ffmpeg-v4l2-request-fourier: route remaining H.264 qpel 8x8 positions through daedalus-fourier (0012)

Closes the H.264 qpel substitution.  Extends 0007 (which routed only
mc20 put_) to ALL 15 useful positions in BOTH the put_ and avg_
tables, skipping mc00 (integer copy / pointer-only fast path).

29 substitutions total: 14 new put_ + 15 avg_.  Each wraps a single
daedalus_recipe_dispatch_h264_qpel_{avg_,}mcXY call (the dispatches
landed in daedalus-fourier PRs #15-#20).  Collapsed via a single
DEFINE_QPEL_WRAPPER macro on the libavcodec shim side so the diff
is uniform.

All recipe-table entries route AUTO to CPU NEON — no QPU shaders
for any qpel position other than mc20 yet.  Plumbing-only
NEON-to-NEON via the daedalus recipe layer; bit-exact against
the in-tree ff_*_h264_qpel8_*_neon path (each daedalus dispatch is
already bit-exact-gated by the corresponding fourier PR's test).

16x16 qpel tables ([0][...]) stay on the in-tree NEON.  daedalus
only exposes 8x8 today; 16x16 substitution can land once fourier
provides those variants.

Verified the patch applies cleanly on top of 0001-0011 against the
pinned upstream commit b57fbbe5 on hertz.

arch/ffmpeg-v4l2-request-fourier/0008-h264-deblock-luma-h-daedalus-fourier.patch

@@ -0,0 +1,92 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 luma-h deblock through daedalus-fourier
+
+Sibling of 0005 (which substituted v_loop_filter_luma).  Same
+NEON-to-NEON substitution: H264DSPContext.h_loop_filter_luma →
+daedalus_recipe_dispatch_h264_deblock_luma_h.  The H kernel landed
+in daedalus-fourier PR #9 (CPU NEON only — no QPU shader yet).
+
+libavcodec.so ctx is no-QPU per the existing 0003-0005 / 0007
+pattern; we cannot assume Vulkan in arbitrary host processes
+(firefox-fourier RDD, mpv-fourier, etc.).
+
+Intra (bS=4) h_loop_filter_luma_intra stays on the in-tree NEON .S
+code; daedalus_h264_deblock_meta only covers the non-intra path.
+An intra-h substitution can land once daedalus-fourier exposes a
+dispatch helper (the kernel already exists internally per PR #11).
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 H.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:09:33.694760715 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:09:33.715603719 +0200
+@@ -1,9 +1,10 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma-v deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+  *        H264DSPContext.v_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_v
++ *        H264DSPContext.h_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_h
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -45,6 +46,8 @@
+ void ff_h264_idct8_add_daedalus(uint8_t *dst, int16_t *block, int stride);
+ void ff_h264_v_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                          int alpha, int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -84,3 +87,22 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_v(g_dctx, pix, (size_t)stride,
+                                                  1, &meta);
+ }
++
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_h(g_dctx, pix, (size_t)stride,
++                                                 1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:09:33.695937103 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:09:33.715541700 +0200
+@@ -31,6 +31,8 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                      int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
+ void ff_h264_h_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+@@ -117,7 +119,7 @@
+ 
+     if (have_neon(cpu_flags) && bit_depth == 8) {
+         c->v_loop_filter_luma   = ff_h264_v_loop_filter_luma_daedalus;
+-        c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_neon;
++        c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_daedalus;
+         c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+         c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
+ 
+--
+2.47.3
+

arch/ffmpeg-v4l2-request-fourier/0009-h264-deblock-chroma-daedalus-fourier.patch

@@ -0,0 +1,127 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 chroma v/h deblock through daedalus-fourier
+
+Chroma siblings of 0005 (luma_v) and 0008 (luma_h).  Same
+NEON-to-NEON pattern via the daedalus recipe layer:
+
+  H264DSPContext.v_loop_filter_chroma →
+    daedalus_recipe_dispatch_h264_deblock_chroma_v
+  H264DSPContext.h_loop_filter_chroma →
+    daedalus_recipe_dispatch_h264_deblock_chroma_h
+
+Both kernels landed in daedalus-fourier PR #10.  Recipe table
+routes AUTO to CPU NEON (no chroma QPU shaders yet), so this
+is plumbing-only and stays bit-exact against the in-tree NEON.
+
+Intra chroma (bS=4) loop filters remain on in-tree NEON;
+daedalus_h264_deblock_meta covers the non-intra (bS<4) path.
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 chroma.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:15:45.995368233 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:15:46.015839177 +0200
+@@ -1,10 +1,12 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h + chroma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+- *        H264DSPContext.v_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_v
+- *        H264DSPContext.h_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_h
++ *        H264DSPContext.v_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_v
++ *        H264DSPContext.h_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_h
++ *        H264DSPContext.v_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_v
++ *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -48,6 +50,10 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                          int alpha, int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -106,3 +112,41 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_h(g_dctx, pix, (size_t)stride,
+                                                  1, &meta);
+ }
++
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_chroma_v(g_dctx, pix, (size_t)stride,
++                                                   1, &meta);
++}
++
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_chroma_h(g_dctx, pix, (size_t)stride,
++                                                   1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:15:45.996482360 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:15:46.025604910 +0200
+@@ -39,8 +39,12 @@
+                                            int beta);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma422_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                           int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_intra_neon(uint8_t *pix, ptrdiff_t stride,
+@@ -123,11 +127,11 @@
+         c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+         c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
+ 
+-        c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_neon;
++        c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_daedalus;
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+ 
+         if (chroma_format_idc <= 1) {
+-            c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_neon;
++            c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_daedalus;
+             c->h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon;
+             c->h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon;
+         } else {
+--
+2.47.3
+

arch/ffmpeg-v4l2-request-fourier/0010-h264-deblock-luma-intra-daedalus-fourier.patch

@@ -0,0 +1,126 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:30:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 luma intra deblock through daedalus-fourier
+
+Adds the bS=4 intra-strength variants of the already-substituted
+luma_v / luma_h deblock (0005, 0008).  Intra MBs and certain
+inter-MB edges (4x4 transform boundaries inside an Intra_NxN
+neighbour) force boundary strength to 4 per H.264 §8.7.2.1.
+
+  H264DSPContext.v_loop_filter_luma_intra →
+    daedalus_recipe_dispatch_h264_deblock_luma_v_intra
+  H264DSPContext.h_loop_filter_luma_intra →
+    daedalus_recipe_dispatch_h264_deblock_luma_h_intra
+
+Both kernels landed in daedalus-fourier PR #11.  Recipe table
+routes AUTO to CPU NEON (no intra QPU shaders yet) — plumbing-
+only NEON-to-NEON via daedalus, bit-exact against the in-tree
+FFmpeg NEON path.
+
+Signature differs from bS<4: no tc0 argument.  The wrapper
+passes daedalus_h264_deblock_meta with alpha/beta set; tc0[] is
+ignored by the intra dispatch (bS=4 hardcodes the strength).
+
+Chroma intra variants are deferred to a follow-up PR because the
+chroma path has a 4:2:0 / 4:2:2 split (chroma_format_idc gating)
+that needs explicit conditional substitution to avoid running
+the 4:2:0-only daedalus dispatch on 4:2:2 chroma.
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 intra.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:18:54.992244965 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:20:12.338122217 +0200
+@@ -1,5 +1,5 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h + chroma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h (inter + intra) + chroma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+@@ -7,6 +7,8 @@
+  *        H264DSPContext.h_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_h
+  *        H264DSPContext.v_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_v
+  *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
++ *        H264DSPContext.v_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_v_intra
++ *        H264DSPContext.h_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_h_intra
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -54,6 +56,10 @@
+                                            int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                            int alpha, int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -150,3 +156,34 @@
+     daedalus_recipe_dispatch_h264_deblock_chroma_h(g_dctx, pix, (size_t)stride,
+                                                    1, &meta);
+ }
++
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    /* tc0[] is ignored by the intra-strength dispatch (bS=4 hardcodes the strength). */
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_v_intra(g_dctx, pix, (size_t)stride,
++                                                        1, &meta);
++}
++
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_h_intra(g_dctx, pix, (size_t)stride,
++                                                        1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:18:54.993349573 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:20:12.338265830 +0200
+@@ -35,8 +35,12 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ void ff_h264_h_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+@@ -124,8 +128,8 @@
+     if (have_neon(cpu_flags) && bit_depth == 8) {
+         c->v_loop_filter_luma   = ff_h264_v_loop_filter_luma_daedalus;
+         c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_daedalus;
+-        c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+-        c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
++        c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_daedalus;
++        c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_daedalus;
+ 
+         c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_daedalus;
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+--
+2.47.3
+

arch/ffmpeg-v4l2-request-fourier/0011-h264-chroma-dc-hadamard-daedalus-fourier.patch

