Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(17)

Issues Search
    My Issues | Starred     Open | Closed | All

Unified Diff: source/libvpx/vp9/common/vp9_loopfilter.c

Issue 1124333011: libvpx: Pull from upstream (Closed) Base URL: https://chromium.googlesource.com/chromium/deps/libvpx.git@master
Patch Set: only update to last nights LKGR Created 5 years, 7 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « source/libvpx/vp9/common/vp9_loopfilter.h ('k') | source/libvpx/vp9/common/vp9_mfqe.c » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: source/libvpx/vp9/common/vp9_loopfilter.c
diff --git a/source/libvpx/vp9/common/vp9_loopfilter.c b/source/libvpx/vp9/common/vp9_loopfilter.c
index 676382dc8a97a508c7879c518f35c78f8db7cf42..69d393ef469dd0736dd661424d7f98e3245eed0b 100644
--- a/source/libvpx/vp9/common/vp9_loopfilter.c
+++ b/source/libvpx/vp9/common/vp9_loopfilter.c
@@ -222,9 +222,9 @@ static void update_sharpness(loop_filter_info_n *lfi, int sharpness_lvl) {
if (block_inside_limit < 1)
block_inside_limit = 1;
- vpx_memset(lfi->lfthr[lvl].lim, block_inside_limit, SIMD_WIDTH);
- vpx_memset(lfi->lfthr[lvl].mblim, (2 * (lvl + 2) + block_inside_limit),
- SIMD_WIDTH);
+ memset(lfi->lfthr[lvl].lim, block_inside_limit, SIMD_WIDTH);
+ memset(lfi->lfthr[lvl].mblim, (2 * (lvl + 2) + block_inside_limit),
+ SIMD_WIDTH);
}
}
@@ -245,7 +245,7 @@ void vp9_loop_filter_init(VP9_COMMON *cm) {
// init hev threshold const vectors
for (lvl = 0; lvl <= MAX_LOOP_FILTER; lvl++)
- vpx_memset(lfi->lfthr[lvl].hev_thr, (lvl >> 4), SIMD_WIDTH);
+ memset(lfi->lfthr[lvl].hev_thr, (lvl >> 4), SIMD_WIDTH);
}
void vp9_loop_filter_frame_init(VP9_COMMON *cm, int default_filt_lvl) {
@@ -276,7 +276,7 @@ void vp9_loop_filter_frame_init(VP9_COMMON *cm, int default_filt_lvl) {
if (!lf->mode_ref_delta_enabled) {
// we could get rid of this if we assume that deltas are set to
// zero when not in use; encoder always uses deltas
- vpx_memset(lfi->lvl[seg_id], lvl_seg, sizeof(lfi->lvl[seg_id]));
+ memset(lfi->lvl[seg_id], lvl_seg, sizeof(lfi->lvl[seg_id]));
} else {
int ref, mode;
const int intra_lvl = lvl_seg + lf->ref_deltas[INTRA_FRAME] * scale;
@@ -293,7 +293,7 @@ void vp9_loop_filter_frame_init(VP9_COMMON *cm, int default_filt_lvl) {
}
}
-static void filter_selectively_vert_row2(PLANE_TYPE plane_type,
+static void filter_selectively_vert_row2(int subsampling_factor,
uint8_t *s, int pitch,
unsigned int mask_16x16_l,
unsigned int mask_8x8_l,
@@ -301,9 +301,9 @@ static void filter_selectively_vert_row2(PLANE_TYPE plane_type,
unsigned int mask_4x4_int_l,
const loop_filter_info_n *lfi_n,
const uint8_t *lfl) {
- const int mask_shift = plane_type ? 4 : 8;
- const int mask_cutoff = plane_type ? 0xf : 0xff;
- const int lfl_forward = plane_type ? 4 : 8;
+ const int mask_shift = subsampling_factor ? 4 : 8;
