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

h264: promote remaining intra prediction modes (17) to public API

Browse Source 
Follows PR #26 (Intra_4x4 luma) with the same promotion pattern for
the rest of the intra prediction primitive set:

  Intra_16x16 luma   (4 modes, PR #13) — V/H/DC/Plane
  Intra_8x8  chroma  (4 modes, PR #14) — DC/H/V/Plane (4:2:0)
  Intra_8x8  luma    (9 modes, PRs #21 + #22) — High profile,
                                                 with 1-2-1 pre-filter

3 file moves via `git mv`, ~17 function renames stripping the `_ref`
suffix.  Test binaries rewired to link daedalus_core instead of
compiling the (now moved) ref files directly.  No code change — pure
plumbing for substitution-arc consumers.

26 intra prediction modes total now in the public API after this PR.

Verified on hertz:

  test_intra_pred_16x16:    5/5  PASS
  test_intra_pred_chroma8x8: 5/5  PASS
  test_intra_pred_8x8_luma: 11/11 PASS

All via public symbols (test binaries linked against daedalus_core).

Unblocks marfrit-packages substitution arc patch 0014 — wires
H264PredContext.pred4x4[], pred16x16[], pred8x8[], pred8x8l[]
through daedalus alongside the existing IDCT / deblock / qpel / DC
Hadamard substitutions.

After 0014 lands, the libavcodec.so built by marfrit-packages will
have EVERY hot-path pixel-math kernel of an H.264 8-bit 4:2:0
decode routing through daedalus — the substitution arc is feature-
complete for the campaign target (Pi 5 Firefox YouTube playback).
This commit is contained in:
Claude (noether)
2026-05-25 15:37:44 +02:00
parent 31c68d0d0e
commit cb3aef3dac
8 changed files with 108 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/h264_intra_pred_16x16_ref.c
-106
View File
@@ -1,106 +0,0 @@
/*
* Standalone bit-exact C reference for H.264 luma Intra_16x16
* prediction modes (per H.264 spec §8.3.2). All 4 modes.
*
* Mode index → name (per H.264 Table 7-15):
* 0 = Vertical
* 1 = Horizontal
* 2 = DC
* 3 = Plane
*
* Calling convention (FFmpeg-style, matches the Intra_4x4 ref):
* pred_16x16_<mode>(uint8_t *dst, ptrdiff_t stride)
*
* `dst` points at row 0, col 0 of the 16x16 output block. Neighbours:
* top[0..15] = dst[-stride + 0 .. -stride + 15]
* top-left = dst[-stride - 1]
* left[0..15] = dst[ 0*stride - 1 .. 15*stride - 1]
*
* AVAILABILITY: assumes all neighbours valid (interior-MB case). The
* H.264 spec defines fallback for boundary cases (DC averages just
* the available side, etc.); the eventual libavcodec intercept
* handles availability before calling.
*
* License: BSD-2-Clause.
*/
#include <stdint.h>
#include <stddef.h>
static inline int clip_u8(int v) { return v < 0 ? 0 : v > 255 ? 255 : v; }
/* Mode 0 — Vertical: each col = top[col]. */
void daedalus_h264_pred_16x16_vertical_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
for (int r = 0; r < 16; r++)
for (int c = 0; c < 16; c++) dst[r * stride + c] = top[c];
}
/* Mode 1 — Horizontal: each row = left[row]. */
void daedalus_h264_pred_16x16_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
{
for (int r = 0; r < 16; r++) {
uint8_t l = dst[r * stride - 1];
for (int c = 0; c < 16; c++) dst[r * stride + c] = l;
}
}
/* Mode 2 — DC: ((sum_top16 + sum_left16 + 16) >> 5) broadcast. */
void daedalus_h264_pred_16x16_dc_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
int sum = 16; /* rounding for >> 5 over 32 samples */
for (int i = 0; i < 16; i++) sum += top[i];
for (int i = 0; i < 16; i++) sum += dst[i * stride - 1];
uint8_t v = (uint8_t)(sum >> 5);
for (int r = 0; r < 16; r++)
for (int c = 0; c < 16; c++) dst[r * stride + c] = v;
}
/* Mode 3 — Plane (per H.264 §8.3.2.4):
* H = sum_{i=0..7} (i+1) * (p[7+i+1, -1] - p[7-i-1, -1])
* = sum_{i=0..7} (i+1) * (top[8+i] - top[6-i])
* V = sum_{j=0..7} (j+1) * (p[-1, 7+j+1] - p[-1, 7-j-1])
* = sum_{j=0..7} (j+1) * (left[8+j] - left[6-j])
* b = (5*H + 32) >> 6
* c = (5*V + 32) >> 6
* a = 16 * (p[-1, 15] + p[15, -1])
* = 16 * (left[15] + top[15])
* pred[y][x] = Clip1((a + b*(x-7) + c*(y-7) + 16) >> 5)
*
* Note: spec indexing uses [x, y] with x = col, y = row (or vice
* versa depending on the section). Here I use the FFmpeg convention
* pred[y][x] = pred[row][col]; the H = horizontal-slope formula uses
* the TOP row's left-vs-right asymmetry; V = vertical-slope uses the
* LEFT col's top-vs-bottom asymmetry. Boundary participants are
* the top-left corner p[-1,-1] inferred from the spec's index range
* (it does NOT participate in the H/V sums in the 16x16 case — only
* for the chroma 8x8 plane mode).
