/**
* @file
- * H.264 / AVC / MPEG4 part10 cabac decoding.
+ * H.264 / AVC / MPEG-4 part10 cabac decoding.
* @author Michael Niedermayer <michaelni@gmx.at>
*/
#include "cabac_functions.h"
#include "internal.h"
#include "avcodec.h"
-#include "h264.h"
+#include "h264dec.h"
#include "h264data.h"
#include "h264_mvpred.h"
-#include "golomb.h"
#include "mpegutils.h"
#if ARCH_X86
-#include "x86/h264_i386.h"
+#include "x86/h264_cabac.c"
#endif
#include <assert.h>
{ 2, 54 }, { 3, 74 }, { -28,127 }, { -23, 104 },
{ -6, 53 }, { -1, 54 }, { 7, 51 },
- /* 11 - 23 unsused for I */
+ /* 11 - 23 unused for I */
{ 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 },
{ 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 },
{ 0, 0 }, { 0, 0 }, { 0, 0 }, { 0, 0 },
{
int i;
const int8_t (*tab)[2];
- const int slice_qp = av_clip(sl->qscale - 6*(h->sps.bit_depth_luma-8), 0, 51);
+ const int slice_qp = av_clip(sl->qscale - 6*(h->ps.sps->bit_depth_luma-8), 0, 51);
if (sl->slice_type_nos == AV_PICTURE_TYPE_I) tab = cabac_context_init_I;
else tab = cabac_context_init_PB[sl->cabac_init_idc];
decode_cabac_residual_dc(h, sl, sl->mb_luma_dc[p], ctx_cat[0][p], LUMA_DC_BLOCK_INDEX+p, scan, 16);
if( cbp&15 ) {
- qmul = h->dequant4_coeff[p][qscale];
+ qmul = h->ps.pps->dequant4_coeff[p][qscale];
for( i4x4 = 0; i4x4 < 16; i4x4++ ) {
const int index = 16*p + i4x4;
decode_cabac_residual_nondc(h, sl, sl->mb + (16*index << pixel_shift), ctx_cat[1][p], index, scan + 1, qmul, 15);
if( IS_8x8DCT(mb_type) ) {
const int index = 16*p + 4*i8x8;
decode_cabac_residual_nondc(h, sl, sl->mb + (16*index << pixel_shift), ctx_cat[3][p], index,
- scan8x8, h->dequant8_coeff[cqm][qscale], 64);
+ scan8x8, h->ps.pps->dequant8_coeff[cqm][qscale], 64);
} else {
- qmul = h->dequant4_coeff[cqm][qscale];
+ qmul = h->ps.pps->dequant4_coeff[cqm][qscale];
for( i4x4 = 0; i4x4 < 4; i4x4++ ) {
const int index = 16*p + 4*i8x8 + i4x4;
//START_TIMER
*/
int ff_h264_decode_mb_cabac(const H264Context *h, H264SliceContext *sl)
{
+ const SPS *sps = h->ps.sps;
int mb_xy;
int mb_type, partition_count, cbp = 0;
- int dct8x8_allowed= h->pps.transform_8x8_mode;
- int decode_chroma = h->sps.chroma_format_idc == 1 || h->sps.chroma_format_idc == 2;
+ int dct8x8_allowed= h->ps.pps->transform_8x8_mode;
+ int decode_chroma = sps->chroma_format_idc == 1 || sps->chroma_format_idc == 2;
const int pixel_shift = h->pixel_shift;
mb_xy = sl->mb_xy = sl->mb_x + sl->mb_y*h->mb_stride;
- ff_tlog(h->avctx, "pic:%d mb:%d/%d\n", h->frame_num, sl->mb_x, sl->mb_y);
if (sl->slice_type_nos != AV_PICTURE_TYPE_I) {
int skip;
/* a skipped mb needs the aff flag from the following mb */
h->slice_table[mb_xy] = sl->slice_num;
if(IS_INTRA_PCM(mb_type)) {
- const int mb_size = ff_h264_mb_sizes[h->sps.chroma_format_idc] *
- h->sps.bit_depth_luma >> 3;
+ const int mb_size = ff_h264_mb_sizes[sps->chroma_format_idc] *
+ sps->bit_depth_luma >> 3;
const uint8_t *ptr;
// We assume these blocks are very rare so we do not optimize it.