+ const int mask_cutoff = subsampling_factor ? 0xf : 0xff;
+ const int lfl_forward = subsampling_factor ? 4 : 8;
unsigned int mask_16x16_0 = mask_16x16_l & mask_cutoff;
unsigned int mask_8x8_0 = mask_8x8_l & mask_cutoff;
@@ -393,7 +393,7 @@ static void filter_selectively_vert_row2(PLANE_TYPE plane_type,
}
#if CONFIG_VP9_HIGHBITDEPTH
-static void highbd_filter_selectively_vert_row2(PLANE_TYPE plane_type,
+static void highbd_filter_selectively_vert_row2(int subsampling_factor,
uint16_t *s, int pitch,
unsigned int mask_16x16_l,
unsigned int mask_8x8_l,
@@ -401,9 +401,9 @@ static void highbd_filter_selectively_vert_row2(PLANE_TYPE plane_type,
unsigned int mask_4x4_int_l,
const loop_filter_info_n *lfi_n,
const uint8_t *lfl, int bd) {
- const int mask_shift = plane_type ? 4 : 8;
- const int mask_cutoff = plane_type ? 0xf : 0xff;
- const int lfl_forward = plane_type ? 4 : 8;
+ const int mask_shift = subsampling_factor ? 4 : 8;
+ const int mask_cutoff = subsampling_factor ? 0xf : 0xff;
+ const int lfl_forward = subsampling_factor ? 4 : 8;
unsigned int mask_16x16_0 = mask_16x16_l & mask_cutoff;
unsigned int mask_8x8_0 = mask_8x8_l & mask_cutoff;
@@ -727,7 +727,7 @@ static void build_masks(const loop_filter_info_n *const lfi_n,
const int h = num_8x8_blocks_high_lookup[block_size];
int index = shift_y;
for (i = 0; i < h; i++) {
- vpx_memset(&lfm->lfl_y[index], filter_level, w);
+ memset(&lfm->lfl_y[index], filter_level, w);
index += 8;
}
}
@@ -801,7 +801,7 @@ static void build_y_mask(const loop_filter_info_n *const lfi_n,
const int h = num_8x8_blocks_high_lookup[block_size];
int index = shift_y;
for (i = 0; i < h; i++) {
- vpx_memset(&lfm->lfl_y[index], filter_level, w);
+ memset(&lfm->lfl_y[index], filter_level, w);
index += 8;
}
}
@@ -826,12 +826,12 @@ static void build_y_mask(const loop_filter_info_n *const lfi_n,
// by mi_row, mi_col.
// TODO(JBB): This function only works for yv12.
void vp9_setup_mask(VP9_COMMON *const cm, const int mi_row, const int mi_col,
- MODE_INFO *mi, const int mode_info_stride,
+ MODE_INFO **mi, const int mode_info_stride,
LOOP_FILTER_MASK *lfm) {
int idx_32, idx_16, idx_8;
const loop_filter_info_n *const lfi_n = &cm->lf_info;
- MODE_INFO *mip = mi;
- MODE_INFO *mip2 = mi;
+ MODE_INFO **mip = mi;
+ MODE_INFO **mip2 = mi;
// These are offsets to the next mi in the 64x64 block. It is what gets
// added to the mi ptr as we go through each loop. It helps us to avoid
@@ -859,28 +859,28 @@ void vp9_setup_mask(VP9_COMMON *const cm, const int mi_row, const int mi_col,
cm->mi_cols - mi_col : MI_BLOCK_SIZE);
vp9_zero(*lfm);
- assert(mip != NULL);
+ assert(mip[0] != NULL);
// TODO(jimbankoski): Try moving most of the following code into decode
// loop and storing lfm in the mbmi structure so that we don't have to go
// through the recursive loop structure multiple times.