*/
void daedalus_h264_pred_16x16_plane_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
/* H accumulates differences across the right vs left half of the
* top row. Per spec, the top-left p[-1,-1] participates: i=7 uses
* p[15,-1] - p[-1,-1]. We include it by reading top[-1]. */
int H = 0, V = 0;
for (int i = 0; i < 8; i++) {
int t_right = top[8 + i];
int t_left = (i == 7) ? top[-1] : top[6 - i];
H += (i + 1) * (t_right - t_left);
}
for (int j = 0; j < 8; j++) {
int l_bot = dst[(8 + j) * stride - 1];
int l_top = (j == 7) ? top[-1] : dst[(6 - j) * stride - 1];
V += (j + 1) * (l_bot - l_top);
}
int b = (5 * H + 32) >> 6;
int c = (5 * V + 32) >> 6;
int a = 16 * (dst[15 * stride - 1] + top[15]);
for (int y = 0; y < 16; y++) {
for (int x = 0; x < 16; x++) {
int v = (a + b * (x - 7) + c * (y - 7) + 16) >> 5;
dst[y * stride + x] = (uint8_t) clip_u8(v);
}
}
}
tests/h264_intra_pred_8x8_luma_ref.c
-305
View File
@@ -1,305 +0,0 @@
/*
* Standalone bit-exact C reference for H.264 luma Intra_8x8
* prediction modes (per H.264 spec §8.3.2.1). High-profile-only
* MB type — Baseline/Main/Extended profiles don't see Intra_8x8.
*
* Distinct from Intra_4x4 in two ways:
*
* 1. REFERENCE SAMPLE FILTERING (§8.3.2.1.1). The 25 raw
* neighbour samples are pre-filtered with a 1-2-1 smoothing
* filter BEFORE prediction. The filtering has spec-defined
* boundary handling at the corners and the right-edge of the
* top-row extension.
*
* 2. SCALE. All 9 prediction modes operate at 8x8 with the
* filtered samples (Intra_4x4 operates at 4x4 with the raw
* samples).
*
* This PR implements the filter + the 3 simple modes (Vertical,
* Horizontal, DC). The 6 directional modes (DDL, DDR, VR, HD, VL,
* HU at 8x8) follow in a separate PR — same template, different
* formulas per spec sections §8.3.2.1.4..§8.3.2.1.9.
*
* Calling convention (FFmpeg-style):
* pred_8x8_<mode>_ref(uint8_t *dst, ptrdiff_t stride)
*
* `dst` points at row 0 col 0 of the 8x8 output block. Reads from
* top[0..15] = dst[-stride + 0..15]
* top-left = dst[-stride - 1]
* left[0..7] = dst[ 0*stride - 1 .. 7*stride - 1]
*
* AVAILABILITY: assumes all neighbours valid (interior-MB case).
*
* License: BSD-2-Clause.
*/
#include <stdint.h>
#include <stddef.h>
#include <string.h>
static inline int clip_u8(int v) { return v < 0 ? 0 : v > 255 ? 255 : v; }
/* H.264 §8.3.2.1.1 reference sample filtering. Filters the 25 raw
* samples around the 8x8 block into a `filt` array with the same
* indices. When called against an "all neighbours available" tile,
* the filtered output uses these spec-defined formulas:
*
* filt[top -1] (= filtered top-left) = (top[0] + 2*tl + left[0] + 2) >> 2
*
* filt[top 0] = (tl + 2*top[0] + top[1] + 2) >> 2
* filt[top i] for 1<=i<=14 = (top[i-1] + 2*top[i] + top[i+1] + 2) >> 2
* filt[top 15] = (top[14] + 3*top[15] + 2) >> 2 (boundary)
*
* filt[left 0] = (tl + 2*left[0] + left[1] + 2) >> 2
* filt[left j] for 1<=j<=6 = (left[j-1] + 2*left[j] + left[j+1] + 2) >> 2
