x264源代码简单分析：编码器主干部分-1
本文来自：http://blog.csdn.net/leixiaohua1020/article/details/45644367
本文分析x264编码器主干部分的源代码。"主干部分"指的就是 libx264中最核心的接口函数——x264_encoder_encode()，以及相关的几个接口函数 x264_encoder_open()，x264_encoder_headers()，和x264_encoder_close()。这一部分源代码 比较复杂，现在看了半天依然感觉很多地方不太清晰，暂且把已经理解的地方整理出来，以后再慢慢补充还不太清晰的地方。由于主干部分内容比较多，因此打算分 成两篇文章来记录：第一篇文章记录x264_encoder_open()，x264_encoder_headers()，和 x264_encoder_close()这三个函数，第二篇文章记录x264_encoder_encode()函数。
本文将会记录x264_encoder_open()，x264_encoder_headers()，和x264_encoder_close()这三个函数的源代码。下一篇文章记录x264_encoder_encode()函数。
x264_encoder_open()
x264_encoder_open()是一个libx264的API。该函数用于打开编码器，其中初始化了libx264编码所需要的各种变量。该函数的声明如下所示。
/* x264_encoder_open: * create a new encoder handler, all parameters from x264_param_t are copied */ x264_t *x264_encoder_open( x264_param_t * );
x264_encoder_open()的定义位于encoder\encoder.c，如下所示。
/**************************************************************************** * x264_encoder_open: * 注释和处理：雷霄骅 * http://blog.csdn.net/leixiaohua1020 * leixiaohua1020@126.com ****************************************************************************/ //打开编码器 x264_t *x264_encoder_open( x264_param_t *param ) { x264_t *h; char buf[1000], *p; int qp, i_slicetype_length; CHECKED_MALLOCZERO( h, sizeof(x264_t) ); /* Create a copy of param */ //将参数拷贝进来 memcpy( &h->param, param, sizeof(x264_param_t) ); if( param->param_free ) param->param_free( param ); if( x264_threading_init() ) { x264_log( h, X264_LOG_ERROR, "unable to initialize threading\n" ); goto fail; } //检查输入参数 if( x264_validate_parameters( h, 1 ) < 0 ) goto fail; if( h->param.psz_cqm_file ) if( x264_cqm_parse_file( h, h->param.psz_cqm_file ) < 0 ) goto fail; if( h->param.rc.psz_stat_out ) h->param.rc.psz_stat_out = strdup( h->param.rc.psz_stat_out ); if( h->param.rc.psz_stat_in ) h->param.rc.psz_stat_in = strdup( h->param.rc.psz_stat_in ); x264_reduce_fraction( &h->param.i_fps_num, &h->param.i_fps_den ); x264_reduce_fraction( &h->param.i_timebase_num, &h->param.i_timebase_den ); /* Init x264_t */ h->i_frame = -1; h->i_frame_num = 0; if( h->param.i_avcintra_class ) h->i_idr_pic_id = 5; else h->i_idr_pic_id = 0; if( (uint64_t)h->param.i_timebase_den * 2 > UINT32_MAX ) { x264_log( h, X264_LOG_ERROR, "Effective timebase denominator %u exceeds H.264 maximum\n", h->param.i_timebase_den ); goto fail; } x264_set_aspect_ratio( h, &h->param, 1 ); //初始化SPS和PPS x264_sps_init( h->sps, h->param.i_sps_id, &h->param ); x264_pps_init( h->pps, h->param.i_sps_id, &h->param, h->sps ); //检查级Level-通过宏块个数等等 x264_validate_levels( h, 1 ); h->chroma_qp_table = i_chroma_qp_table + 12 + h->pps->i_chroma_qp_index_offset; if( x264_cqm_init( h ) < 0 ) goto fail; //各种赋值 h->mb.i_mb_width = h->sps->i_mb_width; h->mb.i_mb_height = h->sps->i_mb_height; h->mb.i_mb_count = h->mb.i_mb_width * h->mb.i_mb_height; h->mb.chroma_h_shift = CHROMA_FORMAT == CHROMA_420 || CHROMA_FORMAT == CHROMA_422; h->mb.chroma_v_shift = CHROMA_FORMAT == CHROMA_420; /* Adaptive MBAFF and subme 0 are not supported as we require halving motion * vectors during prediction, resulting in hpel mvs. * The chosen solution is to make MBAFF non-adaptive in this case. */ h->mb.b_adaptive_mbaff = PARAM_INTERLACED && h->param.analyse.i_subpel_refine; /* Init frames. */ if( h->param.i_bframe_adaptive == X264_B_ADAPT_TRELLIS && !h->param.rc.b_stat_read ) h->frames.i_delay = X264_MAX(h->param.i_bframe,3)*4; else h->frames.i_delay = h->param.i_bframe; if( h->param.rc.b_mb_tree || h->param.rc.i_vbv_buffer_size ) h->frames.i_delay = X264_MAX( h->frames.i_delay, h->param.rc.i_lookahead ); i_slicetype_length = h->frames.i_delay; h->frames.i_delay += h->i_thread_frames - 1; h->frames.i_delay += h->param.i_sync_lookahead; h->frames.i_delay += h->param.b_vfr_input; h->frames.i_bframe_delay = h->param.i_bframe ? (h->param.i_bframe_pyramid ? 2 : 1) : 0; h->frames.i_max_ref0 = h->param.i_frame_reference; h->frames.i_max_ref1 = X264_MIN( h->sps->vui.i_num_reorder_frames, h->param.i_frame_reference ); h->frames.i_max_dpb = h->sps->vui.i_max_dec_frame_buffering; h->frames.b_have_lowres = !h->param.rc.b_stat_read && ( h->param.rc.i_rc_method == X264_RC_ABR || h->param.rc.i_rc_method == X264_RC_CRF || h->param.i_bframe_adaptive || h->param.i_scenecut_threshold || h->param.rc.b_mb_tree || h->param.analyse.i_weighted_pred ); h->frames.b_have_lowres |= h->param.rc.b_stat_read && h->param.rc.i_vbv_buffer_size > 0; h->frames.b_have_sub8x8_esa = !!(h->param.analyse.inter & X264_ANALYSE_PSUB8x8); h->frames.i_last_idr = h->frames.i_last_keyframe = - h->param.i_keyint_max; h->frames.i_input = 0; h->frames.i_largest_pts = h->frames.i_second_largest_pts = -1; h->frames.i_poc_last_open_gop = -1; //CHECKED_MALLOCZERO(var, size) //调用malloc()分配内存,然后调用memset()置零 CHECKED_MALLOCZERO( h->frames.unused[0], (h->frames.i_delay + 3) * sizeof(x264_frame_t *) ); /* Allocate room for max refs plus a few extra just in case. */ CHECKED_MALLOCZERO( h->frames.unused[1], (h->i_thread_frames + X264_REF_MAX + 4) * sizeof(x264_frame_t *) ); CHECKED_MALLOCZERO( h->frames.current, (h->param.i_sync_lookahead + h->param.i_bframe + h->i_thread_frames + 3) * sizeof(x264_frame_t *) ); if( h->param.analyse.i_weighted_pred > 0 ) CHECKED_MALLOCZERO( h->frames.blank_unused, h->i_thread_frames * 4 * sizeof(x264_frame_t *) ); h->i_ref[0] = h->i_ref[1] = 0; h->i_cpb_delay = h->i_coded_fields = h->i_disp_fields = 0; h->i_prev_duration = ((uint64_t)h->param.i_fps_den * h->sps->vui.i_time_scale) / ((uint64_t)h->param.i_fps_num * h->sps->vui.i_num_units_in_tick); h->i_disp_fields_last_frame = -1; //RDO初始化 x264_rdo_init(); /* init CPU functions */ //初始化包含汇编优化的函数 //帧内预测 x264_predict_16x16_init( h->param.cpu, h->predict_16x16 ); x264_predict_8x8c_init( h->param.cpu, h->predict_8x8c ); x264_predict_8x16c_init( h->param.cpu, h->predict_8x16c ); x264_predict_8x8_init( h->param.cpu, h->predict_8x8, &h->predict_8x8_filter ); x264_predict_4x4_init( h->param.cpu, h->predict_4x4 ); //SAD等和像素计算有关的函数 x264_pixel_init( h->param.cpu, &h->pixf ); //DCT x264_dct_init( h->param.cpu, &h->dctf ); //"之"字扫描 x264_zigzag_init( h->param.cpu, &h->zigzagf_progressive, &h->zigzagf_interlaced ); memcpy( &h->zigzagf, PARAM_INTERLACED ? &h->zigzagf_interlaced : &h->zigzagf_progressive, sizeof(h->zigzagf) ); //运动补偿 x264_mc_init( h->param.cpu, &h->mc, h->param.b_cpu_independent ); //量化 x264_quant_init( h, h->param.cpu, &h->quantf ); //去块效应滤波 x264_deblock_init( h->param.cpu, &h->loopf, PARAM_INTERLACED ); x264_bitstream_init( h->param.cpu, &h->bsf ); //初始化CABAC或者是CAVLC if( h->param.b_cabac ) x264_cabac_init( h ); else x264_stack_align( x264_cavlc_init, h ); //决定了像素比较的时候用SAD还是SATD mbcmp_init( h ); chroma_dsp_init( h ); //CPU属性 p = buf + sprintf( buf, "using cpu capabilities:" ); for( int i = 0; x264_cpu_names[i].flags; i++ ) { if( !strcmp(x264_cpu_names[i].name, "SSE") && h->param.cpu & (X264_CPU_SSE2) ) continue; if( !strcmp(x264_cpu_names[i].name, "SSE2") && h->param.cpu & (X264_CPU_SSE2_IS_FAST|X264_CPU_SSE2_IS_SLOW) ) continue; if( !strcmp(x264_cpu_names[i].name, "SSE3") && (h->param.cpu & X264_CPU_SSSE3 || !(h->param.cpu & X264_CPU_CACHELINE_64)) ) continue; if( !strcmp(x264_cpu_names[i].name, "SSE4.1") && (h->param.cpu & X264_CPU_SSE42) ) continue; if( !strcmp(x264_cpu_names[i].name, "BMI1") && (h->param.cpu & X264_CPU_BMI2) ) continue; if( (h->param.cpu & x264_cpu_names[i].flags) == x264_cpu_names[i].flags && (!i || x264_cpu_names[i].flags != x264_cpu_names[i-1].flags) ) p += sprintf( p, " %s", x264_cpu_names[i].name ); } if( !h->param.cpu ) p += sprintf( p, " none!" ); x264_log( h, X264_LOG_INFO, "%s\n", buf ); float *logs = x264_analyse_prepare_costs( h ); if( !logs ) goto fail; for( qp = X264_MIN( h->param.rc.i_qp_min, QP_MAX_SPEC ); qp <= h->param.rc.i_qp_max; qp++ ) if( x264_analyse_init_costs( h, logs, qp ) ) goto fail; if( x264_analyse_init_costs( h, logs, X264_LOOKAHEAD_QP ) ) goto fail; x264_free( logs ); static const uint16_t cost_mv_correct[7] = { 24, 47, 95, 189, 379, 757, 1515 }; /* Checks for known miscompilation issues. */ if( h->cost_mv[X264_LOOKAHEAD_QP][2013] != cost_mv_correct[BIT_DEPTH-8] ) { x264_log( h, X264_LOG_ERROR, "MV cost test failed: x264 has been miscompiled!\n" ); goto fail; } /* Must be volatile or else GCC will optimize it out. */ volatile int temp = 392; if( x264_clz( temp ) != 23 ) { x264_log( h, X264_LOG_ERROR, "CLZ test failed: x264 has been miscompiled!\n" ); #if ARCH_X86 || ARCH_X86_64 x264_log( h, X264_LOG_ERROR, "Are you attempting to run an SSE4a/LZCNT-targeted build on a CPU that\n" ); x264_log( h, X264_LOG_ERROR, "doesn't support it?\n" ); #endif goto fail; } h->out.i_nal = 0; h->out.i_bitstream = X264_MAX( 1000000, h->param.i_width * h->param.i_height * 4 * ( h->param.rc.i_rc_method == X264_RC_ABR ? pow( 0.95, h->param.rc.i_qp_min ) : pow( 0.95, h->param.rc.i_qp_constant ) * X264_MAX( 1, h->param.rc.f_ip_factor ))); h->nal_buffer_size = h->out.i_bitstream * 3/2 + 4 + 64; /* +4 for startcode, +64 for nal_escape assembly padding */ CHECKED_MALLOC( h->nal_buffer, h->nal_buffer_size ); CHECKED_MALLOC( h->reconfig_h, sizeof(x264_t) ); if( h->param.i_threads > 1 && x264_threadpool_init( &h->threadpool, h->param.i_threads, (void*)x264_encoder_thread_init, h ) ) goto fail; if( h->param.i_lookahead_threads > 1 && x264_threadpool_init( &h->lookaheadpool, h->param.i_lookahead_threads, NULL, NULL ) ) goto fail; #if HAVE_OPENCL if( h->param.b_opencl ) { h->opencl.ocl = x264_opencl_load_library(); if( !h->opencl.ocl ) { x264_log( h, X264_LOG_WARNING, "failed to load OpenCL\n" ); h->param.b_opencl = 0; } } #endif h->thread[0] = h; for( int i = 1; i < h->param.i_threads + !!h->param.i_sync_lookahead; i++ ) CHECKED_MALLOC( h->thread[i], sizeof(x264_t) ); if( h->param.i_lookahead_threads > 1 ) for( int i = 0; i < h->param.i_lookahead_threads; i++ ) { CHECKED_MALLOC( h->lookahead_thread[i], sizeof(x264_t) ); *h->lookahead_thread[i] = *h; } *h->reconfig_h = *h; for( int i = 0; i < h->param.i_threads; i++ ) { int init_nal_count = h->param.i_slice_count + 3; int allocate_threadlocal_data = !h->param.b_sliced_threads || !i; if( i > 0 ) *h->thread[i] = *h; if( x264_pthread_mutex_init( &h->thread[i]->mutex, NULL ) ) goto fail; if( x264_pthread_cond_init( &h->thread[i]->cv, NULL ) ) goto fail; if( allocate_threadlocal_data ) { h->thread[i]->fdec = x264_frame_pop_unused( h, 1 ); if( !h->thread[i]->fdec ) goto fail; } else h->thread[i]->fdec = h->thread[0]->fdec; CHECKED_MALLOC( h->thread[i]->out.p_bitstream, h->out.i_bitstream ); /* Start each thread with room for init_nal_count NAL units; it'll realloc later if needed. */ CHECKED_MALLOC( h->thread[i]->out.nal, init_nal_count*sizeof(x264_nal_t) ); h->thread[i]->out.i_nals_allocated = init_nal_count; if( allocate_threadlocal_data && x264_macroblock_cache_allocate( h->thread[i] ) < 0 ) goto fail; } #if HAVE_OPENCL if( h->param.b_opencl && x264_opencl_lookahead_init( h ) < 0 ) h->param.b_opencl = 0; #endif //初始化lookahead if( x264_lookahead_init( h, i_slicetype_length ) ) goto fail; for( int i = 0; i < h->param.i_threads; i++ ) if( x264_macroblock_thread_allocate( h->thread[i], 0 ) < 0 ) goto fail; //创建码率控制 if( x264_ratecontrol_new( h ) < 0 ) goto fail; if( h->param.i_nal_hrd ) { x264_log( h, X264_LOG_DEBUG, "HRD bitrate: %i bits/sec\n", h->sps->vui.hrd.i_bit_rate_unscaled ); x264_log( h, X264_LOG_DEBUG, "CPB size: %i bits\n", h->sps->vui.hrd.i_cpb_size_unscaled ); } if( h->param.psz_dump_yuv ) { /* create or truncate the reconstructed video file */ FILE *f = x264_fopen( h->param.psz_dump_yuv, "w" ); if( !f ) { x264_log( h, X264_LOG_ERROR, "dump_yuv: can't write to %s\n", h->param.psz_dump_yuv ); goto fail; } else if( !x264_is_regular_file( f ) ) { x264_log( h, X264_LOG_ERROR, "dump_yuv: incompatible with non-regular file %s\n", h->param.psz_dump_yuv ); goto fail; } fclose( f ); } //这写法...... const char *profile = h->sps->i_profile_idc == PROFILE_BASELINE ? "Constrained Baseline" : h->sps->i_profile_idc == PROFILE_MAIN ? "Main" : h->sps->i_profile_idc == PROFILE_HIGH ? "High" : h->sps->i_profile_idc == PROFILE_HIGH10 ? (h->sps->b_constraint_set3 == 1 ? "High 10 Intra" : "High 10") : h->sps->i_profile_idc == PROFILE_HIGH422 ? (h->sps->b_constraint_set3 == 1 ? "High 4:2:2 Intra" : "High 4:2:2") : h->sps->b_constraint_set3 == 1 ? "High 4:4:4 Intra" : "High 4:4:4 Predictive"; char level[4]; snprintf( level, sizeof(level), "%d.%d", h->sps->i_level_idc/10, h->sps->i_level_idc%10 ); if( h->sps->i_level_idc == 9 || ( h->sps->i_level_idc == 11 && h->sps->b_constraint_set3 && (h->sps->i_profile_idc == PROFILE_BASELINE || h->sps->i_profile_idc == PROFILE_MAIN) ) ) strcpy( level, "1b" ); //输出型和级 if( h->sps->i_profile_idc < PROFILE_HIGH10 ) { x264_log( h, X264_LOG_INFO, "profile %s, level %s\n", profile, level ); } else { static const char * const subsampling[4] = { "4:0:0", "4:2:0", "4:2:2", "4:4:4" }; x264_log( h, X264_LOG_INFO, "profile %s, level %s, %s %d-bit\n", profile, level, subsampling[CHROMA_FORMAT], BIT_DEPTH ); } return h; fail: //释放 x264_free( h ); return NULL; }
由于源代码中已经做了比较详细的注释，在这里就不重复叙述了。下面根据函数调用的顺序，看一下x264_encoder_open()调用的下面几个函数：
