h264: Intra_8x8 chroma prediction — 4-mode C reference + spec gates

Third intra-prediction primitive after PR #12 (Intra_4x4 luma) and
PR #13 (Intra_16x16 luma).  Covers Intra_8x8 chroma per H.264 §8.3.3:
4 modes used for BOTH Cb and Cr planes at 4:2:0.

Mode quirks worth flagging in code review:

  - Mode 0 DC is asymmetric per quadrant.  The 8x8 chroma block
    splits into four 4x4 quadrants with different DC formulas:
      (0,0) top-left  : (sum_top[0..3] + sum_left[0..3] + 4) >> 3
      (0,1) top-right : (sum_top[4..7]                  + 2) >> 2
      (1,0) bot-left  : (sum_left[4..7]                 + 2) >> 2
      (1,1) bot-right : (sum_top[4..7] + sum_left[4..7] + 4) >> 3
    The top-right quadrant deliberately IGNORES the top-left half
    even though it's available — that's per spec §8.3.3.2.

  - Mode 3 Plane uses slope coefficient 34 (not 5 like Intra_16x16
    luma).  Centre is (x-3, y-3) instead of (x-7, y-7).  Sums span
    4 differences instead of 8.  Easy to copy-paste-bug from the
    luma Plane if you don't notice the constants change.

Test highlights:

  - DC quadrants: distinct expected values per quadrant (16, 16,
    40, 28 from asymmetric top/left halves) — any quadrant mix-up
    would surface immediately.  Hand-derived from the formulas
    in the test comment.
  - Plane uniform: all-100 context → all-100 output (a = 3200,
    H = V = 0, (3200+16) >> 5 = 100 exactly).
  - Plane gradient: top + left = 0..7, hand-derives pred[0][0] = 1
    and pred[7][7] = 15 via the full arithmetic chain (H = V = 56,
    b = c = 30, a = 224).  Same hand-traced spec-walkthrough as
    the Intra_16x16 Plane gradient test.

Verified on hertz:

  $ ./build/test_intra_pred_chroma8x8
    Horizontal (mode 1)            PASS
    Vertical (mode 2)              PASS
    DC quadrants (mode 0)          PASS
    Plane uniform (mode 3)         PASS
    Plane gradient (mode 3)        PASS (corners 1, 15)

  ALL Intra_8x8 chroma mode references PASS

All 5 tests PASS first try.  The DC quadrant correctness is meaningful
(4 different formulas in one kernel) and the Plane gradient corners
validate the slope=34 + centre=(x-3,y-3) constants vs the luma
equivalents.

Combined coverage after this PR:
  - Intra_4x4 luma:   9 modes ✓ (PR #12, all 9 PASS)
  - Intra_16x16 luma: 4 modes ✓ (PR #13, all 5 tests PASS)
  - Intra_8x8 chroma: 4 modes ✓ (this PR, all 5 tests PASS)
  - Intra_8x8 luma (High profile): 9 modes + smoothing — pending.

