On Tue, 11 Feb 2025, Krzysztof Pyrkosz via ffmpeg-devel wrote:
---
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 22ecdf7ac8..9002aa028f 100644
--- a/libswscale/aarch64/rgb2rgb_neon.S
+++ b/libswscale/aarch64/rgb2rgb_neon.S
@@ -427,3 +427,265 @@ 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
+.if \dst_fmt == yuv420
This doesn't work as you want it to across all supported tools; .if
conditionals are meant for pure numerical comparisons, and yuv420 isn't a
numerical constant. In practice it does seem to work with binutils though,
but not with Clang (or with gas-preprocessor).
You can use .ifc for string comparisons, see
https://sourceware.org/binutils/docs/as/If.html for more references.
Also see
https://github.com/mstorsjo/FFmpeg/actions/runs/13282469154/job/37083639139
for the fallout from trying to build this patch with various tool setups.
Please do consider trying the aarch64 assembly testset from
https://github.com/mstorsjo/FFmpeg/commits/gha-aarch64 on your commits.
// Martin
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