* filt[left 7] = (left[6] + 3*left[7] + 2) >> 2 (boundary)
*
* Reads neighbours from the dst buffer; writes filtered values to
* a caller-provided 26-element array indexed as:
* filt[0] = filtered top-left
* filt[1..16] = filtered top[0..15]
* filt[17..24] = filtered left[0..7]
*/
static void filter_refs(const uint8_t *dst, ptrdiff_t stride,
uint8_t filt[25])
{
int tl = dst[-stride - 1];
int t[16];
for (int i = 0; i < 16; i++) t[i] = dst[-stride + i];
int l[8];
for (int j = 0; j < 8; j++) l[j] = dst[j * stride - 1];
/* Filtered top-left. */
filt[0] = (uint8_t)((t[0] + 2*tl + l[0] + 2) >> 2);
/* Filtered top. */
filt[1] = (uint8_t)((tl + 2*t[0] + t[1] + 2) >> 2);
for (int i = 1; i <= 14; i++)
filt[1 + i] = (uint8_t)((t[i-1] + 2*t[i] + t[i+1] + 2) >> 2);
filt[1 + 15] = (uint8_t)((t[14] + 3*t[15] + 2) >> 2);
/* Filtered left. */
filt[17 + 0] = (uint8_t)((tl + 2*l[0] + l[1] + 2) >> 2);
for (int j = 1; j <= 6; j++)
filt[17 + j] = (uint8_t)((l[j-1] + 2*l[j] + l[j+1] + 2) >> 2);
filt[17 + 7] = (uint8_t)((l[6] + 3*l[7] + 2) >> 2);
}
/* Convenience macros for accessing the filt[] array by spec-style index. */
#define FT(i) filt[1 + (i)] /* filtered top[i], i in 0..15 */
#define FL(j) filt[17 + (j)] /* filtered left[j], j in 0..7 */
#define FTL filt[0] /* filtered top-left */
/* Mode 0 Vertical (§8.3.2.1.2): pred[r,c] = filt_top[c]. */
void daedalus_h264_pred_8x8l_vertical_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++) dst[r * stride + c] = FT(c);
}
/* Mode 1 Horizontal (§8.3.2.1.3): pred[r,c] = filt_left[r]. */
void daedalus_h264_pred_8x8l_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++) dst[r * stride + c] = FL(r);
}
/* Mode 2 DC (§8.3.2.1.4): ((sum_filt_top[0..7] + sum_filt_left[0..7]
* + 8) >> 4) broadcast. Note the +8 (not +4 like 4x4): there are
* 16 samples summed total, so >> 4 with half-step rounding +8. */
void daedalus_h264_pred_8x8l_dc_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
int sum = 8;
for (int i = 0; i < 8; i++) sum += FT(i);
for (int j = 0; j < 8; j++) sum += FL(j);
uint8_t v = (uint8_t)(sum >> 4);
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++) dst[r * stride + c] = v;
}
/* --- 6 directional modes for Intra_8x8 (H.264 §8.3.2.1.5..§8.3.2.1.10).
* Transcribed from FFmpeg libavcodec/h264pred_template.c
* pred8x8l_{down_left, down_right, vertical_right, horizontal_down,
* vertical_left, horizontal_up} (LGPL-2.1+ in the original; algorithm
* reproduced here for test purposes).
*
* All 6 use the same FILTERED reference samples produced by
* filter_refs() above. Mapping from FFmpeg's t0..t15 / l0..l7 / lt
* notation:
* tN = FT(N) for N in 0..15
* lN = FL(N) for N in 0..7
* lt = FTL
*
* SRC(x,y) maps to dst[y*stride + x] (col x, row y).
*/
#define SRC(x, y) dst[(y) * stride + (x)]
#define T(i) FT(i)
#define L(j) FL(j)
#define LT FTL
/* Mode 3 DDL (Diagonal_Down_Left) — uses TOP + TOP_RIGHT, no LEFT. */