Remaining backlog: Intra_8x8 luma (High profile, 9 modes + 1-2-1
smoothing pre-filter — distinct algorithm from Intra_4x4 because of
the pre-filter), neighbour-availability fallback, dispatch wrappers.
This commit is contained in:
2026-05-25 00:42:49 +02:00
parent dff610e13d
commit d7100459f2
3 changed files with 302 additions and 0 deletions
+170
View File
@@ -0,0 +1,170 @@
/*
* Tests the 4 H.264 Intra_8x8 chroma prediction modes against
* spec-derived expected patterns. Same buffer layout idea as the
* other intra tests: a buffer that holds the 8x8 output + 1-pixel
* top/left context + 1-pixel top-left corner.
*
* row 0: [tl][t0..t7]
* row 1: [l0][output row 0]
* ...
* row 8: [l7][output row 7]
*
* Dimensions: 9 rows × 9 cols. dst (passed to pred fns) = &buf[1][1].
*/
#include <stdint.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
extern void daedalus_h264_pred_chroma8x8_dc_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_horizontal_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_vertical_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_plane_ref(uint8_t *dst, ptrdiff_t stride);
#define STRIDE 9
#define ROWS 9
static void set_ctx(uint8_t buf[ROWS][STRIDE], int tl,
const int t[8], 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 < 8; 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_per_cell(const uint8_t buf[ROWS][STRIDE], const char *name,
const uint8_t expect[8][8])
{
int diff = 0;
int first_r = 0, first_c = 0, first_got = 0, first_exp = 0;
for (int r = 0; r < 8; r++) {
for (int c = 0; c < 8; c++) {
uint8_t got = buf[1 + r][1 + c];
uint8_t exp = expect[r][c];
if (got != exp) {
if (diff == 0) {
first_r = r; first_c = c;
first_got = got; first_exp = exp;
}
diff++;
}
}
}
if (diff == 0)
printf(" %-30s PASS\n", name);
else
printf(" %-30s FAIL (%d/64 wrong, first r=%d c=%d got=%u exp=%u)\n",
name, diff, first_r, first_c, first_got, first_exp);
return diff == 0 ? 0 : 1;
}
int main(void)
{
int fail = 0;
/* --- Mode 1 Horizontal --- */
{
uint8_t buf[ROWS][STRIDE];
int t[8] = {0}, l[8] = {10, 20, 30, 40, 50, 60, 70, 80};
set_ctx(buf, 0, t, l);
daedalus_h264_pred_chroma8x8_horizontal_ref(&buf[1][1], STRIDE);
uint8_t exp[8][8];
for (int r = 0; r < 8; r++) for (int c = 0; c < 8; c++) exp[r][c] = (uint8_t) l[r];
fail |= check_per_cell(buf, "Horizontal (mode 1)", exp);
}
/* --- Mode 2 Vertical --- */
{
uint8_t buf[ROWS][STRIDE];
int t[8] = {15, 25, 35, 45, 55, 65, 75, 85}, l[8] = {0};
set_ctx(buf, 0, t, l);
daedalus_h264_pred_chroma8x8_vertical_ref(&buf[1][1], STRIDE);
uint8_t exp[8][8];
for (int r = 0; r < 8; r++) for (int c = 0; c < 8; c++) exp[r][c] = (uint8_t) t[c];
fail |= check_per_cell(buf, "Vertical (mode 2)", exp);
}
/* --- Mode 0 DC: per-quadrant. Test with distinct halves so any
* quadrant mix-up surfaces immediately.
*
* top[0..3] = 4 × 8 → sum_top_lo = 32
* top[4..7] = 4 × 16 → sum_top_hi = 64
* left[0..3] = 4 × 24 → sum_left_lo = 96
* left[4..7] = 4 × 40 → sum_left_hi = 160
*
* dc00 = (32 + 96 + 4) >> 3 = 132/8 = 16
* dc01 = (64 + 2) >> 2 = 66/4 = 16
* dc10 = ( 160 + 2) >> 2 = 162/4 = 40
* dc11 = (64 + 160 + 4) >> 3 = 228/8 = 28
*/
{
uint8_t buf[ROWS][STRIDE];
int t[8] = { 8, 8, 8, 8, 16, 16, 16, 16 };
int l[8] = { 24, 24, 24, 24, 40, 40, 40, 40 };
set_ctx(buf, 99, t, l);
daedalus_h264_pred_chroma8x8_dc_ref(&buf[1][1], STRIDE);
uint8_t exp[8][8] = {
{16,16,16,16, 16,16,16,16},
{16,16,16,16, 16,16,16,16},
{16,16,16,16, 16,16,16,16},
{16,16,16,16, 16,16,16,16},
{40,40,40,40, 28,28,28,28},
{40,40,40,40, 28,28,28,28},
{40,40,40,40, 28,28,28,28},
{40,40,40,40, 28,28,28,28},
};
fail |= check_per_cell(buf, "DC quadrants (mode 0)", exp);
}
/* --- Mode 3 Plane (uniform): H = V = 0; a = 16 * (100 + 100) = 3200.
* pred[y][x] = (3200 + 0 + 0 + 16) >> 5 = 3216 >> 5 = 100. */
{
uint8_t buf[ROWS][STRIDE];
int t[8], l[8];
for (int i = 0; i < 8; i++) { t[i] = 100; l[i] = 100; }
set_ctx(buf, 100, t, l);
daedalus_h264_pred_chroma8x8_plane_ref(&buf[1][1], STRIDE);
uint8_t exp[8][8];
for (int r = 0; r < 8; r++) for (int c = 0; c < 8; c++) exp[r][c] = 100;
fail |= check_per_cell(buf, "Plane uniform (mode 3)", exp);
}
/* --- Mode 3 Plane gradient sanity ---
* t = 0..7, l = 0..7, tl = 0.
* H = 1*(t[4]-t[2]) + 2*(t[5]-t[1]) + 3*(t[6]-t[0]) + 4*(t[7]-tl)
* = 1*(4-2) + 2*(5-1) + 3*(6-0) + 4*(7-0)
* = 2 + 8 + 18 + 28 = 56
* V = same shape on left = 56
* b = (34*56 + 32) >> 6 = 1936 >> 6 = 30
* c = 30
* a = 16 * (l[7] + t[7]) = 16 * (7 + 7) = 224
*
* pred[0][0] = (224 + 30*(-3) + 30*(-3) + 16) >> 5
* = (224 - 90 - 90 + 16) >> 5
* = 60 >> 5 = 1
* pred[7][7] = (224 + 30*4 + 30*4 + 16) >> 5
* = (224 + 120 + 120 + 16) >> 5
* = 480 >> 5 = 15
* Spot-check those two corners. */
{
uint8_t buf[ROWS][STRIDE];
int t[8], l[8];
for (int i = 0; i < 8; i++) { t[i] = i; l[i] = i; }
set_ctx(buf, 0, t, l);
daedalus_h264_pred_chroma8x8_plane_ref(&buf[1][1], STRIDE);
uint8_t tl_actual = buf[1 + 0][1 + 0];
uint8_t br_actual = buf[1 + 7][1 + 7];
int spot_fail = 0;
if (tl_actual != 1) { fprintf(stderr, "Plane gradient pred[0][0] = %u, expected 1\n", tl_actual); spot_fail = 1; }
if (br_actual != 15) { fprintf(stderr, "Plane gradient pred[7][7] = %u, expected 15\n", br_actual); spot_fail = 1; }
if (!spot_fail) printf(" %-30s PASS (corners 1, 15)\n", "Plane gradient (mode 3)");
else printf(" %-30s FAIL\n", "Plane gradient (mode 3)");
fail |= spot_fail;
}
if (fail == 0) printf("\nALL Intra_8x8 chroma mode references PASS\n");
else fprintf(stderr, "\n%d test(s) FAILED\n", fail);
return fail ? 1 : 0;
}