static void FUNC(intra_pred)(HEVCContext *s, int x0, int y0, int log2_size, int c_idx)
{
#define PU(x) \
((x) >> s->sps->log2_min_pu_size)
#define MVF(x, y) \
(s->ref->tab_mvf[(x) + (y) * min_pu_width])
#define MVF_PU(x, y) \
MVF(PU(x0 + ((x) << hshift)), PU(y0 + ((y) << vshift)))
#define IS_INTRA(x, y) \
(MVF_PU(x, y).pred_flag == PF_INTRA)
#define MIN_TB_ADDR_ZS(x, y) \
s->pps->min_tb_addr_zs[(y) * s->sps->min_tb_width + (x)]
#define EXTEND_LEFT(ptr, start, length) \
for (i = (start); i > (start) - (length); i--) \
ptr[i - 1] = ptr[i]
#define EXTEND_RIGHT(ptr, start, length) \
for (i = (start); i < (start) + (length); i++) \
ptr[i] = ptr[i - 1]
#define EXTEND_UP(ptr, start, length) EXTEND_LEFT(ptr, start, length)
#define EXTEND_DOWN(ptr, start, length) EXTEND_RIGHT(ptr, start, length)
#define EXTEND_LEFT_CIP(ptr, start, length) \
for (i = (start); i > (start) - (length); i--) \
if (!IS_INTRA(i - 1, -1)) \
ptr[i - 1] = ptr[i]
#define EXTEND_RIGHT_CIP(ptr, start, length) \
for (i = (start); i < (start) + (length); i++) \
if (!IS_INTRA(i, -1)) \
ptr[i] = ptr[i - 1]
#define EXTEND_UP_CIP(ptr, start, length) \
for (i = (start); i > (start) - (length); i--) \
if (!IS_INTRA(-1, i - 1)) \
ptr[i - 1] = ptr[i]
#define EXTEND_UP_CIP_0(ptr, start, length) \
for (i = (start); i > (start) - (length); i--) \
ptr[i - 1] = ptr[i]
#define EXTEND_DOWN_CIP(ptr, start, length) \
for (i = (start); i < (start) + (length); i++) \
if (!IS_INTRA(-1, i)) \
ptr[i] = ptr[i - 1]
HEVCLocalContext *lc = s->HEVClc;
int i;
int hshift = s->sps->hshift[c_idx];
int vshift = s->sps->vshift[c_idx];
int size = (1 << log2_size);
int size_in_luma = size << hshift;
int size_in_tbs = size_in_luma >> s->sps->log2_min_tb_size;
int x = x0 >> hshift;
int y = y0 >> vshift;
int x_tb = x0 >> s->sps->log2_min_tb_size;
int y_tb = y0 >> s->sps->log2_min_tb_size;
int cur_tb_addr = MIN_TB_ADDR_ZS(x_tb, y_tb);
ptrdiff_t stride = s->frame->linesize[c_idx] / sizeof(pixel);
pixel *src = (pixel*)s->frame->data[c_idx] + x + y * stride;
int min_pu_width = s->sps->min_pu_width;
enum IntraPredMode mode = c_idx ? lc->pu.intra_pred_mode_c :
lc->tu.cur_intra_pred_mode;
pixel left_array[2 * MAX_TB_SIZE + 1];
pixel filtered_left_array[2 * MAX_TB_SIZE + 1];
pixel top_array[2 * MAX_TB_SIZE + 1];
pixel filtered_top_array[2 * MAX_TB_SIZE + 1];
pixel *left = left_array + 1;
pixel *top = top_array + 1;
pixel *filtered_left = filtered_left_array + 1;
pixel *filtered_top = filtered_top_array + 1;
int cand_bottom_left = lc->na.cand_bottom_left && cur_tb_addr > MIN_TB_ADDR_ZS(x_tb - 1, y_tb + size_in_tbs);
int cand_left = lc->na.cand_left;
int cand_up_left = lc->na.cand_up_left;
int cand_up = lc->na.cand_up;
int cand_up_right = lc->na.cand_up_right && cur_tb_addr > MIN_TB_ADDR_ZS(x_tb + size_in_tbs, y_tb - 1);
int bottom_left_size = (FFMIN(y0 + 2 * size_in_luma, s->sps->height) -
(y0 + size_in_luma)) >> vshift;
int top_right_size = (FFMIN(x0 + 2 * size_in_luma, s->sps->width) -
(x0 + size_in_luma)) >> hshift;
