44ca4e550f
Surfaces daedalus-fourier's substrate-override capability at the
decoder boundary. Lets tests run on CPU-only hosts (CI runners,
x86 dev boxes) AND cross-checks V3D shader output against NEON
reference on hosts that have both.
API additions (pre-0.1 ABI, additive):
- daedalus_decoder_substrate enum { AUTO, CPU, QPU }
(mirrors daedalus_substrate; isolated for ABI reasons).
- daedalus_decoder_set_substrate(dec, sub) setter, same
mid-frame-change restrictions as set_output_format.
- Default remains AUTO — the only sensible choice for production.
Internal:
- flush_frame now calls daedalus_dispatch_h264_idct{4,8} with an
explicit substrate instead of daedalus_recipe_dispatch_*. Mapped
via a small map_substrate() helper. No perf delta on AUTO (recipe
layer was just doing the same dispatch under the hood).
Test changes:
- test_smoke: new EXPECTs for set_substrate (valid + bogus).
- test_idct_bitexact: new argv[4] takes "auto" (default), "cpu", or
"qpu" to force the substrate.
- CMakeLists.txt: new ctest entry `idct_bitexact_cpu` re-runs the
QVGA case forcing the CPU path. Catches silent drift between
the V3D shader and the NEON reference; both must produce
identical output for the same coefficient input (and they do —
see ctest log below).
Verified on hertz (Pi 5 / V3D 7.1 / daedalus-fourier 0.1.0):
$ ctest --test-dir build --output-on-failure
Start 1: smoke
1/4 Test #1: smoke ............................ Passed 0.10 sec
Start 2: idct_bitexact
2/4 Test #2: idct_bitexact .................... Passed 0.03 sec
Start 3: idct_bitexact_cpu
3/4 Test #3: idct_bitexact_cpu ................ Passed 0.03 sec
Start 4: idct_bitexact_1080p
4/4 Test #4: idct_bitexact_1080p .............. Passed 0.06 sec
100% tests passed, 0 tests failed out of 4
CPU substrate produces byte-identical Y + Cb + Cr planes against the
same C reference that the AUTO/QPU path matches — confirming the V3D
shaders and the daedalus-fourier NEON path agree at the spec level.
Why we plumbed the lower-level dispatch instead of leaving recipe in
place: recipe is just a thin wrapper that calls dispatch with
AUTO. Once we needed substrate control, the wrapper became a
liability (would have required adding a parallel recipe API for each
substrate); going direct is simpler and the AUTO path is unchanged.
Coverage note: idct_bitexact_cpu runs at QVGA (300 MBs); not also at
1080p because the CPU path's wall time scales linearly with block
count and a 1080p CPU run is ~0.5s on hertz — fine standalone but
slows ctest enough that it would tempt opt-in gating. The bit-exact
content is the same regardless of frame size; the 1080p variant only
exists to gate index-arithmetic bugs that surface above small int
boundaries.
176 lines
6.6 KiB
C
176 lines
6.6 KiB
C
/* SPDX-License-Identifier: BSD-2-Clause */
|
|
/*
|
|
* Scaffold smoke test — verifies the daedalus-decoder library links
|
|
* cleanly against daedalus-fourier and the lifecycle entry points
|
|
* don't immediately crash. No actual decoding work yet.
|
|
*
|
|
* Returns 0 on success, non-zero on any unexpected behaviour.
|
|
*/
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
#include "daedalus_decoder.h"
|
|
|
|
#define EXPECT(cond, msg) do { \
|
|
if (!(cond)) { \
|
|
fprintf(stderr, "EXPECT FAIL %s:%d: %s\n", __FILE__, __LINE__, msg); \
|
|
return 1; \
|
|
} \
|
|
} while (0)
|
|
|
|
int main(void)
|
|
{
|
|
printf("daedalus-decoder version: %s\n", daedalus_decoder_version());
|
|
|
|
/* Create / destroy null is a no-op. */
|
|
daedalus_decoder_destroy(NULL);
|
|
|
|
/* Bad dimensions rejected. */
|
|
EXPECT(daedalus_decoder_create(0, 0 ) == NULL, "zero dims must reject");
|
|
EXPECT(daedalus_decoder_create(1919, 1088) == NULL, "non-16-multiple width must reject");
|
|
EXPECT(daedalus_decoder_create(1920, 1079) == NULL, "non-16-multiple height must reject");
|
|
|
|
/* Valid 1088p create. */
|
|
daedalus_decoder *dec = daedalus_decoder_create(1920, 1088);
|
|
if (!dec) {
|
|
/* Vulkan init failure on this host — degrades to skip, not fail.