@@ -0,0 +1,101 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 13:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 chroma DC Hadamard through daedalus-fourier
+
+Substitutes H264DSPContext.chroma_dc_dequant_idct in the
+4:2:0 / bit_depth=8 init path with a wrapper that composes
+the daedalus chroma DC Hadamard primitive (fourier PR #25)
+with qmul scaling FFmpeg does in one fused function.
+
+Bit-exact against ff_h264_chroma_dc_dequant_idct_8_c.
+Hadamard correctness gated by fourier PR #23 test suite.
+
+4:2:2 chroma stays on the in-tree 422 variant (same
+gating shape as 0009 chroma deblock substitution).
+
+Requires daedalus-fourier commit b9f9ff2 or later (PR #25
+exposing the public Hadamard symbol).  Pin bumps in PKGBUILD
+and build-deb.sh come in the same commit.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:38:32.019491484 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:38:32.033821507 +0200
+@@ -1,5 +1,5 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h (inter + intra) + chroma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h (inter+intra) + chroma v/h deblock + chroma DC Hadamard — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+@@ -9,6 +9,7 @@
+  *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
+  *        H264DSPContext.v_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_v_intra
+  *        H264DSPContext.h_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_h_intra
++ *        H264DSPContext.chroma_dc_dequant_idct   → daedalus_h264_chroma_dc_hadamard_2x2 + caller-side qmul
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -60,6 +61,7 @@
+                                                 int alpha, int beta);
+ void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                                 int alpha, int beta);
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -187,3 +189,32 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_h_intra(g_dctx, pix, (size_t)stride,
+                                                         1, &meta);
+ }
++
++/* Composes daedalus_h264_chroma_dc_hadamard_2x2 with the qmul scaling
++ * that FFmpeg's reference does in one fused function (h264idct_template.c
++ * ff_h264_chroma_dc_dequant_idct).
++ *
++ * The 4 DC coefficients are scattered across the per-MB coefficient
++ * buffer at offsets [r*stride + c*xStride] (stride=32, xStride=16).
++ * Extract into a contiguous int16[4], run the Hadamard, then apply
++ * the qmul scale and write back to the original positions.
++ *
++ * No daedalus ctx needed; the Hadamard is a pure stateless primitive.
++ */
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul)
++{
++    enum { stride = 32, xStride = 16 };
++    int16_t dc[4];
++
++    dc[0] = block[stride*0 + xStride*0];
++    dc[1] = block[stride*0 + xStride*1];
++    dc[2] = block[stride*1 + xStride*0];
++    dc[3] = block[stride*1 + xStride*1];
++
++    daedalus_h264_chroma_dc_hadamard_2x2(dc);
++
++    block[stride*0 + xStride*0] = (int16_t)((int)dc[0] * qmul >> 7);
++    block[stride*0 + xStride*1] = (int16_t)((int)dc[1] * qmul >> 7);
++    block[stride*1 + xStride*0] = (int16_t)((int)dc[2] * qmul >> 7);
++    block[stride*1 + xStride*1] = (int16_t)((int)dc[3] * qmul >> 7);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:38:32.020346459 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:38:32.033909804 +0200
+@@ -41,6 +41,7 @@
+                                            int beta);
+ void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                                 int alpha, int beta);
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+@@ -135,6 +136,7 @@
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+ 
+         if (chroma_format_idc <= 1) {
++            c->chroma_dc_dequant_idct = ff_h264_chroma_dc_dequant_idct_daedalus;
+             c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_daedalus;
+             c->h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon;
+             c->h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon;
+--
+2.47.3
+