}
}
write_back_intra_pred_mode(h, sl);
- if (ff_h264_check_intra4x4_pred_mode(h, sl) < 0 ) return -1;
+ if (ff_h264_check_intra4x4_pred_mode(sl->intra4x4_pred_mode_cache, h->avctx,
+ sl->top_samples_available, sl->left_samples_available) < 0 )
+ return -1;
} else {
- sl->intra16x16_pred_mode = ff_h264_check_intra_pred_mode(h, sl, sl->intra16x16_pred_mode, 0);
+ sl->intra16x16_pred_mode = ff_h264_check_intra_pred_mode(h->avctx, sl->top_samples_available,
+ sl->left_samples_available, sl->intra16x16_pred_mode, 0);
if (sl->intra16x16_pred_mode < 0) return -1;
}
if(decode_chroma){
h->chroma_pred_mode_table[mb_xy] =
pred_mode = decode_cabac_mb_chroma_pre_mode(h, sl);
- pred_mode= ff_h264_check_intra_pred_mode(h, sl, pred_mode, 1 );
+ pred_mode= ff_h264_check_intra_pred_mode(h->avctx, sl->top_samples_available,
+ sl->left_samples_available, pred_mode, 1 );
if( pred_mode < 0 ) return -1;
sl->chroma_pred_mode = pred_mode;
} else {
ff_h264_pred_direct_motion(h, sl, &mb_type);
fill_rectangle(sl->mvd_cache[0][scan8[0]], 4, 4, 8, 0, 2);
fill_rectangle(sl->mvd_cache[1][scan8[0]], 4, 4, 8, 0, 2);
- dct8x8_allowed &= h->sps.direct_8x8_inference_flag;
+ dct8x8_allowed &= sps->direct_8x8_inference_flag;
} else {
int list, i;
if(IS_16X16(mb_type)){
if (CHROMA444(h) && IS_8x8DCT(mb_type)){
int i;
uint8_t *nnz_cache = sl->non_zero_count_cache;
- for (i = 0; i < 2; i++){
- if (sl->left_type[LEFT(i)] && !IS_8x8DCT(sl->left_type[LEFT(i)])) {
- nnz_cache[3+8* 1 + 2*8*i]=
- nnz_cache[3+8* 2 + 2*8*i]=
- nnz_cache[3+8* 6 + 2*8*i]=
- nnz_cache[3+8* 7 + 2*8*i]=
- nnz_cache[3+8*11 + 2*8*i]=
- nnz_cache[3+8*12 + 2*8*i]= IS_INTRA(mb_type) ? 64 : 0;
+ if (h->x264_build < 151U) {
+ for (i = 0; i < 2; i++){
+ if (sl->left_type[LEFT(i)] && !IS_8x8DCT(sl->left_type[LEFT(i)])) {
+ nnz_cache[3+8* 1 + 2*8*i]=
+ nnz_cache[3+8* 2 + 2*8*i]=
+ nnz_cache[3+8* 6 + 2*8*i]=
+ nnz_cache[3+8* 7 + 2*8*i]=
+ nnz_cache[3+8*11 + 2*8*i]=
+ nnz_cache[3+8*12 + 2*8*i]= IS_INTRA(mb_type) ? 64 : 0;
+ }
+ }
+ if (sl->top_type && !IS_8x8DCT(sl->top_type)){
+ uint32_t top_empty = !IS_INTRA(mb_type) ? 0 : 0x40404040;
+ AV_WN32A(&nnz_cache[4+8* 0], top_empty);
+ AV_WN32A(&nnz_cache[4+8* 5], top_empty);
+ AV_WN32A(&nnz_cache[4+8*10], top_empty);
+ }
+ } else {
+ for (i = 0; i < 2; i++){
+ if (sl->left_type[LEFT(i)] && !IS_8x8DCT(sl->left_type[LEFT(i)])) {
+ nnz_cache[3+8* 1 + 2*8*i]=
+ nnz_cache[3+8* 2 + 2*8*i]=
+ nnz_cache[3+8* 6 + 2*8*i]=
+ nnz_cache[3+8* 7 + 2*8*i]=
+ nnz_cache[3+8*11 + 2*8*i]=
+ nnz_cache[3+8*12 + 2*8*i]= !IS_INTRA_PCM(sl->left_type[LEFT(i)]) ? 0 : 64;
+ }
+ }
+ if (sl->top_type && !IS_8x8DCT(sl->top_type)){
+ uint32_t top_empty = !IS_INTRA_PCM(sl->top_type) ? 0 : 0x40404040;
