marfrit/daedalus-fourier
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

h264: deblock chroma_v + chroma_h (CPU/NEON, bS<4)

Browse Source 
Continues the deblock buildout after PR #9 (luma_h).  Adds the two
chroma orientations via the same recipe-table-routed-to-CPU pattern;
QPU shaders for chroma deblock are still a follow-up.

Scope:
  - Public API: 4 new fns (dispatch + recipe wrapper × {v, h}).
  - Internal: dispatch_h264_deblock_chroma_{v,h}_cpu calling the
    vendored ff_h264_{v,h}_loop_filter_chroma_neon symbols.
  - Recipe table: DAEDALUS_KERNEL_H264_DEBLOCK_CV = 11,
    DAEDALUS_KERNEL_H264_DEBLOCK_CH = 12, both → CPU.  Explicit
    SUBSTRATE_QPU returns -1 (no shader yet).
  - C reference: tests/h264_chroma_loop_filter_ref.c — covers both
    orientations.  Algorithm per H.264 §8.7.2.4 (bS<4 chroma inter):
    tC = tc0_seg + 1 (no luma-style ap/aq side bonus); only p0/q0
    are updated (chroma never modifies p1/p2/q1/q2).
  - Tests: test_deblock_chroma_v (8x4 tile, edge at row 2) +
    test_deblock_chroma_h (4x8 tile, edge at col 2), 4 segments x
    2 cells per segment per spec.

Verified on hertz (Pi 5 / V3D 7.1):

  $ ./build/test_api_h264
  === Phase 8a API smoke: H.264 kernels via recipe dispatch ===
    H264_IDCT4 recipe substrate:      2 (1=CPU, 2=QPU)
    H264_IDCT8 recipe substrate:      2
    H264_DEBLOCK_LV recipe substrate: 2
    H264_QPEL_MC20 recipe substrate:  2
    H264_DEBLOCK_LH recipe substrate: 1 (CPU, no QPU H shader yet)
    H264_DEBLOCK_CV recipe substrate: 1 (CPU)
    H264_DEBLOCK_CH recipe substrate: 1 (CPU)
    H.264 IDCT 4x4: 2048/2048 bytes bit-exact (100.0000%)
    H.264 IDCT 8x8: 2048/2048 bytes bit-exact (100.0000%)
    H.264 deblock luma v: 2048/2048 bytes bit-exact (100.0000%)
    H.264 deblock luma h: 1024/1024 bytes bit-exact (100.0000%)
    H.264 deblock chroma v: 256/256 bytes bit-exact (100.0000%)
    H.264 deblock chroma h: 256/256 bytes bit-exact (100.0000%)
    H.264 qpel mc20: 1024/1024 bytes bit-exact (100.0000%)

  All 7 kernels bit-exact PASS.  Chroma test sizes are smaller (256
  bytes per orientation) because the per-MB chroma deblock surface is
  smaller than luma — accurate to the production geometry.

Why no QPU shader yet (per the established pattern):
  - Chroma deblock is ~25% of total deblock work at 4:2:0 (one quarter
    the pixel count of luma per MB) — modest QPU win even after the
    shader exists.
  - Same R-band considerations as the luma _h follow-up: the V shader
    transpose isn't mechanical, and the 8-cell tile is small enough
    that NEON's per-edge cost (~3 ns) is already inside the budget.
  - Total bench at 1080p: 8160 MBs × 4 chroma edges × 3 ns = ~100 us.
    Negligible compared to the IDCT layer's 10 ms (CPU NEON).

Now coverage in fourier for the bS<4 8-bit 4:2:0 deblock matrix is
complete: luma_v ✓, luma_h ✓, chroma_v ✓, chroma_h ✓.  Remaining
deblock work: bS=4 intra variants (luma + chroma, V + H).