arch/ffmpeg-v4l2-request-fourier/0012-h264-qpel-rest-daedalus-fourier.patch

@@ -0,0 +1,245 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 14:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264qpel: route remaining qpel 8x8 positions through daedalus-fourier
+
+Closes the H.264 qpel substitution.  Extends 0007 (which routed only
+mc20 put_) to ALL 15 useful positions in BOTH the put_ and avg_
+tables, skipping mc00 (integer copy / pointer-only fast path).
+
+29 substitutions total: 14 new put_ + 15 avg_.  Each is a uniform
+wrapper around daedalus_recipe_dispatch_h264_qpel_{avg_,}mcXY exposed
+by daedalus-fourier PRs #15-#20.
+
+All recipe-table entries route AUTO to CPU NEON (no QPU shaders
+for any qpel position other than mc20 yet), so this is plumbing-only
+NEON-to-NEON — bit-exact against the in-tree ff_*_h264_qpel8_*_neon
+path.
+
+16x16 qpel tables ([0][...]) stay on the in-tree NEON.  daedalus
+only exposes 8x8 today; 16x16 substitution can land once fourier
+provides those variants (likely just dispatching the 8x8 path four
+times with shifted dst/src offsets).
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc qpel buildout.
+---
+diff --git a/libavcodec/aarch64/h264_qpel_daedalus.c b/libavcodec/aarch64/h264_qpel_daedalus.c
+--- a/libavcodec/aarch64/h264_qpel_daedalus.c	2026-05-25 14:05:05.789298250 +0200
++++ libavcodec/aarch64/h264_qpel_daedalus.c	2026-05-25 14:05:05.818358374 +0200
+@@ -1,10 +1,13 @@
+ /*
+- * H.264 luma qpel mc20 (8x8, horizontal half-pel, 6-tap "put")
+- * — daedalus-fourier substitution shim.
++ * H.264 luma qpel 8x8 — daedalus-fourier substitution shims (put_ + avg_).
+  *
+- * Routes H264QpelContext.put_h264_qpel_pixels_tab[1][2] through
+- * daedalus_recipe_dispatch_h264_qpel_mc20 instead of
+- * ff_put_h264_qpel8_mc20_neon.  The recipe layer picks the substrate
++ * Routes ALL 15 useful positions in H264QpelContext's 8x8 put_ and
++ * avg_ tables through daedalus_recipe_dispatch_h264_qpel_mc{XY}
++ * (skipping mc00 which is integer copy / FFmpeg's pointer-only fast
++ * path).  Plumbing-only NEON-by-recipe — daedalus-fourier PRs #15-#20
++ * exposed each variant via the same dispatch signature, so the
++ * substitution is a uniform macro across put_/avg_ and across all
++ * 15 mc positions.  The recipe layer picks the substrate
+  * (CPU NEON for cycle 9; QPU not viable — per-block 7.6 ns vs
+  * ~250 ns QPU dispatch floor, see docs/k9_h264qpel_mc20.md).
+  *
+@@ -48,3 +51,53 @@
+     daedalus_recipe_dispatch_h264_qpel_mc20(g_dctx, dst, src, (size_t)stride,
+                                             1, &meta);
+ }
++
++
++/* All other 8x8 qpel positions follow the same dispatch shape as mc20
++ * above.  The macro collapses ~600 LOC of one-wrapper-per-variant
++ * boilerplate (29 variants total: 14 put_ + 15 avg_). */
++#define DEFINE_QPEL_WRAPPER(type, suffix, dispatch_fn)                          \
++void ff_ ## type ## _h264_qpel8_ ## suffix ## _daedalus(uint8_t *dst,           \
++    const uint8_t *src, ptrdiff_t stride);                                      \
++void ff_ ## type ## _h264_qpel8_ ## suffix ## _daedalus(uint8_t *dst,           \
++    const uint8_t *src, ptrdiff_t stride)                                       \
++{                                                                               \
++    static const daedalus_h264_qpel_meta meta = { .dst_off = 0, .src_off = 0 }; \
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);                         \
++    dispatch_fn(g_dctx, dst, src, (size_t)stride, 1, &meta);                    \
++}
++
++/* put_ variants (mc20 stays on the explicit definition above). */
++DEFINE_QPEL_WRAPPER(put, mc10, daedalus_recipe_dispatch_h264_qpel_mc10)
++DEFINE_QPEL_WRAPPER(put, mc30, daedalus_recipe_dispatch_h264_qpel_mc30)
++DEFINE_QPEL_WRAPPER(put, mc01, daedalus_recipe_dispatch_h264_qpel_mc01)
++DEFINE_QPEL_WRAPPER(put, mc11, daedalus_recipe_dispatch_h264_qpel_mc11)
++DEFINE_QPEL_WRAPPER(put, mc21, daedalus_recipe_dispatch_h264_qpel_mc21)
++DEFINE_QPEL_WRAPPER(put, mc31, daedalus_recipe_dispatch_h264_qpel_mc31)
++DEFINE_QPEL_WRAPPER(put, mc02, daedalus_recipe_dispatch_h264_qpel_mc02)
++DEFINE_QPEL_WRAPPER(put, mc12, daedalus_recipe_dispatch_h264_qpel_mc12)
++DEFINE_QPEL_WRAPPER(put, mc22, daedalus_recipe_dispatch_h264_qpel_mc22)
++DEFINE_QPEL_WRAPPER(put, mc32, daedalus_recipe_dispatch_h264_qpel_mc32)
++DEFINE_QPEL_WRAPPER(put, mc03, daedalus_recipe_dispatch_h264_qpel_mc03)
++DEFINE_QPEL_WRAPPER(put, mc13, daedalus_recipe_dispatch_h264_qpel_mc13)
++DEFINE_QPEL_WRAPPER(put, mc23, daedalus_recipe_dispatch_h264_qpel_mc23)
++DEFINE_QPEL_WRAPPER(put, mc33, daedalus_recipe_dispatch_h264_qpel_mc33)
++
++/* avg_ variants — all 15 useful positions. */
++DEFINE_QPEL_WRAPPER(avg, mc10, daedalus_recipe_dispatch_h264_qpel_avg_mc10)
++DEFINE_QPEL_WRAPPER(avg, mc20, daedalus_recipe_dispatch_h264_qpel_avg_mc20)
++DEFINE_QPEL_WRAPPER(avg, mc30, daedalus_recipe_dispatch_h264_qpel_avg_mc30)
++DEFINE_QPEL_WRAPPER(avg, mc01, daedalus_recipe_dispatch_h264_qpel_avg_mc01)
++DEFINE_QPEL_WRAPPER(avg, mc11, daedalus_recipe_dispatch_h264_qpel_avg_mc11)
++DEFINE_QPEL_WRAPPER(avg, mc21, daedalus_recipe_dispatch_h264_qpel_avg_mc21)
++DEFINE_QPEL_WRAPPER(avg, mc31, daedalus_recipe_dispatch_h264_qpel_avg_mc31)
++DEFINE_QPEL_WRAPPER(avg, mc02, daedalus_recipe_dispatch_h264_qpel_avg_mc02)
++DEFINE_QPEL_WRAPPER(avg, mc12, daedalus_recipe_dispatch_h264_qpel_avg_mc12)
++DEFINE_QPEL_WRAPPER(avg, mc22, daedalus_recipe_dispatch_h264_qpel_avg_mc22)
++DEFINE_QPEL_WRAPPER(avg, mc32, daedalus_recipe_dispatch_h264_qpel_avg_mc32)
++DEFINE_QPEL_WRAPPER(avg, mc03, daedalus_recipe_dispatch_h264_qpel_avg_mc03)
++DEFINE_QPEL_WRAPPER(avg, mc13, daedalus_recipe_dispatch_h264_qpel_avg_mc13)
++DEFINE_QPEL_WRAPPER(avg, mc23, daedalus_recipe_dispatch_h264_qpel_avg_mc23)
++DEFINE_QPEL_WRAPPER(avg, mc33, daedalus_recipe_dispatch_h264_qpel_avg_mc33)
++
++#undef DEFINE_QPEL_WRAPPER
+diff --git a/libavcodec/aarch64/h264qpel_init_aarch64.c b/libavcodec/aarch64/h264qpel_init_aarch64.c
+--- a/libavcodec/aarch64/h264qpel_init_aarch64.c	2026-05-25 14:05:05.790403989 +0200
++++ libavcodec/aarch64/h264qpel_init_aarch64.c	2026-05-25 14:05:05.819136071 +0200
+@@ -50,6 +50,64 @@
+ void ff_put_h264_qpel8_mc30_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc20_daedalus(uint8_t *dst, const uint8_t *src,
+                                      ptrdiff_t stride);
++void ff_put_h264_qpel8_mc10_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc30_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc01_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc11_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc21_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc31_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc02_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc12_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc22_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc32_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc03_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc13_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc23_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc33_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc10_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc20_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc30_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc01_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc11_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc21_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc31_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc02_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc12_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc22_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc32_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc03_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc13_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc23_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc33_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc01_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc11_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc21_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+@@ -164,21 +222,21 @@
+         c->put_h264_qpel_pixels_tab[0][15] = ff_put_h264_qpel16_mc33_neon;
+ 
+         c->put_h264_qpel_pixels_tab[1][ 0] = ff_put_h264_qpel8_mc00_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 1] = ff_put_h264_qpel8_mc10_neon;
++        c->put_h264_qpel_pixels_tab[1][ 1] = ff_put_h264_qpel8_mc10_daedalus;
+         c->put_h264_qpel_pixels_tab[1][ 2] = ff_put_h264_qpel8_mc20_daedalus;
+-        c->put_h264_qpel_pixels_tab[1][ 3] = ff_put_h264_qpel8_mc30_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 4] = ff_put_h264_qpel8_mc01_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 5] = ff_put_h264_qpel8_mc11_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 6] = ff_put_h264_qpel8_mc21_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 7] = ff_put_h264_qpel8_mc31_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 8] = ff_put_h264_qpel8_mc02_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 9] = ff_put_h264_qpel8_mc12_neon;
+-        c->put_h264_qpel_pixels_tab[1][10] = ff_put_h264_qpel8_mc22_neon;
+-        c->put_h264_qpel_pixels_tab[1][11] = ff_put_h264_qpel8_mc32_neon;
+-        c->put_h264_qpel_pixels_tab[1][12] = ff_put_h264_qpel8_mc03_neon;
+-        c->put_h264_qpel_pixels_tab[1][13] = ff_put_h264_qpel8_mc13_neon;
+-        c->put_h264_qpel_pixels_tab[1][14] = ff_put_h264_qpel8_mc23_neon;
+-        c->put_h264_qpel_pixels_tab[1][15] = ff_put_h264_qpel8_mc33_neon;
++        c->put_h264_qpel_pixels_tab[1][ 3] = ff_put_h264_qpel8_mc30_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 4] = ff_put_h264_qpel8_mc01_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 5] = ff_put_h264_qpel8_mc11_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 6] = ff_put_h264_qpel8_mc21_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 7] = ff_put_h264_qpel8_mc31_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 8] = ff_put_h264_qpel8_mc02_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 9] = ff_put_h264_qpel8_mc12_daedalus;
++        c->put_h264_qpel_pixels_tab[1][10] = ff_put_h264_qpel8_mc22_daedalus;
++        c->put_h264_qpel_pixels_tab[1][11] = ff_put_h264_qpel8_mc32_daedalus;
++        c->put_h264_qpel_pixels_tab[1][12] = ff_put_h264_qpel8_mc03_daedalus;
++        c->put_h264_qpel_pixels_tab[1][13] = ff_put_h264_qpel8_mc13_daedalus;
++        c->put_h264_qpel_pixels_tab[1][14] = ff_put_h264_qpel8_mc23_daedalus;
++        c->put_h264_qpel_pixels_tab[1][15] = ff_put_h264_qpel8_mc33_daedalus;
+ 
+         c->avg_h264_qpel_pixels_tab[0][ 0] = ff_avg_h264_qpel16_mc00_neon;
+         c->avg_h264_qpel_pixels_tab[0][ 1] = ff_avg_h264_qpel16_mc10_neon;
+@@ -198,21 +256,21 @@
+         c->avg_h264_qpel_pixels_tab[0][15] = ff_avg_h264_qpel16_mc33_neon;
+ 
+         c->avg_h264_qpel_pixels_tab[1][ 0] = ff_avg_h264_qpel8_mc00_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 1] = ff_avg_h264_qpel8_mc10_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 2] = ff_avg_h264_qpel8_mc20_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 3] = ff_avg_h264_qpel8_mc30_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 4] = ff_avg_h264_qpel8_mc01_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 5] = ff_avg_h264_qpel8_mc11_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 6] = ff_avg_h264_qpel8_mc21_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 7] = ff_avg_h264_qpel8_mc31_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 8] = ff_avg_h264_qpel8_mc02_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 9] = ff_avg_h264_qpel8_mc12_neon;
+-        c->avg_h264_qpel_pixels_tab[1][10] = ff_avg_h264_qpel8_mc22_neon;
+-        c->avg_h264_qpel_pixels_tab[1][11] = ff_avg_h264_qpel8_mc32_neon;
+-        c->avg_h264_qpel_pixels_tab[1][12] = ff_avg_h264_qpel8_mc03_neon;
+-        c->avg_h264_qpel_pixels_tab[1][13] = ff_avg_h264_qpel8_mc13_neon;
+-        c->avg_h264_qpel_pixels_tab[1][14] = ff_avg_h264_qpel8_mc23_neon;
+-        c->avg_h264_qpel_pixels_tab[1][15] = ff_avg_h264_qpel8_mc33_neon;
++        c->avg_h264_qpel_pixels_tab[1][ 1] = ff_avg_h264_qpel8_mc10_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 2] = ff_avg_h264_qpel8_mc20_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 3] = ff_avg_h264_qpel8_mc30_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 4] = ff_avg_h264_qpel8_mc01_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 5] = ff_avg_h264_qpel8_mc11_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 6] = ff_avg_h264_qpel8_mc21_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 7] = ff_avg_h264_qpel8_mc31_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 8] = ff_avg_h264_qpel8_mc02_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 9] = ff_avg_h264_qpel8_mc12_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][10] = ff_avg_h264_qpel8_mc22_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][11] = ff_avg_h264_qpel8_mc32_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][12] = ff_avg_h264_qpel8_mc03_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][13] = ff_avg_h264_qpel8_mc13_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][14] = ff_avg_h264_qpel8_mc23_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][15] = ff_avg_h264_qpel8_mc33_daedalus;
+     } else if (have_neon(cpu_flags) && bit_depth == 10) {
+         c->put_h264_qpel_pixels_tab[0][ 1] = ff_put_h264_qpel16_mc10_neon_10;
+         c->put_h264_qpel_pixels_tab[0][ 2] = ff_put_h264_qpel16_mc20_neon_10;
+--
+2.47.3
+