void daedalus_h264_pred_8x8l_ddl_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,0)= (T(0) + 2*T(1) + T(2) + 2) >> 2;
SRC(0,1)=SRC(1,0)= (T(1) + 2*T(2) + T(3) + 2) >> 2;
SRC(0,2)=SRC(1,1)=SRC(2,0)= (T(2) + 2*T(3) + T(4) + 2) >> 2;
SRC(0,3)=SRC(1,2)=SRC(2,1)=SRC(3,0)= (T(3) + 2*T(4) + T(5) + 2) >> 2;
SRC(0,4)=SRC(1,3)=SRC(2,2)=SRC(3,1)=SRC(4,0)= (T(4) + 2*T(5) + T(6) + 2) >> 2;
SRC(0,5)=SRC(1,4)=SRC(2,3)=SRC(3,2)=SRC(4,1)=SRC(5,0)= (T(5) + 2*T(6) + T(7) + 2) >> 2;
SRC(0,6)=SRC(1,5)=SRC(2,4)=SRC(3,3)=SRC(4,2)=SRC(5,1)=SRC(6,0)= (T(6) + 2*T(7) + T(8) + 2) >> 2;
SRC(0,7)=SRC(1,6)=SRC(2,5)=SRC(3,4)=SRC(4,3)=SRC(5,2)=SRC(6,1)=SRC(7,0)= (T(7) + 2*T(8) + T(9) + 2) >> 2;
SRC(1,7)=SRC(2,6)=SRC(3,5)=SRC(4,4)=SRC(5,3)=SRC(6,2)=SRC(7,1)= (T(8) + 2*T(9) + T(10) + 2) >> 2;
SRC(2,7)=SRC(3,6)=SRC(4,5)=SRC(5,4)=SRC(6,3)=SRC(7,2)= (T(9) + 2*T(10) + T(11) + 2) >> 2;
SRC(3,7)=SRC(4,6)=SRC(5,5)=SRC(6,4)=SRC(7,3)= (T(10) + 2*T(11) + T(12) + 2) >> 2;
SRC(4,7)=SRC(5,6)=SRC(6,5)=SRC(7,4)= (T(11) + 2*T(12) + T(13) + 2) >> 2;
SRC(5,7)=SRC(6,6)=SRC(7,5)= (T(12) + 2*T(13) + T(14) + 2) >> 2;
SRC(6,7)=SRC(7,6)= (T(13) + 2*T(14) + T(15) + 2) >> 2;
SRC(7,7)= (T(14) + 3*T(15) + 2) >> 2;
}
/* Mode 4 DDR (Diagonal_Down_Right). */
void daedalus_h264_pred_8x8l_ddr_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,7)= (L(7) + 2*L(6) + L(5) + 2) >> 2;
SRC(0,6)=SRC(1,7)= (L(6) + 2*L(5) + L(4) + 2) >> 2;
SRC(0,5)=SRC(1,6)=SRC(2,7)= (L(5) + 2*L(4) + L(3) + 2) >> 2;
SRC(0,4)=SRC(1,5)=SRC(2,6)=SRC(3,7)= (L(4) + 2*L(3) + L(2) + 2) >> 2;
SRC(0,3)=SRC(1,4)=SRC(2,5)=SRC(3,6)=SRC(4,7)= (L(3) + 2*L(2) + L(1) + 2) >> 2;
SRC(0,2)=SRC(1,3)=SRC(2,4)=SRC(3,5)=SRC(4,6)=SRC(5,7)= (L(2) + 2*L(1) + L(0) + 2) >> 2;
SRC(0,1)=SRC(1,2)=SRC(2,3)=SRC(3,4)=SRC(4,5)=SRC(5,6)=SRC(6,7)= (L(1) + 2*L(0) + LT + 2) >> 2;
SRC(0,0)=SRC(1,1)=SRC(2,2)=SRC(3,3)=SRC(4,4)=SRC(5,5)=SRC(6,6)=SRC(7,7)= (L(0) + 2*LT + T(0) + 2) >> 2;
SRC(1,0)=SRC(2,1)=SRC(3,2)=SRC(4,3)=SRC(5,4)=SRC(6,5)=SRC(7,6)= (LT + 2*T(0) + T(1) + 2) >> 2;
SRC(2,0)=SRC(3,1)=SRC(4,2)=SRC(5,3)=SRC(6,4)=SRC(7,5)= (T(0) + 2*T(1) + T(2) + 2) >> 2;
SRC(3,0)=SRC(4,1)=SRC(5,2)=SRC(6,3)=SRC(7,4)= (T(1) + 2*T(2) + T(3) + 2) >> 2;
SRC(4,0)=SRC(5,1)=SRC(6,2)=SRC(7,3)= (T(2) + 2*T(3) + T(4) + 2) >> 2;
SRC(5,0)=SRC(6,1)=SRC(7,2)= (T(3) + 2*T(4) + T(5) + 2) >> 2;
SRC(6,0)=SRC(7,1)= (T(4) + 2*T(5) + T(6) + 2) >> 2;
SRC(7,0)= (T(5) + 2*T(6) + T(7) + 2) >> 2;
}
/* Mode 5 VR (Vertical_Right). */
void daedalus_h264_pred_8x8l_vr_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,6)= (L(5) + 2*L(4) + L(3) + 2) >> 2;
SRC(0,7)= (L(6) + 2*L(5) + L(4) + 2) >> 2;
SRC(0,4)=SRC(1,6)= (L(3) + 2*L(2) + L(1) + 2) >> 2;
SRC(0,5)=SRC(1,7)= (L(4) + 2*L(3) + L(2) + 2) >> 2;
SRC(0,2)=SRC(1,4)=SRC(2,6)= (L(1) + 2*L(0) + LT + 2) >> 2;
SRC(0,3)=SRC(1,5)=SRC(2,7)= (L(2) + 2*L(1) + L(0) + 2) >> 2;
SRC(0,1)=SRC(1,3)=SRC(2,5)=SRC(3,7)= (L(0) + 2*LT + T(0) + 2) >> 2;
SRC(0,0)=SRC(1,2)=SRC(2,4)=SRC(3,6)= (LT + T(0) + 1) >> 1;
SRC(1,1)=SRC(2,3)=SRC(3,5)=SRC(4,7)= (LT + 2*T(0) + T(1) + 2) >> 2;