What this unblocks downstream:
  - daedalus-decoder Stage 4 deblock can now dispatch all four bS<4
    edge categories that a typical inter MB needs.
This commit is contained in:
Claude (noether)
2026-05-24 23:53:09 +02:00
parent f4af24020f
commit a5c47aa51c
5 changed files with 315 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/daedalus_core.c
+80
View File
@@ -131,6 +131,8 @@ daedalus_substrate daedalus_recipe_substrate_for(daedalus_kernel k)
case DAEDALUS_KERNEL_H264_IDCT8: return DAEDALUS_SUBSTRATE_QPU; /* v3d_h264_idct8.spv */
case DAEDALUS_KERNEL_H264_DEBLOCK_LV: return DAEDALUS_SUBSTRATE_QPU; /* v3d_h264deblock.spv */
case DAEDALUS_KERNEL_H264_DEBLOCK_LH: return DAEDALUS_SUBSTRATE_CPU; /* QPU H shader pending */
case DAEDALUS_KERNEL_H264_DEBLOCK_CV: return DAEDALUS_SUBSTRATE_CPU; /* chroma QPU pending */
case DAEDALUS_KERNEL_H264_DEBLOCK_CH: return DAEDALUS_SUBSTRATE_CPU; /* chroma QPU pending */
case DAEDALUS_KERNEL_H264_QPEL_MC20: return DAEDALUS_SUBSTRATE_QPU; /* v3d_h264_qpel_mc20.spv */
}
return DAEDALUS_SUBSTRATE_CPU;
@@ -158,6 +160,10 @@ extern void ff_h264_v_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
extern void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
extern void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
extern void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
extern void ff_put_h264_qpel8_mc20_neon(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride);
@@ -284,6 +290,36 @@ static int dispatch_h264_deblock_h_cpu(daedalus_ctx *ctx,
return 0;
}
static int dispatch_h264_deblock_chroma_v_cpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
(void) ctx;
for (size_t i = 0; i < n_edges; i++) {
int8_t tc0_local[4] = { meta[i].tc0[0], meta[i].tc0[1],
meta[i].tc0[2], meta[i].tc0[3] };
ff_h264_v_loop_filter_chroma_neon(dst + meta[i].dst_off,
(ptrdiff_t) dst_stride,
meta[i].alpha, meta[i].beta, tc0_local);
}
return 0;
}
static int dispatch_h264_deblock_chroma_h_cpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
(void) ctx;
for (size_t i = 0; i < n_edges; i++) {
int8_t tc0_local[4] = { meta[i].tc0[0], meta[i].tc0[1],
meta[i].tc0[2], meta[i].tc0[3] };
ff_h264_h_loop_filter_chroma_neon(dst + meta[i].dst_off,
(ptrdiff_t) dst_stride,
meta[i].alpha, meta[i].beta, tc0_local);
}
return 0;
}
static int dispatch_h264_qpel_mc20_cpu(daedalus_ctx *ctx,
uint8_t *dst, const uint8_t *src, size_t stride,
size_t n_blocks, const daedalus_h264_qpel_meta *meta)
@@ -1206,6 +1242,34 @@ int daedalus_dispatch_h264_deblock_luma_h(daedalus_ctx *ctx, daedalus_substrate
return dispatch_h264_deblock_h_cpu(ctx, dst, dst_stride, n_edges, meta);
}
int daedalus_dispatch_h264_deblock_chroma_v(daedalus_ctx *ctx, daedalus_substrate sub,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
daedalus_substrate eff = sub;
if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_CV);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_QPU)
return -1; /* No chroma QPU shader yet. */
return dispatch_h264_deblock_chroma_v_cpu(ctx, dst, dst_stride, n_edges, meta);
}
int daedalus_dispatch_h264_deblock_chroma_h(daedalus_ctx *ctx, daedalus_substrate sub,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
daedalus_substrate eff = sub;
if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_CH);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_QPU)
return -1;
return dispatch_h264_deblock_chroma_h_cpu(ctx, dst, dst_stride, n_edges, meta);
}
int daedalus_dispatch_h264_qpel_mc20(daedalus_ctx *ctx, daedalus_substrate sub,
uint8_t *dst, const uint8_t *src, size_t stride,
size_t n_blocks, const daedalus_h264_qpel_meta *meta)
@@ -1301,6 +1365,22 @@ int daedalus_recipe_dispatch_h264_deblock_luma_h(daedalus_ctx *ctx,
dst, dst_stride, n_edges, meta);
}
int daedalus_recipe_dispatch_h264_deblock_chroma_v(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
return daedalus_dispatch_h264_deblock_chroma_v(ctx, DAEDALUS_SUBSTRATE_AUTO,
dst, dst_stride, n_edges, meta);
}
int daedalus_recipe_dispatch_h264_deblock_chroma_h(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
return daedalus_dispatch_h264_deblock_chroma_h(ctx, DAEDALUS_SUBSTRATE_AUTO,
dst, dst_stride, n_edges, meta);
}
int daedalus_recipe_dispatch_h264_qpel_mc20(daedalus_ctx *ctx,
uint8_t *dst, const uint8_t *src, size_t stride,
size_t n_blocks, const daedalus_h264_qpel_meta *meta)