arch/ffmpeg-v4l2-request-fourier/PKGBUILD

@@ -30,7 +30,7 @@ epoch=2
 # daedalus-fourier pin.  209a421 = PR #2 merge (Phase 8c — public API
 # gains daedalus_recipe_dispatch_h264_qpel_mc20 + DAEDALUS_KERNEL_H264_QPEL_MC20).
 # Cycle 9 closes the libavcodec.so substitution arc started at cycle 6.
-_daedalus_fourier_commit='209a4218bcb98b91c04f07ad61513bb04adb13ad'
+_daedalus_fourier_commit='b9f9ff2a89c068aea54dcb52b543afddad28311e'  # PR #25 — public chroma DC Hadamard symbol
 pkgdesc='FFmpeg with V4L2 Request API hwaccel (Rockchip / Allwinner stateless decode)'
 arch=('aarch64')
 url='https://github.com/Kwiboo/FFmpeg'
@@ -94,8 +94,13 @@ source=("git+https://github.com/Kwiboo/FFmpeg.git#commit=${_commit}"
         '0004-h264-idct8-daedalus-fourier.patch'
         '0005-h264-deblock-luma-v-daedalus-fourier.patch'
         '0006-h264-restore-low-delay.patch'
-        '0007-h264-qpel-mc20-daedalus-fourier.patch')
+        '0007-h264-qpel-mc20-daedalus-fourier.patch'
-sha256sums=('SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP')
+        '0008-h264-deblock-luma-h-daedalus-fourier.patch'
+        '0009-h264-deblock-chroma-daedalus-fourier.patch'
+        '0010-h264-deblock-luma-intra-daedalus-fourier.patch'
+        '0011-h264-chroma-dc-hadamard-daedalus-fourier.patch'
+        '0012-h264-qpel-rest-daedalus-fourier.patch')
+sha256sums=('SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP' 'SKIP')
 
 pkgver() {
   cd "${_srcname}"
@@ -113,6 +118,11 @@ prepare() {
   patch -Np1 -i "${srcdir}/0005-h264-deblock-luma-v-daedalus-fourier.patch"
   patch -Np1 -i "${srcdir}/0006-h264-restore-low-delay.patch"
   patch -Np1 -i "${srcdir}/0007-h264-qpel-mc20-daedalus-fourier.patch"
+  patch -Np1 -i "${srcdir}/0008-h264-deblock-luma-h-daedalus-fourier.patch"
+  patch -Np1 -i "${srcdir}/0009-h264-deblock-chroma-daedalus-fourier.patch"
+  patch -Np1 -i "${srcdir}/0010-h264-deblock-luma-intra-daedalus-fourier.patch"
+  patch -Np1 -i "${srcdir}/0011-h264-chroma-dc-hadamard-daedalus-fourier.patch"
+  patch -Np1 -i "${srcdir}/0012-h264-qpel-rest-daedalus-fourier.patch"
 }
 
 build() {

arch/mesa-panvk-bifrost/0007-panvk-bifrost-xfb-component-base-fix.patch

@@ -0,0 +1,103 @@
+From: marfrit-packages noether <claude-noether@reauktion.de>
+Subject: [PATCH] panvk-bifrost: fix XFB store channel-extract for packed varyings
+
+iter19 — fixes a reliable SIGSEGV during vkCreateGraphicsPipeline on any
+shader that uses XFB-bound varyings declared with non-zero `layout
+(component=N)` qualifiers. Surfaced by
+dEQP-VK.transform_feedback.simple.holes_vert; backtrace lands 11 frames
+into libvulkan_panfrost.so called from `vkt::TransformFeedback::
+TransformFeedbackHolesInstance::iterate`.
+
+Root cause: `lower_xfb_output_iter17` (and upstream `lower_xfb_output`,
+which carries a `// TODO` on the same assertion) computes the source-
+channel mask as `mask << channel_idx`, where `channel_idx` is the
+varying-location component (0..3) but `src` only contains channels for
+the source-side range starting at `nir_intrinsic_component(intr)`. For
+`flat out float vegeta` declared with `component=2`, NIR emits
+`store_output src=<vec1>, component=2`, and the lowering computes
+`mask << 2` against a single-component src — out-of-range; the
+resulting malformed nir_def then segfaults inside downstream NIR
+constant-folding (`nir_constant_expressions.c::evaluate_*`).
+
+The assertion `assert(nir_intrinsic_component(intr) == 0)` was inherited
+from upstream `pan_nir_lower_xfb.c` as a documented `// TODO`; release
+builds (-DNDEBUG) elide it. The fix translates `channel_idx` to the
+source-channel space by subtracting `nir_intrinsic_component(intr)`
+before shifting the mask, and replaces the elided asserts with explicit
+release-mode guards (the patch closes the same release-mode-elision
+class as the original bug).
+
+Verified on PineTab2 (Mali-G52 r1 MC1, PAN_ARCH 7) against vulkan-cts
+1.3.10.0:
+  - holes_vert / holes_extra_draw_vert no longer SIGSEGV (now Fail on
+    color-check; that is a separate iter20 finding — the rasterized
+    varying gets removed alongside the XFB-bound one).
+  - basic_*: 36/36 Pass. depth_clip_*: 1 Pass + 4 NotSupported.
+    lines_or_triangles*: 16 NotSupported. 0 Fail across the full set.
+  - holes_geom / holes_extra_draw_geom remain NotSupported
+    (geometryShader not on G52) — unchanged.
+
+Caveat: max_output_components_64/_128/_256 were never reached on the
+r5 sweep (watchdog killed transform_feedback after the holes_vert
+crash). With this fix in place, those tests now run and surface
+*their own pre-existing* coredumps — confirmed on shipped r6 baseline
+too. They are NOT regressions from this patch; they are latent crashes
+unmasked by it. iter20+ territory.
+
+Phase 5 (2nd-model) review: APPROVE WITH CHANGES (non-blocking).
+Changes applied: release-mode defensive guards on both preconditions
+plus a dispatcher-side comment clarifying the i*2+j semantics.
+
+Cross-refs:
+  - iter19/phase{0,1,2,3}_holes_vert*.md in panvk-bifrost repo
+
+---
+ src/panfrost/vulkan/panvk_vX_xfb_lower.c | 24 +++++++++++++++++++++---
+ 1 file changed, 21 insertions(+), 3 deletions(-)
+
+diff --git a/src/panfrost/vulkan/panvk_vX_xfb_lower.c b/src/panfrost/vulkan/panvk_vX_xfb_lower.c
+@@ -339,7 +339,20 @@
+                         unsigned buffer, unsigned offset_words)
+ {
+    assert(buffer < MAX_XFB_BUFFERS);
+-   assert(nir_intrinsic_component(intr) == 0);
++
++   /* iter19: nir_intrinsic_component(intr) is the source-channel base —
++    * for a packed varying like `layout (location=0, component=2) flat out
++    * float vegeta`, NIR emits store_output with component=2 and a single-
++    * component src. The XFB iteration index `channel_idx` (0..3) is the
++    * varying-location component, not the source channel. Translate by
++    * subtracting the base before shifting the mask. Fixes the long-
++    * standing `assert(nir_intrinsic_component(intr) == 0) // TODO` in
++    * upstream pan_nir_lower_xfb that surfaces on holes_vert. */
++   const unsigned base_comp = nir_intrinsic_component(intr);
++   /* Defensive against release-build elision: this is precisely the
++    * bug class the patch is fixing, so don't re-introduce it. */
++   if (channel_idx < base_comp)
++      return;
+ 
+    uint16_t stride = b->shader->info.xfb_stride[buffer] * 4;
+    assert(stride != 0);
+@@ -357,7 +370,11 @@
+ 
+    nir_def *src = intr->src[0].ssa;
+    nir_component_mask_t mask = nir_component_mask(num_components);
+-   nir_def *value = nir_channels(b, src, mask << channel_idx);
++   const unsigned src_channel = channel_idx - base_comp;
++   /* Same defensive class as the channel_idx >= base_comp guard above. */
++   if (src_channel + num_components > src->num_components)
++      return;
++   nir_def *value = nir_channels(b, src, mask << src_channel);
+ 
+    /* Topology dispatch ladder. LIST first (fast path). */
+    nir_push_if(b, nir_ieq_imm(b, topology, PANVK_XFB_TOPO_LIST));
+@@ -465,6 +482,9 @@
+       for (unsigned j = 0; j < 2; ++j) {
+          if (!xfb.out[j].num_components)
+             continue;
++         /* `i*2+j` is the varying-location component (0..3) — io_xfb covers
++          * slots 0..1, io_xfb2 covers 2..3. The leaf translates this into
++          * a source-channel index by subtracting nir_intrinsic_component(intr). */
+          lower_xfb_output_iter17(b, intr, i * 2 + j, xfb.out[j].num_components,
+                                  xfb.out[j].buffer, xfb.out[j].offset);
+          progress = true;