SRC(1,0)=SRC(2,2)=SRC(3,4)=SRC(4,6)= (T(0) + T(1) + 1) >> 1;
SRC(2,1)=SRC(3,3)=SRC(4,5)=SRC(5,7)= (T(0) + 2*T(1) + T(2) + 2) >> 2;
SRC(2,0)=SRC(3,2)=SRC(4,4)=SRC(5,6)= (T(1) + T(2) + 1) >> 1;
SRC(3,1)=SRC(4,3)=SRC(5,5)=SRC(6,7)= (T(1) + 2*T(2) + T(3) + 2) >> 2;
SRC(3,0)=SRC(4,2)=SRC(5,4)=SRC(6,6)= (T(2) + T(3) + 1) >> 1;
SRC(4,1)=SRC(5,3)=SRC(6,5)=SRC(7,7)= (T(2) + 2*T(3) + T(4) + 2) >> 2;
SRC(4,0)=SRC(5,2)=SRC(6,4)=SRC(7,6)= (T(3) + T(4) + 1) >> 1;
SRC(5,1)=SRC(6,3)=SRC(7,5)= (T(3) + 2*T(4) + T(5) + 2) >> 2;
SRC(5,0)=SRC(6,2)=SRC(7,4)= (T(4) + T(5) + 1) >> 1;
SRC(6,1)=SRC(7,3)= (T(4) + 2*T(5) + T(6) + 2) >> 2;
SRC(6,0)=SRC(7,2)= (T(5) + T(6) + 1) >> 1;
SRC(7,1)= (T(5) + 2*T(6) + T(7) + 2) >> 2;
SRC(7,0)= (T(6) + T(7) + 1) >> 1;
}
/* Mode 6 HD (Horizontal_Down). */
void daedalus_h264_pred_8x8l_hd_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,7)= (L(6) + L(7) + 1) >> 1;
SRC(1,7)= (L(5) + 2*L(6) + L(7) + 2) >> 2;
SRC(0,6)=SRC(2,7)= (L(5) + L(6) + 1) >> 1;
SRC(1,6)=SRC(3,7)= (L(4) + 2*L(5) + L(6) + 2) >> 2;
SRC(0,5)=SRC(2,6)=SRC(4,7)= (L(4) + L(5) + 1) >> 1;
SRC(1,5)=SRC(3,6)=SRC(5,7)= (L(3) + 2*L(4) + L(5) + 2) >> 2;
SRC(0,4)=SRC(2,5)=SRC(4,6)=SRC(6,7)= (L(3) + L(4) + 1) >> 1;
SRC(1,4)=SRC(3,5)=SRC(5,6)=SRC(7,7)= (L(2) + 2*L(3) + L(4) + 2) >> 2;
SRC(0,3)=SRC(2,4)=SRC(4,5)=SRC(6,6)= (L(2) + L(3) + 1) >> 1;
SRC(1,3)=SRC(3,4)=SRC(5,5)=SRC(7,6)= (L(1) + 2*L(2) + L(3) + 2) >> 2;
SRC(0,2)=SRC(2,3)=SRC(4,4)=SRC(6,5)= (L(1) + L(2) + 1) >> 1;
SRC(1,2)=SRC(3,3)=SRC(5,4)=SRC(7,5)= (L(0) + 2*L(1) + L(2) + 2) >> 2;
SRC(0,1)=SRC(2,2)=SRC(4,3)=SRC(6,4)= (L(0) + L(1) + 1) >> 1;
SRC(1,1)=SRC(3,2)=SRC(5,3)=SRC(7,4)= (LT + 2*L(0) + L(1) + 2) >> 2;
SRC(0,0)=SRC(2,1)=SRC(4,2)=SRC(6,3)= (LT + L(0) + 1) >> 1;
SRC(1,0)=SRC(3,1)=SRC(5,2)=SRC(7,3)= (L(0) + 2*LT + T(0) + 2) >> 2;
SRC(2,0)=SRC(4,1)=SRC(6,2)= (T(1) + 2*T(0) + LT + 2) >> 2;
SRC(3,0)=SRC(5,1)=SRC(7,2)= (T(2) + 2*T(1) + T(0) + 2) >> 2;
SRC(4,0)=SRC(6,1)= (T(3) + 2*T(2) + T(1) + 2) >> 2;
SRC(5,0)=SRC(7,1)= (T(4) + 2*T(3) + T(2) + 2) >> 2;
SRC(6,0)= (T(5) + 2*T(4) + T(3) + 2) >> 2;
SRC(7,0)= (T(6) + 2*T(5) + T(4) + 2) >> 2;
}
/* Mode 7 VL (Vertical_Left) — uses TOP + TOP_RIGHT only. */
void daedalus_h264_pred_8x8l_vl_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,0)= (T(0) + T(1) + 1) >> 1;
SRC(0,1)= (T(0) + 2*T(1) + T(2) + 2) >> 2;
SRC(0,2)=SRC(1,0)= (T(1) + T(2) + 1) >> 1;
SRC(0,3)=SRC(1,1)= (T(1) + 2*T(2) + T(3) + 2) >> 2;
SRC(0,4)=SRC(1,2)=SRC(2,0)= (T(2) + T(3) + 1) >> 1;
SRC(0,5)=SRC(1,3)=SRC(2,1)= (T(2) + 2*T(3) + T(4) + 2) >> 2;
SRC(0,6)=SRC(1,4)=SRC(2,2)=SRC(3,0)= (T(3) + T(4) + 1) >> 1;
SRC(0,7)=SRC(1,5)=SRC(2,3)=SRC(3,1)= (T(3) + 2*T(4) + T(5) + 2) >> 2;
SRC(1,6)=SRC(2,4)=SRC(3,2)=SRC(4,0)= (T(4) + T(5) + 1) >> 1;
SRC(1,7)=SRC(2,5)=SRC(3,3)=SRC(4,1)= (T(4) + 2*T(5) + T(6) + 2) >> 2;
SRC(2,6)=SRC(3,4)=SRC(4,2)=SRC(5,0)= (T(5) + T(6) + 1) >> 1;
SRC(2,7)=SRC(3,5)=SRC(4,3)=SRC(5,1)= (T(5) + 2*T(6) + T(7) + 2) >> 2;
SRC(3,6)=SRC(4,4)=SRC(5,2)=SRC(6,0)= (T(6) + T(7) + 1) >> 1;