if (s->pps->constrained_intra_pred_flag == 1) {
int size_in_luma_pu = PU(size_in_luma);
int on_pu_edge_x = !(x0 & ((1 << s->sps->log2_min_pu_size) - 1));
int on_pu_edge_y = !(y0 & ((1 << s->sps->log2_min_pu_size) - 1));
if (!size_in_luma_pu)
size_in_luma_pu++;
if (cand_bottom_left == 1 && on_pu_edge_x) {
int x_left_pu = PU(x0 - 1);
int y_bottom_pu = PU(y0 + size_in_luma);
int max = FFMIN(size_in_luma_pu, s->sps->min_pu_height - y_bottom_pu);
cand_bottom_left = 0;
for (i = 0; i < max; i++)
cand_bottom_left |= (MVF(x_left_pu, y_bottom_pu + i).pred_flag == PF_INTRA);
}
if (cand_left == 1 && on_pu_edge_x) {
int x_left_pu = PU(x0 - 1);
int y_left_pu = PU(y0);
int max = FFMIN(size_in_luma_pu, s->sps->min_pu_height - y_left_pu);
cand_left = 0;
for (i = 0; i < max; i++)
cand_left |= (MVF(x_left_pu, y_left_pu + i).pred_flag == PF_INTRA);
}
if (cand_up_left == 1) {
int x_left_pu = PU(x0 - 1);
int y_top_pu = PU(y0 - 1);
cand_up_left = MVF(x_left_pu, y_top_pu).pred_flag == PF_INTRA;
}
if (cand_up == 1 && on_pu_edge_y) {
int x_top_pu = PU(x0);
int y_top_pu = PU(y0 - 1);
int max = FFMIN(size_in_luma_pu, s->sps->min_pu_width - x_top_pu);
cand_up = 0;
for (i = 0; i < max; i++)
cand_up |= (MVF(x_top_pu + i, y_top_pu).pred_flag == PF_INTRA);
}
if (cand_up_right == 1 && on_pu_edge_y) {
int y_top_pu = PU(y0 - 1);
int x_right_pu = PU(x0 + size_in_luma);
int max = FFMIN(size_in_luma_pu, s->sps->min_pu_width - x_right_pu);
cand_up_right = 0;
for (i = 0; i < max; i++)
cand_up_right |= (MVF(x_right_pu + i, y_top_pu).pred_flag == PF_INTRA);
}
for (i = 0; i < 2 * MAX_TB_SIZE; i++) {
left[i] = 128;
top[i] = 128;
}
top[-1] = 128;
}
if (cand_bottom_left) {
for (i = size + bottom_left_size; i < (size << 1); i++)
if (IS_INTRA(-1, size + bottom_left_size - 1) ||
!s->pps->constrained_intra_pred_flag)
left[i] = POS(-1, size + bottom_left_size - 1);
for (i = size + bottom_left_size - 1; i >= size; i--)
if (IS_INTRA(-1, i) || !s->pps->constrained_intra_pred_flag)
left[i] = POS(-1, i);
}
if (cand_left)
for (i = size - 1; i >= 0; i--)
if (IS_INTRA(-1, i) || !s->pps->constrained_intra_pred_flag)
left[i] = POS(-1, i);
if (cand_up_left)
if (IS_INTRA(-1, -1) || !s->pps->constrained_intra_pred_flag) {
left[-1] = POS(-1, -1);
top[-1] = left[-1];
}
if (cand_up)
for (i = size - 1; i >= 0; i--)
if (IS_INTRA(i, -1) || !s->pps->constrained_intra_pred_flag)
top[i] = POS(i, -1);
if (cand_up_right) {
for (i = size + top_right_size; i < (size << 1); i++)
if (IS_INTRA(size + top_right_size - 1, -1) ||
!s->pps->constrained_intra_pred_flag)
top[i] = POS(size + top_right_size - 1, -1);
for (i = size + top_right_size - 1; i >= size; i--)
if (IS_INTRA(i, -1) || !s->pps->constrained_intra_pred_flag)
top[i] = POS(i, -1);
}
if (s->pps->constrained_intra_pred_flag == 1) {
if (cand_bottom_left || cand_left || cand_up_left || cand_up || cand_up_right) {
int size_max_x = x0 + ((2 * size) << hshift) < s->sps->width ?
2 * size : (s->sps->width - x0) >> hshift;
int size_max_y = y0 + ((2 * size) << vshift) < s->sps->height ?