arch/mesa-panvk-bifrost/PKGBUILD

@@ -30,7 +30,7 @@
 
 pkgname=mesa-panvk-bifrost
 _mesaver=26.0.6
-pkgver=26.0.6.r6
+pkgver=26.0.6.r7
 pkgrel=1
 pkgdesc="Patched Mesa libvulkan_panfrost.so exposing Bifrost-gen Mali to Vulkan apps (panvk-bifrost campaign)"
 arch=('aarch64')
@@ -83,6 +83,7 @@ source=(
     "0004-panvk-bifrost-xfb-primitive-decomposition.patch"
     "0005-panvk-bifrost-fragment-stores-atomics.patch"
     "0006-panvk-bifrost-legacy-dithering.patch"
+    "0007-panvk-bifrost-xfb-component-base-fix.patch"
     "brave-vulkan"
     "icd.json"
 )
@@ -96,6 +97,7 @@ sha256sums=(
     'SKIP'
     'SKIP'
     'SKIP'
+    'SKIP'
 )
 
 prepare() {
@@ -152,6 +154,16 @@ prepare() {
     # extension as Mali-G52-architecture supported.
     patch -p1 < "${srcdir}/0006-panvk-bifrost-legacy-dithering.patch"
 
+    # r7 (2026-05-25): XFB store channel-extract fix for packed varyings.
+    # Eliminates a reliable SIGSEGV in vkCreateGraphicsPipeline whenever
+    # an XFB-bound vertex output is declared with non-zero
+    # `layout (component=N)`. Surfaced by dEQP-VK.transform_feedback.
+    # simple.holes_vert (now Fails on color-check rather than crashing;
+    # the color-check residual is a separate iter20 finding).
+    # Phase-doc context: ~/src/panvk-bifrost/iter19/phase{0,1,2,3}_*.md.
+    # Phase 5 reviewed; release-mode-elision defensive guards applied.
+    patch -p1 < "${srcdir}/0007-panvk-bifrost-xfb-component-base-fix.patch"
+
     # Sanity-check the patches landed.
     grep -q "KHR_robustness2 = true," src/panfrost/vulkan/panvk_vX_physical_device.c
     grep -q "EXT_robustness2 = true," src/panfrost/vulkan/panvk_vX_physical_device.c
@@ -171,6 +183,9 @@ prepare() {
     grep -q "xfb_topology" src/panfrost/vulkan/panvk_shader.h
     grep -q "panvk_xfb_topology" src/panfrost/vulkan/panvk_shader.h
     test -f src/panfrost/vulkan/panvk_vX_xfb_lower.c
+    # r7 sanity: XFB channel-base correction landed
+    grep -q "iter19: nir_intrinsic_component(intr) is the source-channel base" src/panfrost/vulkan/panvk_vX_xfb_lower.c
+    grep -q "mask << src_channel" src/panfrost/vulkan/panvk_vX_xfb_lower.c
 }
 
 build() {

debian/ffmpeg-v4l2-request-fourier/0008-h264-deblock-luma-h-daedalus-fourier.patch

@@ -0,0 +1,92 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 luma-h deblock through daedalus-fourier
+
+Sibling of 0005 (which substituted v_loop_filter_luma).  Same
+NEON-to-NEON substitution: H264DSPContext.h_loop_filter_luma →
+daedalus_recipe_dispatch_h264_deblock_luma_h.  The H kernel landed
+in daedalus-fourier PR #9 (CPU NEON only — no QPU shader yet).
+
+libavcodec.so ctx is no-QPU per the existing 0003-0005 / 0007
+pattern; we cannot assume Vulkan in arbitrary host processes
+(firefox-fourier RDD, mpv-fourier, etc.).
+
+Intra (bS=4) h_loop_filter_luma_intra stays on the in-tree NEON .S
+code; daedalus_h264_deblock_meta only covers the non-intra path.
+An intra-h substitution can land once daedalus-fourier exposes a
+dispatch helper (the kernel already exists internally per PR #11).
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 H.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:09:33.694760715 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:09:33.715603719 +0200
+@@ -1,9 +1,10 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma-v deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+  *        H264DSPContext.v_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_v
++ *        H264DSPContext.h_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_h
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -45,6 +46,8 @@
+ void ff_h264_idct8_add_daedalus(uint8_t *dst, int16_t *block, int stride);
+ void ff_h264_v_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                          int alpha, int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -84,3 +87,22 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_v(g_dctx, pix, (size_t)stride,
+                                                  1, &meta);
+ }
++
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_h(g_dctx, pix, (size_t)stride,
++                                                 1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:09:33.695937103 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:09:33.715541700 +0200
+@@ -31,6 +31,8 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                      int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                         int alpha, int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
+ void ff_h264_h_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+@@ -117,7 +119,7 @@
+ 
+     if (have_neon(cpu_flags) && bit_depth == 8) {
+         c->v_loop_filter_luma   = ff_h264_v_loop_filter_luma_daedalus;
+-        c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_neon;
++        c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_daedalus;
+         c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+         c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
+ 
+--
+2.47.3
+

debian/ffmpeg-v4l2-request-fourier/0009-h264-deblock-chroma-daedalus-fourier.patch

@@ -0,0 +1,127 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 chroma v/h deblock through daedalus-fourier
+
+Chroma siblings of 0005 (luma_v) and 0008 (luma_h).  Same
+NEON-to-NEON pattern via the daedalus recipe layer:
+
+  H264DSPContext.v_loop_filter_chroma →
+    daedalus_recipe_dispatch_h264_deblock_chroma_v
+  H264DSPContext.h_loop_filter_chroma →
+    daedalus_recipe_dispatch_h264_deblock_chroma_h
+
+Both kernels landed in daedalus-fourier PR #10.  Recipe table
+routes AUTO to CPU NEON (no chroma QPU shaders yet), so this
+is plumbing-only and stays bit-exact against the in-tree NEON.
+
+Intra chroma (bS=4) loop filters remain on in-tree NEON;
+daedalus_h264_deblock_meta covers the non-intra (bS<4) path.
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 chroma.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:15:45.995368233 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:15:46.015839177 +0200
+@@ -1,10 +1,12 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h + chroma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+- *        H264DSPContext.v_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_v
+- *        H264DSPContext.h_loop_filter_luma → daedalus_recipe_dispatch_h264_deblock_luma_h
++ *        H264DSPContext.v_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_v
++ *        H264DSPContext.h_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_h
++ *        H264DSPContext.v_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_v
++ *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -48,6 +50,10 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_luma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                          int alpha, int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -106,3 +112,41 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_h(g_dctx, pix, (size_t)stride,
+                                                  1, &meta);
+ }
++
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_chroma_v(g_dctx, pix, (size_t)stride,
++                                                   1, &meta);
++}
++
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    meta.tc0[0] = tc0[0];
++    meta.tc0[1] = tc0[1];
++    meta.tc0[2] = tc0[2];
++    meta.tc0[3] = tc0[3];
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_chroma_h(g_dctx, pix, (size_t)stride,
++                                                   1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:15:45.996482360 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:15:46.025604910 +0200
+@@ -39,8 +39,12 @@
+                                            int beta);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
++void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                           int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma422_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                           int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_intra_neon(uint8_t *pix, ptrdiff_t stride,
+@@ -123,11 +127,11 @@
+         c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+         c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
+ 
+-        c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_neon;
++        c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_daedalus;
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+ 
+         if (chroma_format_idc <= 1) {
+-            c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_neon;
++            c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_daedalus;
+             c->h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon;
+             c->h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon;
+         } else {
+--
+2.47.3
+

debian/ffmpeg-v4l2-request-fourier/0010-h264-deblock-luma-intra-daedalus-fourier.patch