SRC(3,7)=SRC(4,5)=SRC(5,3)=SRC(6,1)= (T(6) + 2*T(7) + T(8) + 2) >> 2;
SRC(4,6)=SRC(5,4)=SRC(6,2)=SRC(7,0)= (T(7) + T(8) + 1) >> 1;
SRC(4,7)=SRC(5,5)=SRC(6,3)=SRC(7,1)= (T(7) + 2*T(8) + T(9) + 2) >> 2;
SRC(5,6)=SRC(6,4)=SRC(7,2)= (T(8) + T(9) + 1) >> 1;
SRC(5,7)=SRC(6,5)=SRC(7,3)= (T(8) + 2*T(9) + T(10) + 2) >> 2;
SRC(6,6)=SRC(7,4)= (T(9) + T(10) + 1) >> 1;
SRC(6,7)=SRC(7,5)= (T(9) + 2*T(10) + T(11) + 2) >> 2;
SRC(7,6)= (T(10) + T(11) + 1) >> 1;
SRC(7,7)= (T(10) + 2*T(11) + T(12) + 2) >> 2;
}
/* Mode 8 HU (Horizontal_Up) — uses LEFT only. */
void daedalus_h264_pred_8x8l_hu_ref(uint8_t *dst, ptrdiff_t stride)
{
uint8_t filt[25];
filter_refs(dst, stride, filt);
SRC(0,0)= (L(0) + L(1) + 1) >> 1;
SRC(1,0)= (L(0) + 2*L(1) + L(2) + 2) >> 2;
SRC(0,1)=SRC(2,0)= (L(1) + L(2) + 1) >> 1;
SRC(1,1)=SRC(3,0)= (L(1) + 2*L(2) + L(3) + 2) >> 2;
SRC(0,2)=SRC(2,1)=SRC(4,0)= (L(2) + L(3) + 1) >> 1;
SRC(1,2)=SRC(3,1)=SRC(5,0)= (L(2) + 2*L(3) + L(4) + 2) >> 2;
SRC(0,3)=SRC(2,2)=SRC(4,1)=SRC(6,0)= (L(3) + L(4) + 1) >> 1;
SRC(1,3)=SRC(3,2)=SRC(5,1)=SRC(7,0)= (L(3) + 2*L(4) + L(5) + 2) >> 2;
SRC(0,4)=SRC(2,3)=SRC(4,2)=SRC(6,1)= (L(4) + L(5) + 1) >> 1;
SRC(1,4)=SRC(3,3)=SRC(5,2)=SRC(7,1)= (L(4) + 2*L(5) + L(6) + 2) >> 2;
SRC(0,5)=SRC(2,4)=SRC(4,3)=SRC(6,2)= (L(5) + L(6) + 1) >> 1;
SRC(1,5)=SRC(3,4)=SRC(5,3)=SRC(7,2)= (L(5) + 2*L(6) + L(7) + 2) >> 2;
SRC(0,6)=SRC(2,5)=SRC(4,4)=SRC(6,3)= (L(6) + L(7) + 1) >> 1;
SRC(1,6)=SRC(3,5)=SRC(5,4)=SRC(7,3)= (L(6) + 3*L(7) + 2) >> 2;
/* 20 positions all = L(7) per FFmpeg lines 1097-1100. */
SRC(0,7)=SRC(1,7)=SRC(2,6)=SRC(2,7)=SRC(3,6)=
SRC(3,7)=SRC(4,5)=SRC(4,6)=SRC(4,7)=SRC(5,5)=
SRC(5,6)=SRC(5,7)=SRC(6,4)=SRC(6,5)=SRC(6,6)=
SRC(6,7)=SRC(7,4)=SRC(7,5)=SRC(7,6)=SRC(7,7)= L(7);
}
#undef SRC
#undef T
#undef L
#undef LT
tests/h264_intra_pred_chroma8x8_ref.c
-123
View File
@@ -1,123 +0,0 @@
/*
* Standalone bit-exact C reference for H.264 chroma Intra_8x8
* prediction modes (per H.264 §8.3.3), used for both Cb and Cr
* planes at 4:2:0. All 4 modes.
*
* Mode index → name (per H.264 Table 7-16):
* 0 = DC (per-quadrant — asymmetric, see §8.3.3.2)
* 1 = Horizontal
* 2 = Vertical
* 3 = Plane (slope coefficient 34, distinct from luma's 5)
*
* Calling convention (same shape as luma intra refs):
* pred_chroma8x8_<mode>(uint8_t *dst, ptrdiff_t stride)
*
* `dst` points at row 0, col 0 of the 8x8 output block (single
* component plane — Cb or Cr, dispatched independently). Neighbours:
* top[0..7] = dst[-stride + 0 .. -stride + 7]
* top-left = dst[-stride - 1]
* left[0..7] = dst[ 0*stride - 1 .. 7*stride - 1]
*
* AVAILABILITY: assumes all neighbours valid (interior-MB case).
* The H.264 spec defines per-quadrant fallback for the DC mode at
* MB boundaries; that's caller-side via the libavcodec intercept.
*
* License: BSD-2-Clause.
*/
#include <stdint.h>
#include <stddef.h>
static inline int clip_u8(int v) { return v < 0 ? 0 : v > 255 ? 255 : v; }
/* Mode 0 — DC (per-quadrant, 4:2:0 layout per §8.3.3.2).