x264_sps_init()：根据输入参数生成H.264码流的SPS信息。
x264_pps_init()：根据输入参数生成H.264码流的PPS信息。
x264_predict_16x16_init()：初始化Intra16x16帧内预测汇编函数。
x264_predict_4x4_init()：初始化Intra4x4帧内预测汇编函数。
x264_pixel_init()：初始化像素值计算相关的汇编函数（包括SAD、SATD、SSD等）。
x264_dct_init()：初始化DCT变换和DCT反变换相关的汇编函数。
x264_mc_init()：初始化运动补偿相关的汇编函数。
x264_quant_init()：初始化量化和反量化相关的汇编函数。
x264_deblock_init()：初始化去块效应滤波器相关的汇编函数。
mbcmp_init()：决定像素比较的时候使用SAD还是SATD。
x264_sps_init()
x264_sps_init()根据输入参数生成H.264码流的SPS （Sequence Parameter Set，序列参数集）信息。该函数的定义位于encoder\set.c，如下所示。
//初始化SPS void x264_sps_init( x264_sps_t *sps, int i_id, x264_param_t *param ) { int csp = param->i_csp & X264_CSP_MASK; sps->i_id = i_id; //以宏块为单位的宽度 sps->i_mb_width = ( param->i_width + 15 ) / 16; //以宏块为单位的高度 sps->i_mb_height= ( param->i_height + 15 ) / 16; //色度取样格式 sps->i_chroma_format_idc = csp >= X264_CSP_I444 ? CHROMA_444 : csp >= X264_CSP_I422 ? CHROMA_422 : CHROMA_420; sps->b_qpprime_y_zero_transform_bypass = param->rc.i_rc_method == X264_RC_CQP && param->rc.i_qp_constant == 0; //型profile if( sps->b_qpprime_y_zero_transform_bypass || sps->i_chroma_format_idc == CHROMA_444 ) sps->i_profile_idc = PROFILE_HIGH444_PREDICTIVE;//YUV444的时候 else if( sps->i_chroma_format_idc == CHROMA_422 ) sps->i_profile_idc = PROFILE_HIGH422; else if( BIT_DEPTH > 8 ) sps->i_profile_idc = PROFILE_HIGH10; else if( param->analyse.b_transform_8x8 || param->i_cqm_preset != X264_CQM_FLAT ) sps->i_profile_idc = PROFILE_HIGH;//高型 High Profile 目前最常见 else if( param->b_cabac || param->i_bframe > 0 || param->b_interlaced || param->b_fake_interlaced || param->analyse.i_weighted_pred > 0 ) sps->i_profile_idc = PROFILE_MAIN;//主型 else sps->i_profile_idc = PROFILE_BASELINE;//基本型 sps->b_constraint_set0 = sps->i_profile_idc == PROFILE_BASELINE; /* x264 doesn't support the features that are in Baseline and not in Main, * namely arbitrary_slice_order and slice_groups. */ sps->b_constraint_set1 = sps->i_profile_idc <= PROFILE_MAIN; /* Never set constraint_set2, it is not necessary and not used in real world. */ sps->b_constraint_set2 = 0; sps->b_constraint_set3 = 0; //级level sps->i_level_idc = param->i_level_idc; if( param->i_level_idc == 9 && ( sps->i_profile_idc == PROFILE_BASELINE || sps->i_profile_idc == PROFILE_MAIN ) ) { sps->b_constraint_set3 = 1; /* level 1b with Baseline or Main profile is signalled via constraint_set3 */ sps->i_level_idc = 11; } /* Intra profiles */ if( param->i_keyint_max == 1 && sps->i_profile_idc > PROFILE_HIGH ) sps->b_constraint_set3 = 1; sps->vui.i_num_reorder_frames = param->i_bframe_pyramid ? 2 : param->i_bframe ? 1 : 0; /* extra slot with pyramid so that we don't have to override the * order of forgetting old pictures */ //参考帧数量 sps->vui.i_max_dec_frame_buffering = sps->i_num_ref_frames = X264_MIN(X264_REF_MAX, X264_MAX4(param->i_frame_reference, 1 + sps->vui.i_num_reorder_frames, param->i_bframe_pyramid ? 4 : 1, param->i_dpb_size)); sps->i_num_ref_frames -= param->i_bframe_pyramid == X264_B_PYRAMID_STRICT; if( param->i_keyint_max == 1 ) { sps->i_num_ref_frames = 0; sps->vui.i_max_dec_frame_buffering = 0; } /* number of refs + current frame */ int max_frame_num = sps->vui.i_max_dec_frame_buffering * (!!param->i_bframe_pyramid+1) + 1; /* Intra refresh cannot write a recovery time greater than max frame num-1 */ if( param->b_intra_refresh ) { int time_to_recovery = X264_MIN( sps->i_mb_width - 1, param->i_keyint_max ) + param->i_bframe - 1; max_frame_num = X264_MAX( max_frame_num, time_to_recovery+1 ); } sps->i_log2_max_frame_num = 4; while( (1 << sps->i_log2_max_frame_num) <= max_frame_num ) sps->i_log2_max_frame_num++; //POC类型 sps->i_poc_type = param->i_bframe || param->b_interlaced ? 0 : 2; if( sps->i_poc_type == 0 ) { int max_delta_poc = (param->i_bframe + 2) * (!!param->i_bframe_pyramid + 1) * 2; sps->i_log2_max_poc_lsb = 4; while( (1 << sps->i_log2_max_poc_lsb) <= max_delta_poc * 2 ) sps->i_log2_max_poc_lsb++; } sps->b_vui = 1; sps->b_gaps_in_frame_num_value_allowed = 0; sps->b_frame_mbs_only = !(param->b_interlaced || param->b_fake_interlaced); if( !sps->b_frame_mbs_only ) sps->i_mb_height = ( sps->i_mb_height + 1 ) & ~1; sps->b_mb_adaptive_frame_field = param->b_interlaced; sps->b_direct8x8_inference = 1; sps->crop.i_left = param->crop_rect.i_left; sps->crop.i_top = param->crop_rect.i_top; sps->crop.i_right = param->crop_rect.i_right + sps->i_mb_width*16 - param->i_width; sps->crop.i_bottom = (param->crop_rect.i_bottom + sps->i_mb_height*16 - param->i_height) >> !sps->b_frame_mbs_only; sps->b_crop = sps->crop.i_left || sps->crop.i_top || sps->crop.i_right || sps->crop.i_bottom; sps->vui.b_aspect_ratio_info_present = 0; if( param->vui.i_sar_width > 0 && param->vui.i_sar_height > 0 ) { sps->vui.b_aspect_ratio_info_present = 1; sps->vui.i_sar_width = param->vui.i_sar_width; sps->vui.i_sar_height= param->vui.i_sar_height; } sps->vui.b_overscan_info_present = param->vui.i_overscan > 0 && param->vui.i_overscan <= 2; if( sps->vui.b_overscan_info_present ) sps->vui.b_overscan_info = ( param->vui.i_overscan == 2 ? 1 : 0 ); sps->vui.b_signal_type_present = 0; sps->vui.i_vidformat = ( param->vui.i_vidformat >= 0 && param->vui.i_vidformat <= 5 ? param->vui.i_vidformat : 5 ); sps->vui.b_fullrange = ( param->vui.b_fullrange >= 0 && param->vui.b_fullrange <= 1 ? param->vui.b_fullrange : ( csp >= X264_CSP_BGR ? 1 : 0 ) ); sps->vui.b_color_description_present = 0; sps->vui.i_colorprim = ( param->vui.i_colorprim >= 0 && param->vui.i_colorprim <= 9 ? param->vui.i_colorprim : 2 ); sps->vui.i_transfer = ( param->vui.i_transfer >= 0 && param->vui.i_transfer <= 15 ? param->vui.i_transfer : 2 ); sps->vui.i_colmatrix = ( param->vui.i_colmatrix >= 0 && param->vui.i_colmatrix <= 10 ? param->vui.i_colmatrix : ( csp >= X264_CSP_BGR ? 0 : 2 ) ); if( sps->vui.i_colorprim != 2 || sps->vui.i_transfer != 2 || sps->vui.i_colmatrix != 2 ) { sps->vui.b_color_description_present = 1; } if( sps->vui.i_vidformat != 5 || sps->vui.b_fullrange || sps->vui.b_color_description_present ) { sps->vui.b_signal_type_present = 1; } /* FIXME: not sufficient for interlaced video */ sps->vui.b_chroma_loc_info_present = param->vui.i_chroma_loc > 0 && param->vui.i_chroma_loc <= 5 && sps->i_chroma_format_idc == CHROMA_420; if( sps->vui.b_chroma_loc_info_present ) { sps->vui.i_chroma_loc_top = param->vui.i_chroma_loc; sps->vui.i_chroma_loc_bottom = param->vui.i_chroma_loc; } sps->vui.b_timing_info_present = param->i_timebase_num > 0 && param->i_timebase_den > 0; if( sps->vui.b_timing_info_present ) { sps->vui.i_num_units_in_tick = param->i_timebase_num; sps->vui.i_time_scale = param->i_timebase_den * 2; sps->vui.b_fixed_frame_rate = !param->b_vfr_input; } sps->vui.b_vcl_hrd_parameters_present = 0; // we don't support VCL HRD sps->vui.b_nal_hrd_parameters_present = !!param->i_nal_hrd; sps->vui.b_pic_struct_present = param->b_pic_struct; // NOTE: HRD related parts of the SPS are initialised in x264_ratecontrol_init_reconfigurable sps->vui.b_bitstream_restriction = param->i_keyint_max > 1; if( sps->vui.b_bitstream_restriction ) { sps->vui.b_motion_vectors_over_pic_boundaries = 1; sps->vui.i_max_bytes_per_pic_denom = 0; sps->vui.i_max_bits_per_mb_denom = 0; sps->vui.i_log2_max_mv_length_horizontal = sps->vui.i_log2_max_mv_length_vertical = (int)log2f( X264_MAX( 1, param->analyse.i_mv_range*4-1 ) ) + 1; } }
从源代码可以看出，x264_sps_init()根据输入参数集x264_param_t中的信息，初始化了SPS结构体中的成员变量。有关这些成员变量的具体信息，可以参考《H.264标准》。
x264_pps_init()
x264_pps_init()根据输入参数生成H.264码流的PPS（Picture Parameter Set，图像参数集）信息。该函数的定义位于encoder\set.c，如下所示。
//初始化PPS void x264_pps_init( x264_pps_t *pps, int i_id, x264_param_t *param, x264_sps_t *sps ) { pps->i_id = i_id; //所属的SPS pps->i_sps_id = sps->i_id; //是否使用CABAC？ pps->b_cabac = param->b_cabac; pps->b_pic_order = !param->i_avcintra_class && param->b_interlaced; pps->i_num_slice_groups = 1; //目前参考帧队列的长度 //注意是这个队列中当前实际的、已存在的参考帧数目，这从它的名字"active"中也可以看出来。 pps->i_num_ref_idx_l0_default_active = param->i_frame_reference; pps->i_num_ref_idx_l1_default_active = 1; //加权预测 pps->b_weighted_pred = param->analyse.i_weighted_pred > 0; pps->b_weighted_bipred = param->analyse.b_weighted_bipred ? 2 : 0; //量化参数QP的初始值 pps->i_pic_init_qp = param->rc.i_rc_method == X264_RC_ABR || param->b_stitchable ? 26 + QP_BD_OFFSET : SPEC_QP( param->rc.i_qp_constant ); pps->i_pic_init_qs = 26 + QP_BD_OFFSET; pps->i_chroma_qp_index_offset = param->analyse.i_chroma_qp_offset; pps->b_deblocking_filter_control = 1; pps->b_constrained_intra_pred = param->b_constrained_intra; pps->b_redundant_pic_cnt = 0; pps->b_transform_8x8_mode = param->analyse.b_transform_8x8 ? 1 : 0; pps->i_cqm_preset = param->i_cqm_preset; switch( pps->i_cqm_preset ) { case X264_CQM_FLAT: for( int i = 0; i < 8; i++ ) pps->scaling_list[i] = x264_cqm_flat16; break; case X264_CQM_JVT: for( int i = 0; i < 8; i++ ) pps->scaling_list[i] = x264_cqm_jvt[i]; break; case X264_CQM_CUSTOM: /* match the transposed DCT & zigzag */ transpose( param->cqm_4iy, 4 ); transpose( param->cqm_4py, 4 ); transpose( param->cqm_4ic, 4 ); transpose( param->cqm_4pc, 4 ); transpose( param->cqm_8iy, 8 ); transpose( param->cqm_8py, 8 ); transpose( param->cqm_8ic, 8 ); transpose( param->cqm_8pc, 8 ); pps->scaling_list[CQM_4IY] = param->cqm_4iy; pps->scaling_list[CQM_4PY] = param->cqm_4py; pps->scaling_list[CQM_4IC] = param->cqm_4ic; pps->scaling_list[CQM_4PC] = param->cqm_4pc; pps->scaling_list[CQM_8IY+4] = param->cqm_8iy; pps->scaling_list[CQM_8PY+4] = param->cqm_8py; pps->scaling_list[CQM_8IC+4] = param->cqm_8ic; pps->scaling_list[CQM_8PC+4] = param->cqm_8pc; for( int i = 0; i < 8; i++ ) for( int j = 0; j < (i < 4 ? 16 : 64); j++ ) if( pps->scaling_list[i][j] == 0 ) pps->scaling_list[i] = x264_cqm_jvt[i]; break; } }
从源代码可以看出，x264_pps_init()根据输入参数集x264_param_t中的信息，初始化了PPS结构体中的成员变量。有关这些成员变量的具体信息，可以参考《H.264标准》。
x264_predict_16x16_init()
x264_predict_16x16_init()用于初始化Intra16x16帧内预测汇编函数。该函数的定义位于x264\common\predict.c，如下所示。
//Intra16x16帧内预测汇编函数初始化 void x264_predict_16x16_init( int cpu, x264_predict_t pf[7] ) { //C语言版本 //================================================ //垂直 Vertical pf[I_PRED_16x16_V ] = x264_predict_16x16_v_c; //水平 Horizontal pf[I_PRED_16x16_H ] = x264_predict_16x16_h_c; //DC pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_c; //Plane pf[I_PRED_16x16_P ] = x264_predict_16x16_p_c; //这几种是啥？ pf[I_PRED_16x16_DC_LEFT]= x264_predict_16x16_dc_left_c; pf[I_PRED_16x16_DC_TOP ]= x264_predict_16x16_dc_top_c; pf[I_PRED_16x16_DC_128 ]= x264_predict_16x16_dc_128_c; //================================================ //MMX版本 #if HAVE_MMX x264_predict_16x16_init_mmx( cpu, pf ); #endif //ALTIVEC版本 #if HAVE_ALTIVEC if( cpu&X264_CPU_ALTIVEC ) x264_predict_16x16_init_altivec( pf ); #endif //ARMV6版本 #if HAVE_ARMV6 x264_predict_16x16_init_arm( cpu, pf ); #endif //AARCH64版本 #if ARCH_AARCH64 x264_predict_16x16_init_aarch64( cpu, pf ); #endif }
从 源代码可看出，x264_predict_16x16_init()首先对帧内预测函数指针数组x264_predict_t[]中的元素赋值了C语言版 本的函数 x264_predict_16x16_v_c()，x264_predict_16x16_h_c()，x264_predict_16x16_dc_c()，x264_predict_16x16_p_c()； 然后会判断系统平台的特性，如果平台支持的话，会调用 x264_predict_16x16_init_mmx()，x264_predict_16x16_init_arm()等给 x264_predict_t[]中的元素赋值经过汇编优化的函数。下文将会简单看几个其中的函数。
简单记录一下帧内预测的方法。帧内预测根据宏块左边和上边的边界像素值推算宏块内部的像素值，帧内预测的效果如下图所示。其中左边的图为图像原始画面，右边的图为经过帧内预测后没有叠加残差的画面。
H.264中有两种帧内预测模式：16x16亮度帧内预测模式和4x4亮度帧内预测模式。其中16x16帧内预测模式一共有4种，如下图所示。
这4种模式列表如下。
|
模式 |
描述 |
|
Vertical |
由上边像素推出相应像素值 |
|
Horizontal |
由左边像素推出相应像素值 |
|
DC |
由上边和左边像素平均值推出相应像素值 |
|
Plane |
由上边和左边像素推出相应像素值 |
4x4帧内预测模式一共有9种，如下图所示。
有关Intra4x4的帧内预测模式的代码将在后文中进行记录。下面举例看一下Intra16x16的Vertical预测模式的实现函数x264_predict_16x16_v_c()。
x264_predict_16x16_v_c()
x264_predict_16x16_v_c()实现了Intra16x16的Vertical预测模式。该函数的定义位于common\predict.c，如下所示。
//16x16帧内预测 //垂直预测（Vertical） void x264_predict_16x16_v_c( pixel *src ) { /* * Vertical预测方式 * |X1 X2 X3 X4 * --+----------- * |X1 X2 X3 X4 * |X1 X2 X3 X4 * |X1 X2 X3 X4 * |X1 X2 X3 X4 * */ /* * 【展开宏定义】 * uint32_t v0 = ((x264_union32_t*)(&src[ 0-FDEC_STRIDE]))->i; * uint32_t v1 = ((x264_union32_t*)(&src[ 4-FDEC_STRIDE]))->i; * uint32_t v2 = ((x264_union32_t*)(&src[ 8-FDEC_STRIDE]))->i; * uint32_t v3 = ((x264_union32_t*)(&src[12-FDEC_STRIDE]))->i; * 在这里，上述代码实际上相当于： * uint32_t v0 = *((uint32_t*)(&src[ 0-FDEC_STRIDE])); * uint32_t v1 = *((uint32_t*)(&src[ 4-FDEC_STRIDE])); * uint32_t v2 = *((uint32_t*)(&src[ 8-FDEC_STRIDE])); * uint32_t v3 = *((uint32_t*)(&src[12-FDEC_STRIDE])); * 即分成4次，每次取出4个像素（一共16个像素），分别赋值给v0，v1，v2，v3 * 取出的值源自于16x16块上面的一行像素 * 0| 4 8 12 16 * || v0 | v1 | v2 | v3 | * ---++==========+==========+==========+==========+ * || * || * || * || * || * || * */ //pixel4实际上是uint32_t（占用32bit），存储4个像素的值（每个像素占用8bit） pixel4 v0 = MPIXEL_X4( &src[ 0-FDEC_STRIDE] ); pixel4 v1 = MPIXEL_X4( &src[ 4-FDEC_STRIDE] ); pixel4 v2 = MPIXEL_X4( &src[ 8-FDEC_STRIDE] ); pixel4 v3 = MPIXEL_X4( &src[12-FDEC_STRIDE] ); //循环赋值16行 for( int i = 0; i < 16; i++ ) { //【展开宏定义】 //(((x264_union32_t*)(src+ 0))->i) = v0; //(((x264_union32_t*)(src+ 4))->i) = v1; //(((x264_union32_t*)(src+ 8))->i) = v2; //(((x264_union32_t*)(src+12))->i) = v3; //即分成4次，每次赋值4个像素 // MPIXEL_X4( src+ 0 ) = v0; MPIXEL_X4( src+ 4 ) = v1; MPIXEL_X4( src+ 8 ) = v2; MPIXEL_X4( src+12 ) = v3; //下一行 //FDEC_STRIDE=32,是重建宏块缓存fdec_buf一行的数据量 src += FDEC_STRIDE; } }