2 * size : (s->sps->height - y0) >> vshift;
int j = size + (cand_bottom_left? bottom_left_size: 0) -1;
if (!cand_up_right) {
size_max_x = x0 + ((size) << hshift) < s->sps->width ?
size : (s->sps->width - x0) >> hshift;
}
if (!cand_bottom_left) {
size_max_y = y0 + (( size) << vshift) < s->sps->height ?
size : (s->sps->height - y0) >> vshift;
}
static av_always_inline void FUNC(intra_pred)(HEVCContext *s, int x0, int y0,
int log2_size, int c_idx)
{
#define PU(x) \
((x) >> s->sps->log2_min_pu_size)
#define MVF(x, y) \
(s->ref->tab_mvf[(x) + (y) * min_pu_width])
#define MVF_PU(x, y) \
MVF(PU(x0 + ((x) << hshift)), PU(y0 + ((y) << vshift)))
#define IS_INTRA(x, y) \
(MVF_PU(x, y).pred_flag == PF_INTRA)
#define MIN_TB_ADDR_ZS(x, y) \
s->pps->min_tb_addr_zs[(y) * s->sps->min_tb_width + (x)]
#define EXTEND(ptr, val, len) \
do { \
pixel4 pix = PIXEL_SPLAT_X4(val); \
for (i = 0; i < (len); i += 4) \
AV_WN4P(ptr + i, pix); \
} while (0)
#define EXTEND_RIGHT_CIP(ptr, start, length) \
for (i = start; i < (start) + (length); i += 4) \
if (!IS_INTRA(i, -1)) \
AV_WN4P(&ptr[i], a); \
else \
a = PIXEL_SPLAT_X4(ptr[i+3])
#define EXTEND_LEFT_CIP(ptr, start, length) \
for (i = start; i > (start) - (length); i--) \
if (!IS_INTRA(i - 1, -1)) \
ptr[i - 1] = ptr[i]
#define EXTEND_UP_CIP(ptr, start, length) \
for (i = (start); i > (start) - (length); i -= 4) \
if (!IS_INTRA(-1, i - 3)) \
AV_WN4P(&ptr[i - 3], a); \
else \
a = PIXEL_SPLAT_X4(ptr[i - 3])
#define EXTEND_DOWN_CIP(ptr, start, length) \
for (i = start; i < (start) + (length); i += 4) \
if (!IS_INTRA(-1, i)) \
AV_WN4P(&ptr[i], a); \
else \
a = PIXEL_SPLAT_X4(ptr[i + 3])
HEVCLocalContext *lc = s->HEVClc;
int i;
int hshift = s->sps->hshift[c_idx];
int vshift = s->sps->vshift[c_idx];
int size = (1 << log2_size);
int size_in_luma_h = size << hshift;
int size_in_tbs_h = size_in_luma_h >> s->sps->log2_min_tb_size;
int size_in_luma_v = size << vshift;
int size_in_tbs_v = size_in_luma_v >> s->sps->log2_min_tb_size;
int x = x0 >> hshift;
int y = y0 >> vshift;
int x_tb = x0 >> s->sps->log2_min_tb_size;
int y_tb = y0 >> s->sps->log2_min_tb_size;
int cur_tb_addr = MIN_TB_ADDR_ZS(x_tb, y_tb);
ptrdiff_t stride = s->frame->linesize[c_idx] / sizeof(pixel);
pixel *src = (pixel*)s->frame->data[c_idx] + x + y * stride;
int min_pu_width = s->sps->min_pu_width;
enum IntraPredMode mode = c_idx ? lc->tu.cur_intra_pred_mode_c :
lc->tu.cur_intra_pred_mode;
pixel4 a;
pixel left_array[2 * MAX_TB_SIZE + 1];
pixel filtered_left_array[2 * MAX_TB_SIZE + 1];
pixel top_array[2 * MAX_TB_SIZE + 1];
pixel filtered_top_array[2 * MAX_TB_SIZE + 1];
pixel *left = left_array + 1;
pixel *top = top_array + 1;
pixel *filtered_left = filtered_left_array + 1;
pixel *filtered_top = filtered_top_array + 1;
int cand_bottom_left = lc->na.cand_bottom_left && cur_tb_addr > MIN_TB_ADDR_ZS(x_tb - 1, y_tb + size_in_tbs_v);
int cand_left = lc->na.cand_left;
int cand_up_left = lc->na.cand_up_left;
int cand_up = lc->na.cand_up;
int cand_up_right = lc->na.cand_up_right && cur_tb_addr > MIN_TB_ADDR_ZS(x_tb + size_in_tbs_h, y_tb - 1);
int bottom_left_size = (FFMIN(y0 + 2 * size_in_luma_v, s->sps->height) -
