ffmpeg-v4l2-request-fourier: route H.264 chroma v/h deblock through daedalus-fourier (0009)

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. Verified the patch applies cleanly on top of 0001-0008 against the pinned upstream commit b57fbbe5 on hertz. Wires the new patch into both arch/PKGBUILD and debian/build-deb.sh.
2026-05-25 13:16:45 +02:00
parent 5b48d1c743
commit babb280410
4 changed files with 259 additions and 2 deletions
@@ -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
+
@@ -75,6 +75,7 @@ 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"

 # --- daedalus-fourier: fetch + build static .a with PIC, install to a
 # per-build prefix; libavcodec.so links it into the shared object so