daedalus-fourier/tests/test_intra_pred_8x8_luma.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);
extern void daedalus_h264_pred_8x8l_ddl_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_ddr_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_vr_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_hd_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_vl_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_hu_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;
    }

    /* Directional modes — uniform-context sanity tests.  With all
     * neighbours = N, the 1-2-1 filter produces uniform N, and any
     * 3-tap / 2-tap on uniform N produces N.  So every directional
     * mode should output uniform N on uniform input. */
    {
        typedef void (*pred_fn_t)(uint8_t *dst, ptrdiff_t stride);
        struct { const char *name; pred_fn_t fn; } modes[] = {
            { "DDL (mode 3, uniform)",        daedalus_h264_pred_8x8l_ddl_ref },
            { "DDR (mode 4, uniform)",        daedalus_h264_pred_8x8l_ddr_ref },
            { "VR (mode 5, uniform)",         daedalus_h264_pred_8x8l_vr_ref  },
            { "HD (mode 6, uniform)",         daedalus_h264_pred_8x8l_hd_ref  },
            { "VL (mode 7, uniform)",         daedalus_h264_pred_8x8l_vl_ref  },
            { "HU (mode 8, uniform)",         daedalus_h264_pred_8x8l_hu_ref  },
        };
        for (size_t i = 0; i < sizeof(modes)/sizeof(modes[0]); i++) {
            uint8_t buf[ROWS][STRIDE];
            int t[16], l[8];
            for (int k = 0; k < 16; k++) t[k] = 120;
            for (int k = 0; k < 8;  k++) l[k] = 120;
            set_ctx(buf, 120, t, l);
            modes[i].fn(&buf[1][1], STRIDE);
            fail |= check_uniform(buf, modes[i].name, 120);
        }
    }

    if (fail == 0) printf("\nALL Intra_8x8 luma PASS (9 modes — V, H, DC, DDL, DDR, VR, HD, VL, HU)\n");
    else           fprintf(stderr, "\n%d test(s) FAILED\n", fail);
    return fail ? 1 : 0;
}