8bc6d27ea7
Adds the High-profile Intra_8x8 luma primitive set. Per H.264
§8.3.2.1, this is distinct from Intra_4x4 in two ways:
1. REFERENCE SAMPLE PRE-FILTER (§8.3.2.1.1). The 25 raw neighbour
samples are smoothed with a 1-2-1 filter BEFORE prediction.
Spec-defined boundary handling at corners and the right edge:
- top-left filt'd: (top[0] + 2*tl + left[0] + 2) >> 2
- top[0] filt'd: (tl + 2*t[0] + t[1] + 2) >> 2
- top[i] for 1..14: (t[i-1] + 2*t[i] + t[i+1] + 2) >> 2
- top[15] filt'd: (t[14] + 3*t[15] + 2) >> 2 ← 3× boundary
- left analogous, with l[7] using 3× boundary.
2. SCALE. All 9 prediction modes operate at 8x8 on the filtered
samples (Intra_4x4 is 4x4 on raw samples).
This PR ships the pre-filter + the 3 simple modes (V, H, DC):
- Mode 0 Vertical (§8.3.2.1.2): pred[r,c] = filt_top[c]
- Mode 1 Horizontal (§8.3.2.1.3): pred[r,c] = filt_left[r]
- Mode 2 DC (§8.3.2.1.4): ((sum_filt_top[0..7] + sum_filt_left[0..7]
+ 8) >> 4) broadcast
The 6 directional modes (DDL, DDR, VR, HD, VL, HU at 8x8 per
§8.3.2.1.5..§8.3.2.1.10) follow in a separate PR. They use the
same filtered samples; only the per-cell formula differs.
Test design (tests/test_intra_pred_8x8_luma.c):
- 3 uniform-context tests, one per mode (sanity).
- 2 gradient tests that exercise the pre-filter's interior +
boundary cases:
* Vertical with top = 0..15: spec arithmetic gives filtered
top[c] = c for c in 0..7 (gradient input → identity through
the 1-2-1 filter on the interior; boundaries arithmetically
verify too). Test expects pred[r,c] = c.
* Horizontal with left = 0..7: same arithmetic chain on the
left col. Test expects pred[r,c] = r.
Verified on hertz:
$ ./build/test_intra_pred_8x8_luma
Vertical (mode 0, uniform top) PASS
Horizontal (mode 1, uniform left) PASS
DC (mode 2, uniform) PASS
Vertical (mode 0, gradient) PASS (filtered gradient)
Horizontal (mode 1, gradient) PASS (filtered gradient)
ALL Intra_8x8 luma PASS (3 modes — V, H, DC)
The pre-filter being right first try is meaningful — the boundary
samples use a 3× weight rather than 2× (filt[top 15] = (t[14] +
3*t[15] + 2) >> 2), which is easy to forget when transcribing. The
gradient test would have surfaced any boundary mistake immediately.
Combined intra-prediction primitive coverage after this PR:
Intra_4x4 luma ✓ (9 modes, PR #12)
Intra_16x16 luma ✓ (4 modes, PR #13)
Intra_8x8 chroma ✓ (4 modes, PR #14)
Intra_8x8 luma △ (3 of 9 modes — V, H, DC ✓; DDL/DDR/VR/HD/VL/HU pending)
The 6 remaining Intra_8x8 luma directional modes are spec-mechanical
follow-ups; each is a ~30-line formula per §8.3.2.1.5+.
140 lines
5.6 KiB
C
140 lines
5.6 KiB
C
/*
|
||
* Tests the H.264 Intra_8x8 luma prediction modes against spec-derived
|
||
* expectations. Buffer layout is 9 rows × 17 cols (extra cols for the
|
||
* top-right extension that DDL/VL need; not exercised by V/H/DC but
|
||
* already in-place for the eventual directional-modes follow-up):
|
||
*
|
||
* row 0: [tl][t0..t15] — 17 bytes
|
||
* row 1: [l0][output row 0 ..] — 17 bytes
|
||
* ...
|
||
* row 8: [l7][output row 7 ..]
