Signed-off-by: Martin Storsjö <mar...@martin.st>
---
This should reduce the risk of anyone accidentally writing new code
based on an incorrect example.
---
libavcodec/aarch64/h264dsp_neon.S | 176 +++++++++++++++---------------
1 file changed, 88 insertions(+), 88 deletions(-)
diff --git a/libavcodec/aarch64/h264dsp_neon.S
b/libavcodec/aarch64/h264dsp_neon.S
index 000ff762a3..ea221e6862 100644
--- a/libavcodec/aarch64/h264dsp_neon.S
+++ b/libavcodec/aarch64/h264dsp_neon.S
@@ -960,117 +960,117 @@ function ff_h264_h_loop_filter_chroma422_neon_10,
export=1
endfunc
.macro h264_loop_filter_chroma_intra_10
- uabd v26.8h, v16.8h, v17.8h // abs(p0 - q0)
- uabd v27.8h, v18.8h, v16.8h // abs(p1 - p0)
- uabd v28.8h, v19.8h, v17.8h // abs(q1 - q0)
- cmhi v26.8h, v30.8h, v26.8h // < alpha
- cmhi v27.8h, v31.8h, v27.8h // < beta
- cmhi v28.8h, v31.8h, v28.8h // < beta
- and v26.16b, v26.16b, v27.16b
- and v26.16b, v26.16b, v28.16b
- mov x2, v26.d[0]
- mov x3, v26.d[1]
-
- shl v4.8h, v18.8h, #1
- shl v6.8h, v19.8h, #1
-
- adds x2, x2, x3
- b.eq 9f
-
- add v20.8h, v16.8h, v19.8h
- add v22.8h, v17.8h, v18.8h
- add v20.8h, v20.8h, v4.8h
- add v22.8h, v22.8h, v6.8h
- urshr v24.8h, v20.8h, #2
- urshr v25.8h, v22.8h, #2
- bit v16.16b, v24.16b, v26.16b
- bit v17.16b, v25.16b, v26.16b
+ uabd v26.8h, v16.8h, v17.8h // abs(p0 - q0)
+ uabd v27.8h, v18.8h, v16.8h // abs(p1 - p0)
+ uabd v28.8h, v19.8h, v17.8h // abs(q1 - q0)
+ cmhi v26.8h, v30.8h, v26.8h // < alpha
+ cmhi v27.8h, v31.8h, v27.8h // < beta
+ cmhi v28.8h, v31.8h, v28.8h // < beta
+ and v26.16b, v26.16b, v27.16b
+ and v26.16b, v26.16b, v28.16b
+ mov x2, v26.d[0]
+ mov x3, v26.d[1]
+
+ shl v4.8h, v18.8h, #1
+ shl v6.8h, v19.8h, #1
+
+ adds x2, x2, x3
+ b.eq 9f
+
+ add v20.8h, v16.8h, v19.8h
+ add v22.8h, v17.8h, v18.8h
+ add v20.8h, v20.8h, v4.8h
+ add v22.8h, v22.8h, v6.8h
+ urshr v24.8h, v20.8h, #2
+ urshr v25.8h, v22.8h, #2
+ bit v16.16b, v24.16b, v26.16b
+ bit v17.16b, v25.16b, v26.16b
.endm
function ff_h264_v_loop_filter_chroma_intra_neon_10, export=1
- h264_loop_filter_start_intra_10
- mov x9, x0
- sub x0, x0, x1, lsl #1
- ld1 {v18.8h}, [x0], x1
- ld1 {v17.8h}, [x9], x1
- ld1 {v16.8h}, [x0], x1
- ld1 {v19.8h}, [x9]
+ h264_loop_filter_start_intra_10
+ mov x9, x0
+ sub x0, x0, x1, lsl #1
+ ld1 {v18.8h}, [x0], x1
+ ld1 {v17.8h}, [x9], x1
+ ld1 {v16.8h}, [x0], x1
+ ld1 {v19.8h}, [x9]
- h264_loop_filter_chroma_intra_10
+ h264_loop_filter_chroma_intra_10
- sub x0, x9, x1, lsl #1
- st1 {v16.8h}, [x0], x1
- st1 {v17.8h}, [x0], x1
+ sub x0, x9, x1, lsl #1
+ st1 {v16.8h}, [x0], x1
+ st1 {v17.8h}, [x0], x1
9:
- ret
+ ret
endfunc
function ff_h264_h_loop_filter_chroma_mbaff_intra_neon_10, export=1
- h264_loop_filter_start_intra_10
+ h264_loop_filter_start_intra_10
- sub x4, x0, #4
- sub x0, x0, #2
- add x9, x4, x1, lsl #1
- ld1 {v18.8h}, [x4], x1