- switch (mip->mbmi.sb_type) {
+ switch (mip[0]->mbmi.sb_type) {
case BLOCK_64X64:
- build_masks(lfi_n, mip , 0, 0, lfm);
+ build_masks(lfi_n, mip[0] , 0, 0, lfm);
break;
case BLOCK_64X32:
- build_masks(lfi_n, mip, 0, 0, lfm);
+ build_masks(lfi_n, mip[0], 0, 0, lfm);
mip2 = mip + mode_info_stride * 4;
if (4 >= max_rows)
break;
- build_masks(lfi_n, mip2, 32, 8, lfm);
+ build_masks(lfi_n, mip2[0], 32, 8, lfm);
break;
case BLOCK_32X64:
- build_masks(lfi_n, mip, 0, 0, lfm);
+ build_masks(lfi_n, mip[0], 0, 0, lfm);
mip2 = mip + 4;
if (4 >= max_cols)
break;
- build_masks(lfi_n, mip2, 4, 2, lfm);
+ build_masks(lfi_n, mip2[0], 4, 2, lfm);
break;
default:
for (idx_32 = 0; idx_32 < 4; mip += offset_32[idx_32], ++idx_32) {
@@ -890,23 +890,23 @@ void vp9_setup_mask(VP9_COMMON *const cm, const int mi_row, const int mi_col,
const int mi_32_row_offset = ((idx_32 >> 1) << 2);
if (mi_32_col_offset >= max_cols || mi_32_row_offset >= max_rows)
continue;
- switch (mip->mbmi.sb_type) {
+ switch (mip[0]->mbmi.sb_type) {
case BLOCK_32X32:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
break;
case BLOCK_32X16:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
if (mi_32_row_offset + 2 >= max_rows)
continue;
mip2 = mip + mode_info_stride * 2;
- build_masks(lfi_n, mip2, shift_y + 16, shift_uv + 4, lfm);
+ build_masks(lfi_n, mip2[0], shift_y + 16, shift_uv + 4, lfm);
break;
case BLOCK_16X32:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
if (mi_32_col_offset + 2 >= max_cols)
continue;
mip2 = mip + 2;
- build_masks(lfi_n, mip2, shift_y + 2, shift_uv + 1, lfm);
+ build_masks(lfi_n, mip2[0], shift_y + 2, shift_uv + 1, lfm);
break;
default:
for (idx_16 = 0; idx_16 < 4; mip += offset_16[idx_16], ++idx_16) {
@@ -920,29 +920,29 @@ void vp9_setup_mask(VP9_COMMON *const cm, const int mi_row, const int mi_col,
if (mi_16_col_offset >= max_cols || mi_16_row_offset >= max_rows)
continue;
- switch (mip->mbmi.sb_type) {
+ switch (mip[0]->mbmi.sb_type) {
case BLOCK_16X16:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
break;
case BLOCK_16X8:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
if (mi_16_row_offset + 1 >= max_rows)
continue;
mip2 = mip + mode_info_stride;
- build_y_mask(lfi_n, mip2, shift_y+8, lfm);
+ build_y_mask(lfi_n, mip2[0], shift_y+8, lfm);
break;
case BLOCK_8X16:
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
if (mi_16_col_offset +1 >= max_cols)
continue;
mip2 = mip + 1;
- build_y_mask(lfi_n, mip2, shift_y+1, lfm);
+ build_y_mask(lfi_n, mip2[0], shift_y+1, lfm);
break;
default: {
const int shift_y = shift_32_y[idx_32] +
shift_16_y[idx_16] +
shift_8_y[0];
- build_masks(lfi_n, mip, shift_y, shift_uv, lfm);
+ build_masks(lfi_n, mip[0], shift_y, shift_uv, lfm);
mip += offset[0];
for (idx_8 = 1; idx_8 < 4; mip += offset[idx_8], ++idx_8) {
const int shift_y = shift_32_y[idx_32] +
@@ -956,7 +956,7 @@ void vp9_setup_mask(VP9_COMMON *const cm, const int mi_row, const int mi_col,
if (mi_8_col_offset >= max_cols ||
mi_8_row_offset >= max_rows)
continue;
- build_y_mask(lfi_n, mip, shift_y, lfm);
+ build_y_mask(lfi_n, mip[0], shift_y, lfm);
}
break;
}
@@ -1151,7 +1151,7 @@ static void highbd_filter_selectively_vert(uint16_t *s, int pitch,
void vp9_filter_block_plane_non420(VP9_COMMON *cm,
struct macroblockd_plane *plane,
- MODE_INFO *mi_8x8,
+ MODE_INFO **mi_8x8,
int mi_row, int mi_col) {
const int ss_x = plane->subsampling_x;
const int ss_y = plane->subsampling_y;