@@ -0,0 +1,126 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 12:30:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 luma intra deblock through daedalus-fourier
+
+Adds the bS=4 intra-strength variants of the already-substituted
+luma_v / luma_h deblock (0005, 0008).  Intra MBs and certain
+inter-MB edges (4x4 transform boundaries inside an Intra_NxN
+neighbour) force boundary strength to 4 per H.264 §8.7.2.1.
+
+  H264DSPContext.v_loop_filter_luma_intra →
+    daedalus_recipe_dispatch_h264_deblock_luma_v_intra
+  H264DSPContext.h_loop_filter_luma_intra →
+    daedalus_recipe_dispatch_h264_deblock_luma_h_intra
+
+Both kernels landed in daedalus-fourier PR #11.  Recipe table
+routes AUTO to CPU NEON (no intra QPU shaders yet) — plumbing-
+only NEON-to-NEON via daedalus, bit-exact against the in-tree
+FFmpeg NEON path.
+
+Signature differs from bS<4: no tc0 argument.  The wrapper
+passes daedalus_h264_deblock_meta with alpha/beta set; tc0[] is
+ignored by the intra dispatch (bS=4 hardcodes the strength).
+
+Chroma intra variants are deferred to a follow-up PR because the
+chroma path has a 4:2:0 / 4:2:2 split (chroma_format_idc gating)
+that needs explicit conditional substitution to avoid running
+the 4:2:0-only daedalus dispatch on 4:2:2 chroma.
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 8 intra.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:18:54.992244965 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:20:12.338122217 +0200
+@@ -1,5 +1,5 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h + chroma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h (inter + intra) + chroma v/h deblock — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+@@ -7,6 +7,8 @@
+  *        H264DSPContext.h_loop_filter_luma   → daedalus_recipe_dispatch_h264_deblock_luma_h
+  *        H264DSPContext.v_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_v
+  *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
++ *        H264DSPContext.v_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_v_intra
++ *        H264DSPContext.h_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_h_intra
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -54,6 +56,10 @@
+                                            int alpha, int beta, int8_t *tc0);
+ void ff_h264_h_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                            int alpha, int beta, int8_t *tc0);
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -150,3 +156,34 @@
+     daedalus_recipe_dispatch_h264_deblock_chroma_h(g_dctx, pix, (size_t)stride,
+                                                    1, &meta);
+ }
++
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++    /* tc0[] is ignored by the intra-strength dispatch (bS=4 hardcodes the strength). */
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_v_intra(g_dctx, pix, (size_t)stride,
++                                                        1, &meta);
++}
++
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta)
++{
++    daedalus_h264_deblock_meta meta = {
++        .dst_off = 0,
++        .alpha   = alpha,
++        .beta    = beta,
++    };
++
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);
++
++    daedalus_recipe_dispatch_h264_deblock_luma_h_intra(g_dctx, pix, (size_t)stride,
++                                                        1, &meta);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:18:54.993349573 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:20:12.338265830 +0200
+@@ -35,8 +35,12 @@
+                                          int alpha, int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
++void ff_h264_v_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ void ff_h264_h_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                            int beta);
++void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
++                                                int alpha, int beta);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+@@ -124,8 +128,8 @@
+     if (have_neon(cpu_flags) && bit_depth == 8) {
+         c->v_loop_filter_luma   = ff_h264_v_loop_filter_luma_daedalus;
+         c->h_loop_filter_luma   = ff_h264_h_loop_filter_luma_daedalus;
+-        c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
+-        c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
++        c->v_loop_filter_luma_intra= ff_h264_v_loop_filter_luma_intra_daedalus;
++        c->h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_daedalus;
+ 
+         c->v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_daedalus;
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+--
+2.47.3
+

debian/ffmpeg-v4l2-request-fourier/0011-h264-chroma-dc-hadamard-daedalus-fourier.patch

@@ -0,0 +1,101 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 13:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264dsp: route H.264 chroma DC Hadamard through daedalus-fourier
+
+Substitutes H264DSPContext.chroma_dc_dequant_idct in the
+4:2:0 / bit_depth=8 init path with a wrapper that composes
+the daedalus chroma DC Hadamard primitive (fourier PR #25)
+with qmul scaling FFmpeg does in one fused function.
+
+Bit-exact against ff_h264_chroma_dc_dequant_idct_8_c.
+Hadamard correctness gated by fourier PR #23 test suite.
+
+4:2:2 chroma stays on the in-tree 422 variant (same
+gating shape as 0009 chroma deblock substitution).
+
+Requires daedalus-fourier commit b9f9ff2 or later (PR #25
+exposing the public Hadamard symbol).  Pin bumps in PKGBUILD
+and build-deb.sh come in the same commit.
+---
+diff --git a/libavcodec/aarch64/h264_idct_daedalus.c b/libavcodec/aarch64/h264_idct_daedalus.c
+--- a/libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:38:32.019491484 +0200
++++ libavcodec/aarch64/h264_idct_daedalus.c	2026-05-25 13:38:32.033821507 +0200
+@@ -1,5 +1,5 @@
+ /*
+- * H.264 4x4 / 8x8 IDCT + luma v/h (inter + intra) + chroma v/h deblock — daedalus-fourier substitution shims.
++ * H.264 4x4 / 8x8 IDCT + luma v/h (inter+intra) + chroma v/h deblock + chroma DC Hadamard — daedalus-fourier substitution shims.
+  *
+  * Routes H264DSPContext.idct_add           → daedalus_recipe_dispatch_h264_idct4
+  *        H264DSPContext.idct8_add          → daedalus_recipe_dispatch_h264_idct8
+@@ -9,6 +9,7 @@
+  *        H264DSPContext.h_loop_filter_chroma → daedalus_recipe_dispatch_h264_deblock_chroma_h
+  *        H264DSPContext.v_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_v_intra
+  *        H264DSPContext.h_loop_filter_luma_intra → daedalus_recipe_dispatch_h264_deblock_luma_h_intra
++ *        H264DSPContext.chroma_dc_dequant_idct   → daedalus_h264_chroma_dc_hadamard_2x2 + caller-side qmul
+  * instead of the in-tree ff_h264_*_neon assembly.  The recipe layer
+  * picks the substrate (CPU NEON for cycles 6 + 7 by default; cycle 8
+  * is CPU primary with QPU opportunistic — the ctx below is no-QPU,
+@@ -60,6 +61,7 @@
+                                                 int alpha, int beta);
+ void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                                 int alpha, int beta);
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul);
+ 
+ void ff_h264_idct_add_daedalus(uint8_t *dst, int16_t *block, int stride)
+ {
+@@ -187,3 +189,32 @@
+     daedalus_recipe_dispatch_h264_deblock_luma_h_intra(g_dctx, pix, (size_t)stride,
+                                                         1, &meta);
+ }
++
++/* Composes daedalus_h264_chroma_dc_hadamard_2x2 with the qmul scaling
++ * that FFmpeg's reference does in one fused function (h264idct_template.c
++ * ff_h264_chroma_dc_dequant_idct).
++ *
++ * The 4 DC coefficients are scattered across the per-MB coefficient
++ * buffer at offsets [r*stride + c*xStride] (stride=32, xStride=16).
++ * Extract into a contiguous int16[4], run the Hadamard, then apply
++ * the qmul scale and write back to the original positions.
++ *
++ * No daedalus ctx needed; the Hadamard is a pure stateless primitive.
++ */
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul)
++{
++    enum { stride = 32, xStride = 16 };
++    int16_t dc[4];
++
++    dc[0] = block[stride*0 + xStride*0];
++    dc[1] = block[stride*0 + xStride*1];
++    dc[2] = block[stride*1 + xStride*0];
++    dc[3] = block[stride*1 + xStride*1];
++
++    daedalus_h264_chroma_dc_hadamard_2x2(dc);
++
++    block[stride*0 + xStride*0] = (int16_t)((int)dc[0] * qmul >> 7);
++    block[stride*0 + xStride*1] = (int16_t)((int)dc[1] * qmul >> 7);
++    block[stride*1 + xStride*0] = (int16_t)((int)dc[2] * qmul >> 7);
++    block[stride*1 + xStride*1] = (int16_t)((int)dc[3] * qmul >> 7);
++}
+diff --git a/libavcodec/aarch64/h264dsp_init_aarch64.c b/libavcodec/aarch64/h264dsp_init_aarch64.c
+--- a/libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:38:32.020346459 +0200
++++ libavcodec/aarch64/h264dsp_init_aarch64.c	2026-05-25 13:38:32.033909804 +0200
+@@ -41,6 +41,7 @@
+                                            int beta);
+ void ff_h264_h_loop_filter_luma_intra_daedalus(uint8_t *pix, ptrdiff_t stride,
+                                                 int alpha, int beta);
++void ff_h264_chroma_dc_dequant_idct_daedalus(int16_t *block, int qmul);
+ void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
+                                        int beta, int8_t *tc0);
+ void ff_h264_v_loop_filter_chroma_daedalus(uint8_t *pix, ptrdiff_t stride,
+@@ -135,6 +136,7 @@
+         c->v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
+ 
+         if (chroma_format_idc <= 1) {
++            c->chroma_dc_dequant_idct = ff_h264_chroma_dc_dequant_idct_daedalus;
+             c->h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_daedalus;
+             c->h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon;
+             c->h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon;
+--
+2.47.3
+