从源代码可以看出，x264_predict_16x16_v_c()首先取出了16x16图像块上面一行16个像素的值存储在v0，v1，v2，v3四个变量中（每个变量存储4个像素），然后循环16次将v0，v1，v2，v3赋值给16x16图像块的16行。
看 完C语言版本Intra16x16的Vertical预测模式的实现函数之后，我们可以继续看一下该预测模式汇编语言版本的实现函数。从前面的初始化函数 中已经可以看出，当系统支持X86汇编的时候，会调用x264_predict_16x16_init_mmx()初始化x86汇编优化过的函数；当系统 支持ARM的时候，会调用x264_predict_16x16_init_arm()初始化ARM汇编优化过的函数。
x264_predict_16x16_init_mmx()
x264_predict_16x16_init_mmx()用于初始化经过x86汇编优化过的Intra16x16的帧内预测函数。该函数的定义位于common\x86\predict-c.c（在"x86"子文件夹下），如下所示。
//Intra16x16帧内预测汇编函数-MMX版本 void x264_predict_16x16_init_mmx( int cpu, x264_predict_t pf[7] ) { if( !(cpu&X264_CPU_MMX2) ) return; pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_mmx2; pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_mmx2; pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_mmx2; pf[I_PRED_16x16_V] = x264_predict_16x16_v_mmx2; pf[I_PRED_16x16_H] = x264_predict_16x16_h_mmx2; #if HIGH_BIT_DEPTH if( !(cpu&X264_CPU_SSE) ) return; pf[I_PRED_16x16_V] = x264_predict_16x16_v_sse; if( !(cpu&X264_CPU_SSE2) ) return; pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_sse2; pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_sse2; pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_sse2; pf[I_PRED_16x16_H] = x264_predict_16x16_h_sse2; pf[I_PRED_16x16_P] = x264_predict_16x16_p_sse2; if( !(cpu&X264_CPU_AVX) ) return; pf[I_PRED_16x16_V] = x264_predict_16x16_v_avx; if( !(cpu&X264_CPU_AVX2) ) return; pf[I_PRED_16x16_H] = x264_predict_16x16_h_avx2; #else #if !ARCH_X86_64 pf[I_PRED_16x16_P] = x264_predict_16x16_p_mmx2; #endif if( !(cpu&X264_CPU_SSE) ) return; pf[I_PRED_16x16_V] = x264_predict_16x16_v_sse; if( !(cpu&X264_CPU_SSE2) ) return; pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_sse2; if( cpu&X264_CPU_SSE2_IS_SLOW ) return; pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_sse2; pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_sse2; pf[I_PRED_16x16_P] = x264_predict_16x16_p_sse2; if( !(cpu&X264_CPU_SSSE3) ) return; if( !(cpu&X264_CPU_SLOW_PSHUFB) ) pf[I_PRED_16x16_H] = x264_predict_16x16_h_ssse3; #if HAVE_X86_INLINE_ASM pf[I_PRED_16x16_P] = x264_predict_16x16_p_ssse3; #endif if( !(cpu&X264_CPU_AVX) ) return; pf[I_PRED_16x16_P] = x264_predict_16x16_p_avx; #endif // HIGH_BIT_DEPTH if( cpu&X264_CPU_AVX2 ) { pf[I_PRED_16x16_P] = x264_predict_16x16_p_avx2; pf[I_PRED_16x16_DC] = x264_predict_16x16_dc_avx2; pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_avx2; pf[I_PRED_16x16_DC_LEFT] = x264_predict_16x16_dc_left_avx2; } }
可 以看出，针对Intra16x16的Vertical帧内预测模式，x264_predict_16x16_init_mmx()会根据系统的特型初始化 2个函数：如果系统仅支持MMX指令集，就会初始化x264_predict_16x16_v_mmx2()；如果系统还支持SSE指令集，就会初始化 x264_predict_16x16_v_sse()。下面看一下这2个函数的代码。
x264_predict_16x16_v_sse()
在x264中，x264_predict_16x16_v_mmx2()和x264_predict_16x16_v_sse()这两个函数的定义是写到一起的。它们的定义位于common\x86\predict-a.asm，如下所示。
;----------------------------------------------------------------------------- ; void predict_16x16_v( pixel *src ) ; Intra16x16帧内预测Vertical模式 ;----------------------------------------------------------------------------- ;SIZEOF_PIXEL取值为1 ;FDEC_STRIDEB为重建宏块缓存fdec_buf一行像素的大小，取值为32 ; ;平台相关的信息位于x86inc.asm ;INIT_MMX中 ; mmsize为8 ; mova为movq ;INIT_XMM中： ; mmsize为16 ; mova为movdqa ; ;STORE16的定义在前面，用于循环16行存储数据 %macro PREDICT_16x16_V 0 cglobal predict_16x16_v, 1,2 %assign %%i 0 %rep 16*SIZEOF_PIXEL/mmsize ;rep循环执行，拷贝16x16块上方的1行像素数据至m0,m1... ;mmssize为指令1次处理比特数 mova m %+ %%i, [r0-FDEC_STRIDEB+%%i*mmsize] ;移入m0,m1... %assign %%i %%i+1 %endrep %if 16*SIZEOF_PIXEL/mmsize == 4 ;1行需要处理4次 STORE16 m0, m1, m2, m3 ;循环存储16行，每次存储4个寄存器 %elif 16*SIZEOF_PIXEL/mmsize == 2 ;1行需要处理2次 STORE16 m0, m1 ;循环存储16行，每次存储2个寄存器 %else ;1行需要处理1次 STORE16 m0 ;循环存储16行，每次存储1个寄存器 %endif RET %endmacro INIT_MMX mmx2 PREDICT_16x16_V INIT_XMM sse PREDICT_16x16_V
从 汇编代码可以看出，x264_predict_16x16_v_mmx2()和x264_predict_16x16_v_sse()的逻辑是一模一样 的。它们之间的不同主要在于一条指令处理的数据量：MMX指令的MOVA对应的是MOVQ，一次处理8Byte（8个像素）；SSE指令的MOVA对应的 是MOVDQA，一次处理16Byte（16个像素，正好是16x16块中的一行像素）。
作为对比，我们可以看一下ARM平台下汇编优化过的Intra16x16的帧内预测函数。这些汇编函数的初始化函数是x264_predict_16x16_init_arm()。
x264_predict_16x16_init_arm()
x264_predict_16x16_init_arm()用于初始化ARM平台下汇编优化过的Intra16x16的帧内预测函数。该函数的定义位于common\arm\predict-c.c（"arm"文件夹下），如下所示。
void x264_predict_16x16_init_arm( int cpu, x264_predict_t pf[7] ) { if (!(cpu&X264_CPU_NEON)) return; #if !HIGH_BIT_DEPTH pf[I_PRED_16x16_DC ] = x264_predict_16x16_dc_neon; pf[I_PRED_16x16_DC_TOP] = x264_predict_16x16_dc_top_neon; pf[I_PRED_16x16_DC_LEFT]= x264_predict_16x16_dc_left_neon; pf[I_PRED_16x16_H ] = x264_predict_16x16_h_neon; pf[I_PRED_16x16_V ] = x264_predict_16x16_v_neon; pf[I_PRED_16x16_P ] = x264_predict_16x16_p_neon; #endif // !HIGH_BIT_DEPTH }
从源代码可以看出，针对Vertical预测模式，x264_predict_16x16_init_arm()初始化了经过NEON指令集优化的函数x264_predict_16x16_v_neon()。
x264_predict_16x16_v_neon()
x264_predict_16x16_v_neon()的定义位于common\arm\predict-a.S，如下所示。
/* * Intra16x16帧内预测Vertical模式-NEON * */ /* FDEC_STRIDE=32Bytes，为重建宏块一行像素的大小 */ /* R0存储16x16像素块地址 */ function x264_predict_16x16_v_neon sub r0, r0, #FDEC_STRIDE /* r0=r0-FDEC_STRIDE */ mov ip, #FDEC_STRIDE /* ip=32 */ /* VLD向量加载: 内存->NEON寄存器 */ /* d0,d1为64bit双字寄存器，共16Byte，在这里存储16x16块上方一行像素 */ vld1.64 {d0-d1}, [r0,:128], ip /* 将R0指向的数据从内存加载到d0和d1寄存器（64bit） */ /* r0=r0+ip */ .rept 16 /* 循环16次，一次处理1行 */ /* VST向量存储: NEON寄存器->内存 */ vst1.64 {d0-d1}, [r0,:128], ip /* 将d0和d1寄存器中的数据传递给R0指向的内存 */ /* r0=r0+ip */ .endr bx lr /* 子程序返回 */ endfunc
可以看出，x264_predict_16x16_v_neon()使用vld1.64指令载入16x16块上方的一行像素，然后在一个16次的循环中，使用vst1.64指令将该行像素值赋值给16x16块的每一行。
至此有关Intra16x16的Vertical帧内预测方式的源代码就分析完了。后文为了简便，都只讨论C语言版本汇编函数。
x264_predict_4x4_init()
x264_predict_4x4_init()用于初始化Intra4x4帧内预测汇编函数。该函数的定义位于common\predict.c，如下所示。
//Intra4x4帧内预测汇编函数初始化 void x264_predict_4x4_init( int cpu, x264_predict_t pf[12] ) { //9种Intra4x4预测方式 pf[I_PRED_4x4_V] = x264_predict_4x4_v_c; pf[I_PRED_4x4_H] = x264_predict_4x4_h_c; pf[I_PRED_4x4_DC] = x264_predict_4x4_dc_c; pf[I_PRED_4x4_DDL] = x264_predict_4x4_ddl_c; pf[I_PRED_4x4_DDR] = x264_predict_4x4_ddr_c; pf[I_PRED_4x4_VR] = x264_predict_4x4_vr_c; pf[I_PRED_4x4_HD] = x264_predict_4x4_hd_c; pf[I_PRED_4x4_VL] = x264_predict_4x4_vl_c; pf[I_PRED_4x4_HU] = x264_predict_4x4_hu_c; //这些是？ pf[I_PRED_4x4_DC_LEFT]= x264_predict_4x4_dc_left_c; pf[I_PRED_4x4_DC_TOP] = x264_predict_4x4_dc_top_c; pf[I_PRED_4x4_DC_128] = x264_predict_4x4_dc_128_c; #if HAVE_MMX x264_predict_4x4_init_mmx( cpu, pf ); #endif #if HAVE_ARMV6 x264_predict_4x4_init_arm( cpu, pf ); #endif #if ARCH_AARCH64 x264_predict_4x4_init_aarch64( cpu, pf ); #endif }
从 源代码可看出，x264_predict_4x4_init()首先对帧内预测函数指针数组x264_predict_t[]中的元素赋值了C语言版本的 函数 x264_predict_4x4_v_c()，x264_predict_4x4_h_c()，x264_predict_4x4_dc_c()，x264_predict_4x4_p_c() 等一系列函数（Intra4x4有9种，后面那几种是怎么回事？）；然后会判断系统平台的特性，如果平台支持的话，会调用 x264_predict_4x4_init_mmx()，x264_predict_4x4_init_arm()等给 x264_predict_t[]中的元素赋值经过汇编优化的函数。作为例子，下文看一个Intra4x4的Vertical帧内预测模式的C语言函数。
Intra4x4的帧内预测模式一共有9种。如下图所示。
可以看出，Intra4x4帧内预测模式中前4种和Intra16x16是一样的。后面多增加了几种预测箭头不是45度角的方式——前面的箭头位于"口"中，而后面的箭头位于"日"中。
x264_predict_4x4_v_c()
x264_predict_4x4_v_c()实现了Intra4x4的Vertical帧内预测方式。该函数的定义位于common\predict.c，如下所示。
void x264_predict_4x4_v_c( pixel *src ) { /* * Vertical预测方式 * |X1 X2 X3 X4 * --+----------- * |X1 X2 X3 X4 * |X1 X2 X3 X4 * |X1 X2 X3 X4 * |X1 X2 X3 X4 * */ /* * 宏展开后的结果如下所示 * 注：重建宏块缓存fdec_buf一行的数据量为32Byte * * (((x264_union32_t*)(&src[(0)+(0)*32]))->i) = * (((x264_union32_t*)(&src[(0)+(1)*32]))->i) = * (((x264_union32_t*)(&src[(0)+(2)*32]))->i) = * (((x264_union32_t*)(&src[(0)+(3)*32]))->i) = (((x264_union32_t*)(&src[(0)+(-1)*32]))->i); */ PREDICT_4x4_DC(SRC_X4(0,-1)); }
x264_predict_4x4_v_c()函数的函数体极其简单，只有一个宏定义"PREDICT_4x4_DC(SRC_X4(0,-1));"。如果把该宏展开后，可以看出它取了4x4块上面一行4个像素的值，然后分别赋值给4x4块的4行像素。
x264_pixel_init()
x264_pixel_init()初始化像素值计算相关的汇编函数（包括SAD、SATD、SSD等）。该函数的定义位于common\pixel.c，如下所示。
/**************************************************************************** * x264_pixel_init: ****************************************************************************/ //SAD等和像素计算有关的函数 void x264_pixel_init( int cpu, x264_pixel_function_t *pixf ) { memset( pixf, 0, sizeof(*pixf) ); //初始化2个函数-16x16,16x8 #define INIT2_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_16x16] = x264_pixel_##name2##_16x16##cpu;\ pixf->name1[PIXEL_16x8] = x264_pixel_##name2##_16x8##cpu; //初始化4个函数-(16x16,16x8),8x16,8x8 #define INIT4_NAME( name1, name2, cpu ) \ INIT2_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_8x16] = x264_pixel_##name2##_8x16##cpu;\ pixf->name1[PIXEL_8x8] = x264_pixel_##name2##_8x8##cpu; //初始化5个函数-(16x16,16x8,8x16,8x8),8x4 #define INIT5_NAME( name1, name2, cpu ) \ INIT4_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_8x4] = x264_pixel_##name2##_8x4##cpu; //初始化6个函数-(16x16,16x8,8x16,8x8,8x4),4x8 #define INIT6_NAME( name1, name2, cpu ) \ INIT5_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_4x8] = x264_pixel_##name2##_4x8##cpu; //初始化7个函数-(16x16,16x8,8x16,8x8,8x4,4x8),4x4 #define INIT7_NAME( name1, name2, cpu ) \ INIT6_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_4x4] = x264_pixel_##name2##_4x4##cpu; #define INIT8_NAME( name1, name2, cpu ) \ INIT7_NAME( name1, name2, cpu ) \ pixf->name1[PIXEL_4x16] = x264_pixel_##name2##_4x16##cpu; //重新起个名字 #define INIT2( name, cpu ) INIT2_NAME( name, name, cpu ) #define INIT4( name, cpu ) INIT4_NAME( name, name, cpu ) #define INIT5( name, cpu ) INIT5_NAME( name, name, cpu ) #define INIT6( name, cpu ) INIT6_NAME( name, name, cpu ) #define INIT7( name, cpu ) INIT7_NAME( name, name, cpu ) #define INIT8( name, cpu ) INIT8_NAME( name, name, cpu ) #define INIT_ADS( cpu ) \ pixf->ads[PIXEL_16x16] = x264_pixel_ads4##cpu;\ pixf->ads[PIXEL_16x8] = x264_pixel_ads2##cpu;\ pixf->ads[PIXEL_8x8] = x264_pixel_ads1##cpu; //8个sad函数 INIT8( sad, ); INIT8_NAME( sad_aligned, sad, ); //7个sad函数-一次性计算3次 INIT7( sad_x3, ); //7个sad函数-一次性计算4次 INIT7( sad_x4, ); //8个ssd函数 //ssd可以用来计算PSNR INIT8( ssd, ); //8个satd函数 //satd计算的是经过Hadamard变换后的值 INIT8( satd, ); //8个satd函数-一次性计算3次 INIT7( satd_x3, ); //8个satd函数-一次性计算4次 INIT7( satd_x4, ); INIT4( hadamard_ac, ); INIT_ADS( ); pixf->sa8d[PIXEL_16x16] = x264_pixel_sa8d_16x16; pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8; pixf->var[PIXEL_16x16] = x264_pixel_var_16x16; pixf->var[PIXEL_8x16] = x264_pixel_var_8x16; pixf->var[PIXEL_8x8] = x264_pixel_var_8x8; pixf->var2[PIXEL_8x16] = x264_pixel_var2_8x16; pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8; //计算UV的 pixf->ssd_nv12_core = pixel_ssd_nv12_core; //计算SSIM pixf->ssim_4x4x2_core = ssim_4x4x2_core; pixf->ssim_end4 = ssim_end4; pixf->vsad = pixel_vsad; pixf->asd8 = pixel_asd8; pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4; pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4; pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8; pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8; pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c; pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c; pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c; pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c; pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16; pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16; //后面的初始化基本上都是汇编优化过的函数 #if HIGH_BIT_DEPTH #if HAVE_MMX if( cpu&X264_CPU_MMX2 ) { INIT7( sad, _mmx2 ); INIT7_NAME( sad_aligned, sad, _mmx2 ); INIT7( sad_x3, _mmx2 ); INIT7( sad_x4, _mmx2 ); INIT8( satd, _mmx2 ); INIT7( satd_x3, _mmx2 ); INIT7( satd_x4, _mmx2 ); INIT4( hadamard_ac, _mmx2 ); INIT8( ssd, _mmx2 ); INIT_ADS( _mmx2 ); pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_mmx2; pixf->var[PIXEL_16x16] = x264_pixel_var_16x16_mmx2; pixf->var[PIXEL_8x8] = x264_pixel_var_8x8_mmx2; #if ARCH_X86 pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8_mmx2; pixf->var2[PIXEL_8x16] = x264_pixel_var2_8x16_mmx2; #endif pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_mmx2; pixf->intra_satd_x3_4x4 = x264_intra_satd_x3_4x4_mmx2; pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_mmx2; pixf->intra_sad_x3_8x8c = x264_intra_sad_x3_8x8c_mmx2; pixf->intra_satd_x3_8x8c = x264_intra_satd_x3_8x8c_mmx2; pixf->intra_sad_x3_8x16c = x264_intra_sad_x3_8x16c_mmx2; pixf->intra_satd_x3_8x16c = x264_intra_satd_x3_8x16c_mmx2; pixf->intra_sad_x3_16x16 = x264_intra_sad_x3_16x16_mmx2; pixf->intra_satd_x3_16x16 = x264_intra_satd_x3_16x16_mmx2; } if( cpu&X264_CPU_SSE2 ) { INIT4_NAME( sad_aligned, sad, _sse2_aligned ); INIT5( ssd, _sse2 ); INIT6( satd, _sse2 ); pixf->satd[PIXEL_4x16] = x264_pixel_satd_4x16_sse2; pixf->sa8d[PIXEL_16x16] = x264_pixel_sa8d_16x16_sse2; pixf->sa8d[PIXEL_8x8] = x264_pixel_sa8d_8x8_sse2; #if ARCH_X86_64 pixf->intra_sa8d_x3_8x8 = x264_intra_sa8d_x3_8x8_sse2; pixf->sa8d_satd[PIXEL_16x16] = x264_pixel_sa8d_satd_16x16_sse2; #endif pixf->intra_sad_x3_4x4 = x264_intra_sad_x3_4x4_sse2; pixf->ssd_nv12_core = x264_pixel_ssd_nv12_core_sse2; pixf->ssim_4x4x2_core = x264_pixel_ssim_4x4x2_core_sse2; pixf->ssim_end4 = x264_pixel_ssim_end4_sse2; pixf->var[PIXEL_16x16] = x264_pixel_var_16x16_sse2; pixf->var[PIXEL_8x8] = x264_pixel_var_8x8_sse2; pixf->var2[PIXEL_8x8] = x264_pixel_var2_8x8_sse2; pixf->var2[PIXEL_8x16] = x264_pixel_var2_8x16_sse2; pixf->intra_sad_x3_8x8 = x264_intra_sad_x3_8x8_sse2; } //此处省略大量的X86、ARM等平台的汇编函数初始化代码 }