@@ -1175,7 +1175,7 @@ void vp9_filter_block_plane_non420(VP9_COMMON *cm,
// Determine the vertical edges that need filtering
for (c = 0; c < MI_BLOCK_SIZE && mi_col + c < cm->mi_cols; c += col_step) {
- const MODE_INFO *mi = mi_8x8[c].src_mi;
+ const MODE_INFO *mi = mi_8x8[c];
const BLOCK_SIZE sb_type = mi[0].mbmi.sb_type;
const int skip_this = mi[0].mbmi.skip && is_inter_block(&mi[0].mbmi);
// left edge of current unit is block/partition edge -> no skip
@@ -1326,248 +1326,203 @@ void vp9_filter_block_plane_non420(VP9_COMMON *cm,
}
}
-void vp9_filter_block_plane(VP9_COMMON *const cm,
- struct macroblockd_plane *const plane,
- int mi_row,
- LOOP_FILTER_MASK *lfm) {
+void vp9_filter_block_plane_ss00(VP9_COMMON *const cm,
+ struct macroblockd_plane *const plane,
+ int mi_row,
+ LOOP_FILTER_MASK *lfm) {
struct buf_2d *const dst = &plane->dst;
- uint8_t* const dst0 = dst->buf;
- int r, c;
+ uint8_t *const dst0 = dst->buf;
+ int r;
+ uint64_t mask_16x16 = lfm->left_y[TX_16X16];
+ uint64_t mask_8x8 = lfm->left_y[TX_8X8];
+ uint64_t mask_4x4 = lfm->left_y[TX_4X4];
+ uint64_t mask_4x4_int = lfm->int_4x4_y;
+
+ assert(plane->subsampling_x == 0 && plane->subsampling_y == 0);
+
+ // Vertical pass: do 2 rows at one time
+ for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 2) {
+ unsigned int mask_16x16_l = mask_16x16 & 0xffff;
+ unsigned int mask_8x8_l = mask_8x8 & 0xffff;
+ unsigned int mask_4x4_l = mask_4x4 & 0xffff;
+ unsigned int mask_4x4_int_l = mask_4x4_int & 0xffff;
+
+// Disable filtering on the leftmost column.
+#if CONFIG_VP9_HIGHBITDEPTH
+ if (cm->use_highbitdepth) {
+ highbd_filter_selectively_vert_row2(
+ plane->subsampling_x, CONVERT_TO_SHORTPTR(dst->buf), dst->stride,
+ mask_16x16_l, mask_8x8_l, mask_4x4_l, mask_4x4_int_l, &cm->lf_info,
+ &lfm->lfl_y[r << 3], (int)cm->bit_depth);
+ } else {
+ filter_selectively_vert_row2(
+ plane->subsampling_x, dst->buf, dst->stride, mask_16x16_l, mask_8x8_l,
+ mask_4x4_l, mask_4x4_int_l, &cm->lf_info, &lfm->lfl_y[r << 3]);
+ }
+#else
+ filter_selectively_vert_row2(
+ plane->subsampling_x, dst->buf, dst->stride, mask_16x16_l, mask_8x8_l,
+ mask_4x4_l, mask_4x4_int_l, &cm->lf_info, &lfm->lfl_y[r << 3]);
+#endif // CONFIG_VP9_HIGHBITDEPTH
+ dst->buf += 16 * dst->stride;
+ mask_16x16 >>= 16;
+ mask_8x8 >>= 16;
+ mask_4x4 >>= 16;
+ mask_4x4_int >>= 16;
+ }
- if (!plane->plane_type) {
- uint64_t mask_16x16 = lfm->left_y[TX_16X16];
- uint64_t mask_8x8 = lfm->left_y[TX_8X8];
- uint64_t mask_4x4 = lfm->left_y[TX_4X4];
- uint64_t mask_4x4_int = lfm->int_4x4_y;
+ // Horizontal pass
+ dst->buf = dst0;
+ mask_16x16 = lfm->above_y[TX_16X16];
+ mask_8x8 = lfm->above_y[TX_8X8];
+ mask_4x4 = lfm->above_y[TX_4X4];
+ mask_4x4_int = lfm->int_4x4_y;
- // Vertical pass: do 2 rows at one time
- for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 2) {
- unsigned int mask_16x16_l = mask_16x16 & 0xffff;
- unsigned int mask_8x8_l = mask_8x8 & 0xffff;
- unsigned int mask_4x4_l = mask_4x4 & 0xffff;
- unsigned int mask_4x4_int_l = mask_4x4_int & 0xffff;
+ for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r++) {
+ unsigned int mask_16x16_r;
+ unsigned int mask_8x8_r;
+ unsigned int mask_4x4_r;
+
+ if (mi_row + r == 0) {
+ mask_16x16_r = 0;
+ mask_8x8_r = 0;
+ mask_4x4_r = 0;
+ } else {
+ mask_16x16_r = mask_16x16 & 0xff;
+ mask_8x8_r = mask_8x8 & 0xff;
+ mask_4x4_r = mask_4x4 & 0xff;
+ }
- // Disable filtering on the leftmost column.
