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
tests/test_api_h264.c
+93
View File
@@ -18,6 +18,10 @@ extern void daedalus_h264_idct_add_ref(uint8_t *dst, int16_t *block, ptrdiff_t s
extern void daedalus_h264_idct8_add_ref(uint8_t *dst, int16_t *block, ptrdiff_t stride);
extern void daedalus_h264_h_loop_filter_luma_ref(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t tc0[4]);
extern void daedalus_h264_v_loop_filter_chroma_ref(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t tc0[4]);
extern void daedalus_h264_h_loop_filter_chroma_ref(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t tc0[4]);
extern void daedalus_h264_v_loop_filter_luma_ref(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t tc0[4]);
extern void daedalus_put_h264_qpel8_mc20_ref(uint8_t *dst, const uint8_t *src,
@@ -191,6 +195,89 @@ static int test_deblock_h(void)
return diff == 0 ? 0 : 1;
}
static int test_deblock_chroma_v(void)
{
/* Chroma V: per-tile 8 cols × 4 rows, edge between rows 1 and 2
* (EDGE_ROW=2 lets the kernel read pix[-2..+1]*stride safely). */
enum { N_EDGES = 8, TILE_STRIDE = 8, TILE_ROWS = 4,
TILE_BYTES = TILE_STRIDE * TILE_ROWS,
TOTAL = N_EDGES * TILE_BYTES, EDGE_ROW = 2,
EDGE_OFF = EDGE_ROW * TILE_STRIDE };
daedalus_ctx *ctx = daedalus_ctx_create();
if (!ctx) return 1;
uint8_t dst[TOTAL], dst_ref[TOTAL];
daedalus_h264_deblock_meta meta[N_EDGES];
for (int i = 0; i < TOTAL; i++) dst[i] = dst_ref[i] = (uint8_t)(xs() & 0xff);
for (int i = 0; i < N_EDGES; i++) {
meta[i].dst_off = i * TILE_BYTES + EDGE_OFF;
meta[i].alpha = (int)(xs() % 64) + 1;
meta[i].beta = (int)(xs() % 16) + 1;
for (int s = 0; s < 4; s++) {
int r = (int)(xs() % 8);
meta[i].tc0[s] = (int8_t)(r == 0 ? -1 : (r - 1));
}
}
for (int 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] };
daedalus_h264_v_loop_filter_chroma_ref(dst_ref + meta[i].dst_off, TILE_STRIDE,
meta[i].alpha, meta[i].beta, tc0_local);
}
int rc = daedalus_recipe_dispatch_h264_deblock_chroma_v(ctx, dst, TILE_STRIDE,
N_EDGES, meta);
if (rc) { fprintf(stderr, "deblock_chroma_v dispatch rc=%d\n", rc); return 1; }
int diff = 0;
for (int i = 0; i < TOTAL; i++) if (dst[i] != dst_ref[i]) diff++;
printf(" H.264 deblock chroma v: %d/%d bytes bit-exact (%.4f%%)\n",
TOTAL - diff, TOTAL, 100.0 * (TOTAL - diff) / TOTAL);
daedalus_ctx_destroy(ctx);
return diff == 0 ? 0 : 1;
}
static int test_deblock_chroma_h(void)
{
/* Chroma H: per-tile 4 cols × 8 rows, edge between cols 1 and 2
* (EDGE_COL=2 lets the kernel read pix[-2..+1] safely). */
enum { N_EDGES = 8, TILE_STRIDE = 4, TILE_ROWS = 8,
TILE_BYTES = TILE_STRIDE * TILE_ROWS,
TOTAL = N_EDGES * TILE_BYTES, EDGE_COL = 2 };
daedalus_ctx *ctx = daedalus_ctx_create();
if (!ctx) return 1;
uint8_t dst[TOTAL], dst_ref[TOTAL];
daedalus_h264_deblock_meta meta[N_EDGES];
for (int i = 0; i < TOTAL; i++) dst[i] = dst_ref[i] = (uint8_t)(xs() & 0xff);
for (int i = 0; i < N_EDGES; i++) {
meta[i].dst_off = i * TILE_BYTES + EDGE_COL;
meta[i].alpha = (int)(xs() % 64) + 1;
meta[i].beta = (int)(xs() % 16) + 1;
for (int s = 0; s < 4; s++) {
int r = (int)(xs() % 8);
meta[i].tc0[s] = (int8_t)(r == 0 ? -1 : (r - 1));
}
}
for (int 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] };
daedalus_h264_h_loop_filter_chroma_ref(dst_ref + meta[i].dst_off, TILE_STRIDE,
meta[i].alpha, meta[i].beta, tc0_local);
}
int rc = daedalus_recipe_dispatch_h264_deblock_chroma_h(ctx, dst, TILE_STRIDE,
N_EDGES, meta);
if (rc) { fprintf(stderr, "deblock_chroma_h dispatch rc=%d\n", rc); return 1; }
int diff = 0;
for (int i = 0; i < TOTAL; i++) if (dst[i] != dst_ref[i]) diff++;
printf(" H.264 deblock chroma h: %d/%d bytes bit-exact (%.4f%%)\n",
TOTAL - diff, TOTAL, 100.0 * (TOTAL - diff) / TOTAL);
daedalus_ctx_destroy(ctx);
return diff == 0 ? 0 : 1;
}
static int test_qpel_mc20(void)
{
/* Cycle 9 — one 8x8 block per 16-wide row-tile, 8 tiles. Each tile
@@ -245,12 +332,18 @@ int main(void)
printf(" H264_DEBLOCK_LH recipe substrate: %d (CPU, no QPU H shader yet)\n",
(int) daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_LH));
printf(" H264_DEBLOCK_CV recipe substrate: %d (CPU)\n",
(int) daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_CV));
printf(" H264_DEBLOCK_CH recipe substrate: %d (CPU)\n",
(int) daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_CH));
int fail = 0;
fail |= test_idct4();
fail |= test_idct8();
fail |= test_deblock();
fail |= test_deblock_h();
fail |= test_deblock_chroma_v();
fail |= test_deblock_chroma_h();
fail |= test_qpel_mc20();
return fail;
}