debian/ffmpeg-v4l2-request-fourier/0012-h264-qpel-rest-daedalus-fourier.patch

@@ -0,0 +1,245 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: claude-noether <claude-noether@noreply.localhost>
+Date: Sun, 25 May 2026 14:00:00 +0200
+Subject: [PATCH] avcodec/aarch64/h264qpel: route remaining qpel 8x8 positions through daedalus-fourier
+
+Closes the H.264 qpel substitution.  Extends 0007 (which routed only
+mc20 put_) to ALL 15 useful positions in BOTH the put_ and avg_
+tables, skipping mc00 (integer copy / pointer-only fast path).
+
+29 substitutions total: 14 new put_ + 15 avg_.  Each is a uniform
+wrapper around daedalus_recipe_dispatch_h264_qpel_{avg_,}mcXY exposed
+by daedalus-fourier PRs #15-#20.
+
+All recipe-table entries route AUTO to CPU NEON (no QPU shaders
+for any qpel position other than mc20 yet), so this is plumbing-only
+NEON-to-NEON — bit-exact against the in-tree ff_*_h264_qpel8_*_neon
+path.
+
+16x16 qpel tables ([0][...]) stay on the in-tree NEON.  daedalus
+only exposes 8x8 today; 16x16 substitution can land once fourier
+provides those variants (likely just dispatching the 8x8 path four
+times with shifted dst/src offsets).
+
+Refs reauktion/daedalus-v4l2#11 — substitution arc qpel buildout.
+---
+diff --git a/libavcodec/aarch64/h264_qpel_daedalus.c b/libavcodec/aarch64/h264_qpel_daedalus.c
+--- a/libavcodec/aarch64/h264_qpel_daedalus.c	2026-05-25 14:05:05.789298250 +0200
++++ libavcodec/aarch64/h264_qpel_daedalus.c	2026-05-25 14:05:05.818358374 +0200
+@@ -1,10 +1,13 @@
+ /*
+- * H.264 luma qpel mc20 (8x8, horizontal half-pel, 6-tap "put")
+- * — daedalus-fourier substitution shim.
++ * H.264 luma qpel 8x8 — daedalus-fourier substitution shims (put_ + avg_).
+  *
+- * Routes H264QpelContext.put_h264_qpel_pixels_tab[1][2] through
+- * daedalus_recipe_dispatch_h264_qpel_mc20 instead of
+- * ff_put_h264_qpel8_mc20_neon.  The recipe layer picks the substrate
++ * Routes ALL 15 useful positions in H264QpelContext's 8x8 put_ and
++ * avg_ tables through daedalus_recipe_dispatch_h264_qpel_mc{XY}
++ * (skipping mc00 which is integer copy / FFmpeg's pointer-only fast
++ * path).  Plumbing-only NEON-by-recipe — daedalus-fourier PRs #15-#20
++ * exposed each variant via the same dispatch signature, so the
++ * substitution is a uniform macro across put_/avg_ and across all
++ * 15 mc positions.  The recipe layer picks the substrate
+  * (CPU NEON for cycle 9; QPU not viable — per-block 7.6 ns vs
+  * ~250 ns QPU dispatch floor, see docs/k9_h264qpel_mc20.md).
+  *
+@@ -48,3 +51,53 @@
+     daedalus_recipe_dispatch_h264_qpel_mc20(g_dctx, dst, src, (size_t)stride,
+                                             1, &meta);
+ }
++
++
++/* All other 8x8 qpel positions follow the same dispatch shape as mc20
++ * above.  The macro collapses ~600 LOC of one-wrapper-per-variant
++ * boilerplate (29 variants total: 14 put_ + 15 avg_). */
++#define DEFINE_QPEL_WRAPPER(type, suffix, dispatch_fn)                          \
++void ff_ ## type ## _h264_qpel8_ ## suffix ## _daedalus(uint8_t *dst,           \
++    const uint8_t *src, ptrdiff_t stride);                                      \
++void ff_ ## type ## _h264_qpel8_ ## suffix ## _daedalus(uint8_t *dst,           \
++    const uint8_t *src, ptrdiff_t stride)                                       \
++{                                                                               \
++    static const daedalus_h264_qpel_meta meta = { .dst_off = 0, .src_off = 0 }; \
++    pthread_once(&g_dctx_once, daedalus_ctx_init_once);                         \
++    dispatch_fn(g_dctx, dst, src, (size_t)stride, 1, &meta);                    \
++}
++
++/* put_ variants (mc20 stays on the explicit definition above). */
++DEFINE_QPEL_WRAPPER(put, mc10, daedalus_recipe_dispatch_h264_qpel_mc10)
++DEFINE_QPEL_WRAPPER(put, mc30, daedalus_recipe_dispatch_h264_qpel_mc30)
++DEFINE_QPEL_WRAPPER(put, mc01, daedalus_recipe_dispatch_h264_qpel_mc01)
++DEFINE_QPEL_WRAPPER(put, mc11, daedalus_recipe_dispatch_h264_qpel_mc11)
++DEFINE_QPEL_WRAPPER(put, mc21, daedalus_recipe_dispatch_h264_qpel_mc21)
++DEFINE_QPEL_WRAPPER(put, mc31, daedalus_recipe_dispatch_h264_qpel_mc31)
++DEFINE_QPEL_WRAPPER(put, mc02, daedalus_recipe_dispatch_h264_qpel_mc02)
++DEFINE_QPEL_WRAPPER(put, mc12, daedalus_recipe_dispatch_h264_qpel_mc12)
++DEFINE_QPEL_WRAPPER(put, mc22, daedalus_recipe_dispatch_h264_qpel_mc22)
++DEFINE_QPEL_WRAPPER(put, mc32, daedalus_recipe_dispatch_h264_qpel_mc32)
++DEFINE_QPEL_WRAPPER(put, mc03, daedalus_recipe_dispatch_h264_qpel_mc03)
++DEFINE_QPEL_WRAPPER(put, mc13, daedalus_recipe_dispatch_h264_qpel_mc13)
++DEFINE_QPEL_WRAPPER(put, mc23, daedalus_recipe_dispatch_h264_qpel_mc23)
++DEFINE_QPEL_WRAPPER(put, mc33, daedalus_recipe_dispatch_h264_qpel_mc33)
++
++/* avg_ variants — all 15 useful positions. */
++DEFINE_QPEL_WRAPPER(avg, mc10, daedalus_recipe_dispatch_h264_qpel_avg_mc10)
++DEFINE_QPEL_WRAPPER(avg, mc20, daedalus_recipe_dispatch_h264_qpel_avg_mc20)
++DEFINE_QPEL_WRAPPER(avg, mc30, daedalus_recipe_dispatch_h264_qpel_avg_mc30)
++DEFINE_QPEL_WRAPPER(avg, mc01, daedalus_recipe_dispatch_h264_qpel_avg_mc01)
++DEFINE_QPEL_WRAPPER(avg, mc11, daedalus_recipe_dispatch_h264_qpel_avg_mc11)
++DEFINE_QPEL_WRAPPER(avg, mc21, daedalus_recipe_dispatch_h264_qpel_avg_mc21)
++DEFINE_QPEL_WRAPPER(avg, mc31, daedalus_recipe_dispatch_h264_qpel_avg_mc31)
++DEFINE_QPEL_WRAPPER(avg, mc02, daedalus_recipe_dispatch_h264_qpel_avg_mc02)
++DEFINE_QPEL_WRAPPER(avg, mc12, daedalus_recipe_dispatch_h264_qpel_avg_mc12)
++DEFINE_QPEL_WRAPPER(avg, mc22, daedalus_recipe_dispatch_h264_qpel_avg_mc22)
++DEFINE_QPEL_WRAPPER(avg, mc32, daedalus_recipe_dispatch_h264_qpel_avg_mc32)
++DEFINE_QPEL_WRAPPER(avg, mc03, daedalus_recipe_dispatch_h264_qpel_avg_mc03)
++DEFINE_QPEL_WRAPPER(avg, mc13, daedalus_recipe_dispatch_h264_qpel_avg_mc13)
++DEFINE_QPEL_WRAPPER(avg, mc23, daedalus_recipe_dispatch_h264_qpel_avg_mc23)
++DEFINE_QPEL_WRAPPER(avg, mc33, daedalus_recipe_dispatch_h264_qpel_avg_mc33)
++
++#undef DEFINE_QPEL_WRAPPER
+diff --git a/libavcodec/aarch64/h264qpel_init_aarch64.c b/libavcodec/aarch64/h264qpel_init_aarch64.c
+--- a/libavcodec/aarch64/h264qpel_init_aarch64.c	2026-05-25 14:05:05.790403989 +0200
++++ libavcodec/aarch64/h264qpel_init_aarch64.c	2026-05-25 14:05:05.819136071 +0200
+@@ -50,6 +50,64 @@
+ void ff_put_h264_qpel8_mc30_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc20_daedalus(uint8_t *dst, const uint8_t *src,
+                                      ptrdiff_t stride);
++void ff_put_h264_qpel8_mc10_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc30_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc01_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc11_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc21_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc31_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc02_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc12_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc22_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc32_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc03_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc13_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc23_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_put_h264_qpel8_mc33_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc10_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc20_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc30_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc01_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc11_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc21_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc31_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc02_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc12_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc22_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc32_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc03_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc13_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc23_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
++void ff_avg_h264_qpel8_mc33_daedalus(uint8_t *dst, const uint8_t *src,
++                                  ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc01_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc11_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+ void ff_put_h264_qpel8_mc21_neon(uint8_t *dst, const uint8_t *src, ptrdiff_t stride);
+@@ -164,21 +222,21 @@
+         c->put_h264_qpel_pixels_tab[0][15] = ff_put_h264_qpel16_mc33_neon;
+ 
+         c->put_h264_qpel_pixels_tab[1][ 0] = ff_put_h264_qpel8_mc00_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 1] = ff_put_h264_qpel8_mc10_neon;
++        c->put_h264_qpel_pixels_tab[1][ 1] = ff_put_h264_qpel8_mc10_daedalus;
+         c->put_h264_qpel_pixels_tab[1][ 2] = ff_put_h264_qpel8_mc20_daedalus;
+-        c->put_h264_qpel_pixels_tab[1][ 3] = ff_put_h264_qpel8_mc30_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 4] = ff_put_h264_qpel8_mc01_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 5] = ff_put_h264_qpel8_mc11_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 6] = ff_put_h264_qpel8_mc21_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 7] = ff_put_h264_qpel8_mc31_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 8] = ff_put_h264_qpel8_mc02_neon;
+-        c->put_h264_qpel_pixels_tab[1][ 9] = ff_put_h264_qpel8_mc12_neon;
+-        c->put_h264_qpel_pixels_tab[1][10] = ff_put_h264_qpel8_mc22_neon;
+-        c->put_h264_qpel_pixels_tab[1][11] = ff_put_h264_qpel8_mc32_neon;
+-        c->put_h264_qpel_pixels_tab[1][12] = ff_put_h264_qpel8_mc03_neon;
+-        c->put_h264_qpel_pixels_tab[1][13] = ff_put_h264_qpel8_mc13_neon;
+-        c->put_h264_qpel_pixels_tab[1][14] = ff_put_h264_qpel8_mc23_neon;
+-        c->put_h264_qpel_pixels_tab[1][15] = ff_put_h264_qpel8_mc33_neon;
++        c->put_h264_qpel_pixels_tab[1][ 3] = ff_put_h264_qpel8_mc30_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 4] = ff_put_h264_qpel8_mc01_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 5] = ff_put_h264_qpel8_mc11_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 6] = ff_put_h264_qpel8_mc21_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 7] = ff_put_h264_qpel8_mc31_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 8] = ff_put_h264_qpel8_mc02_daedalus;
++        c->put_h264_qpel_pixels_tab[1][ 9] = ff_put_h264_qpel8_mc12_daedalus;
++        c->put_h264_qpel_pixels_tab[1][10] = ff_put_h264_qpel8_mc22_daedalus;
++        c->put_h264_qpel_pixels_tab[1][11] = ff_put_h264_qpel8_mc32_daedalus;
++        c->put_h264_qpel_pixels_tab[1][12] = ff_put_h264_qpel8_mc03_daedalus;
++        c->put_h264_qpel_pixels_tab[1][13] = ff_put_h264_qpel8_mc13_daedalus;
++        c->put_h264_qpel_pixels_tab[1][14] = ff_put_h264_qpel8_mc23_daedalus;
++        c->put_h264_qpel_pixels_tab[1][15] = ff_put_h264_qpel8_mc33_daedalus;
+ 
+         c->avg_h264_qpel_pixels_tab[0][ 0] = ff_avg_h264_qpel16_mc00_neon;
+         c->avg_h264_qpel_pixels_tab[0][ 1] = ff_avg_h264_qpel16_mc10_neon;
+@@ -198,21 +256,21 @@
+         c->avg_h264_qpel_pixels_tab[0][15] = ff_avg_h264_qpel16_mc33_neon;
+ 
+         c->avg_h264_qpel_pixels_tab[1][ 0] = ff_avg_h264_qpel8_mc00_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 1] = ff_avg_h264_qpel8_mc10_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 2] = ff_avg_h264_qpel8_mc20_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 3] = ff_avg_h264_qpel8_mc30_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 4] = ff_avg_h264_qpel8_mc01_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 5] = ff_avg_h264_qpel8_mc11_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 6] = ff_avg_h264_qpel8_mc21_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 7] = ff_avg_h264_qpel8_mc31_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 8] = ff_avg_h264_qpel8_mc02_neon;
+-        c->avg_h264_qpel_pixels_tab[1][ 9] = ff_avg_h264_qpel8_mc12_neon;
+-        c->avg_h264_qpel_pixels_tab[1][10] = ff_avg_h264_qpel8_mc22_neon;
+-        c->avg_h264_qpel_pixels_tab[1][11] = ff_avg_h264_qpel8_mc32_neon;
+-        c->avg_h264_qpel_pixels_tab[1][12] = ff_avg_h264_qpel8_mc03_neon;
+-        c->avg_h264_qpel_pixels_tab[1][13] = ff_avg_h264_qpel8_mc13_neon;
+-        c->avg_h264_qpel_pixels_tab[1][14] = ff_avg_h264_qpel8_mc23_neon;
+-        c->avg_h264_qpel_pixels_tab[1][15] = ff_avg_h264_qpel8_mc33_neon;
++        c->avg_h264_qpel_pixels_tab[1][ 1] = ff_avg_h264_qpel8_mc10_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 2] = ff_avg_h264_qpel8_mc20_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 3] = ff_avg_h264_qpel8_mc30_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 4] = ff_avg_h264_qpel8_mc01_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 5] = ff_avg_h264_qpel8_mc11_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 6] = ff_avg_h264_qpel8_mc21_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 7] = ff_avg_h264_qpel8_mc31_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 8] = ff_avg_h264_qpel8_mc02_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][ 9] = ff_avg_h264_qpel8_mc12_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][10] = ff_avg_h264_qpel8_mc22_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][11] = ff_avg_h264_qpel8_mc32_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][12] = ff_avg_h264_qpel8_mc03_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][13] = ff_avg_h264_qpel8_mc13_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][14] = ff_avg_h264_qpel8_mc23_daedalus;
++        c->avg_h264_qpel_pixels_tab[1][15] = ff_avg_h264_qpel8_mc33_daedalus;
+     } else if (have_neon(cpu_flags) && bit_depth == 10) {
+         c->put_h264_qpel_pixels_tab[0][ 1] = ff_put_h264_qpel16_mc10_neon_10;
+         c->put_h264_qpel_pixels_tab[0][ 2] = ff_put_h264_qpel16_mc20_neon_10;
+--
+2.47.3
+