#if CONFIG_VP9_HIGHBITDEPTH
- if (cm->use_highbitdepth) {
- highbd_filter_selectively_vert_row2(plane->plane_type,
- CONVERT_TO_SHORTPTR(dst->buf),
- dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info, &lfm->lfl_y[r << 3],
- (int)cm->bit_depth);
- } else {
- filter_selectively_vert_row2(plane->plane_type,
- dst->buf, dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info,
- &lfm->lfl_y[r << 3]);
- }
+ if (cm->use_highbitdepth) {
+ highbd_filter_selectively_horiz(
+ CONVERT_TO_SHORTPTR(dst->buf), dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int & 0xff, &cm->lf_info, &lfm->lfl_y[r << 3],
+ (int)cm->bit_depth);
+ } else {
+ filter_selectively_horiz(dst->buf, dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int & 0xff, &cm->lf_info,
+ &lfm->lfl_y[r << 3]);
+ }
#else
- filter_selectively_vert_row2(plane->plane_type,
- dst->buf, dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info, &lfm->lfl_y[r << 3]);
+ filter_selectively_horiz(dst->buf, dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int & 0xff, &cm->lf_info,
+ &lfm->lfl_y[r << 3]);
#endif // CONFIG_VP9_HIGHBITDEPTH
- dst->buf += 16 * dst->stride;
- mask_16x16 >>= 16;
- mask_8x8 >>= 16;
- mask_4x4 >>= 16;
- mask_4x4_int >>= 16;
- }
- // Horizontal pass
- dst->buf = dst0;
- mask_16x16 = lfm->above_y[TX_16X16];
- mask_8x8 = lfm->above_y[TX_8X8];
- mask_4x4 = lfm->above_y[TX_4X4];
- mask_4x4_int = lfm->int_4x4_y;
-
- for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r++) {
- unsigned int mask_16x16_r;
- unsigned int mask_8x8_r;
- unsigned int mask_4x4_r;
-
- if (mi_row + r == 0) {
- mask_16x16_r = 0;
- mask_8x8_r = 0;
- mask_4x4_r = 0;
- } else {
- mask_16x16_r = mask_16x16 & 0xff;
- mask_8x8_r = mask_8x8 & 0xff;
- mask_4x4_r = mask_4x4 & 0xff;
+ dst->buf += 8 * dst->stride;
+ mask_16x16 >>= 8;
+ mask_8x8 >>= 8;
+ mask_4x4 >>= 8;
+ mask_4x4_int >>= 8;
+ }
+}
+
+void vp9_filter_block_plane_ss11(VP9_COMMON *const cm,
+ struct macroblockd_plane *const plane,
+ int mi_row,
+ LOOP_FILTER_MASK *lfm) {
+ struct buf_2d *const dst = &plane->dst;
+ uint8_t *const dst0 = dst->buf;
+ int r, c;
+
+ uint16_t mask_16x16 = lfm->left_uv[TX_16X16];
+ uint16_t mask_8x8 = lfm->left_uv[TX_8X8];
+ uint16_t mask_4x4 = lfm->left_uv[TX_4X4];
+ uint16_t mask_4x4_int = lfm->int_4x4_uv;
+
+ assert(plane->subsampling_x == 1 && plane->subsampling_y == 1);
+
+ // Vertical pass: do 2 rows at one time
+ for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 4) {
+ if (plane->plane_type == 1) {
+ for (c = 0; c < (MI_BLOCK_SIZE >> 1); c++) {
+ lfm->lfl_uv[(r << 1) + c] = lfm->lfl_y[(r << 3) + (c << 1)];
+ lfm->lfl_uv[((r + 2) << 1) + c] = lfm->lfl_y[((r + 2) << 3) + (c << 1)];
}
+ }
+
+ {
+ unsigned int mask_16x16_l = mask_16x16 & 0xff;
+ unsigned int mask_8x8_l = mask_8x8 & 0xff;
+ unsigned int mask_4x4_l = mask_4x4 & 0xff;
+ unsigned int mask_4x4_int_l = mask_4x4_int & 0xff;
+// Disable filtering on the leftmost column.
