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

Phase 8c: H.264 luma qpel mc20 through public API

Browse Source 
Extends daedalus-fourier with daedalus_recipe_dispatch_h264_qpel_mc20
so libavcodec.so can route H264QpelContext.put_h264_qpel_pixels_tab[1][2]
through the recipe layer instead of ff_put_h264_qpel8_mc20_neon directly.

API additions (header + library):
  - daedalus_h264_qpel_meta { dst_off, src_off }
  - daedalus_dispatch_h264_qpel_mc20(ctx, sub, dst, src, stride,
                                     n_blocks, meta)
  - daedalus_recipe_dispatch_h264_qpel_mc20(...)  (AUTO wrapper)
  - DAEDALUS_KERNEL_H264_QPEL_MC20 = 9 in the recipe-query enum
  - daedalus_recipe_substrate_for() returns CPU NEON for cycle 9

The 6-tap horizontal half-pel filter signature matches FFmpeg's
H264QpelContext convention exactly: dst and src share a single stride
and src already points at output column 0 (filter reads cols -2..+3).
Single-stride API to make the marfrit-packages FFmpeg shim a
straight pointer-pass; no buffer rearrangement.

Verdict per docs/k9_h264qpel_mc20.md: CPU NEON.  Per-block 7.6 ns
gives 135x margin over 30 fps 1080p; QPU dispatch floor at ~250 ns
makes any V3D shader strictly worse.  Recipe table reflects that —
the recipe_dispatch entry is a one-line forward to the CPU path.

CMakeLists changes:
  - h264qpel_neon.S added to the daedalus_core static lib (only the
    bench targets owned it before; now the public API needs it too)
  - tests/h264_qpel8_mc20_ref.c added to the test_api_h264 target

Phase 8a/8b smoke gains a 4th case (test_qpel_mc20): 1024/1024
bytes bit-exact via daedalus_recipe_dispatch_h264_qpel_mc20.

Refs reauktion/daedalus-v4l2#11 — substitution arc step 2 cycle 9.
This commit is contained in:
Claude (noether)
2026-05-23 03:25:24 +02:00
parent d87239d817
commit 8fdef27a7d
4 changed files with 116 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/daedalus_core.c
+35
View File
@@ -93,6 +93,7 @@ daedalus_substrate daedalus_recipe_substrate_for(daedalus_kernel k)
case DAEDALUS_KERNEL_H264_IDCT4: return DAEDALUS_SUBSTRATE_CPU;
case DAEDALUS_KERNEL_H264_IDCT8: return DAEDALUS_SUBSTRATE_CPU;
case DAEDALUS_KERNEL_H264_DEBLOCK_LV: return DAEDALUS_SUBSTRATE_CPU;
case DAEDALUS_KERNEL_H264_QPEL_MC20: return DAEDALUS_SUBSTRATE_CPU;
}
return DAEDALUS_SUBSTRATE_CPU;
}
@@ -117,6 +118,8 @@ extern void ff_h264_idct_add_neon(uint8_t *dst, int16_t *block, ptrdiff_t stride
extern void ff_h264_idct8_add_neon(uint8_t *dst, int16_t *block, ptrdiff_t stride);
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_put_h264_qpel8_mc20_neon(uint8_t *dst, const uint8_t *src,
ptrdiff_t stride);
/* -------------------- CPU dispatch implementations -------------- */
@@ -226,6 +229,22 @@ static int dispatch_h264_deblock_cpu(daedalus_ctx *ctx,
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)
{
(void) ctx;
/* FFmpeg's NEON entry uses a single stride for both dst and src
* (H264QpelContext convention). Caller already guarantees this
* via the public API contract documented in daedalus.h. */
for (size_t i = 0; i < n_blocks; i++) {
ff_put_h264_qpel8_mc20_neon(dst + meta[i].dst_off,
src + meta[i].src_off,
(ptrdiff_t) stride);
}
return 0;
}
/* -------------------- IDCT QPU dispatch (cycle 1 v4 shader) ---- */
typedef struct {
@@ -811,6 +830,14 @@ int daedalus_dispatch_h264_deblock_luma_v(daedalus_ctx *ctx, daedalus_substrate
return dispatch_h264_deblock_qpu(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)
{
ROUTE_CPU_ONLY(DAEDALUS_KERNEL_H264_QPEL_MC20, dispatch_h264_qpel_mc20_cpu,
dst, src, stride, n_blocks, meta);
}
/* -------------------- Recipe convenience wrappers --------------- */
int daedalus_recipe_dispatch_vp9_idct8(daedalus_ctx *ctx,
@@ -881,3 +908,11 @@ int daedalus_recipe_dispatch_h264_deblock_luma_v(daedalus_ctx *ctx,
return daedalus_dispatch_h264_deblock_luma_v(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)
{
return daedalus_dispatch_h264_qpel_mc20(ctx, DAEDALUS_SUBSTRATE_AUTO,
dst, src, stride, n_blocks, meta);
}