- ld1 {v17.8h}, [x9], x1
- ld1 {v16.8h}, [x4], x1
- ld1 {v19.8h}, [x9], x1
+ sub x4, x0, #4
+ sub x0, x0, #2
+ add x9, x4, x1, lsl #1
+ ld1 {v18.8h}, [x4], x1
+ ld1 {v17.8h}, [x9], x1
+ ld1 {v16.8h}, [x4], x1
+ ld1 {v19.8h}, [x9], x1
- transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29
+ transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29
- h264_loop_filter_chroma_intra_10
+ h264_loop_filter_chroma_intra_10
- st2 {v16.h,v17.h}[0], [x0], x1
- st2 {v16.h,v17.h}[1], [x0], x1
- st2 {v16.h,v17.h}[2], [x0], x1
- st2 {v16.h,v17.h}[3], [x0], x1
+ st2 {v16.h,v17.h}[0], [x0], x1
+ st2 {v16.h,v17.h}[1], [x0], x1
+ st2 {v16.h,v17.h}[2], [x0], x1
+ st2 {v16.h,v17.h}[3], [x0], x1
9:
- ret
+ ret
endfunc
function ff_h264_h_loop_filter_chroma_intra_neon_10, export=1
- h264_loop_filter_start_intra_10
- sub x4, x0, #4
- sub x0, x0, #2
+ h264_loop_filter_start_intra_10
+ sub x4, x0, #4
+ sub x0, x0, #2
h_loop_filter_chroma420_intra_10:
- add x9, x4, x1, lsl #2
- ld1 {v18.4h}, [x4], x1
- ld1 {v18.d}[1], [x9], x1
- ld1 {v16.4h}, [x4], x1
- ld1 {v16.d}[1], [x9], x1
- ld1 {v17.4h}, [x4], x1
- ld1 {v17.d}[1], [x9], x1
- ld1 {v19.4h}, [x4], x1
- ld1 {v19.d}[1], [x9], x1
-
- transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29
-
- h264_loop_filter_chroma_intra_10
-
- st2 {v16.h,v17.h}[0], [x0], x1
- st2 {v16.h,v17.h}[1], [x0], x1
- st2 {v16.h,v17.h}[2], [x0], x1
- st2 {v16.h,v17.h}[3], [x0], x1
- st2 {v16.h,v17.h}[4], [x0], x1
- st2 {v16.h,v17.h}[5], [x0], x1
- st2 {v16.h,v17.h}[6], [x0], x1
- st2 {v16.h,v17.h}[7], [x0], x1
+ add x9, x4, x1, lsl #2
+ ld1 {v18.4h}, [x4], x1
+ ld1 {v18.d}[1], [x9], x1
+ ld1 {v16.4h}, [x4], x1
+ ld1 {v16.d}[1], [x9], x1
+ ld1 {v17.4h}, [x4], x1
+ ld1 {v17.d}[1], [x9], x1
+ ld1 {v19.4h}, [x4], x1
+ ld1 {v19.d}[1], [x9], x1
+
+ transpose_4x8H v18, v16, v17, v19, v26, v27, v28, v29
+
+ h264_loop_filter_chroma_intra_10
+
+ st2 {v16.h,v17.h}[0], [x0], x1
+ st2 {v16.h,v17.h}[1], [x0], x1
+ st2 {v16.h,v17.h}[2], [x0], x1
+ st2 {v16.h,v17.h}[3], [x0], x1
+ st2 {v16.h,v17.h}[4], [x0], x1
+ st2 {v16.h,v17.h}[5], [x0], x1
+ st2 {v16.h,v17.h}[6], [x0], x1
+ st2 {v16.h,v17.h}[7], [x0], x1
9:
- ret
+ ret
endfunc
function ff_h264_h_loop_filter_chroma422_intra_neon_10, export=1
- h264_loop_filter_start_intra_10
- sub x4, x0, #4
- add x5, x0, x1, lsl #3
- sub x0, x0, #2
- mov x7, x30
- bl h_loop_filter_chroma420_intra_10
- mov x4, x9
- sub x0, x5, #2
- mov x30, x7
- b h_loop_filter_chroma420_intra_10
+ h264_loop_filter_start_intra_10
+ sub x4, x0, #4
+ add x5, x0, x1, lsl #3
+ sub x0, x0, #2
+ mov x7, x30
+ bl h_loop_filter_chroma420_intra_10
+ mov x4, x9
+ sub x0, x5, #2
+ mov x30, x7
+ b h_loop_filter_chroma420_intra_10
endfunc
--
2.25.1
_______________________________________________
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".