#if CONFIG_VP9_HIGHBITDEPTH
if (cm->use_highbitdepth) {
- highbd_filter_selectively_horiz(CONVERT_TO_SHORTPTR(dst->buf),
- dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int & 0xff,
- &cm->lf_info,
- &lfm->lfl_y[r << 3],
- (int)cm->bit_depth);
+ highbd_filter_selectively_vert_row2(
+ plane->subsampling_x, CONVERT_TO_SHORTPTR(dst->buf), dst->stride,
+ mask_16x16_l, mask_8x8_l, mask_4x4_l, mask_4x4_int_l, &cm->lf_info,
+ &lfm->lfl_uv[r << 1], (int)cm->bit_depth);
} else {
- filter_selectively_horiz(dst->buf, dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int & 0xff,
- &cm->lf_info,
- &lfm->lfl_y[r << 3]);
+ filter_selectively_vert_row2(
+ plane->subsampling_x, dst->buf, dst->stride,
+ mask_16x16_l, mask_8x8_l, mask_4x4_l, mask_4x4_int_l, &cm->lf_info,
+ &lfm->lfl_uv[r << 1]);
}
#else
- filter_selectively_horiz(dst->buf, dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int & 0xff,
- &cm->lf_info,
- &lfm->lfl_y[r << 3]);
+ filter_selectively_vert_row2(
+ plane->subsampling_x, dst->buf, dst->stride,
+ mask_16x16_l, mask_8x8_l, mask_4x4_l, mask_4x4_int_l, &cm->lf_info,
+ &lfm->lfl_uv[r << 1]);
#endif // CONFIG_VP9_HIGHBITDEPTH
- dst->buf += 8 * dst->stride;
+ dst->buf += 16 * dst->stride;
mask_16x16 >>= 8;
mask_8x8 >>= 8;
mask_4x4 >>= 8;
mask_4x4_int >>= 8;
}
- } else {
- uint16_t mask_16x16 = lfm->left_uv[TX_16X16];
- uint16_t mask_8x8 = lfm->left_uv[TX_8X8];
- uint16_t mask_4x4 = lfm->left_uv[TX_4X4];
- uint16_t mask_4x4_int = lfm->int_4x4_uv;
-
- // Vertical pass: do 2 rows at one time
- for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 4) {
- if (plane->plane_type == 1) {
- for (c = 0; c < (MI_BLOCK_SIZE >> 1); c++) {
- lfm->lfl_uv[(r << 1) + c] = lfm->lfl_y[(r << 3) + (c << 1)];
- lfm->lfl_uv[((r + 2) << 1) + c] = lfm->lfl_y[((r + 2) << 3) +
- (c << 1)];
- }
- }
-
- {
- unsigned int mask_16x16_l = mask_16x16 & 0xff;
- unsigned int mask_8x8_l = mask_8x8 & 0xff;
- unsigned int mask_4x4_l = mask_4x4 & 0xff;
- unsigned int mask_4x4_int_l = mask_4x4_int & 0xff;
+ }
- // Disable filtering on the leftmost column.