*
* The 8×8 block is split into four 4×4 quadrants. For interior
* MBs (all neighbours available), the DC value per quadrant uses:
* (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 asymmetry mirrors what neighbours are "logically available"
* for each quadrant in the spec's availability model. Top-right
* quadrant ignores the top-left-half because that half is "vertically
* above" the top-left quadrant; the spec uses top[4..7] only.
*/
void daedalus_h264_pred_chroma8x8_dc_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
int top_lo = 0, top_hi = 0, left_lo = 0, left_hi = 0;
for (int i = 0; i < 4; i++) {
top_lo += top[i];
top_hi += top[4 + i];
left_lo += dst[i * stride - 1];
left_hi += dst[(4 + i) * stride - 1];
}
uint8_t dc00 = (uint8_t)((top_lo + left_lo + 4) >> 3); /* top-left */
uint8_t dc01 = (uint8_t)((top_hi + 2) >> 2); /* top-right */
uint8_t dc10 = (uint8_t)(( left_hi + 2) >> 2); /* bot-left */
uint8_t dc11 = (uint8_t)((top_hi + left_hi + 4) >> 3); /* bot-right */
for (int r = 0; r < 4; r++) {
for (int c = 0; c < 4; c++) {
dst[( r) * stride + c ] = dc00;
dst[( r) * stride + 4 + c ] = dc01;
dst[(4 + r) * stride + c ] = dc10;
dst[(4 + r) * stride + 4 + c ] = dc11;
}
}
}
/* Mode 1 — Horizontal: each row = left[row]. */
void daedalus_h264_pred_chroma8x8_horizontal_ref(uint8_t *dst, ptrdiff_t stride)
{
for (int r = 0; r < 8; r++) {
uint8_t l = dst[r * stride - 1];
for (int c = 0; c < 8; c++) dst[r * stride + c] = l;
}
}
/* Mode 2 — Vertical: each col = top[col]. */
void daedalus_h264_pred_chroma8x8_vertical_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++) dst[r * stride + c] = top[c];
}
/* Mode 3 — Plane (per H.264 §8.3.3.4):
* H = sum_{i=0..3} (i+1) * (p[4+i, -1] - p[2-i, -1]) ; i=3 uses p[-1,-1]
* V = sum_{j=0..3} (j+1) * (p[-1, 4+j] - p[-1, 2-j]) ; j=3 uses p[-1,-1]
* b = (34 * H + 32) >> 6
* c = (34 * V + 32) >> 6
* a = 16 * (p[-1, 7] + p[7, -1])
* pred[y][x] = Clip1((a + b*(x - 3) + c*(y - 3) + 16) >> 5)
*
* Distinct from the Intra_16x16 luma Plane:
* - Slope coefficient is 34 (not 5).
* - Centre is (x-3, y-3) (not x-7, y-7).
* - Spans 4 differences per sum (not 8).
*/
void daedalus_h264_pred_chroma8x8_plane_ref(uint8_t *dst, ptrdiff_t stride)
{
const uint8_t *top = dst - stride;
int H = 0, V = 0;
for (int i = 0; i < 4; i++) {
int t_right = top[4 + i];
int t_left = (i == 3) ? top[-1] : top[2 - i];
H += (i + 1) * (t_right - t_left);
}
for (int j = 0; j < 4; j++) {
int l_bot = dst[(4 + j) * stride - 1];
int l_top = (j == 3) ? top[-1] : dst[(2 - j) * stride - 1];
V += (j + 1) * (l_bot - l_top);
}
int b = (34 * H + 32) >> 6;
int c = (34 * V + 32) >> 6;
int a = 16 * (dst[7 * stride - 1] + top[7]);
for (int y = 0; y < 8; y++) {
for (int x = 0; x < 8; x++) {
int v = (a + b * (x - 3) + c * (y - 3) + 16) >> 5;
dst[y * stride + x] = (uint8_t) clip_u8(v);
}
}
}
tests/test_intra_pred_16x16.c
+9 -9
View File
@@ -18,10 +18,10 @@
#include <stdio.h>
#include <string.h>
extern void daedalus_h264_pred_16x16_vertical_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_horizontal_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_dc_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_plane_ref(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_vertical(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_horizontal(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_dc(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_16x16_plane(uint8_t *dst, ptrdiff_t stride);
#define STRIDE 17
#define ROWS 17
@@ -84,7 +84,7 @@ int main(void)
int t[16], l[16];
for (int i = 0; i < 16; i++) { t[i] = 10 + i; l[i] = 0; }
set_ctx(buf, 0, t, l);
daedalus_h264_pred_16x16_vertical_ref(&buf[1][1], STRIDE);
daedalus_h264_pred_16x16_vertical(&buf[1][1], STRIDE);
struct vertical_ctx vc = { t };
fail |= check(buf, "Vertical (mode 0)", expect_vertical, &vc);
}
@@ -95,7 +95,7 @@ int main(void)
int t[16] = {0}, l[16];
for (int i = 0; i < 16; i++) l[i] = 50 + i;
set_ctx(buf, 0, t, l);
daedalus_h264_pred_16x16_horizontal_ref(&buf[1][1], STRIDE);
daedalus_h264_pred_16x16_horizontal(&buf[1][1], STRIDE);
struct horizontal_ctx hc = { l };
fail |= check(buf, "Horizontal (mode 1)", expect_horizontal, &hc);
}
@@ -108,7 +108,7 @@ int main(void)
int t[16], l[16];
for (int i = 0; i < 16; i++) { t[i] = 2; l[i] = 6; }
set_ctx(buf, 99, t, l);
daedalus_h264_pred_16x16_dc_ref(&buf[1][1], STRIDE);
daedalus_h264_pred_16x16_dc(&buf[1][1], STRIDE);
uint8_t exp_val = 4;