x264_pixel_init() 的源代码非常的长，主要原因在于它把C语言版本的函数以及各种平台的汇编函数都写到一块了（不知道现在最新的版本是不是还是这样）。 x264_pixel_init()包含了大量和像素计算有关的函数，包括SAD、SATD、SSD、SSIM等等。它的输入参数 x264_pixel_function_t是一个结构体，其中包含了各种像素计算的函数接口。x264_pixel_function_t的定义如下所 示。
typedef struct { x264_pixel_cmp_t sad[8]; x264_pixel_cmp_t ssd[8]; x264_pixel_cmp_t satd[8]; x264_pixel_cmp_t ssim[7]; x264_pixel_cmp_t sa8d[4]; x264_pixel_cmp_t mbcmp[8]; /* either satd or sad for subpel refine and mode decision */ x264_pixel_cmp_t mbcmp_unaligned[8]; /* unaligned mbcmp for subpel */ x264_pixel_cmp_t fpelcmp[8]; /* either satd or sad for fullpel motion search */ x264_pixel_cmp_x3_t fpelcmp_x3[7]; x264_pixel_cmp_x4_t fpelcmp_x4[7]; x264_pixel_cmp_t sad_aligned[8]; /* Aligned SAD for mbcmp */ int (*vsad)( pixel *, intptr_t, int ); int (*asd8)( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int height ); uint64_t (*sa8d_satd[1])( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2 ); uint64_t (*var[4])( pixel *pix, intptr_t stride ); int (*var2[4])( pixel *pix1, intptr_t stride1, pixel *pix2, intptr_t stride2, int *ssd ); uint64_t (*hadamard_ac[4])( pixel *pix, intptr_t stride ); void (*ssd_nv12_core)( pixel *pixuv1, intptr_t stride1, pixel *pixuv2, intptr_t stride2, int width, int height, uint64_t *ssd_u, uint64_t *ssd_v ); void (*ssim_4x4x2_core)( const pixel *pix1, intptr_t stride1, const pixel *pix2, intptr_t stride2, int sums[2][4] ); float (*ssim_end4)( int sum0[5][4], int sum1[5][4], int width ); /* multiple parallel calls to cmp. */ x264_pixel_cmp_x3_t sad_x3[7]; x264_pixel_cmp_x4_t sad_x4[7]; x264_pixel_cmp_x3_t satd_x3[7]; x264_pixel_cmp_x4_t satd_x4[7]; /* abs-diff-sum for successive elimination. * may round width up to a multiple of 16. */ int (*ads[7])( int enc_dc[4], uint16_t *sums, int delta, uint16_t *cost_mvx, int16_t *mvs, int width, int thresh ); /* calculate satd or sad of V, H, and DC modes. */ void (*intra_mbcmp_x3_16x16)( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_satd_x3_16x16) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_sad_x3_16x16) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_mbcmp_x3_4x4) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_satd_x3_4x4) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_sad_x3_4x4) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_mbcmp_x3_chroma)( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_satd_x3_chroma) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_sad_x3_chroma) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_mbcmp_x3_8x16c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_satd_x3_8x16c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_sad_x3_8x16c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_mbcmp_x3_8x8c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_satd_x3_8x8c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_sad_x3_8x8c) ( pixel *fenc, pixel *fdec, int res[3] ); void (*intra_mbcmp_x3_8x8) ( pixel *fenc, pixel edge[36], int res[3] ); void (*intra_sa8d_x3_8x8) ( pixel *fenc, pixel edge[36], int res[3] ); void (*intra_sad_x3_8x8) ( pixel *fenc, pixel edge[36], int res[3] ); /* find minimum satd or sad of all modes, and set fdec. * may be NULL, in which case just use pred+satd instead. */ int (*intra_mbcmp_x9_4x4)( pixel *fenc, pixel *fdec, uint16_t *bitcosts ); int (*intra_satd_x9_4x4) ( pixel *fenc, pixel *fdec, uint16_t *bitcosts ); int (*intra_sad_x9_4x4) ( pixel *fenc, pixel *fdec, uint16_t *bitcosts ); int (*intra_mbcmp_x9_8x8)( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds ); int (*intra_sa8d_x9_8x8) ( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds ); int (*intra_sad_x9_8x8) ( pixel *fenc, pixel *fdec, pixel edge[36], uint16_t *bitcosts, uint16_t *satds ); } x264_pixel_function_t;
在x264_pixel_init()中定义了好几个宏，用于给x264_pixel_function_t结构体中的函数接口赋值。例如"INIT8( sad, )"用于给x264_pixel_function_t中的sad[8]赋值。该宏展开后的代码如下。
pixf->sad[PIXEL_16x16] = x264_pixel_sad_16x16; pixf->sad[PIXEL_16x8] = x264_pixel_sad_16x8; pixf->sad[PIXEL_8x16] = x264_pixel_sad_8x16; pixf->sad[PIXEL_8x8] = x264_pixel_sad_8x8; pixf->sad[PIXEL_8x4] = x264_pixel_sad_8x4; pixf->sad[PIXEL_4x8] = x264_pixel_sad_4x8; pixf->sad[PIXEL_4x4] = x264_pixel_sad_4x4; pixf->sad[PIXEL_4x16] = x264_pixel_sad_4x16;
"INIT8( ssd, )" 用于给x264_pixel_function_t中的ssd[8]赋值。该宏展开后的代码如下。
pixf->ssd[PIXEL_16x16] = x264_pixel_ssd_16x16; pixf->ssd[PIXEL_16x8] = x264_pixel_ssd_16x8; pixf->ssd[PIXEL_8x16] = x264_pixel_ssd_8x16; pixf->ssd[PIXEL_8x8] = x264_pixel_ssd_8x8; pixf->ssd[PIXEL_8x4] = x264_pixel_ssd_8x4; pixf->ssd[PIXEL_4x8] = x264_pixel_ssd_4x8; pixf->ssd[PIXEL_4x4] = x264_pixel_ssd_4x4; pixf->ssd[PIXEL_4x16] = x264_pixel_ssd_4x16;
"INIT8( satd, )" 用于给x264_pixel_function_t中的satd[8]赋值。该宏展开后的代码如下。
pixf->satd[PIXEL_16x16] = x264_pixel_satd_16x16; pixf->satd[PIXEL_16x8] = x264_pixel_satd_16x8; pixf->satd[PIXEL_8x16] = x264_pixel_satd_8x16; pixf->satd[PIXEL_8x8] = x264_pixel_satd_8x8; pixf->satd[PIXEL_8x4] = x264_pixel_satd_8x4; pixf->satd[PIXEL_4x8] = x264_pixel_satd_4x8; pixf->satd[PIXEL_4x4] = x264_pixel_satd_4x4; pixf->satd[PIXEL_4x16] = x264_pixel_satd_4x16;
下 文打算分别记录SAD、SSD和SATD计算的函数x264_pixel_sad_4x4()，x264_pixel_ssd_4x4()，和 x264_pixel_satd_4x4()。此外再记录一个一次性"批量"计算4个点的函数x264_pixel_sad_x4_4x4()。
简单记录几个像素计算中的概念。SAD和SATD主要用于帧内预测模式以及帧间预测模式的判断。有关SAD、SATD、SSD的定义如下：
SAD（Sum of Absolute Difference）也可以称为SAE（Sum of Absolute Error），即绝对误差和。它的计算方法就是求出两个像素块对应像素点的差值，将这些差值分别求绝对值之后再进行累加。
SATD（Sum of Absolute Transformed Difference）即Hadamard变换后再绝对值求和。它和SAD的区别在于多了一个"变换"。
SSD（Sum of Squared Difference）也可以称为SSE（Sum of Squared Error），即差值的平方和。它和SAD的区别在于多了一个"平方"。
H.264 中使用SAD和SATD进行宏块预测模式的判断。早期的编码器使用SAD进行计算，近期的编码器多使用SATD进行计算。为什么使用SATD而不使用 SAD呢？关键原因在于编码之后码流的大小是和图像块DCT变换后频域信息紧密相关的，而和变换前的时域信息关联性小一些。SAD只能反应时域信 息；SATD却可以反映频域信息，而且计算复杂度也低于DCT变换，因此是比较合适的模式选择的依据。
使 用SAD进行模式选择的示例如下所示。下面这张图代表了一个普通的Intra16x16的宏块的像素。它的下方包含了使用 Vertical，Horizontal，DC和Plane四种帧内预测模式预测的像素。通过计算可以得到这几种预测像素和原始像素之间的 SAD（SAE）分别为3985，5097，4991，2539。由于Plane模式的SAD取值最小，由此可以断定Plane模式对于这个宏块来说是最 好的帧内预测模式。
x264_pixel_sad_4x4()
x264_pixel_sad_4x4()用于计算4x4块的SAD。该函数的定义位于common\pixel.c，如下所示。
static int x264_pixel_sad_4x4( pixel *pix1, intptr_t i_stride_pix1, pixel *pix2, intptr_t i_stride_pix2 ) { int i_sum = 0; for( int y = 0; y < 4; y++ ) //4个像素 { for( int x = 0; x < 4; x++ ) //4个像素 { i_sum += abs( pix1[x] - pix2[x] );//相减之后求绝对值，然后累加 } pix1 += i_stride_pix1; pix2 += i_stride_pix2; } return i_sum; }
可以看出x264_pixel_sad_4x4()将两个4x4图像块对应点相减之后，调用abs()求出绝对值，然后累加到i_sum变量上。
x264_pixel_sad_x4_4x4()
x264_pixel_sad_4x4()用于计算4个4x4块的SAD。该函数的定义位于common\pixel.c，如下所示。
static void x264_pixel_sad_x4_4x4( pixel *fenc, pixel *pix0, pixel *pix1,pixel *pix2, pixel *pix3, intptr_t i_stride, int scores[4] ) { scores[0] = x264_pixel_sad_4x4( fenc, 16, pix0, i_stride ); scores[1] = x264_pixel_sad_4x4( fenc, 16, pix1, i_stride ); scores[2] = x264_pixel_sad_4x4( fenc, 16, pix2, i_stride ); scores[3] = x264_pixel_sad_4x4( fenc, 16, pix3, i_stride ); }
可以看出，x264_pixel_sad_4x4()计算了起始点在pix0，pix1，pix2，pix3四个4x4的图像块和fenc之间的SAD，并将结果存储于scores[4]数组中。
x264_pixel_ssd_4x4()
x264_pixel_ssd_4x4()用于计算4x4块的SSD。该函数的定义位于common\pixel.c，如下所示。
static int x264_pixel_ssd_4x4( pixel *pix1, intptr_t i_stride_pix1, pixel *pix2, intptr_t i_stride_pix2 ) { int i_sum = 0; for( int y = 0; y < 4; y++ ) //4个像素 { for( int x = 0; x < 4; x++ ) //4个像素 { int d = pix1[x] - pix2[x]; //相减 i_sum += d*d; //平方之后，累加 } pix1 += i_stride_pix1; pix2 += i_stride_pix2; } return i_sum; }
可以看出x264_pixel_ssd_4x4()将两个4x4图像块对应点相减之后，取了平方值，然后累加到i_sum变量上。
x264_pixel_satd_4x4()
x264_pixel_satd_4x4()用于计算4x4块的SATD。该函数的定义位于common\pixel.c，如下所示。
//SAD（Sum of Absolute Difference）=SAE（Sum of Absolute Error)即绝对误差和 //SATD（Sum of Absolute Transformed Difference）即hadamard变换后再绝对值求和 // //为什么帧内模式选择要用SATD？ //SAD即绝对误差和，仅反映残差时域差异，影响PSNR值，不能有效反映码流的大小。 //SATD即将残差经哈德曼变换的4x4块的预测残差绝对值总和，可以将其看作简单的时频变换，其值在一定程度上可以反映生成码流的大小。 //4x4的SATD static NOINLINE int x264_pixel_satd_4x4( pixel *pix1, intptr_t i_pix1, pixel *pix2, intptr_t i_pix2 ) { sum2_t tmp[4][2]; sum2_t a0, a1, a2, a3, b0, b1; sum2_t sum = 0; for( int i = 0; i < 4; i++, pix1 += i_pix1, pix2 += i_pix2 ) { a0 = pix1[0] - pix2[0]; a1 = pix1[1] - pix2[1]; b0 = (a0+a1) + ((a0-a1)<<BITS_PER_SUM); a2 = pix1[2] - pix2[2]; a3 = pix1[3] - pix2[3]; b1 = (a2+a3) + ((a2-a3)<<BITS_PER_SUM); tmp[i][0] = b0 + b1; tmp[i][1] = b0 - b1; } for( int i = 0; i < 2; i++ ) { HADAMARD4( a0, a1, a2, a3, tmp[0][i], tmp[1][i], tmp[2][i], tmp[3][i] ); a0 = abs2(a0) + abs2(a1) + abs2(a2) + abs2(a3); sum += ((sum_t)a0) + (a0>>BITS_PER_SUM); } return sum >> 1; }
有 关x264_pixel_satd_4x4()中的Hadamard变换在下面的DCT变换中再进行分析。可以看出该函数调用了一个宏 HADAMARD4()用于Hadamard变换的计算，并最终将两个像素块Hadamard变换后对应元素求差的绝对值之后，累加到sum变量上。
x264_dct_init()
x264_dct_init()用于初始化DCT变换和DCT反变换相关的汇编函数。该函数的定义位于common\dct.c，如下所示。
/**************************************************************************** * x264_dct_init: ****************************************************************************/ void x264_dct_init( int cpu, x264_dct_function_t *dctf ) { //C语言版本 //4x4DCT变换 dctf->sub4x4_dct = sub4x4_dct; dctf->add4x4_idct = add4x4_idct; //8x8块：分解成4个4x4DCT变换，调用4次sub4x4_dct() dctf->sub8x8_dct = sub8x8_dct; dctf->sub8x8_dct_dc = sub8x8_dct_dc; dctf->add8x8_idct = add8x8_idct; dctf->add8x8_idct_dc = add8x8_idct_dc; dctf->sub8x16_dct_dc = sub8x16_dct_dc; //16x16块：分解成4个8x8块，调用4次sub8x8_dct() //实际上每个sub8x8_dct()又分解成4个4x4DCT变换，调用4次sub4x4_dct() dctf->sub16x16_dct = sub16x16_dct; dctf->add16x16_idct = add16x16_idct; dctf->add16x16_idct_dc = add16x16_idct_dc; //8x8DCT，注意：后缀是_dct8 dctf->sub8x8_dct8 = sub8x8_dct8; dctf->add8x8_idct8 = add8x8_idct8; dctf->sub16x16_dct8 = sub16x16_dct8; dctf->add16x16_idct8 = add16x16_idct8; //Hadamard变换 dctf->dct4x4dc = dct4x4dc; dctf->idct4x4dc = idct4x4dc; dctf->dct2x4dc = dct2x4dc; #if HIGH_BIT_DEPTH #if HAVE_MMX if( cpu&X264_CPU_MMX ) { dctf->sub4x4_dct = x264_sub4x4_dct_mmx; dctf->sub8x8_dct = x264_sub8x8_dct_mmx; dctf->sub16x16_dct = x264_sub16x16_dct_mmx; } if( cpu&X264_CPU_SSE2 ) { dctf->add4x4_idct = x264_add4x4_idct_sse2; dctf->dct4x4dc = x264_dct4x4dc_sse2; dctf->idct4x4dc = x264_idct4x4dc_sse2; dctf->sub8x8_dct8 = x264_sub8x8_dct8_sse2; dctf->sub16x16_dct8 = x264_sub16x16_dct8_sse2; dctf->add8x8_idct = x264_add8x8_idct_sse2; dctf->add16x16_idct = x264_add16x16_idct_sse2; dctf->add8x8_idct8 = x264_add8x8_idct8_sse2; dctf->add16x16_idct8 = x264_add16x16_idct8_sse2; dctf->sub8x8_dct_dc = x264_sub8x8_dct_dc_sse2; dctf->add8x8_idct_dc = x264_add8x8_idct_dc_sse2; dctf->sub8x16_dct_dc = x264_sub8x16_dct_dc_sse2; dctf->add16x16_idct_dc= x264_add16x16_idct_dc_sse2; } if( cpu&X264_CPU_SSE4 ) { dctf->sub8x8_dct8 = x264_sub8x8_dct8_sse4; dctf->sub16x16_dct8 = x264_sub16x16_dct8_sse4; } if( cpu&X264_CPU_AVX ) { dctf->add4x4_idct = x264_add4x4_idct_avx; dctf->dct4x4dc = x264_dct4x4dc_avx; dctf->idct4x4dc = x264_idct4x4dc_avx; dctf->sub8x8_dct8 = x264_sub8x8_dct8_avx; dctf->sub16x16_dct8 = x264_sub16x16_dct8_avx; dctf->add8x8_idct = x264_add8x8_idct_avx; dctf->add16x16_idct = x264_add16x16_idct_avx; dctf->add8x8_idct8 = x264_add8x8_idct8_avx; dctf->add16x16_idct8 = x264_add16x16_idct8_avx; dctf->add8x8_idct_dc = x264_add8x8_idct_dc_avx; dctf->sub8x16_dct_dc = x264_sub8x16_dct_dc_avx; dctf->add16x16_idct_dc= x264_add16x16_idct_dc_avx; } #endif // HAVE_MMX #else // !HIGH_BIT_DEPTH //MMX版本 #if HAVE_MMX if( cpu&X264_CPU_MMX ) { dctf->sub4x4_dct = x264_sub4x4_dct_mmx; dctf->add4x4_idct = x264_add4x4_idct_mmx; dctf->idct4x4dc = x264_idct4x4dc_mmx; dctf->sub8x8_dct_dc = x264_sub8x8_dct_dc_mmx2; //此处省略大量的X86、ARM等平台的汇编函数初始化代码 }
从源代码可以看出，x264_dct_init()初始化了一系列的DCT变换的函数，这些DCT函数名称有如下规律：
（1）DCT函数名称前面有"sub"，代表对两块像素相减得到残差之后，再进行DCT变换。
（2）DCT反变换函数名称前面有"add"，代表将DCT反变换之后的残差数据叠加到预测数据上。
（3）以"dct8"为结尾的函数使用了8x8DCT，其余函数是用的都是4x4DCT。
x264_dct_init()的输入参数x264_dct_function_t是一个结构体，其中包含了各种DCT函数的接口。x264_dct_function_t的定义如下所示。
typedef struct { // pix1 stride = FENC_STRIDE // pix2 stride = FDEC_STRIDE // p_dst stride = FDEC_STRIDE void (*sub4x4_dct) ( dctcoef dct[16], pixel *pix1, pixel *pix2 ); void (*add4x4_idct) ( pixel *p_dst, dctcoef dct[16] ); void (*sub8x8_dct) ( dctcoef dct[4][16], pixel *pix1, pixel *pix2 ); void (*sub8x8_dct_dc)( dctcoef dct[4], pixel *pix1, pixel *pix2 ); void (*add8x8_idct) ( pixel *p_dst, dctcoef dct[4][16] ); void (*add8x8_idct_dc) ( pixel *p_dst, dctcoef dct[4] ); void (*sub8x16_dct_dc)( dctcoef dct[8], pixel *pix1, pixel *pix2 ); void (*sub16x16_dct) ( dctcoef dct[16][16], pixel *pix1, pixel *pix2 ); void (*add16x16_idct)( pixel *p_dst, dctcoef dct[16][16] ); void (*add16x16_idct_dc) ( pixel *p_dst, dctcoef dct[16] ); void (*sub8x8_dct8) ( dctcoef dct[64], pixel *pix1, pixel *pix2 ); void (*add8x8_idct8) ( pixel *p_dst, dctcoef dct[64] ); void (*sub16x16_dct8) ( dctcoef dct[4][64], pixel *pix1, pixel *pix2 ); void (*add16x16_idct8)( pixel *p_dst, dctcoef dct[4][64] ); void (*dct4x4dc) ( dctcoef d[16] ); void (*idct4x4dc)( dctcoef d[16] ); void (*dct2x4dc)( dctcoef dct[8], dctcoef dct4x4[8][16] ); } x264_dct_function_t;