-#if CONFIG_VP9_HIGHBITDEPTH
- if (cm->use_highbitdepth) {
- highbd_filter_selectively_vert_row2(plane->plane_type,
- CONVERT_TO_SHORTPTR(dst->buf),
- dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info,
- &lfm->lfl_uv[r << 1],
- (int)cm->bit_depth);
- } else {
- filter_selectively_vert_row2(plane->plane_type,
- dst->buf, dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info,
- &lfm->lfl_uv[r << 1]);
- }
-#else
- filter_selectively_vert_row2(plane->plane_type,
- dst->buf, dst->stride,
- mask_16x16_l,
- mask_8x8_l,
- mask_4x4_l,
- mask_4x4_int_l,
- &cm->lf_info,
- &lfm->lfl_uv[r << 1]);
-#endif // CONFIG_VP9_HIGHBITDEPTH
+ // Horizontal pass
+ dst->buf = dst0;
+ mask_16x16 = lfm->above_uv[TX_16X16];
+ mask_8x8 = lfm->above_uv[TX_8X8];
+ mask_4x4 = lfm->above_uv[TX_4X4];
+ mask_4x4_int = lfm->int_4x4_uv;
+
+ for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 2) {
+ const int skip_border_4x4_r = mi_row + r == cm->mi_rows - 1;
+ const unsigned int mask_4x4_int_r =
+ skip_border_4x4_r ? 0 : (mask_4x4_int & 0xf);
+ unsigned int mask_16x16_r;
+ unsigned int mask_8x8_r;
+ unsigned int mask_4x4_r;
- dst->buf += 16 * dst->stride;
- mask_16x16 >>= 8;
- mask_8x8 >>= 8;
- mask_4x4 >>= 8;
- mask_4x4_int >>= 8;
- }
+ if (mi_row + r == 0) {
+ mask_16x16_r = 0;
+ mask_8x8_r = 0;
+ mask_4x4_r = 0;
+ } else {
+ mask_16x16_r = mask_16x16 & 0xf;
+ mask_8x8_r = mask_8x8 & 0xf;
+ mask_4x4_r = mask_4x4 & 0xf;
}
- // Horizontal pass
- dst->buf = dst0;
- mask_16x16 = lfm->above_uv[TX_16X16];
- mask_8x8 = lfm->above_uv[TX_8X8];
- mask_4x4 = lfm->above_uv[TX_4X4];
- mask_4x4_int = lfm->int_4x4_uv;
-
- for (r = 0; r < MI_BLOCK_SIZE && mi_row + r < cm->mi_rows; r += 2) {
- const int skip_border_4x4_r = mi_row + r == cm->mi_rows - 1;
- const unsigned int mask_4x4_int_r = skip_border_4x4_r ?
- 0 : (mask_4x4_int & 0xf);
- unsigned int mask_16x16_r;
- unsigned int mask_8x8_r;
- unsigned int mask_4x4_r;
-
- if (mi_row + r == 0) {
- mask_16x16_r = 0;
- mask_8x8_r = 0;
- mask_4x4_r = 0;
- } else {
- mask_16x16_r = mask_16x16 & 0xf;
- mask_8x8_r = mask_8x8 & 0xf;
- mask_4x4_r = mask_4x4 & 0xf;
- }
-
#if CONFIG_VP9_HIGHBITDEPTH
- if (cm->use_highbitdepth) {
- highbd_filter_selectively_horiz(CONVERT_TO_SHORTPTR(dst->buf),
- dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int_r,
- &cm->lf_info,
- &lfm->lfl_uv[r << 1],
- (int)cm->bit_depth);
- } else {
- filter_selectively_horiz(dst->buf, dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int_r,
- &cm->lf_info,
- &lfm->lfl_uv[r << 1]);
- }
-#else
- filter_selectively_horiz(dst->buf, dst->stride,
- mask_16x16_r,
- mask_8x8_r,
- mask_4x4_r,
- mask_4x4_int_r,
- &cm->lf_info,
+ if (cm->use_highbitdepth) {
+ highbd_filter_selectively_horiz(CONVERT_TO_SHORTPTR(dst->buf),
+ dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int_r, &cm->lf_info,
+ &lfm->lfl_uv[r << 1], (int)cm->bit_depth);
+ } else {