(y0 + size_in_luma_v)) >> vshift;
int top_right_size = (FFMIN(x0 + 2 * size_in_luma_h, s->sps->width) -
(x0 + size_in_luma_h)) >> hshift;
if (s->pps->constrained_intra_pred_flag == 1) {
int size_in_luma_pu_v = PU(size_in_luma_v);
int size_in_luma_pu_h = PU(size_in_luma_h);
int on_pu_edge_x = !(x0 & ((1 << s->sps->log2_min_pu_size) - 1));
int on_pu_edge_y = !(y0 & ((1 << s->sps->log2_min_pu_size) - 1));
if (!size_in_luma_pu_h)
size_in_luma_pu_h++;
if (cand_bottom_left == 1 && on_pu_edge_x) {
int x_left_pu = PU(x0 - 1);
int y_bottom_pu = PU(y0 + size_in_luma_v);
int max = FFMIN(size_in_luma_pu_v, s->sps->min_pu_height - y_bottom_pu);
cand_bottom_left = 0;
for (i = 0; i < max; i += 2)
cand_bottom_left |= (MVF(x_left_pu, y_bottom_pu + i).pred_flag == PF_INTRA);
}
if (cand_left == 1 && on_pu_edge_x) {
int x_left_pu = PU(x0 - 1);
int y_left_pu = PU(y0);
int max = FFMIN(size_in_luma_pu_v, s->sps->min_pu_height - y_left_pu);
cand_left = 0;
for (i = 0; i < max; i += 2)
cand_left |= (MVF(x_left_pu, y_left_pu + i).pred_flag == PF_INTRA);
}
if (cand_up_left == 1) {
int x_left_pu = PU(x0 - 1);
int y_top_pu = PU(y0 - 1);
cand_up_left = MVF(x_left_pu, y_top_pu).pred_flag == PF_INTRA;
}
if (cand_up == 1 && on_pu_edge_y) {
int x_top_pu = PU(x0);
int y_top_pu = PU(y0 - 1);
int max = FFMIN(size_in_luma_pu_h, s->sps->min_pu_width - x_top_pu);
cand_up = 0;
for (i = 0; i < max; i += 2)
cand_up |= (MVF(x_top_pu + i, y_top_pu).pred_flag == PF_INTRA);
}
if (cand_up_right == 1 && on_pu_edge_y) {
int y_top_pu = PU(y0 - 1);
int x_right_pu = PU(x0 + size_in_luma_h);
int max = FFMIN(size_in_luma_pu_h, s->sps->min_pu_width - x_right_pu);
cand_up_right = 0;
for (i = 0; i < max; i += 2)
cand_up_right |= (MVF(x_right_pu + i, y_top_pu).pred_flag == PF_INTRA);
}
memset(left, 128, 2 * MAX_TB_SIZE*sizeof(pixel));
memset(top , 128, 2 * MAX_TB_SIZE*sizeof(pixel));
top[-1] = 128;
}
if (cand_up_left) {
left[-1] = POS(-1, -1);
top[-1] = left[-1];
}
if (cand_up)
memcpy(top, src - stride, size * sizeof(pixel));
if (cand_up_right) {
memcpy(top + size, src - stride + size, size * sizeof(pixel));
EXTEND(top + size + top_right_size, POS(size + top_right_size - 1, -1),
size - top_right_size);
}
if (cand_left)
for (i = 0; i < size; i++)
left[i] = POS(-1, i);
if (cand_bottom_left) {
for (i = size; i < size + bottom_left_size; i++)
left[i] = POS(-1, i);
EXTEND(left + size + bottom_left_size, POS(-1, size + bottom_left_size - 1),
size - bottom_left_size);
}
if (s->pps->constrained_intra_pred_flag == 1) {
if (cand_bottom_left || cand_left || cand_up_left || cand_up || cand_up_right) {
int size_max_x = x0 + ((2 * size) << hshift) < s->sps->width ?
2 * size : (s->sps->width - x0) >> hshift;
int size_max_y = y0 + ((2 * size) << vshift) < s->sps->height ?
2 * size : (s->sps->height - y0) >> vshift;
int j = size + (cand_bottom_left? bottom_left_size: 0) -1;
if (!cand_up_right) {
size_max_x = x0 + ((size) << hshift) < s->sps->width ?
size : (s->sps->width - x0) >> hshift;
}
if (!cand_bottom_left) {
size_max_y = y0 + (( size) << vshift) < s->sps->height ?
size : (s->sps->height - y0) >> vshift;
}