x264_dct_init() 的工作就是对x264_dct_function_t中的函数指针进行赋值。由于DCT函数很多，不便于一一研究，下文仅举例分析几个典型的4x4DCT 函数：4x4DCT变换函数sub4x4_dct()，4x4IDCT变换函数add4x4_idct()，8x8块的4x4DCT变换函数 sub8x8_dct()，16x16块的4x4DCT变换函数sub16x16_dct()，4x4Hadamard变换函数dct4x4dc()。
简 单记录一下DCT相关的知识。DCT变换的核心理念就是把图像的低频信息（对应大面积平坦区域）变换到系数矩阵的左上角，而把高频信息变换到系数矩阵的右 下角，这样就可以在压缩的时候（量化）去除掉人眼不敏感的高频信息（位于矩阵右下角的系数）从而达到压缩数据的目的。二维8x8DCT变换常见的示意图如 下所示。
早 期的DCT变换都使用了8x8的矩阵（变换系数为小数）。在H.264标准中新提出了一种4x4的矩阵。这种4x4 DCT变换的系数都是整数，一方面提高了运算的准确性，一方面也利于代码的优化。4x4整数DCT变换的示意图如下所示（作为对比，右侧为4x4块的 Hadamard变换的示意图）。
4x4整数DCT变换的公式如下所示。
对该公式中的矩阵乘法可以转换为2次一维DCT变换：首先对4x4块中的每行像素进行一维DCT变换，然后再对4x4块中的每列像素进行一维DCT变换。而一维的DCT变换是可以改造成为蝶形快速算法的，如下所示。
同理，DCT反变换就是DCT变换的逆变换。DCT反变换的公式如下所示。
同理，DCT反变换的矩阵乘法也可以改造成为2次一维IDCT变换：首先对4x4块中的每行像素进行一维IDCT变换，然后再对4x4块中的每列像素进行一维IDCT变换。而一维的IDCT变换也可以改造成为蝶形快速算法，如下所示。
除了4x4DCT变换之外，新版本的H.264标准中还引入了一种8x8DCT。目前针对这种8x8DCT我还没有做研究，暂时不做记录。
sub4x4_dct()
sub4x4_dct()可以将两块4x4的图像相减求残差后，进行DCT变换。该函数的定义位于common\dct.c，如下所示。
/* * 求残差用 * 注意求的是一个"方块"形像素 * * 参数的含义如下： * diff：输出的残差数据 * i_size：方块的大小 * pix1：输入数据1 * i_pix1：输入数据1一行像素大小（stride） * pix2：输入数据2 * i_pix2：输入数据2一行像素大小（stride） * */ static inline void pixel_sub_wxh( dctcoef *diff, int i_size, pixel *pix1, int i_pix1, pixel *pix2, int i_pix2 ) { for( int y = 0; y < i_size; y++ ) { for( int x = 0; x < i_size; x++ ) diff[x + y*i_size] = pix1[x] - pix2[x];//求残差 pix1 += i_pix1;//前进到下一行 pix2 += i_pix2; } } //4x4DCT变换 //注意首先获取pix1和pix2两块数据的残差，然后再进行变换 //返回dct[16] static void sub4x4_dct( dctcoef dct[16], pixel *pix1, pixel *pix2 ) { dctcoef d[16]; dctcoef tmp[16]; //获取残差数据，存入d[16] //pix1一般为编码帧（enc） //pix2一般为重建帧（dec） pixel_sub_wxh( d, 4, pix1, FENC_STRIDE, pix2, FDEC_STRIDE ); //处理残差d[16] //蝶形算法：横向4个像素 for( int i = 0; i < 4; i++ ) { int s03 = d[i*4+0] + d[i*4+3]; int s12 = d[i*4+1] + d[i*4+2]; int d03 = d[i*4+0] - d[i*4+3]; int d12 = d[i*4+1] - d[i*4+2]; tmp[0*4+i] = s03 + s12; tmp[1*4+i] = 2*d03 + d12; tmp[2*4+i] = s03 - s12; tmp[3*4+i] = d03 - 2*d12; } //蝶形算法：纵向 for( int i = 0; i < 4; i++ ) { int s03 = tmp[i*4+0] + tmp[i*4+3]; int s12 = tmp[i*4+1] + tmp[i*4+2]; int d03 = tmp[i*4+0] - tmp[i*4+3]; int d12 = tmp[i*4+1] - tmp[i*4+2]; dct[i*4+0] = s03 + s12; dct[i*4+1] = 2*d03 + d12; dct[i*4+2] = s03 - s12; dct[i*4+3] = d03 - 2*d12; } }
从源代码可以看出，sub4x4_dct()首先调用pixel_sub_wxh()求出两个输入图像块的残差，然后使用蝶形快速算法计算残差图像的DCT系数。
add4x4_idct()
add4x4_idct()可以将残差数据进行DCT反变换，并将变换后得到的残差像素数据叠加到预测数据上。该函数的定义位于common\dct.c，如下所示。
//4x4DCT反变换（"add"代表叠加到已有的像素上） static void add4x4_idct( pixel *p_dst, dctcoef dct[16] ) { dctcoef d[16]; dctcoef tmp[16]; for( int i = 0; i < 4; i++ ) { int s02 = dct[0*4+i] + dct[2*4+i]; int d02 = dct[0*4+i] - dct[2*4+i]; int s13 = dct[1*4+i] + (dct[3*4+i]>>1); int d13 = (dct[1*4+i]>>1) - dct[3*4+i]; tmp[i*4+0] = s02 + s13; tmp[i*4+1] = d02 + d13; tmp[i*4+2] = d02 - d13; tmp[i*4+3] = s02 - s13; } for( int i = 0; i < 4; i++ ) { int s02 = tmp[0*4+i] + tmp[2*4+i]; int d02 = tmp[0*4+i] - tmp[2*4+i]; int s13 = tmp[1*4+i] + (tmp[3*4+i]>>1); int d13 = (tmp[1*4+i]>>1) - tmp[3*4+i]; d[0*4+i] = ( s02 + s13 + 32 ) >> 6; d[1*4+i] = ( d02 + d13 + 32 ) >> 6; d[2*4+i] = ( d02 - d13 + 32 ) >> 6; d[3*4+i] = ( s02 - s13 + 32 ) >> 6; } for( int y = 0; y < 4; y++ ) { for( int x = 0; x < 4; x++ ) p_dst[x] = x264_clip_pixel( p_dst[x] + d[y*4+x] ); p_dst += FDEC_STRIDE; } }
从源代码可以看出，add4x4_idct()首先采用快速蝶形算法对DCT系数进行DCT反变换后得到残差像素数据，然后再将残差数据叠加到p_dst指向的像素上。需要注意这里是"叠加"而不是"赋值"。
sub8x8_dct()
sub8x8_dct()可以将两块8x8的图像相减求残差后，进行4x4DCT变换。该函数的定义位于common\dct.c，如下所示。
//8x8块：分解成4个4x4DCT变换，调用4次sub4x4_dct() //返回dct[4][16] static void sub8x8_dct( dctcoef dct[4][16], pixel *pix1, pixel *pix2 ) { /* * 8x8 宏块被划分为4个4x4子块 * * +---+---+ * | 0 | 1 | * +---+---+ * | 2 | 3 | * +---+---+ * */ sub4x4_dct( dct[0], &pix1[0], &pix2[0] ); sub4x4_dct( dct[1], &pix1[4], &pix2[4] ); sub4x4_dct( dct[2], &pix1[4*FENC_STRIDE+0], &pix2[4*FDEC_STRIDE+0] ); sub4x4_dct( dct[3], &pix1[4*FENC_STRIDE+4], &pix2[4*FDEC_STRIDE+4] ); }
从源代码可以看出， sub8x8_dct()将8x8的图像块分成4个4x4的图像块，分别调用了sub4x4_dct()。
sub16x16_dct()
sub16x16_dct()可以将两块16x16的图像相减求残差后，进行4x4DCT变换。该函数的定义位于common\dct.c，如下所示。
//16x16块：分解成4个8x8的块做DCT变换，调用4次sub8x8_dct() //返回dct[16][16] static void sub16x16_dct( dctcoef dct[16][16], pixel *pix1, pixel *pix2 ) { /* * 16x16 宏块被划分为4个8x8子块 * * +--------+--------+ * | | | * | 0 | 1 | * | | | * +--------+--------+ * | | | * | 2 | 3 | * | | | * +--------+--------+ * */ sub8x8_dct( &dct[ 0], &pix1[0], &pix2[0] ); //0 sub8x8_dct( &dct[ 4], &pix1[8], &pix2[8] ); //1 sub8x8_dct( &dct[ 8], &pix1[8*FENC_STRIDE+0], &pix2[8*FDEC_STRIDE+0] ); //2 sub8x8_dct( &dct[12], &pix1[8*FENC_STRIDE+8], &pix2[8*FDEC_STRIDE+8] ); //3 }
从 源代码可以看出， sub8x8_dct()将16x16的图像块分成4个8x8的图像块，分别调用了sub8x8_dct()。而sub8x8_dct()实际上又调用了 4次sub4x4_dct()。所以可以得知，不论sub16x16_dct()，sub8x8_dct()还是sub4x4_dct()，本质都是进行 4x4DCT。
dct4x4dc()
dct4x4dc()可以将输入的4x4图像块进行Hadamard变换。该函数的定义位于common\dct.c，如下所示。
//Hadamard变换 static void dct4x4dc( dctcoef d[16] ) { dctcoef tmp[16]; //蝶形算法：横向的4个像素 for( int i = 0; i < 4; i++ ) { int s01 = d[i*4+0] + d[i*4+1]; int d01 = d[i*4+0] - d[i*4+1]; int s23 = d[i*4+2] + d[i*4+3]; int d23 = d[i*4+2] - d[i*4+3]; tmp[0*4+i] = s01 + s23; tmp[1*4+i] = s01 - s23; tmp[2*4+i] = d01 - d23; tmp[3*4+i] = d01 + d23; } //蝶形算法：纵向 for( int i = 0; i < 4; i++ ) { int s01 = tmp[i*4+0] + tmp[i*4+1]; int d01 = tmp[i*4+0] - tmp[i*4+1]; int s23 = tmp[i*4+2] + tmp[i*4+3]; int d23 = tmp[i*4+2] - tmp[i*4+3]; d[i*4+0] = ( s01 + s23 + 1 ) >> 1; d[i*4+1] = ( s01 - s23 + 1 ) >> 1; d[i*4+2] = ( d01 - d23 + 1 ) >> 1; d[i*4+3] = ( d01 + d23 + 1 ) >> 1; } }
从源代码可以看出，dct4x4dc()实现了Hadamard快速蝶形算法。
x264_mc_init()
x264_mc_init()用于初始化运动补偿相关的汇编函数。该函数的定义位于common\mc.c，如下所示。
//运动补偿 void x264_mc_init( int cpu, x264_mc_functions_t *pf, int cpu_independent ) { //亮度运动补偿 pf->mc_luma = mc_luma; //获得匹配块 pf->get_ref = get_ref; pf->mc_chroma = mc_chroma; //求平均 pf->avg[PIXEL_16x16]= pixel_avg_16x16; pf->avg[PIXEL_16x8] = pixel_avg_16x8; pf->avg[PIXEL_8x16] = pixel_avg_8x16; pf->avg[PIXEL_8x8] = pixel_avg_8x8; pf->avg[PIXEL_8x4] = pixel_avg_8x4; pf->avg[PIXEL_4x16] = pixel_avg_4x16; pf->avg[PIXEL_4x8] = pixel_avg_4x8; pf->avg[PIXEL_4x4] = pixel_avg_4x4; pf->avg[PIXEL_4x2] = pixel_avg_4x2; pf->avg[PIXEL_2x8] = pixel_avg_2x8; pf->avg[PIXEL_2x4] = pixel_avg_2x4; pf->avg[PIXEL_2x2] = pixel_avg_2x2; //加权相关 pf->weight = x264_mc_weight_wtab; pf->offsetadd = x264_mc_weight_wtab; pf->offsetsub = x264_mc_weight_wtab; pf->weight_cache = x264_weight_cache; //赋值-只包含了方形的 pf->copy_16x16_unaligned = mc_copy_w16; pf->copy[PIXEL_16x16] = mc_copy_w16; pf->copy[PIXEL_8x8] = mc_copy_w8; pf->copy[PIXEL_4x4] = mc_copy_w4; pf->store_interleave_chroma = store_interleave_chroma; pf->load_deinterleave_chroma_fenc = load_deinterleave_chroma_fenc; pf->load_deinterleave_chroma_fdec = load_deinterleave_chroma_fdec; //拷贝像素-不论像素块大小 pf->plane_copy = x264_plane_copy_c; pf->plane_copy_interleave = x264_plane_copy_interleave_c; pf->plane_copy_deinterleave = x264_plane_copy_deinterleave_c; pf->plane_copy_deinterleave_rgb = x264_plane_copy_deinterleave_rgb_c; pf->plane_copy_deinterleave_v210 = x264_plane_copy_deinterleave_v210_c; //关键：半像素内插 pf->hpel_filter = hpel_filter; //几个空函数 pf->prefetch_fenc_420 = prefetch_fenc_null; pf->prefetch_fenc_422 = prefetch_fenc_null; pf->prefetch_ref = prefetch_ref_null; pf->memcpy_aligned = memcpy; pf->memzero_aligned = memzero_aligned; //降低分辨率-线性内插（不是半像素内插） pf->frame_init_lowres_core = frame_init_lowres_core; pf->integral_init4h = integral_init4h; pf->integral_init8h = integral_init8h; pf->integral_init4v = integral_init4v; pf->integral_init8v = integral_init8v; pf->mbtree_propagate_cost = mbtree_propagate_cost; pf->mbtree_propagate_list = mbtree_propagate_list; //各种汇编版本 #if HAVE_MMX x264_mc_init_mmx( cpu, pf ); #endif #if HAVE_ALTIVEC if( cpu&X264_CPU_ALTIVEC ) x264_mc_altivec_init( pf ); #endif #if HAVE_ARMV6 x264_mc_init_arm( cpu, pf ); #endif #if ARCH_AARCH64 x264_mc_init_aarch64( cpu, pf ); #endif if( cpu_independent ) { pf->mbtree_propagate_cost = mbtree_propagate_cost; pf->mbtree_propagate_list = mbtree_propagate_list; } }
从 源代码可以看出，x264_mc_init()中包含了大量的像素内插、拷贝、求平均的函数。这些函数都是用于在H.264编码过程中进行运动估计和运动 补偿的。x264_mc_init()的参数x264_mc_functions_t是一个结构体，其中包含了运动补偿函数相关的函数接口。 x264_mc_functions_t的定义如下。
typedef struct { void (*mc_luma)( pixel *dst, intptr_t i_dst, pixel **src, intptr_t i_src, int mvx, int mvy, int i_width, int i_height, const x264_weight_t *weight ); /* may round up the dimensions if they're not a power of 2 */ pixel* (*get_ref)( pixel *dst, intptr_t *i_dst, pixel **src, intptr_t i_src, int mvx, int mvy, int i_width, int i_height, const x264_weight_t *weight ); /* mc_chroma may write up to 2 bytes of garbage to the right of dst, * so it must be run from left to right. */ void (*mc_chroma)( pixel *dstu, pixel *dstv, intptr_t i_dst, pixel *src, intptr_t i_src, int mvx, int mvy, int i_width, int i_height ); void (*avg[12])( pixel *dst, intptr_t dst_stride, pixel *src1, intptr_t src1_stride, pixel *src2, intptr_t src2_stride, int i_weight ); /* only 16x16, 8x8, and 4x4 defined */ void (*copy[7])( pixel *dst, intptr_t dst_stride, pixel *src, intptr_t src_stride, int i_height ); void (*copy_16x16_unaligned)( pixel *dst, intptr_t dst_stride, pixel *src, intptr_t src_stride, int i_height ); void (*store_interleave_chroma)( pixel *dst, intptr_t i_dst, pixel *srcu, pixel *srcv, int height ); void (*load_deinterleave_chroma_fenc)( pixel *dst, pixel *src, intptr_t i_src, int height ); void (*load_deinterleave_chroma_fdec)( pixel *dst, pixel *src, intptr_t i_src, int height ); void (*plane_copy)( pixel *dst, intptr_t i_dst, pixel *src, intptr_t i_src, int w, int h ); void (*plane_copy_interleave)( pixel *dst, intptr_t i_dst, pixel *srcu, intptr_t i_srcu, pixel *srcv, intptr_t i_srcv, int w, int h ); /* may write up to 15 pixels off the end of each plane */ void (*plane_copy_deinterleave)( pixel *dstu, intptr_t i_dstu, pixel *dstv, intptr_t i_dstv, pixel *src, intptr_t i_src, int w, int h ); void (*plane_copy_deinterleave_rgb)( pixel *dsta, intptr_t i_dsta, pixel *dstb, intptr_t i_dstb, pixel *dstc, intptr_t i_dstc, pixel *src, intptr_t i_src, int pw, int w, int h ); void (*plane_copy_deinterleave_v210)( pixel *dsty, intptr_t i_dsty, pixel *dstc, intptr_t i_dstc, uint32_t *src, intptr_t i_src, int w, int h ); void (*hpel_filter)( pixel *dsth, pixel *dstv, pixel *dstc, pixel *src, intptr_t i_stride, int i_width, int i_height, int16_t *buf ); /* prefetch the next few macroblocks of fenc or fdec */ void (*prefetch_fenc) ( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); void (*prefetch_fenc_420)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); void (*prefetch_fenc_422)( pixel *pix_y, intptr_t stride_y, pixel *pix_uv, intptr_t stride_uv, int mb_x ); /* prefetch the next few macroblocks of a hpel reference frame */ void (*prefetch_ref)( pixel *pix, intptr_t stride, int parity ); void *(*memcpy_aligned)( void *dst, const void *src, size_t n ); void (*memzero_aligned)( void *dst, size_t n ); /* successive elimination prefilter */ void (*integral_init4h)( uint16_t *sum, pixel *pix, intptr_t stride ); void (*integral_init8h)( uint16_t *sum, pixel *pix, intptr_t stride ); void (*integral_init4v)( uint16_t *sum8, uint16_t *sum4, intptr_t stride ); void (*integral_init8v)( uint16_t *sum8, intptr_t stride ); void (*frame_init_lowres_core)( pixel *src0, pixel *dst0, pixel *dsth, pixel *dstv, pixel *dstc, intptr_t src_stride, intptr_t dst_stride, int width, int height ); weight_fn_t *weight; weight_fn_t *offsetadd; weight_fn_t *offsetsub; void (*weight_cache)( x264_t *, x264_weight_t * ); void (*mbtree_propagate_cost)( int16_t *dst, uint16_t *propagate_in, uint16_t *intra_costs, uint16_t *inter_costs, uint16_t *inv_qscales, float *fps_factor, int len ); void (*mbtree_propagate_list)( x264_t *h, uint16_t *ref_costs, int16_t (*mvs)[2], int16_t *propagate_amount, uint16_t *lowres_costs, int bipred_weight, int mb_y, int len, int list ); } x264_mc_functions_t;
x264_mc_init() 的工作就是对x264_mc_functions_t中的函数指针进行赋值。由于运动估计和运动补偿在x264中属于相对复杂的环节，其中许多函数的作用 很难三言两语表述出来，因此只举一个相对简单的例子——半像素内插函数hpel_filter()。
简 单记录一下半像素插值的知识。《H.264标准》中规定，运动估计为1/4像素精度。因此在H.264编码和解码的过程中，需要将画面中的像素进行插值 ——简单地说就是把原先的1个像素点拓展成4x4一共16个点。下图显示了H.264编码和解码过程中像素插值情况。可以看出原先的G点的右下方通过插值 的方式产生了a、b、c、d等一共16个点。
如图所示，1/4像素内插一般分成两步：
（1）半像素内插。这一步通过6抽头滤波器获得5个半像素点。
（2）线性内插。这一步通过简单的线性内插获得剩余的1/4像素点。
图中半像素内插点为b、m、h、s、j五个点。半像素内插方法是对整像素点进行6 抽头滤波得出，滤波器的权重为(1/32, -5/32, 5/8, 5/8, -5/32, 1/32)。例如b的计算公式为：
b=round( (E - 5F + 20G + 20H - 5I + J ) / 32)
剩下几个半像素点的计算关系如下：
m：由B、D、H、N、S、U计算
h：由A、C、G、M、R、T计算
s：由K、L、M、N、P、Q计算
j：由cc、dd、h、m、ee、ff计算。需要注意j点的运算量比较大，因为cc、dd、ee、ff都需要通过半像素内插方法进行计算。
在获得半像素点之后，就可以通过简单的线性内插获得1/4像素内插点了。1/4像素内插的方式如下图所示。例如图中a点的计算公式如下：
A=round( (G+b)/2 )
在这里有一点需要注意：位于4个角的e、g、p、r四个点并不是通过j点计算计算的，而是通过b、h、s、m四个半像素点计算的。
hpel_filter()
hpel_filter()用于进行半像素插值。该函数的定义位于common\mc.c，如下所示。