|
|
* (CI runners without V3D7 will hit this; the smoke test
|
|
* shouldn't gate on hardware presence.) */
|
|
fprintf(stderr, "SKIP: daedalus_decoder_create returned NULL "
|
|
"(Vulkan / V3D7 unavailable on this host)\n");
|
|
return 0;
|
|
}
|
|
|
|
printf("ctx created: 1920x1088, has_qpu=%d\n",
|
|
daedalus_decoder_has_qpu(dec));
|
|
|
|
/* set_output_format mid-frame on virgin ctx is allowed
|
|
* (mbs_appended == 0). */
|
|
EXPECT(daedalus_decoder_set_output_format(dec, DAEDALUS_DECODER_OUTPUT_RGBA) == 0,
|
|
"switch to RGBA on virgin ctx");
|
|
EXPECT(daedalus_decoder_set_output_format(dec, DAEDALUS_DECODER_OUTPUT_NV12) == 0,
|
|
"switch back to NV12");
|
|
|
|
/* Substrate setter — same lifecycle rules. */
|
|
EXPECT(daedalus_decoder_set_substrate(dec, DAEDALUS_DECODER_SUBSTRATE_CPU) == 0,
|
|
"force CPU substrate on virgin ctx");
|
|
EXPECT(daedalus_decoder_set_substrate(dec, DAEDALUS_DECODER_SUBSTRATE_QPU) == 0,
|
|
"force QPU substrate on virgin ctx");
|
|
EXPECT(daedalus_decoder_set_substrate(dec, DAEDALUS_DECODER_SUBSTRATE_AUTO) == 0,
|
|
"back to AUTO");
|
|
EXPECT(daedalus_decoder_set_substrate(dec, (daedalus_decoder_substrate) 99) == -1,
|
|
"bogus substrate rejects");
|
|
|
|
/* Append rejects out-of-bounds + null inputs. */
|
|
int16_t coeffs[384] = {0};
|
|
struct daedalus_decoder_mb_input mb = {0};
|
|
mb.coeffs = coeffs;
|
|
|
|
mb.mb_x = 0; mb.mb_y = 0;
|
|
EXPECT(daedalus_decoder_append_mb(dec, NULL) == -1, "null mb rejects");
|
|
{
|
|
struct daedalus_decoder_mb_input mb2 = mb;
|
|
mb2.coeffs = NULL;
|
|
EXPECT(daedalus_decoder_append_mb(dec, &mb2) == -1, "null coeffs rejects");
|
|
}
|
|
{
|
|
struct daedalus_decoder_mb_input mb2 = mb;
|
|
mb2.mb_x = 9999; mb2.mb_y = 9999;
|
|
EXPECT(daedalus_decoder_append_mb(dec, &mb2) == -1, "OOB coords reject");
|
|
}
|
|
|
|
/* Append first MB at raster index 0 — should succeed. */
|
|
EXPECT(daedalus_decoder_append_mb(dec, &mb) == 0, "append (0,0)");
|
|
|
|
/* Skipping (0,1) and appending (1,0) violates raster order — reject. */
|
|
{
|
|
struct daedalus_decoder_mb_input mb2 = mb;
|
|
mb2.mb_x = 0; mb2.mb_y = 1;
|
|
EXPECT(daedalus_decoder_append_mb(dec, &mb2) == -1,
|
|
"out-of-raster-order rejects");
|
|
}
|
|
|
|
/* In-order: (1,0). */
|
|
mb.mb_x = 1; mb.mb_y = 0;
|
|
EXPECT(daedalus_decoder_append_mb(dec, &mb) == 0, "append (1,0)");
|
|
|
|
/* Flush an incomplete frame: should fail because mbs_appended != n_mbs. */
|
|
EXPECT(daedalus_decoder_flush_frame(dec, NULL, 0, NULL, 0) == -1,
|
|
"incomplete-frame flush rejects");
|
|
|
|
/* set_output_format mid-frame (mbs_appended > 0) must reject. */
|
|
EXPECT(daedalus_decoder_set_output_format(dec, DAEDALUS_DECODER_OUTPUT_RGBA) == -1,
|
|
"mid-frame format change rejects");
|
|
|
|
daedalus_decoder_destroy(dec);
|
|
|
|
/* ---- Full-frame round-trip with all-zero coefficients.