debian/ffmpeg-v4l2-request-fourier/build-deb.sh

@@ -45,7 +45,7 @@ PKGREL=10  # pkgrel=10 — H.264 luma qpel mc20 daedalus-fourier substitution
 # DAEDALUS_KERNEL_H264_QPEL_MC20.  Cycle 9 plumbs the last H.264 NEON
 # kernel through the recipe layer.  Daemon-side build (debian/daedalus-v4l2)
 # can bump in a follow-up; this PR only changes the libavcodec.so consumer.
-DAEDALUS_FOURIER_COMMIT=209a4218bcb98b91c04f07ad61513bb04adb13ad
+DAEDALUS_FOURIER_COMMIT=b9f9ff2a89c068aea54dcb52b543afddad28311e  # PR #25 — public chroma DC Hadamard
 
 HERE=$(dirname "$(readlink -f "$0")")
 
@@ -74,6 +74,11 @@ patch -Np1 -i "$HERE/0004-h264-idct8-daedalus-fourier.patch"
 patch -Np1 -i "$HERE/0005-h264-deblock-luma-v-daedalus-fourier.patch"
 patch -Np1 -i "$HERE/0006-h264-restore-low-delay.patch"
 patch -Np1 -i "$HERE/0007-h264-qpel-mc20-daedalus-fourier.patch"
+patch -Np1 -i "$HERE/0008-h264-deblock-luma-h-daedalus-fourier.patch"
+patch -Np1 -i "$HERE/0009-h264-deblock-chroma-daedalus-fourier.patch"
+patch -Np1 -i "$HERE/0010-h264-deblock-luma-intra-daedalus-fourier.patch"
+patch -Np1 -i "$HERE/0011-h264-chroma-dc-hadamard-daedalus-fourier.patch"
+patch -Np1 -i "$HERE/0012-h264-qpel-rest-daedalus-fourier.patch"
 
 # --- daedalus-fourier: fetch + build static .a with PIC, install to a
 # per-build prefix; libavcodec.so links it into the shared object so