//半像素插值公式 //b= (E - 5F + 20G + 20H - 5I + J)/32 // x //d取1，水平滤波器；d取stride，垂直滤波器（这里没有除以32） #define TAPFILTER(pix, d) ((pix)[x-2*d] + (pix)[x+3*d] - 5*((pix)[x-d] + (pix)[x+2*d]) + 20*((pix)[x] + (pix)[x+d])) /* * 半像素插值 * dsth：水平滤波得到的半像素点(aa,bb,b,s,gg,hh) * dstv：垂直滤波的到的半像素点(cc,dd,h,m,ee,ff) * dstc："水平+垂直"滤波得到的位于4个像素中间的半像素点（j） * * 半像素插值示意图如下： * * A aa B * * C bb D * * E F G b H I J * * cc dd h j m ee ff * * K L M s N P Q * * R gg S * * T hh U * * 计算公式如下： * b=round( (E - 5F + 20G + 20H - 5I + J ) / 32) * * 剩下几个半像素点的计算关系如下： * m：由B、D、H、N、S、U计算 * h：由A、C、G、M、R、T计算 * s：由K、L、M、N、P、Q计算 * j：由cc、dd、h、m、ee、ff计算。需要注意j点的运算量比较大，因为cc、dd、ee、ff都需要通过半像素内插方法进行计算。 * */ static void hpel_filter( pixel *dsth, pixel *dstv, pixel *dstc, pixel *src, intptr_t stride, int width, int height, int16_t *buf ) { const int pad = (BIT_DEPTH > 9) ? (-10 * PIXEL_MAX) : 0; /* * 几种半像素点之间的位置关系 * * X： 像素点 * H：水平滤波半像素点 * V：垂直滤波半像素点 * C： 中间位置半像素点 * * X H X X X * * V C * * X X X X * * * * X X X X * */ //一行一行处理 for( int y = 0; y < height; y++ ) { //一个一个点处理 //每个整像素点都对应h，v，c三个半像素点 //v for( int x = -2; x < width+3; x++ )//(aa,bb,b,s,gg,hh),结果存入buf { //垂直滤波半像素点 int v = TAPFILTER(src,stride); dstv[x] = x264_clip_pixel( (v + 16) >> 5 ); /* transform v for storage in a 16-bit integer */ //这应该是给dstc计算使用的？ buf[x+2] = v + pad; } //c for( int x = 0; x < width; x++ ) dstc[x] = x264_clip_pixel( (TAPFILTER(buf+2,1) - 32*pad + 512) >> 10 );//四个相邻像素中间的半像素点 //h for( int x = 0; x < width; x++ ) dsth[x] = x264_clip_pixel( (TAPFILTER(src,1) + 16) >> 5 );//水平滤波半像素点 dsth += stride; dstv += stride; dstc += stride; src += stride; } }
从 源代码可以看出，hpel_filter()中包含了一个宏TAPFILTER()用来完成半像素点像素值的计算。在完成半像素插值工作后，dsth中存 储的是经过水平插值后的半像素点，dstv中存储的是经过垂直插值后的半像素点，dstc中存储的是位于4个相邻像素点中间位置的半像素点。这三块内存中 的点的位置关系如下图所示（灰色的点是整像素点）。
x264_quant_init()
x264_quant_init()初始化量化和反量化相关的汇编函数。该函数的定义位于common\quant.c，如下所示。
//量化 void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf ) { //这个好像是针对8x8DCT的 pf->quant_8x8 = quant_8x8; //量化4x4=16个 pf->quant_4x4 = quant_4x4; //注意：处理4个4x4的块 pf->quant_4x4x4 = quant_4x4x4; //Intra16x16中，16个DC系数Hadamard变换后对的它们量化 pf->quant_4x4_dc = quant_4x4_dc; pf->quant_2x2_dc = quant_2x2_dc; //反量化4x4=16个 pf->dequant_4x4 = dequant_4x4; pf->dequant_4x4_dc = dequant_4x4_dc; pf->dequant_8x8 = dequant_8x8; pf->idct_dequant_2x4_dc = idct_dequant_2x4_dc; pf->idct_dequant_2x4_dconly = idct_dequant_2x4_dconly; pf->optimize_chroma_2x2_dc = optimize_chroma_2x2_dc; pf->optimize_chroma_2x4_dc = optimize_chroma_2x4_dc; pf->denoise_dct = x264_denoise_dct; pf->decimate_score15 = x264_decimate_score15; pf->decimate_score16 = x264_decimate_score16; pf->decimate_score64 = x264_decimate_score64; pf->coeff_last4 = x264_coeff_last4; pf->coeff_last8 = x264_coeff_last8; pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15; pf->coeff_last[ DCT_LUMA_4x4] = x264_coeff_last16; pf->coeff_last[ DCT_LUMA_8x8] = x264_coeff_last64; pf->coeff_level_run4 = x264_coeff_level_run4; pf->coeff_level_run8 = x264_coeff_level_run8; pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15; pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16; #if HIGH_BIT_DEPTH #if HAVE_MMX INIT_TRELLIS( sse2 ); if( cpu&X264_CPU_MMX2 ) { #if ARCH_X86 pf->denoise_dct = x264_denoise_dct_mmx; pf->decimate_score15 = x264_decimate_score15_mmx2; pf->decimate_score16 = x264_decimate_score16_mmx2; pf->decimate_score64 = x264_decimate_score64_mmx2; pf->coeff_last8 = x264_coeff_last8_mmx2; pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_mmx2; pf->coeff_last[ DCT_LUMA_4x4] = x264_coeff_last16_mmx2; pf->coeff_last[ DCT_LUMA_8x8] = x264_coeff_last64_mmx2; pf->coeff_level_run8 = x264_coeff_level_run8_mmx2; pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_mmx2; pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16_mmx2; #endif pf->coeff_last4 = x264_coeff_last4_mmx2; pf->coeff_level_run4 = x264_coeff_level_run4_mmx2; if( cpu&X264_CPU_LZCNT ) pf->coeff_level_run4 = x264_coeff_level_run4_mmx2_lzcnt; } //此处省略大量的X86、ARM等平台的汇编函数初始化代码 }
从源代码可以看出，x264_quant_init ()初始化了一系列的量化相关的函数。它的输入参数x264_quant_function_t是一个结构体，其中包含了和量化相关各种函数指针。x264_quant_function_t的定义如下所示。
typedef struct { int (*quant_8x8) ( dctcoef dct[64], udctcoef mf[64], udctcoef bias[64] ); int (*quant_4x4) ( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ); int (*quant_4x4x4)( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ); int (*quant_4x4_dc)( dctcoef dct[16], int mf, int bias ); int (*quant_2x2_dc)( dctcoef dct[4], int mf, int bias ); void (*dequant_8x8)( dctcoef dct[64], int dequant_mf[6][64], int i_qp ); void (*dequant_4x4)( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); void (*dequant_4x4_dc)( dctcoef dct[16], int dequant_mf[6][16], int i_qp ); void (*idct_dequant_2x4_dc)( dctcoef dct[8], dctcoef dct4x4[8][16], int dequant_mf[6][16], int i_qp ); void (*idct_dequant_2x4_dconly)( dctcoef dct[8], int dequant_mf[6][16], int i_qp ); int (*optimize_chroma_2x2_dc)( dctcoef dct[4], int dequant_mf ); int (*optimize_chroma_2x4_dc)( dctcoef dct[8], int dequant_mf ); void (*denoise_dct)( dctcoef *dct, uint32_t *sum, udctcoef *offset, int size ); int (*decimate_score15)( dctcoef *dct ); int (*decimate_score16)( dctcoef *dct ); int (*decimate_score64)( dctcoef *dct ); int (*coeff_last[14])( dctcoef *dct ); int (*coeff_last4)( dctcoef *dct ); int (*coeff_last8)( dctcoef *dct ); int (*coeff_level_run[13])( dctcoef *dct, x264_run_level_t *runlevel ); int (*coeff_level_run4)( dctcoef *dct, x264_run_level_t *runlevel ); int (*coeff_level_run8)( dctcoef *dct, x264_run_level_t *runlevel ); #define TRELLIS_PARAMS const int *unquant_mf, const uint8_t *zigzag, int lambda2,\ int last_nnz, dctcoef *coefs, dctcoef *quant_coefs, dctcoef *dct,\ uint8_t *cabac_state_sig, uint8_t *cabac_state_last,\ uint64_t level_state0, uint16_t level_state1 int (*trellis_cabac_4x4)( TRELLIS_PARAMS, int b_ac ); int (*trellis_cabac_8x8)( TRELLIS_PARAMS, int b_interlaced ); int (*trellis_cabac_4x4_psy)( TRELLIS_PARAMS, int b_ac, dctcoef *fenc_dct, int psy_trellis ); int (*trellis_cabac_8x8_psy)( TRELLIS_PARAMS, int b_interlaced, dctcoef *fenc_dct, int psy_trellis ); int (*trellis_cabac_dc)( TRELLIS_PARAMS, int num_coefs ); int (*trellis_cabac_chroma_422_dc)( TRELLIS_PARAMS ); } x264_quant_function_t;
x264_quant_init ()的工作就是对x264_quant_function_t中的函数指针进行赋值。下文举例分析其中2个函数：4x4矩阵量化函数quant_4x4()，4个4x4矩阵量化函数quant_4x4x4()。
简单记录一下量化的概念。量化是H.264视频压缩编码中对视频质量影响最大的地方，也是会导致"信息丢失"的地方。量化的原理可以表示为下面公式：
FQ=round(y/Qstep)
其中，y 为输入样本点编码，Qstep为量化步长，FQ 为y 的量化值，round()为取整函数（其输出为与输入实数最近的整数）。其相反过程，即反量化为：
y'＝FQ*Qstep
如果Qstep较大，则量化值FQ取值较小，其相应的编码长度较小，但是但反量化时损失较多的图像细节信息。简而言之，Qstep越大，视频压缩编码后体积越小，视频质量越差。
在H.264 中，量化步长Qstep 共有52 个值，如下表所示。其中QP 是量化参数，是量化步长的序号。当QP 取最小值0 时代表最精细的量化，当QP 取最大值51 时代表最粗糙的量化。QP 每增加6，Qstep 增加一倍。
《H.264标准》中规定，量化过程除了完成本职工作外，还需要完成它前一步DCT变换中"系数相乘"的工作。这一步骤的推导过程不再记录，直接给出最终的公式（这个公式完全为整数运算，同时避免了除法的使用）：
|Zij| = (|Wij|*MF + f)>>qbits
sign(Zij) = sign (Wij)
其中：
sign()为符号函数。
Wij为DCT变换后的系数。
MF的值如下表所示。表中只列出对应QP 值为0 到5 的MF 值。QP大于6之后，将QP实行对6取余数操作，再找到MF的值。
qbits计算公式为"qbits = 15 + floor(QP/6)"。即它的值随QP 值每增加6 而增加1。
f 是偏移量（用于改善恢复图像的视觉效果）。对帧内预测图像块取2^qbits/3，对帧间预测图像块取2^qbits/6。
为了更形象的显示MF的取值，做了下面一张示意图。图中深蓝色代表MF取值较大的点，而浅蓝色代表MF取值较小的点。
quant_4x4()
quant_4x4()用于对4x4的DCT残差矩阵进行量化。该函数的定义位于common\quant.c，如下所示。
//4x4量化 //输入输出都是dct[16] static int quant_4x4( dctcoef dct[16], udctcoef mf[16], udctcoef bias[16] ) { int nz = 0; //循环16个元素 for( int i = 0; i < 16; i++ ) QUANT_ONE( dct[i], mf[i], bias[i] ); return !!nz; }
可以看出quant_4x4()循环16次调用了QUANT_ONE()完成了量化工作。并且将DCT系数值，MF值，bias偏移值直接传递给了该宏。
QUANT_ONE()
QUANT_ONE()完成了一个DCT系数的量化工作，它的定义如下。
//量化1个元素 #define QUANT_ONE( coef, mf, f ) \ { \ if( (coef) > 0 ) \ (coef) = (f + (coef)) * (mf) >> 16; \ else \ (coef) = - ((f - (coef)) * (mf) >> 16); \ nz |= (coef); \ }
从QUANT_ONE()的定义可以看出，它实现了上文提到的H.264标准中的量化公式。
quant_4x4x4()
quant_4x4x4()用于对4个4x4的DCT残差矩阵进行量化。该函数的定义位于common\quant.c，如下所示。
//处理4个4x4量化 //输入输出都是dct[4][16] static int quant_4x4x4( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] ) { int nza = 0; //处理4个 for( int j = 0; j < 4; j++ ) { int nz = 0; //量化 for( int i = 0; i < 16; i++ ) QUANT_ONE( dct[j][i], mf[i], bias[i] ); nza |= (!!nz)<<j; } return nza; }
从quant_4x4x4()的定义可以看出，该函数相当于调用了4次quant_4x4()函数。
x264_deblock_init()
x264_deblock_init()用于初始化去块效应滤波器相关的汇编函数。该函数的定义位于common\deblock.c，如下所示。
//去块效应滤波 void x264_deblock_init( int cpu, x264_deblock_function_t *pf, int b_mbaff ) { //注意：标记"v"的垂直滤波器是处理水平边界用的 //亮度-普通滤波器-边界强度Bs=1,2,3 pf->deblock_luma[1] = deblock_v_luma_c; pf->deblock_luma[0] = deblock_h_luma_c; //色度的 pf->deblock_chroma[1] = deblock_v_chroma_c; pf->deblock_h_chroma_420 = deblock_h_chroma_c; pf->deblock_h_chroma_422 = deblock_h_chroma_422_c; //亮度-强滤波器-边界强度Bs=4 pf->deblock_luma_intra[1] = deblock_v_luma_intra_c; pf->deblock_luma_intra[0] = deblock_h_luma_intra_c; pf->deblock_chroma_intra[1] = deblock_v_chroma_intra_c; pf->deblock_h_chroma_420_intra = deblock_h_chroma_intra_c; pf->deblock_h_chroma_422_intra = deblock_h_chroma_422_intra_c; pf->deblock_luma_mbaff = deblock_h_luma_mbaff_c; pf->deblock_chroma_420_mbaff = deblock_h_chroma_mbaff_c; pf->deblock_luma_intra_mbaff = deblock_h_luma_intra_mbaff_c; pf->deblock_chroma_420_intra_mbaff = deblock_h_chroma_intra_mbaff_c; pf->deblock_strength = deblock_strength_c; #if HAVE_MMX if( cpu&X264_CPU_MMX2 ) { #if ARCH_X86 pf->deblock_luma[1] = x264_deblock_v_luma_mmx2; pf->deblock_luma[0] = x264_deblock_h_luma_mmx2; pf->deblock_chroma[1] = x264_deblock_v_chroma_mmx2; pf->deblock_h_chroma_420 = x264_deblock_h_chroma_mmx2; pf->deblock_chroma_420_mbaff = x264_deblock_h_chroma_mbaff_mmx2; pf->deblock_h_chroma_422 = x264_deblock_h_chroma_422_mmx2; pf->deblock_h_chroma_422_intra = x264_deblock_h_chroma_422_intra_mmx2; pf->deblock_luma_intra[1] = x264_deblock_v_luma_intra_mmx2; pf->deblock_luma_intra[0] = x264_deblock_h_luma_intra_mmx2; pf->deblock_chroma_intra[1] = x264_deblock_v_chroma_intra_mmx2; pf->deblock_h_chroma_420_intra = x264_deblock_h_chroma_intra_mmx2; pf->deblock_chroma_420_intra_mbaff = x264_deblock_h_chroma_intra_mbaff_mmx2; #endif //此处省略大量的X86、ARM等平台的汇编函数初始化代码 }
从源代码可以看出，x264_deblock_init()中初始化了一系列环路滤波函数。这些函数名称的规则如下：
（1）包含"v"的是垂直滤波器，用于处理水平边界；包含"h"的是水平滤波器，用于处理垂直边界。
（2）包含"luma"的是亮度滤波器，包含"chroma"的是色度滤波器。
（3）包含"intra"的是处理边界强度Bs为4的强滤波器，不包含"intra"的是普通滤波器。
x264_deblock_init()的输入参数x264_deblock_function_t是一个结构体，其中包含了环路滤波器相关的函数指针。x264_deblock_function_t的定义如下所示。
typedef struct { x264_deblock_inter_t deblock_luma[2]; x264_deblock_inter_t deblock_chroma[2]; x264_deblock_inter_t deblock_h_chroma_420; x264_deblock_inter_t deblock_h_chroma_422; x264_deblock_intra_t deblock_luma_intra[2]; x264_deblock_intra_t deblock_chroma_intra[2]; x264_deblock_intra_t deblock_h_chroma_420_intra; x264_deblock_intra_t deblock_h_chroma_422_intra; x264_deblock_inter_t deblock_luma_mbaff; x264_deblock_inter_t deblock_chroma_mbaff; x264_deblock_inter_t deblock_chroma_420_mbaff; x264_deblock_inter_t deblock_chroma_422_mbaff; x264_deblock_intra_t deblock_luma_intra_mbaff; x264_deblock_intra_t deblock_chroma_intra_mbaff; x264_deblock_intra_t deblock_chroma_420_intra_mbaff; x264_deblock_intra_t deblock_chroma_422_intra_mbaff; void (*deblock_strength) ( uint8_t nnz[X264_SCAN8_SIZE], int8_t ref[2][X264_SCAN8_LUMA_SIZE], int16_t mv[2][X264_SCAN8_LUMA_SIZE][2], uint8_t bs[2][8][4], int mvy_limit, int bframe ); } x264_deblock_function_t;
x264_deblock_init() 的工作就是对x264_deblock_function_t中的函数指针进行赋值。可以看出x264_deblock_function_t中很多的元 素是一个包含2个元素的数组，例如deblock_luma[2]，deblock_luma_intra[2]等。这些数组中的元素[0]一般是水平滤 波器，而元素[1]是垂直滤波器。下文将会举例分析一个普通边界的亮度垂直滤波器函数deblock_v_luma_c()。
简单记录一下环路滤波（去块效应滤波）的知识。X264的重建帧（通过解码得到）一般情况下会出现方块效应。产生这种效应的原因主要有两个：
（1）DCT变换后的量化造成误差（主要原因）。
（2）运动补偿
正是由于这种块效应的存在，才需要添加环路滤波器调整相邻的"块"边缘上的像素值以减轻这种视觉上的不连续感。下面一张图显示了环路滤波的效果。图中左边的图没有使用环路滤波，而右边的图使用了环路滤波。
环路滤波分类
环路滤波器根据滤波的强度可以分为两种：
（1）普通滤波器。针对边界的Bs（边界强度）为1、2、3的滤波器。此时环路滤波涉及到方块边界周围的6个点（边界两边各3个点）：p2，p1，p0，q0，q1，q2。需要处理4个点（边界两边各2个点，只以p点为例）：
p0' = p0 + (((q0 - p0 ) << 2) + (p1 - q1) + 4) >> 3
p1' = ( p2 + ( ( p0 + q0 + 1 ) >> 1) – 2p1 ) >> 1
（2）强滤波器。针对边界的Bs（边界强度）为4的滤波器。此时环路滤波涉及到方块边界周围的8个点（边界两边各4个点）：p3，p2，p1，p0，q0，q1，q2，q3。需要处理6个点（边界两边各3个点，只以p点为例）：
p0' = ( p2 + 2*p1 + 2*p0 + 2*q0 + q1 + 4 ) >> 3
p1' = ( p2 + p1 + p0 + q0 + 2 ) >> 2
p2' = ( 2*p3 + 3*p2 + p1 + p0 + q0 + 4 ) >> 3
其中上文中提到的边界强度Bs的判定方式如下。
|
条件（针对两边的图像块） |
Bs |
|
有一个块为帧内预测 + 边界为宏块边界 |
4 |
|
有一个块为帧内预测 |
3 |
|
有一个块对残差编码 |
2 |
|
运动矢量差不小于1像素 |
1 |
|
运动补偿参考帧不同 |
1 |
|
其它 |
0 |
总体说来，与帧内预测相关的图像块（帧内预测块）的边界强度比较大，取值为3或者4；与运动补偿相关的图像块（帧间预测块）的边界强度比较小，取值为1。
环路滤波的门限
并 不是所有的块的边界处都需要环路滤波。例如画面中物体的边界正好和块的边界重合的话，就不能进行滤波，否则会使画面中物体的边界变模糊。因此需要区别开物 体边界和块效应边界。一般情况下，物体边界两边的像素值差别很大，而块效应边界两边像素值差别比较小。《H.264标准》以这个特点定义了2个变量 alpha和beta来判决边界是否需要进行环路滤波。只有满足下面三个条件的时候才能进行环路滤波：
| p0 - q0 | < alpha
| p1 – p0 | < beta
| q1 - q0 | < beta
简 而言之，就是边界两边的两个点的像素值不能太大，即不能超过alpha；边界一边的前两个点之间的像素值也不能太大，即不能超过beta。其中alpha 和beta是根据量化参数QP推算出来（具体方法不再记录）。总体说来QP越大，alpha和beta的值也越大，也就越容易触发环路滤波。由于QP越大 表明压缩的程度越大，所以也可以得知高压缩比的情况下更需要进行环路滤波。
deblock_v_luma_c()
deblock_v_luma_c()是一个普通强度的垂直滤波器，用于处理边界强度Bs为1，2，3的水平边界。该函数的定义位于common\deblock.c，如下所示。
//去块效应滤波-普通滤波，Bs为1,2,3 //垂直（Vertical）滤波器 // 边界 // x // x // 边界---------- // x // x // // static void deblock_v_luma_c( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ) { //xstride=stride（用于选择滤波的像素） //ystride=1 deblock_luma_c( pix, stride, 1, alpha, beta, tc0 ); }
可 以看出deblock_v_luma_c()调用了另一个函数deblock_luma_c()。需要注意传递给deblock_luma_c()是一个 水平滤波器和垂直滤波器都会调用的"通用"滤波器函数。在这里传递给deblock_luma_c()第二个参数xstride的值为stride，第三 个参数ystride的值为1。