+ filter_selectively_horiz(dst->buf, dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int_r, &cm->lf_info,
&lfm->lfl_uv[r << 1]);
+ }
+#else
+ filter_selectively_horiz(dst->buf, dst->stride, mask_16x16_r, mask_8x8_r,
+ mask_4x4_r, mask_4x4_int_r, &cm->lf_info,
+ &lfm->lfl_uv[r << 1]);
#endif // CONFIG_VP9_HIGHBITDEPTH
- dst->buf += 8 * dst->stride;
- mask_16x16 >>= 4;
- mask_8x8 >>= 4;
- mask_4x4 >>= 4;
- mask_4x4_int >>= 4;
- }
+ dst->buf += 8 * dst->stride;
+ mask_16x16 >>= 4;
+ mask_8x8 >>= 4;
+ mask_4x4 >>= 4;
+ mask_4x4_int >>= 4;
}
}
@@ -1576,13 +1531,21 @@ void vp9_loop_filter_rows(YV12_BUFFER_CONFIG *frame_buffer,
struct macroblockd_plane planes[MAX_MB_PLANE],
int start, int stop, int y_only) {
const int num_planes = y_only ? 1 : MAX_MB_PLANE;
- const int use_420 = y_only || (planes[1].subsampling_y == 1 &&
- planes[1].subsampling_x == 1);
+ enum lf_path path;
LOOP_FILTER_MASK lfm;
int mi_row, mi_col;
+ if (y_only)
+ path = LF_PATH_444;
+ else if (planes[1].subsampling_y == 1 && planes[1].subsampling_x == 1)
+ path = LF_PATH_420;
+ else if (planes[1].subsampling_y == 0 && planes[1].subsampling_x == 0)
+ path = LF_PATH_444;
+ else
+ path = LF_PATH_SLOW;
+
for (mi_row = start; mi_row < stop; mi_row += MI_BLOCK_SIZE) {
- MODE_INFO *mi = cm->mi + mi_row * cm->mi_stride;
+ MODE_INFO **mi = cm->mi_grid_visible + mi_row * cm->mi_stride;
for (mi_col = 0; mi_col < cm->mi_cols; mi_col += MI_BLOCK_SIZE) {
int plane;
@@ -1590,16 +1553,23 @@ void vp9_loop_filter_rows(YV12_BUFFER_CONFIG *frame_buffer,
vp9_setup_dst_planes(planes, frame_buffer, mi_row, mi_col);
// TODO(JBB): Make setup_mask work for non 420.
- if (use_420)
- vp9_setup_mask(cm, mi_row, mi_col, mi + mi_col, cm->mi_stride,
- &lfm);
-
- for (plane = 0; plane < num_planes; ++plane) {
- if (use_420)
- vp9_filter_block_plane(cm, &planes[plane], mi_row, &lfm);
- else
- vp9_filter_block_plane_non420(cm, &planes[plane], mi + mi_col,
- mi_row, mi_col);
+ vp9_setup_mask(cm, mi_row, mi_col, mi + mi_col, cm->mi_stride,
+ &lfm);
+
+ vp9_filter_block_plane_ss00(cm, &planes[0], mi_row, &lfm);
+ for (plane = 1; plane < num_planes; ++plane) {
+ switch (path) {
+ case LF_PATH_420:
+ vp9_filter_block_plane_ss11(cm, &planes[plane], mi_row, &lfm);
+ break;
+ case LF_PATH_444:
+ vp9_filter_block_plane_ss00(cm, &planes[plane], mi_row, &lfm);
+ break;
+ case LF_PATH_SLOW:
+ vp9_filter_block_plane_non420(cm, &planes[plane], mi + mi_col,
+ mi_row, mi_col);
+ break;
+ }
}
}
}
@@ -1633,7 +1603,7 @@ void vp9_loop_filter_data_reset(
lf_data->start = 0;
lf_data->stop = 0;
lf_data->y_only = 0;
- vpx_memcpy(lf_data->planes, planes, sizeof(lf_data->planes));
+ memcpy(lf_data->planes, planes, sizeof(lf_data->planes));
}
int vp9_loop_filter_worker(LFWorkerData *const lf_data, void *unused) {
« no previous file with comments | « source/libvpx/vp9/common/vp9_loopfilter.h ('k') | source/libvpx/vp9/common/vp9_mfqe.c » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698