+ AV_WN32A(&nnz_cache[4+8* 0], top_empty);
+ AV_WN32A(&nnz_cache[4+8* 5], top_empty);
+ AV_WN32A(&nnz_cache[4+8*10], top_empty);
}
- }
- if (sl->top_type && !IS_8x8DCT(sl->top_type)){
- uint32_t top_empty = CABAC(h) && !IS_INTRA(mb_type) ? 0 : 0x40404040;
- AV_WN32A(&nnz_cache[4+8* 0], top_empty);
- AV_WN32A(&nnz_cache[4+8* 5], top_empty);
- AV_WN32A(&nnz_cache[4+8*10], top_empty);
}
}
h->cur_pic.mb_type[mb_xy] = mb_type;
const uint8_t *scan, *scan8x8;
const uint32_t *qmul;
- if(IS_INTERLACED(mb_type)){
- scan8x8 = sl->qscale ? h->field_scan8x8 : h->field_scan8x8_q0;
- scan = sl->qscale ? h->field_scan : h->field_scan_q0;
- }else{
- scan8x8 = sl->qscale ? h->zigzag_scan8x8 : h->zigzag_scan8x8_q0;
- scan = sl->qscale ? h->zigzag_scan : h->zigzag_scan_q0;
- }
-
// decode_cabac_mb_dqp
if(get_cabac_noinline( &sl->cabac, &sl->cabac_state[60 + (sl->last_qscale_diff != 0)])){
int val = 1;
int ctx= 2;
- const int max_qp = 51 + 6*(h->sps.bit_depth_luma-8);
+ const int max_qp = 51 + 6*(sps->bit_depth_luma-8);
while( get_cabac_noinline( &sl->cabac, &sl->cabac_state[60 + ctx] ) ) {
ctx= 3;
if (sl->qscale < 0) sl->qscale += max_qp + 1;
else sl->qscale -= max_qp + 1;
}
- sl->chroma_qp[0] = get_chroma_qp(h, 0, sl->qscale);
- sl->chroma_qp[1] = get_chroma_qp(h, 1, sl->qscale);
+ sl->chroma_qp[0] = get_chroma_qp(h->ps.pps, 0, sl->qscale);
+ sl->chroma_qp[1] = get_chroma_qp(h->ps.pps, 1, sl->qscale);
}else
sl->last_qscale_diff=0;
+ if(IS_INTERLACED(mb_type)){
+ scan8x8 = sl->qscale ? h->field_scan8x8 : h->field_scan8x8_q0;
+ scan = sl->qscale ? h->field_scan : h->field_scan_q0;
+ }else{
+ scan8x8 = sl->qscale ? h->zigzag_scan8x8 : h->zigzag_scan8x8_q0;
+ scan = sl->qscale ? h->zigzag_scan : h->zigzag_scan_q0;
+ }
+
decode_cabac_luma_residual(h, sl, scan, scan8x8, pixel_shift, mb_type, cbp, 0);
if (CHROMA444(h)) {
decode_cabac_luma_residual(h, sl, scan, scan8x8, pixel_shift, mb_type, cbp, 1);
int c, i, i8x8;
for( c = 0; c < 2; c++ ) {
int16_t *mb = sl->mb + (16*(16 + 16*c) << pixel_shift);
- qmul = h->dequant4_coeff[c+1+(IS_INTRA( mb_type ) ? 0:3)][sl->chroma_qp[c]];
+ qmul = h->ps.pps->dequant4_coeff[c+1+(IS_INTRA( mb_type ) ? 0:3)][sl->chroma_qp[c]];
for (i8x8 = 0; i8x8 < 2; i8x8++) {
for (i = 0; i < 4; i++) {
const int index = 16 + 16 * c + 8*i8x8 + i;
if( cbp&0x20 ) {
int c, i;
for( c = 0; c < 2; c++ ) {
- qmul = h->dequant4_coeff[c+1+(IS_INTRA( mb_type ) ? 0:3)][sl->chroma_qp[c]];
+ qmul = h->ps.pps->dequant4_coeff[c+1+(IS_INTRA( mb_type ) ? 0:3)][sl->chroma_qp[c]];
for( i = 0; i < 4; i++ ) {
const int index = 16 + 16 * c + i;
decode_cabac_residual_nondc(h, sl, sl->mb + (16*index << pixel_shift), 4, index, scan + 1, qmul, 15);