|
|
* Phase 1 stage 1 validation: flush_frame builds the per-frame IDCT
|
|
* dispatch and a successful GPU round-trip returns 0. IDCT of
|
|
* all-zero coefficients with zero-initialised predicted = all-zero
|
|
* output pixels. */
|
|
dec = daedalus_decoder_create(1920, 1088);
|
|
if (!dec) {
|
|
fprintf(stderr, "SKIP roundtrip: ctx create failed\n");
|
|
return 0;
|
|
}
|
|
|
|
static int16_t zero_coeffs[384] = {0};
|
|
struct daedalus_decoder_mb_input zmb = {0};
|
|
zmb.coeffs = zero_coeffs;
|
|
|
|
int mb_width = 1920 / 16; /* 120 */
|
|
int mb_height = 1088 / 16; /* 68 */
|
|
int n_mbs = mb_width * mb_height;
|
|
|
|
for (int mby = 0; mby < mb_height; mby++) {
|
|
for (int mbx = 0; mbx < mb_width; mbx++) {
|
|
zmb.mb_x = (uint16_t) mbx;
|
|
zmb.mb_y = (uint16_t) mby;
|
|
if (daedalus_decoder_append_mb(dec, &zmb) != 0) {
|
|
fprintf(stderr, "append (%d, %d) failed\n", mbx, mby);
|
|
return 1;
|
|
}
|
|
}
|
|
}
|
|
printf("appended %d MBs (%dx%d)\n", n_mbs, mb_width, mb_height);
|
|
|
|
size_t y_size = (size_t) 1920 * 1088;
|
|
size_t uv_size = (size_t) 1920 * 1088 / 2;
|
|
uint8_t *out_y = malloc(y_size);
|
|
uint8_t *out_uv = malloc(uv_size);
|
|
/* Pre-fill with sentinel so any read-then-write bug becomes visible. */
|
|
memset(out_y, 0xab, y_size);
|
|
memset(out_uv, 0xcd, uv_size);
|
|
|
|
int frc = daedalus_decoder_flush_frame(dec, out_y, 1920, out_uv, 1920);
|
|
printf("flush_frame rc=%d\n", frc);
|
|
EXPECT(frc == 0, "flush succeeds on full frame");
|
|
|
|
/* Y plane should be all zero (clip255(IDCT(zeros)) = 0). */
|
|
int y_nz = 0;
|
|
for (size_t i = 0; i < y_size; i++)
|
|
if (out_y[i] != 0) y_nz++;
|
|
printf("Y non-zero bytes: %d / %zu\n", y_nz, y_size);
|
|
EXPECT(y_nz == 0, "Y plane all zero for zero-coeff frame");
|
|
|
|
/* UV plane should be all zero now (real chroma IDCT runs with
|
|
* zero coeffs → zero residual → clip255(0+0) = 0). Previously a
|
|
* 128 placeholder when chroma was a memset stub; this PR replaced
|
|
* that with the real dispatch. Sentinel 0xcd above guarantees we
|
|
* are observing post-dispatch writes, not the leftover memset. */
|
|
int uv_nz = 0;
|
|
for (size_t i = 0; i < uv_size; i++)
|
|
if (out_uv[i] != 0) uv_nz++;
|
|
printf("UV non-zero bytes: %d / %zu\n", uv_nz, uv_size);
|
|
EXPECT(uv_nz == 0, "UV plane all zero for zero-coeff frame");
|
|
|
|
free(out_y);
|
|
free(out_uv);
|
|
daedalus_decoder_destroy(dec);
|
|
|
|
printf("smoke OK\n");
|
|
return 0;
|
|
}
|