|
||
*/
|
||
#include <stdint.h>
|
||
#include <stddef.h>
|
||
#include <stdio.h>
|
||
#include <string.h>
|
||
|
||
extern void daedalus_h264_pred_8x8l_vertical_ref(uint8_t *dst, ptrdiff_t stride);
|
||
extern void daedalus_h264_pred_8x8l_horizontal_ref(uint8_t *dst, ptrdiff_t stride);
|
||
extern void daedalus_h264_pred_8x8l_dc_ref(uint8_t *dst, ptrdiff_t stride);
|
||
|
||
#define STRIDE 17
|
||
#define ROWS 9
|
||
|
||
static void set_ctx(uint8_t buf[ROWS][STRIDE], int tl,
|
||
const int t[16], const int l[8])
|
||
{
|
||
for (int r = 0; r < ROWS; r++)
|
||
for (int c = 0; c < STRIDE; c++) buf[r][c] = 0xff;
|
||
buf[0][0] = (uint8_t) tl;
|
||
for (int c = 0; c < 16; c++) buf[0][1 + c] = (uint8_t) t[c];
|
||
for (int r = 0; r < 8; r++) buf[1 + r][0] = (uint8_t) l[r];
|
||
}
|
||
|
||
static int check_uniform(const uint8_t buf[ROWS][STRIDE], const char *name,
|
||
uint8_t expect_val)
|
||
{
|
||
int diff = 0;
|
||
for (int r = 0; r < 8; r++)
|
||
for (int c = 0; c < 8; c++)
|
||
if (buf[1+r][1+c] != expect_val) diff++;
|
||
if (diff == 0) printf(" %-30s PASS\n", name);
|
||
else printf(" %-30s FAIL (%d/64 wrong, expected %u)\n", name, diff, expect_val);
|
||
return diff == 0 ? 0 : 1;
|
||
}
|
||
|
||
int main(void)
|
||
{
|
||
int fail = 0;
|
||
|
||
/* Mode 0 Vertical with uniform top → uniform output.
|
||
* Filtered top[c] = (a + 2*a + a + 2) >> 2 = a for uniform a. */
|
||
{
|
||
uint8_t buf[ROWS][STRIDE];
|
||
int t[16], l[8];
|
||
for (int i = 0; i < 16; i++) t[i] = 50;
|
||
for (int j = 0; j < 8; j++) l[j] = 0;
|
||
set_ctx(buf, 50, t, l);
|
||
daedalus_h264_pred_8x8l_vertical_ref(&buf[1][1], STRIDE);
|
||
fail |= check_uniform(buf, "Vertical (mode 0, uniform top)", 50);
|
||
}
|
||
|
||
/* Mode 1 Horizontal with uniform left → uniform output. */
|
||
{
|
||
uint8_t buf[ROWS][STRIDE];
|
||
int t[16] = {0}, l[8];
|
||
for (int j = 0; j < 8; j++) l[j] = 70;
|
||
set_ctx(buf, 70, t, l);
|
||
daedalus_h264_pred_8x8l_horizontal_ref(&buf[1][1], STRIDE);
|
||
fail |= check_uniform(buf, "Horizontal (mode 1, uniform left)", 70);
|
||
}
|
||
|
||
/* Mode 2 DC with all-uniform neighbours → uniform output.
|
||
* Filtered top[c] = top for uniform; filtered left[j] = left.
|
||
* sum = 8*a + 8*a + 8 = 16a + 8. >> 4 = a (exact when +8 rounds). */
|
||
{
|
||
uint8_t buf[ROWS][STRIDE];
|
||
int t[16], l[8];
|
||
for (int i = 0; i < 16; i++) t[i] = 33;
|
||
for (int j = 0; j < 8; j++) l[j] = 33;
|
||
set_ctx(buf, 33, t, l);
|
||
daedalus_h264_pred_8x8l_dc_ref(&buf[1][1], STRIDE);
|
||
fail |= check_uniform(buf, "DC (mode 2, uniform)", 33);
|
||
}
|
||
|
||
/* Mode 0 Vertical with NON-uniform top: gradient 0..15. Filtered
|
||
* top[c] for c in 1..14 = (t[c-1] + 2*t[c] + t[c+1] + 2) >> 2
|
||
* = (c-1 + 2c + c+1 + 2) >> 2
|
||
* = (4c + 2) >> 2 = c (since (4c+2)/4 = c with rounding).