deblock_luma_c()
deblock_luma_c()是一个通用的滤波器函数，定义如下所示。
//去块效应滤波-普通滤波，Bs为1,2,3 static inline void deblock_luma_c( pixel *pix, intptr_t xstride, intptr_t ystride, int alpha, int beta, int8_t *tc0 ) { for( int i = 0; i < 4; i++ ) { if( tc0[i] < 0 ) { pix += 4*ystride; continue; } //滤4个像素 for( int d = 0; d < 4; d++, pix += ystride ) deblock_edge_luma_c( pix, xstride, alpha, beta, tc0[i] ); } }
从源代码中可以看出，具体的滤波在deblock_edge_luma_c()中完成。处理完一个像素后，会继续处理与当前像素距离为ystride的像素。
deblock_edge_luma_c()
deblock_edge_luma_c()用于完成具体的滤波工作。该函数的定义如下所示。
/* From ffmpeg */ //去块效应滤波-普通滤波，Bs为1,2,3 //从FFmpeg复制过来的？ static ALWAYS_INLINE void deblock_edge_luma_c( pixel *pix, intptr_t xstride, int alpha, int beta, int8_t tc0 ) { //p和q //如果xstride=stride，ystride=1 //就是处理纵向的6个像素 //对应的是方块的横向边界的滤波，即如下所示： // p2 // p1 // p0 //=====图像边界===== // q0 // q1 // q2 // //如果xstride=1，ystride=stride //就是处理纵向的6个像素 //对应的是方块的横向边界的滤波，即如下所示： // || // p2 p1 p0 || q0 q1 q2 // || // 边界 //注意：这里乘的是xstride int p2 = pix[-3*xstride]; int p1 = pix[-2*xstride]; int p0 = pix[-1*xstride]; int q0 = pix[ 0*xstride]; int q1 = pix[ 1*xstride]; int q2 = pix[ 2*xstride]; //计算方法参考相关的标准 //alpha和beta是用于检查图像内容的2个参数 //只有满足if()里面3个取值条件的时候（只涉及边界旁边的4个点），才会滤波 if( abs( p0 - q0 ) < alpha && abs( p1 - p0 ) < beta && abs( q1 - q0 ) < beta ) { int tc = tc0; int delta; //上面2个点（p0，p2）满足条件的时候，滤波p1 //int x264_clip3( int v, int i_min, int i_max )用于限幅 if( abs( p2 - p0 ) < beta ) { if( tc0 ) pix[-2*xstride] = p1 + x264_clip3( (( p2 + ((p0 + q0 + 1) >> 1)) >> 1) - p1, -tc0, tc0 ); tc++; } //下面2个点（q0，q2）满足条件的时候，滤波q1 if( abs( q2 - q0 ) < beta ) { if( tc0 ) pix[ 1*xstride] = q1 + x264_clip3( (( q2 + ((p0 + q0 + 1) >> 1)) >> 1) - q1, -tc0, tc0 ); tc++; } delta = x264_clip3( (((q0 - p0 ) << 2) + (p1 - q1) + 4) >> 3, -tc, tc ); //p0 pix[-1*xstride] = x264_clip_pixel( p0 + delta ); /* p0' */ //q0 pix[ 0*xstride] = x264_clip_pixel( q0 - delta ); /* q0' */ } }
从源代码可以看出，deblock_edge_luma_c()实现了前文记录的滤波公式。
deblock_h_luma_c()
deblock_h_luma_c()是一个普通强度的水平滤波器，用于处理边界强度Bs为1，2，3的垂直边界。该函数的定义如下所示。
//去块效应滤波-普通滤波，Bs为1,2,3 //水平（Horizontal）滤波器 // 边界 // | // x x x | x x x // | static void deblock_h_luma_c( pixel *pix, intptr_t stride, int alpha, int beta, int8_t *tc0 ) { //xstride=1（用于选择滤波的像素） //ystride=stride deblock_luma_c( pix, 1, stride, alpha, beta, tc0 ); }
从 源代码可以看出，和deblock_v_luma_c()类似，deblock_h_luma_c()同样调用了deblock_luma_c()函数。 唯一的不同在于它传递给deblock_luma_c()的第2个参数xstride为1，第3个参数ystride为stride。
mbcmp_init()
mbcmp_init()函数决定了x264_pixel_function_t中的像素比较的一系列函数（mbcmp[]）使用SAD还是SATD。该函数的定义位于encoder\encoder.c，如下所示。
//决定了像素比较的时候用SAD还是SATD static void mbcmp_init( x264_t *h ) { //b_lossless一般为0 //主要看i_subpel_refine，大于1的话就使用SATD int satd = !h->mb.b_lossless && h->param.analyse.i_subpel_refine > 1; //sad或者satd赋值给mbcmp memcpy( h->pixf.mbcmp, satd ? h->pixf.satd : h->pixf.sad_aligned, sizeof(h->pixf.mbcmp) ); memcpy( h->pixf.mbcmp_unaligned, satd ? h->pixf.satd : h->pixf.sad, sizeof(h->pixf.mbcmp_unaligned) ); h->pixf.intra_mbcmp_x3_16x16 = satd ? h->pixf.intra_satd_x3_16x16 : h->pixf.intra_sad_x3_16x16; h->pixf.intra_mbcmp_x3_8x16c = satd ? h->pixf.intra_satd_x3_8x16c : h->pixf.intra_sad_x3_8x16c; h->pixf.intra_mbcmp_x3_8x8c = satd ? h->pixf.intra_satd_x3_8x8c : h->pixf.intra_sad_x3_8x8c; h->pixf.intra_mbcmp_x3_8x8 = satd ? h->pixf.intra_sa8d_x3_8x8 : h->pixf.intra_sad_x3_8x8; h->pixf.intra_mbcmp_x3_4x4 = satd ? h->pixf.intra_satd_x3_4x4 : h->pixf.intra_sad_x3_4x4; h->pixf.intra_mbcmp_x9_4x4 = h->param.b_cpu_independent || h->mb.b_lossless ? NULL : satd ? h->pixf.intra_satd_x9_4x4 : h->pixf.intra_sad_x9_4x4; h->pixf.intra_mbcmp_x9_8x8 = h->param.b_cpu_independent || h->mb.b_lossless ? NULL : satd ? h->pixf.intra_sa8d_x9_8x8 : h->pixf.intra_sad_x9_8x8; satd &= h->param.analyse.i_me_method == X264_ME_TESA; memcpy( h->pixf.fpelcmp, satd ? h->pixf.satd : h->pixf.sad, sizeof(h->pixf.fpelcmp) ); memcpy( h->pixf.fpelcmp_x3, satd ? h->pixf.satd_x3 : h->pixf.sad_x3, sizeof(h->pixf.fpelcmp_x3) ); memcpy( h->pixf.fpelcmp_x4, satd ? h->pixf.satd_x4 : h->pixf.sad_x4, sizeof(h->pixf.fpelcmp_x4) ); }
从 mbcmp_init()的源代码可以看出，当i_subpel_refine取值大于1的时候，satd变量为1，此时后续代码中赋值给mbcmp[] 相关的一系列函数指针的函数就是SATD函数；当i_subpel_refine取值小于等于1的时候，satd变量为0，此时后续代码中赋值给 mbcmp[]相关的一系列函数指针的函数就是SAD函数。
至此x264_encoder_open()的源代码就分析完毕了。下文继续分析x264_encoder_headers()和x264_encoder_close()函数。
x264_encoder_headers()
x264_encoder_headers()是libx264的一个API函数，用于输出SPS/PPS/SEI这些H.264码流的头信息。该函数的声明如下。
/* x264_encoder_headers: * return the SPS and PPS that will be used for the whole stream. * *pi_nal is the number of NAL units outputted in pp_nal. * returns the number of bytes in the returned NALs. * returns negative on error. * the payloads of all output NALs are guaranteed to be sequential in memory. */ int x264_encoder_headers( x264_t *, x264_nal_t **pp_nal, int *pi_nal );
x264_encoder_headers()的定义位于encoder\encoder.c，如下所示。
/**************************************************************************** * x264_encoder_headers: * 注释和处理：雷霄骅 * http://blog.csdn.net/leixiaohua1020 * leixiaohua1020@126.com ****************************************************************************/ //输出文件头（SPS、PPS、SEI） int x264_encoder_headers( x264_t *h, x264_nal_t **pp_nal, int *pi_nal ) { int frame_size = 0; /* init bitstream context */ h->out.i_nal = 0; bs_init( &h->out.bs, h->out.p_bitstream, h->out.i_bitstream ); /* Write SEI, SPS and PPS. */ /* generate sequence parameters */ //输出SPS x264_nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST ); x264_sps_write( &h->out.bs, h->sps ); if( x264_nal_end( h ) ) return -1; /* generate picture parameters */ x264_nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST ); //输出PPS x264_pps_write( &h->out.bs, h->sps, h->pps ); if( x264_nal_end( h ) ) return -1; /* identify ourselves */ x264_nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE ); //输出SEI（其中包含了配置信息） if( x264_sei_version_write( h, &h->out.bs ) ) return -1; if( x264_nal_end( h ) ) return -1; frame_size = x264_encoder_encapsulate_nals( h, 0 ); if( frame_size < 0 ) return -1; /* now set output*/ *pi_nal = h->out.i_nal; *pp_nal = &h->out.nal[0]; h->out.i_nal = 0; return frame_size; }
从 源代码可以看出，x264_encoder_headers()分别调用了 x264_sps_write()，x264_pps_write()，x264_sei_version_write()输出了SPS，PPS，和 SEI信息。在输出每个NALU之前，需要调用x264_nal_start()，在输出NALU之后，需要调用x264_nal_end()。下文继续 分析上述三个函数。
x264_sps_write()
x264_sps_write()用于输出SPS。该函数的定义位于encoder\set.c，如下所示。
//输出SPS void x264_sps_write( bs_t *s, x264_sps_t *sps ) { bs_realign( s ); //型profile，8bit bs_write( s, 8, sps->i_profile_idc ); bs_write1( s, sps->b_constraint_set0 ); bs_write1( s, sps->b_constraint_set1 ); bs_write1( s, sps->b_constraint_set2 ); bs_write1( s, sps->b_constraint_set3 ); bs_write( s, 4, 0 ); /* reserved */ //级level，8bit bs_write( s, 8, sps->i_level_idc ); //本SPS的 id号 bs_write_ue( s, sps->i_id ); if( sps->i_profile_idc >= PROFILE_HIGH ) { //色度取样格式 //0代表单色 //1代表4:2:0 //2代表4:2:2 //3代表4:4:4 bs_write_ue( s, sps->i_chroma_format_idc ); if( sps->i_chroma_format_idc == CHROMA_444 ) bs_write1( s, 0 ); // separate_colour_plane_flag //亮度 //颜色位深=bit_depth_luma_minus8+8 bs_write_ue( s, BIT_DEPTH-8 ); // bit_depth_luma_minus8 //色度与亮度一样 bs_write_ue( s, BIT_DEPTH-8 ); // bit_depth_chroma_minus8 bs_write1( s, sps->b_qpprime_y_zero_transform_bypass ); bs_write1( s, 0 ); // seq_scaling_matrix_present_flag } //log2_max_frame_num_minus4主要是为读取另一个句法元素frame_num服务的 //frame_num 是最重要的句法元素之一 //这个句法元素指明了frame_num的所能达到的最大值： //MaxFrameNum = 2^( log2_max_frame_num_minus4 + 4 ) bs_write_ue( s, sps->i_log2_max_frame_num - 4 ); //pic_order_cnt_type 指明了poc (picture order count) 的编码方法 //poc标识图像的播放顺序。 //由于H.264使用了B帧预测，使得图像的解码顺序并不一定等于播放顺序，但它们之间存在一定的映射关系 //poc 可以由frame-num 通过映射关系计算得来，也可以索性由编码器显式地传送。 //H.264 中一共定义了三种poc 的编码方法 bs_write_ue( s, sps->i_poc_type ); if( sps->i_poc_type == 0 ) bs_write_ue( s, sps->i_log2_max_poc_lsb - 4 ); //num_ref_frames 指定参考帧队列可能达到的最大长度，解码器依照这个句法元素的值开辟存储区，这个存储区用于存放已解码的参考帧， //H.264 规定最多可用16 个参考帧，因此最大值为16。 bs_write_ue( s, sps->i_num_ref_frames ); bs_write1( s, sps->b_gaps_in_frame_num_value_allowed ); //pic_width_in_mbs_minus1加1后为图像宽（以宏块为单位）： // PicWidthInMbs = pic_width_in_mbs_minus1 + 1 //以像素为单位图像宽度（亮度）：width=PicWidthInMbs*16 bs_write_ue( s, sps->i_mb_width - 1 ); //pic_height_in_map_units_minus1加1后指明图像高度（以宏块为单位） bs_write_ue( s, (sps->i_mb_height >> !sps->b_frame_mbs_only) - 1); bs_write1( s, sps->b_frame_mbs_only ); if( !sps->b_frame_mbs_only ) bs_write1( s, sps->b_mb_adaptive_frame_field ); bs_write1( s, sps->b_direct8x8_inference ); bs_write1( s, sps->b_crop ); if( sps->b_crop ) { int h_shift = sps->i_chroma_format_idc == CHROMA_420 || sps->i_chroma_format_idc == CHROMA_422; int v_shift = sps->i_chroma_format_idc == CHROMA_420; bs_write_ue( s, sps->crop.i_left >> h_shift ); bs_write_ue( s, sps->crop.i_right >> h_shift ); bs_write_ue( s, sps->crop.i_top >> v_shift ); bs_write_ue( s, sps->crop.i_bottom >> v_shift ); } bs_write1( s, sps->b_vui ); if( sps->b_vui ) { bs_write1( s, sps->vui.b_aspect_ratio_info_present ); if( sps->vui.b_aspect_ratio_info_present ) { int i; static const struct { uint8_t w, h, sar; } sar[] = { // aspect_ratio_idc = 0 -> unspecified { 1, 1, 1 }, { 12, 11, 2 }, { 10, 11, 3 }, { 16, 11, 4 }, { 40, 33, 5 }, { 24, 11, 6 }, { 20, 11, 7 }, { 32, 11, 8 }, { 80, 33, 9 }, { 18, 11, 10}, { 15, 11, 11}, { 64, 33, 12}, {160, 99, 13}, { 4, 3, 14}, { 3, 2, 15}, { 2, 1, 16}, // aspect_ratio_idc = [17..254] -> reserved { 0, 0, 255 } }; for( i = 0; sar[i].sar != 255; i++ ) { if( sar[i].w == sps->vui.i_sar_width && sar[i].h == sps->vui.i_sar_height ) break; } bs_write( s, 8, sar[i].sar ); if( sar[i].sar == 255 ) /* aspect_ratio_idc (extended) */ { bs_write( s, 16, sps->vui.i_sar_width ); bs_write( s, 16, sps->vui.i_sar_height ); } } bs_write1( s, sps->vui.b_overscan_info_present ); if( sps->vui.b_overscan_info_present ) bs_write1( s, sps->vui.b_overscan_info ); bs_write1( s, sps->vui.b_signal_type_present ); if( sps->vui.b_signal_type_present ) { bs_write( s, 3, sps->vui.i_vidformat ); bs_write1( s, sps->vui.b_fullrange ); bs_write1( s, sps->vui.b_color_description_present ); if( sps->vui.b_color_description_present ) { bs_write( s, 8, sps->vui.i_colorprim ); bs_write( s, 8, sps->vui.i_transfer ); bs_write( s, 8, sps->vui.i_colmatrix ); } } bs_write1( s, sps->vui.b_chroma_loc_info_present ); if( sps->vui.b_chroma_loc_info_present ) { bs_write_ue( s, sps->vui.i_chroma_loc_top ); bs_write_ue( s, sps->vui.i_chroma_loc_bottom ); } bs_write1( s, sps->vui.b_timing_info_present ); if( sps->vui.b_timing_info_present ) { bs_write32( s, sps->vui.i_num_units_in_tick ); bs_write32( s, sps->vui.i_time_scale ); bs_write1( s, sps->vui.b_fixed_frame_rate ); } bs_write1( s, sps->vui.b_nal_hrd_parameters_present ); if( sps->vui.b_nal_hrd_parameters_present ) { bs_write_ue( s, sps->vui.hrd.i_cpb_cnt - 1 ); bs_write( s, 4, sps->vui.hrd.i_bit_rate_scale ); bs_write( s, 4, sps->vui.hrd.i_cpb_size_scale ); bs_write_ue( s, sps->vui.hrd.i_bit_rate_value - 1 ); bs_write_ue( s, sps->vui.hrd.i_cpb_size_value - 1 ); bs_write1( s, sps->vui.hrd.b_cbr_hrd ); bs_write( s, 5, sps->vui.hrd.i_initial_cpb_removal_delay_length - 1 ); bs_write( s, 5, sps->vui.hrd.i_cpb_removal_delay_length - 1 ); bs_write( s, 5, sps->vui.hrd.i_dpb_output_delay_length - 1 ); bs_write( s, 5, sps->vui.hrd.i_time_offset_length ); } bs_write1( s, sps->vui.b_vcl_hrd_parameters_present ); if( sps->vui.b_nal_hrd_parameters_present || sps->vui.b_vcl_hrd_parameters_present ) bs_write1( s, 0 ); /* low_delay_hrd_flag */ bs_write1( s, sps->vui.b_pic_struct_present ); bs_write1( s, sps->vui.b_bitstream_restriction ); if( sps->vui.b_bitstream_restriction ) { bs_write1( s, sps->vui.b_motion_vectors_over_pic_boundaries ); bs_write_ue( s, sps->vui.i_max_bytes_per_pic_denom ); bs_write_ue( s, sps->vui.i_max_bits_per_mb_denom ); bs_write_ue( s, sps->vui.i_log2_max_mv_length_horizontal ); bs_write_ue( s, sps->vui.i_log2_max_mv_length_vertical ); bs_write_ue( s, sps->vui.i_num_reorder_frames ); bs_write_ue( s, sps->vui.i_max_dec_frame_buffering ); } } //RBSP拖尾 //无论比特流当前位置是否字节对齐 ， 都向其中写入一个比特1及若干个（0~7个）比特0 ， 使其字节对齐 bs_rbsp_trailing( s ); bs_flush( s ); }
可以看出x264_sps_write()将x264_sps_t结构体中的信息输出出来形成了一个NALU。有关SPS相关的知识可以参考《H.264标准》。
x264_pps_write()
x264_pps_write()用于输出PPS。该函数的定义位于encoder\set.c，如下所示。
