
+ strb w12, [x1], #1
+ strb w14, [x0], #1
+ ldrb w12, [x3], #1
+ ldrb w14, [x3], #1
+ strb w12, [x2], #1
+ strb w14, [x0], #1
+.else
+ ldrb w12, [x3], #1
+ ldrb w14, [x3], #1
+ strb w12, [x0], #1
+ strb w14, [x1], #1
+ ldrb w12, [x3], #1
+ ldrb w14, [x3], #1
+ strb w12, [x0], #1
+ strb w14, [x2], #1
+.endif
+.endif
+.ifc \dst_fmt, yuv420
+.ifc \src_fmt, uyvy
+.if \skip_storing_chroma
+ ldrb w12, [x3], #2
+ ldrb w14, [x3], #2
+ strb w12, [x0], #1
+ strb w14, [x0], #1
+.else
+ ldrb w12, [x3], #1
+ ldrb w14, [x13], #1
+ add w12, w12, w14
+ lsr w12, w12, #1
+ strb w12, [x1], #1
+ ldrb w14, [x3], #1
+ ldrb w12, [x13], #1
+ strb w14, [x0], #1
+ strb w12, [x10], #1
+ ldrb w14, [x13], #1
+ ldrb w12, [x3], #1
+ add w12, w12, w14
+ lsr w12, w12, #1
+ strb w12, [x2], #1
+ ldrb w14, [x3], #1
+ ldrb w12, [x13], #1
+ strb w14, [x0], #1
+ strb w12, [x10], #1
+.endif
+.else
+.if \skip_storing_chroma
+ ldrb w12, [x3], #2
+ ldrb w14, [x3], #2
+ strb w12, [x0], #1
+ strb w14, [x0], #1
+.else
+ ldrb w12, [x3], #1
+ ldrb w14, [x13], #1
+ strb w12, [x0], #1
+ strb w14, [x10], #1
+ ldrb w12, [x3], #1
+ ldrb w14, [x13], #1
+ add w12, w12, w14
+ lsr w12, w12, #1
+ strb w12, [x1], #1
+ ldrb w14, [x3], #1
+ ldrb w12, [x13], #1
+ strb w14, [x0], #1
+ strb w12, [x10], #1
+ ldrb w14, [x13], #1
+ ldrb w12, [x3], #1
+ add w12, w12, w14
+ lsr w12, w12, #1
+ strb w12, [x2], #1
+.endif
+.endif
+.endif
+.endm
+
+.macro move_pointers_to_next_line src_fmt, dst_fmt, is_final_odd_line
+ add x3, x3, x8
+ add x0, x0, x6
+.ifc \dst_fmt, yuv420
+ add x13, x13, x8
+ add x10, x10, x6
+.endif
+ add x1, x1, x7
+ add x2, x2, x7
+.endm
+
+.macro interleaved_yuv_to_planar src_fmt, dst_fmt
+function ff_\src_fmt\()to\dst_fmt\()_neon, export=1
+ sxtw x6, w6
+ sxtw x7, w7
+ ldrsw x8, [sp]
+ ands w11, w4, #~31 // choose between fast and slow path
+
+.ifc \dst_fmt, yuv420
+ add x10, x0, x6
+ add x13, x3, x8
+ add x8, x8, x8
+ add x6, x6, x6
+ and w17, w5, #1
+ asr w5, w5, #1
+.endif
+ asr w9, w4, #1
+ sub x8, x8, w4, sxtw #1 // src offset
+ sub x6, x6, w4, sxtw // lum offset
+ sub x7, x7, x9 // chr offset
+
+ b.eq 6f
+
+1: // fast path - the width is at least 32
+ and w14, w4, #~31 // w14 is the main loop counter
+ and w9, w4, #31 // w9 holds the remaining width, 0 to 31
+2:
+ fastpath_iteration \src_fmt, \dst_fmt, 0, 0
+ b.ne 2b
+ fastpath_shift_back_pointers \src_fmt, \dst_fmt, 0
+ fastpath_iteration \src_fmt, \dst_fmt, 0, 0
+ subs w5, w5, #1
+ move_pointers_to_next_line \src_fmt, \dst_fmt
+ b.ne 1b
+
+.ifc \dst_fmt, yuv420 // handle the last line in case the height is odd
+ cbz w17, 3f
+ and w14, w4, #~31
+4:
+ fastpath_iteration \src_fmt, \dst_fmt, 0, 1
+ b.ne 4b
+ fastpath_shift_back_pointers \src_fmt, \dst_fmt, 1
+ fastpath_iteration \src_fmt, \dst_fmt, 1, 1
+3:
+.endif
+ ret
+
+6: // slow path - width is at most 31
+ and w9, w4, #31
+7:
+ subs w9, w9, #2
+ slowpath_iteration \src_fmt, \dst_fmt, 0
+ b.ne 7b
+ subs w5, w5, #1
+ move_pointers_to_next_line \src_fmt, \dst_fmt
+ b.ne 6b
+
+.ifc \dst_fmt, yuv420
+ cbz w17, 8f
+ and w9, w4, #31
+.ifc \src_fmt, uyvy
+ add x3, x3, #1
+.endif
+5:
+ subs w9, w9, #2
+ slowpath_iteration \src_fmt, \dst_fmt, 1
+ b.ne 5b
+8:
+.endif
+ ret
+endfunc
+.endm
+
+interleaved_yuv_to_planar uyvy, yuv422
+interleaved_yuv_to_planar uyvy, yuv420
+interleaved_yuv_to_planar yuyv, yuv422
+interleaved_yuv_to_planar yuyv, yuv420
More information about the ffmpeg-cvslog
mailing list