fail |= check(buf, "DC (mode 2)", expect_uniform, &exp_val);
}
@@ -123,7 +123,7 @@ int main(void)
int t[16], l[16];
for (int i = 0; i < 16; i++) { t[i] = 100; l[i] = 100; }
set_ctx(buf, 100, t, l); /* uniform tl too — H/V sums actually zero */
daedalus_h264_pred_16x16_plane_ref(&buf[1][1], STRIDE);
daedalus_h264_pred_16x16_plane(&buf[1][1], STRIDE);
uint8_t exp_val = 100;
fail |= check(buf, "Plane (mode 3, uniform)", expect_uniform, &exp_val);
}
@@ -150,7 +150,7 @@ int main(void)
int t[16], l[16];
for (int i = 0; i < 16; i++) { t[i] = i; l[i] = i; }
set_ctx(buf, 0, t, l);
daedalus_h264_pred_16x16_plane_ref(&buf[1][1], STRIDE);
daedalus_h264_pred_16x16_plane(&buf[1][1], STRIDE);
uint8_t tl_actual = buf[1 + 0][1 + 0];
uint8_t br_actual = buf[1 + 15][1 + 15];
int spot_fail = 0;
tests/test_intra_pred_8x8_luma.c
+20 -20
View File
@@ -14,15 +14,15 @@
#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);
extern void daedalus_h264_pred_8x8l_vertical(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_horizontal(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_dc(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_ddl(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_ddr(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_vr(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_hd(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_vl(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_8x8l_hu(uint8_t *dst, ptrdiff_t stride);
#define STRIDE 17
#define ROWS 9
@@ -61,7 +61,7 @@ int main(void)
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);
daedalus_h264_pred_8x8l_vertical(&buf[1][1], STRIDE);
fail |= check_uniform(buf, "Vertical (mode 0, uniform top)", 50);
}
@@ -71,7 +71,7 @@ int main(void)
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);
daedalus_h264_pred_8x8l_horizontal(&buf[1][1], STRIDE);
fail |= check_uniform(buf, "Horizontal (mode 1, uniform left)", 70);
}
@@ -84,7 +84,7 @@ int main(void)
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);
daedalus_h264_pred_8x8l_dc(&buf[1][1], STRIDE);
fail |= check_uniform(buf, "DC (mode 2, uniform)", 33);
}
@@ -108,7 +108,7 @@ int main(void)
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);
daedalus_h264_pred_8x8l_vertical(&buf[1][1], STRIDE);
int diff = 0;
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++)
@@ -129,7 +129,7 @@ int main(void)
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);
daedalus_h264_pred_8x8l_horizontal(&buf[1][1], STRIDE);
int diff = 0;
for (int r = 0; r < 8; r++)
for (int c = 0; c < 8; c++)
@@ -146,12 +146,12 @@ int main(void)
{
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 },
{ "DDL (mode 3, uniform)", daedalus_h264_pred_8x8l_ddl },
{ "DDR (mode 4, uniform)", daedalus_h264_pred_8x8l_ddr },
{ "VR (mode 5, uniform)", daedalus_h264_pred_8x8l_vr },
{ "HD (mode 6, uniform)", daedalus_h264_pred_8x8l_hd },
{ "VL (mode 7, uniform)", daedalus_h264_pred_8x8l_vl },
{ "HU (mode 8, uniform)", daedalus_h264_pred_8x8l_hu },
};
for (size_t i = 0; i < sizeof(modes)/sizeof(modes[0]); i++) {
uint8_t buf[ROWS][STRIDE];
tests/test_intra_pred_chroma8x8.c
+9 -9
View File
@@ -16,10 +16,10 @@
#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);
extern void daedalus_h264_pred_chroma8x8_dc(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_horizontal(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_vertical(uint8_t *dst, ptrdiff_t stride);
extern void daedalus_h264_pred_chroma8x8_plane(uint8_t *dst, ptrdiff_t stride);
#define STRIDE 9
#define ROWS 9
@@ -69,7 +69,7 @@ int main(void)
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);
daedalus_h264_pred_chroma8x8_horizontal(&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);
@@ -80,7 +80,7 @@ int main(void)
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);
daedalus_h264_pred_chroma8x8_vertical(&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);
@@ -104,7 +104,7 @@ int main(void)
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);
daedalus_h264_pred_chroma8x8_dc(&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},
@@ -125,7 +125,7 @@ int main(void)
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);
daedalus_h264_pred_chroma8x8_plane(&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);
@@ -153,7 +153,7 @@ int main(void)
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);
daedalus_h264_pred_chroma8x8_plane(&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;