|
||
* Wait — (4c + 2) >> 2 = c + 0 (since 4c is divisible by 4 and +2 rounds
|
||
* BELOW 4, doesn't change anything). So filtered = c for c=1..14.
|
||
* filt[0] (top-left) = (t[0] + 2*tl + l[0] + 2) >> 2 (not exercised
|
||
* directly by Vertical mode).
|
||
* filt[top 0] = (tl + 2*t[0] + t[1] + 2) >> 2 = (0 + 0 + 1 + 2) >> 2 = 0
|
||
* (tl=0, t[0]=0, t[1]=1)
|
||
* filt[top 15] = (t[14] + 3*t[15] + 2) >> 2 = (14 + 45 + 2) >> 2
|
||
* = 61 >> 2 = 15
|
||
*
|
||
* So Vertical output col 0 = filt[top 0] = 0, col 1 = filt[top 1] = 1,
|
||
* ..., col 7 = filt[top 7] = 7. Same for all 8 rows. */
|
||
{
|
||
uint8_t buf[ROWS][STRIDE];
|
||
int t[16], l[8] = {0};
|
||
for (int i = 0; i < 16; i++) t[i] = i;
|
||
set_ctx(buf, 0, t, l);
|
||
daedalus_h264_pred_8x8l_vertical_ref(&buf[1][1], STRIDE);
|
||
int diff = 0;
|
||
for (int r = 0; r < 8; r++)
|
||
for (int c = 0; c < 8; c++)
|
||
if (buf[1+r][1+c] != c) diff++;
|
||
if (diff == 0) printf(" %-30s PASS (filtered gradient)\n", "Vertical (mode 0, gradient)");
|
||
else printf(" %-30s FAIL (%d/64 wrong)\n", "Vertical (mode 0, gradient)", diff);
|
||
fail |= (diff == 0) ? 0 : 1;
|
||
}
|
||
|
||
/* Mode 1 Horizontal gradient: left = 0..7. Filtered left:
|
||
* filt[left 0] = (tl + 2*l[0] + l[1] + 2) >> 2 = (0 + 0 + 1 + 2) >> 2 = 0
|
||
* filt[left j] for j=1..6 = (l[j-1] + 2*l[j] + l[j+1] + 2) >> 2 = j
|
||
* (same arithmetic as top)
|
||
* filt[left 7] = (l[6] + 3*l[7] + 2) >> 2 = (6 + 21 + 2) >> 2 = 7
|
||
* So Horizontal output row 0 = 0, row 7 = 7. */
|
||
{
|
||
uint8_t buf[ROWS][STRIDE];
|
||
int t[16] = {0}, l[8];
|
||
for (int j = 0; j < 8; j++) l[j] = j;
|
||
set_ctx(buf, 0, t, l);
|
||
daedalus_h264_pred_8x8l_horizontal_ref(&buf[1][1], STRIDE);
|
||
int diff = 0;
|
||
for (int r = 0; r < 8; r++)
|
||
for (int c = 0; c < 8; c++)
|
||
if (buf[1+r][1+c] != r) diff++;
|
||
if (diff == 0) printf(" %-30s PASS (filtered gradient)\n", "Horizontal (mode 1, gradient)");
|
||
else printf(" %-30s FAIL (%d/64 wrong)\n", "Horizontal (mode 1, gradient)", diff);
|
||
fail |= (diff == 0) ? 0 : 1;
|
||
}
|
||
|
||
if (fail == 0) printf("\nALL Intra_8x8 luma PASS (3 modes — V, H, DC)\n");
|
||
else fprintf(stderr, "\n%d test(s) FAILED\n", fail);
|
||
return fail ? 1 : 0;
|
||
}
|