Commit c569ebacce for ffmpeg

commit c569ebacce61fca42f05b2b7b5ad0d5f563c0a04
Author: Zhao Zhili <quinkblack@foxmail.com>
Date:   Wed Sep 30 19:55:14 2026 +0800

    aarch64/h26x: reuse the shared qpel hv window rotation

    The eight positions of the eight-row window are the same walk for every
    vertical tail, and calc_all already carries it. The wider weighted tails stay
    as they are: calc_all2 fixes its window to v16..v31, so handing them over means
    moving their accumulators and weight vectors out of that range first.

    No functional changes.

diff --git a/libavcodec/aarch64/h26x/qpel_neon.S b/libavcodec/aarch64/h26x/qpel_neon.S
index 9c830a2d74..53e0e4c5fa 100644
--- a/libavcodec/aarch64/h26x/qpel_neon.S
+++ b/libavcodec/aarch64/h26x/qpel_neon.S
@@ -5395,22 +5395,7 @@ DISABLE_I8MM
         add             sp, sp, x10, lsl #1
         ldr             \type\()22, [sp]
         add             sp, sp, x10
-1:      \step           v23, v16, v17, v18, v19, v20, v21, v22, v23
-        b.eq            2f
-        \step           v16, v17, v18, v19, v20, v21, v22, v23, v16
-        b.eq            2f
-        \step           v17, v18, v19, v20, v21, v22, v23, v16, v17
-        b.eq            2f
-        \step           v18, v19, v20, v21, v22, v23, v16, v17, v18
-        b.eq            2f
-        \step           v19, v20, v21, v22, v23, v16, v17, v18, v19
-        b.eq            2f
-        \step           v20, v21, v22, v23, v16, v17, v18, v19, v20
-        b.eq            2f
-        \step           v21, v22, v23, v16, v17, v18, v19, v20, v21
-        b.eq            2f
-        \step           v22, v23, v16, v17, v18, v19, v20, v21, v22
-        b.hi            1b
+1:      calc_all        \step
 2:
         QPEL_UNI_W_HV_END
         ret