//输出PPS void x264_pps_write( bs_t *s, x264_sps_t *sps, x264_pps_t *pps ) { bs_realign( s ); //PPS的ID bs_write_ue( s, pps->i_id ); //该PPS引用的SPS的ID bs_write_ue( s, pps->i_sps_id ); //entropy_coding_mode_flag //0表示熵编码使用CAVLC，1表示熵编码使用CABAC bs_write1( s, pps->b_cabac ); bs_write1( s, pps->b_pic_order ); bs_write_ue( s, pps->i_num_slice_groups - 1 ); bs_write_ue( s, pps->i_num_ref_idx_l0_default_active - 1 ); bs_write_ue( s, pps->i_num_ref_idx_l1_default_active - 1 ); //P Slice 是否使用加权预测？ bs_write1( s, pps->b_weighted_pred ); //B Slice 是否使用加权预测？ bs_write( s, 2, pps->b_weighted_bipred ); //pic_init_qp_minus26加26后用以指明亮度分量的QP的初始值。 bs_write_se( s, pps->i_pic_init_qp - 26 - QP_BD_OFFSET ); bs_write_se( s, pps->i_pic_init_qs - 26 - QP_BD_OFFSET ); bs_write_se( s, pps->i_chroma_qp_index_offset ); bs_write1( s, pps->b_deblocking_filter_control ); bs_write1( s, pps->b_constrained_intra_pred ); bs_write1( s, pps->b_redundant_pic_cnt ); if( pps->b_transform_8x8_mode || pps->i_cqm_preset != X264_CQM_FLAT ) { bs_write1( s, pps->b_transform_8x8_mode ); bs_write1( s, (pps->i_cqm_preset != X264_CQM_FLAT) ); if( pps->i_cqm_preset != X264_CQM_FLAT ) { scaling_list_write( s, pps, CQM_4IY ); scaling_list_write( s, pps, CQM_4IC ); bs_write1( s, 0 ); // Cr = Cb scaling_list_write( s, pps, CQM_4PY ); scaling_list_write( s, pps, CQM_4PC ); bs_write1( s, 0 ); // Cr = Cb if( pps->b_transform_8x8_mode ) { if( sps->i_chroma_format_idc == CHROMA_444 ) { scaling_list_write( s, pps, CQM_8IY+4 ); scaling_list_write( s, pps, CQM_8IC+4 ); bs_write1( s, 0 ); // Cr = Cb scaling_list_write( s, pps, CQM_8PY+4 ); scaling_list_write( s, pps, CQM_8PC+4 ); bs_write1( s, 0 ); // Cr = Cb } else { scaling_list_write( s, pps, CQM_8IY+4 ); scaling_list_write( s, pps, CQM_8PY+4 ); } } } bs_write_se( s, pps->i_chroma_qp_index_offset ); } //RBSP拖尾 //无论比特流当前位置是否字节对齐 ， 都向其中写入一个比特1及若干个（0~7个）比特0 ， 使其字节对齐 bs_rbsp_trailing( s ); bs_flush( s ); }
可以看出x264_pps_write()将x264_pps_t结构体中的信息输出出来形成了一个NALU。
x264_sei_version_write()
x264_sei_version_write()用于输出SEI。SEI中一般存储了H.264中的一些附加信息，例如下图中红色方框中的文字就是x264存储在SEI中的中的信息。
x264_sei_version_write()的定义位于encoder\set.c，如下所示。
//输出SEI（其中包含了配置信息） int x264_sei_version_write( x264_t *h, bs_t *s ) { // random ID number generated according to ISO-11578 static const uint8_t uuid[16] = { 0xdc, 0x45, 0xe9, 0xbd, 0xe6, 0xd9, 0x48, 0xb7, 0x96, 0x2c, 0xd8, 0x20, 0xd9, 0x23, 0xee, 0xef }; //把设置信息转换为字符串 char *opts = x264_param2string( &h->param, 0 ); char *payload; int length; if( !opts ) return -1; CHECKED_MALLOC( payload, 200 + strlen( opts ) ); memcpy( payload, uuid, 16 ); //配置信息的内容 //opts字符串内容还是挺多的 sprintf( payload+16, "x264 - core %d%s - H.264/MPEG-4 AVC codec - " "Copy%s 2003-2014 - http://www.videolan.org/x264.html - options: %s", X264_BUILD, X264_VERSION, HAVE_GPL?"left":"right", opts ); length = strlen(payload)+1; //输出SEI //数据类型为USER_DATA_UNREGISTERED x264_sei_write( s, (uint8_t *)payload, length, SEI_USER_DATA_UNREGISTERED ); x264_free( opts ); x264_free( payload ); return 0; fail: x264_free( opts ); return -1; }
从 源代码可以看出，x264_sei_version_write()首先调用了x264_param2string()将当前的配置参数保存到字符串 opts[]中，然后调用sprintf()结合opt[]生成完整的SEI信息，最后调用x264_sei_write()输出SEI信息。在这个过程 中涉及到一个libx264的API函数x264_param2string()。
x264_param2string()
x264_param2string()用于将当前设置转换为字符串输出出来。该函数的声明如下。
/* x264_param2string: return a (malloced) string containing most of * the encoding options */ char *x264_param2string( x264_param_t *p, int b_res );
x264_param2string()的定义位于common\common.c，如下所示。
/**************************************************************************** * x264_param2string: ****************************************************************************/ //把设置信息转换为字符串 char *x264_param2string( x264_param_t *p, int b_res ) { int len = 1000; char *buf, *s; if( p->rc.psz_zones ) len += strlen(p->rc.psz_zones); //1000字节？ buf = s = x264_malloc( len ); if( !buf ) return NULL; if( b_res ) { s += sprintf( s, "%dx%d ", p->i_width, p->i_height ); s += sprintf( s, "fps=%u/%u ", p->i_fps_num, p->i_fps_den ); s += sprintf( s, "timebase=%u/%u ", p->i_timebase_num, p->i_timebase_den ); s += sprintf( s, "bitdepth=%d ", BIT_DEPTH ); } if( p->b_opencl ) s += sprintf( s, "opencl=%d ", p->b_opencl ); s += sprintf( s, "cabac=%d", p->b_cabac ); s += sprintf( s, " ref=%d", p->i_frame_reference ); s += sprintf( s, " deblock=%d:%d:%d", p->b_deblocking_filter, p->i_deblocking_filter_alphac0, p->i_deblocking_filter_beta ); s += sprintf( s, " analyse=%#x:%#x", p->analyse.intra, p->analyse.inter ); s += sprintf( s, " me=%s", x264_motion_est_names[ p->analyse.i_me_method ] ); s += sprintf( s, " subme=%d", p->analyse.i_subpel_refine ); s += sprintf( s, " psy=%d", p->analyse.b_psy ); if( p->analyse.b_psy ) s += sprintf( s, " psy_rd=%.2f:%.2f", p->analyse.f_psy_rd, p->analyse.f_psy_trellis ); s += sprintf( s, " mixed_ref=%d", p->analyse.b_mixed_references ); s += sprintf( s, " me_range=%d", p->analyse.i_me_range ); s += sprintf( s, " chroma_me=%d", p->analyse.b_chroma_me ); s += sprintf( s, " trellis=%d", p->analyse.i_trellis ); s += sprintf( s, " 8x8dct=%d", p->analyse.b_transform_8x8 ); s += sprintf( s, " cqm=%d", p->i_cqm_preset ); s += sprintf( s, " deadzone=%d,%d", p->analyse.i_luma_deadzone[0], p->analyse.i_luma_deadzone[1] ); s += sprintf( s, " fast_pskip=%d", p->analyse.b_fast_pskip ); s += sprintf( s, " chroma_qp_offset=%d", p->analyse.i_chroma_qp_offset ); s += sprintf( s, " threads=%d", p->i_threads ); s += sprintf( s, " lookahead_threads=%d", p->i_lookahead_threads ); s += sprintf( s, " sliced_threads=%d", p->b_sliced_threads ); if( p->i_slice_count ) s += sprintf( s, " slices=%d", p->i_slice_count ); if( p->i_slice_count_max ) s += sprintf( s, " slices_max=%d", p->i_slice_count_max ); if( p->i_slice_max_size ) s += sprintf( s, " slice_max_size=%d", p->i_slice_max_size ); if( p->i_slice_max_mbs ) s += sprintf( s, " slice_max_mbs=%d", p->i_slice_max_mbs ); if( p->i_slice_min_mbs ) s += sprintf( s, " slice_min_mbs=%d", p->i_slice_min_mbs ); s += sprintf( s, " nr=%d", p->analyse.i_noise_reduction ); s += sprintf( s, " decimate=%d", p->analyse.b_dct_decimate ); s += sprintf( s, " interlaced=%s", p->b_interlaced ? p->b_tff ? "tff" : "bff" : p->b_fake_interlaced ? "fake" : "0" ); s += sprintf( s, " bluray_compat=%d", p->b_bluray_compat ); if( p->b_stitchable ) s += sprintf( s, " stitchable=%d", p->b_stitchable ); s += sprintf( s, " constrained_intra=%d", p->b_constrained_intra ); s += sprintf( s, " bframes=%d", p->i_bframe ); if( p->i_bframe ) { s += sprintf( s, " b_pyramid=%d b_adapt=%d b_bias=%d direct=%d weightb=%d open_gop=%d", p->i_bframe_pyramid, p->i_bframe_adaptive, p->i_bframe_bias, p->analyse.i_direct_mv_pred, p->analyse.b_weighted_bipred, p->b_open_gop ); } s += sprintf( s, " weightp=%d", p->analyse.i_weighted_pred > 0 ? p->analyse.i_weighted_pred : 0 ); if( p->i_keyint_max == X264_KEYINT_MAX_INFINITE ) s += sprintf( s, " keyint=infinite" ); else s += sprintf( s, " keyint=%d", p->i_keyint_max ); s += sprintf( s, " keyint_min=%d scenecut=%d intra_refresh=%d", p->i_keyint_min, p->i_scenecut_threshold, p->b_intra_refresh ); if( p->rc.b_mb_tree || p->rc.i_vbv_buffer_size ) s += sprintf( s, " rc_lookahead=%d", p->rc.i_lookahead ); s += sprintf( s, " rc=%s mbtree=%d", p->rc.i_rc_method == X264_RC_ABR ? ( p->rc.b_stat_read ? "2pass" : p->rc.i_vbv_max_bitrate == p->rc.i_bitrate ? "cbr" : "abr" ) : p->rc.i_rc_method == X264_RC_CRF ? "crf" : "cqp", p->rc.b_mb_tree ); if( p->rc.i_rc_method == X264_RC_ABR || p->rc.i_rc_method == X264_RC_CRF ) { if( p->rc.i_rc_method == X264_RC_CRF ) s += sprintf( s, " crf=%.1f", p->rc.f_rf_constant ); else s += sprintf( s, " bitrate=%d ratetol=%.1f", p->rc.i_bitrate, p->rc.f_rate_tolerance ); s += sprintf( s, " qcomp=%.2f qpmin=%d qpmax=%d qpstep=%d", p->rc.f_qcompress, p->rc.i_qp_min, p->rc.i_qp_max, p->rc.i_qp_step ); if( p->rc.b_stat_read ) s += sprintf( s, " cplxblur=%.1f qblur=%.1f", p->rc.f_complexity_blur, p->rc.f_qblur ); if( p->rc.i_vbv_buffer_size ) { s += sprintf( s, " vbv_maxrate=%d vbv_bufsize=%d", p->rc.i_vbv_max_bitrate, p->rc.i_vbv_buffer_size ); if( p->rc.i_rc_method == X264_RC_CRF ) s += sprintf( s, " crf_max=%.1f", p->rc.f_rf_constant_max ); } } else if( p->rc.i_rc_method == X264_RC_CQP ) s += sprintf( s, " qp=%d", p->rc.i_qp_constant ); if( p->rc.i_vbv_buffer_size ) s += sprintf( s, " nal_hrd=%s filler=%d", x264_nal_hrd_names[p->i_nal_hrd], p->rc.b_filler ); if( p->crop_rect.i_left | p->crop_rect.i_top | p->crop_rect.i_right | p->crop_rect.i_bottom ) s += sprintf( s, " crop_rect=%u,%u,%u,%u", p->crop_rect.i_left, p->crop_rect.i_top, p->crop_rect.i_right, p->crop_rect.i_bottom ); if( p->i_frame_packing >= 0 ) s += sprintf( s, " frame-packing=%d", p->i_frame_packing ); if( !(p->rc.i_rc_method == X264_RC_CQP && p->rc.i_qp_constant == 0) ) { s += sprintf( s, " ip_ratio=%.2f", p->rc.f_ip_factor ); if( p->i_bframe && !p->rc.b_mb_tree ) s += sprintf( s, " pb_ratio=%.2f", p->rc.f_pb_factor ); s += sprintf( s, " aq=%d", p->rc.i_aq_mode ); if( p->rc.i_aq_mode ) s += sprintf( s, ":%.2f", p->rc.f_aq_strength ); if( p->rc.psz_zones ) s += sprintf( s, " zones=%s", p->rc.psz_zones ); else if( p->rc.i_zones ) s += sprintf( s, " zones" ); } return buf; }
可以看出x264_param2string()几乎遍历了libx264的所有设置选项，使用"s += sprintf()"的形式将它们连接成一个很长的字符串，并最终将该字符串返回。
x264_encoder_close()
x264_encoder_close()是libx264的一个API函数。该函数用于关闭编码器，同时输出一些统计信息。该函数执行的时候输出的统计信息如下图所示。
x264_encoder_close()的声明如下所示。
/* x264_encoder_close: * close an encoder handler */ void x264_encoder_close ( x264_t * );
x264_encoder_close()的定义位于encoder\encoder.c，如下所示。
/**************************************************************************** * x264_encoder_close: * 注释和处理：雷霄骅 * http://blog.csdn.net/leixiaohua1020 * leixiaohua1020@126.com ****************************************************************************/ void x264_encoder_close ( x264_t *h ) { int64_t i_yuv_size = FRAME_SIZE( h->param.i_width * h->param.i_height ); int64_t i_mb_count_size[2][7] = {{0}}; char buf[200]; int b_print_pcm = h->stat.i_mb_count[SLICE_TYPE_I][I_PCM] || h->stat.i_mb_count[SLICE_TYPE_P][I_PCM] || h->stat.i_mb_count[SLICE_TYPE_B][I_PCM]; x264_lookahead_delete( h ); #if HAVE_OPENCL x264_opencl_lookahead_delete( h ); x264_opencl_function_t *ocl = h->opencl.ocl; #endif if( h->param.b_sliced_threads ) x264_threadpool_wait_all( h ); if( h->param.i_threads > 1 ) x264_threadpool_delete( h->threadpool ); if( h->param.i_lookahead_threads > 1 ) x264_threadpool_delete( h->lookaheadpool ); if( h->i_thread_frames > 1 ) { for( int i = 0; i < h->i_thread_frames; i++ ) if( h->thread[i]->b_thread_active ) { assert( h->thread[i]->fenc->i_reference_count == 1 ); x264_frame_delete( h->thread[i]->fenc ); } x264_t *thread_prev = h->thread[h->i_thread_phase]; x264_thread_sync_ratecontrol( h, thread_prev, h ); x264_thread_sync_ratecontrol( thread_prev, thread_prev, h ); h->i_frame = thread_prev->i_frame + 1 - h->i_thread_frames; } h->i_frame++; /* * x264控制台输出示例 * * x264 [info]: using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX * x264 [info]: profile High, level 2.1 * x264 [info]: frame I:2 Avg QP:20.51 size: 20184 PSNR Mean Y:45.32 U:47.54 V:47.62 Avg:45.94 Global:45.52 * x264 [info]: frame P:33 Avg QP:23.08 size: 3230 PSNR Mean Y:43.23 U:47.06 V:46.87 Avg:44.15 Global:44.00 * x264 [info]: frame B:65 Avg QP:27.87 size: 352 PSNR Mean Y:42.76 U:47.21 V:47.05 Avg:43.79 Global:43.65 * x264 [info]: consecutive B-frames: 3.0% 10.0% 63.0% 24.0% * x264 [info]: mb I I16..4: 15.3% 37.5% 47.3% * x264 [info]: mb P I16..4: 0.6% 0.4% 0.2% P16..4: 34.6% 21.2% 12.7% 0.0% 0.0% skip:30.4% * x264 [info]: mb B I16..4: 0.0% 0.0% 0.0% B16..8: 21.2% 4.1% 0.7% direct: 0.8% skip:73.1% L0:28.7% L1:53.0% BI:18.3% * x264 [info]: 8x8 transform intra:37.1% inter:51.0% * x264 [info]: coded y,uvDC,uvAC intra: 74.1% 83.3% 58.9% inter: 10.4% 6.6% 0.4% * x264 [info]: i16 v,h,dc,p: 21% 25% 7% 48% * x264 [info]: i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 23% 13% 6% 5% 5% 6% 8% 10% * x264 [info]: i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 22% 20% 9% 7% 7% 8% 8% 7% 12% * x264 [info]: i8c dc,h,v,p: 43% 20% 27% 10% * x264 [info]: Weighted P-Frames: Y:0.0% UV:0.0% * x264 [info]: ref P L0: 62.5% 19.7% 13.8% 4.0% * x264 [info]: ref B L0: 88.8% 9.4% 1.9% * x264 [info]: ref B L1: 92.6% 7.4% * x264 [info]: PSNR Mean Y:42.967 U:47.163 V:47.000 Avg:43.950 Global:43.796 kb/s:339.67 * * encoded 100 frames, 178.25 fps, 339.67 kb/s * */ /* Slices used and PSNR */ /* 示例 * x264 [info]: frame I:2 Avg QP:20.51 size: 20184 PSNR Mean Y:45.32 U:47.54 V:47.62 Avg:45.94 Global:45.52 * x264 [info]: frame P:33 Avg QP:23.08 size: 3230 PSNR Mean Y:43.23 U:47.06 V:46.87 Avg:44.15 Global:44.00 * x264 [info]: frame B:65 Avg QP:27.87 size: 352 PSNR Mean Y:42.76 U:47.21 V:47.05 Avg:43.79 Global:43.65 */ for( int i = 0; i < 3; i++ ) { static const uint8_t slice_order[] = { SLICE_TYPE_I, SLICE_TYPE_P, SLICE_TYPE_B }; int i_slice = slice_order[i]; if( h->stat.i_frame_count[i_slice] > 0 ) { int i_count = h->stat.i_frame_count[i_slice]; double dur = h->stat.f_frame_duration[i_slice]; if( h->param.analyse.b_psnr ) { //输出统计信息-包含PSNR //注意PSNR都是通过SSD换算过来的，换算方法就是调用x264_psnr()方法 x264_log( h, X264_LOG_INFO, "frame %c:%-5d Avg QP:%5.2f size:%6.0f PSNR Mean Y:%5.2f U:%5.2f V:%5.2f Avg:%5.2f Global:%5.2f\n", slice_type_to_char[i_slice], i_count, h->stat.f_frame_qp[i_slice] / i_count, (double)h->stat.i_frame_size[i_slice] / i_count, h->stat.f_psnr_mean_y[i_slice] / dur, h->stat.f_psnr_mean_u[i_slice] / dur, h->stat.f_psnr_mean_v[i_slice] / dur, h->stat.f_psnr_average[i_slice] / dur, x264_psnr( h->stat.f_ssd_global[i_slice], dur * i_yuv_size ) ); } else { //输出统计信息-不包含PSNR x264_log( h, X264_LOG_INFO, "frame %c:%-5d Avg QP:%5.2f size:%6.0f\n", slice_type_to_char[i_slice], i_count, h->stat.f_frame_qp[i_slice] / i_count, (double)h->stat.i_frame_size[i_slice] / i_count ); } } } /* 示例 * x264 [info]: consecutive B-frames: 3.0% 10.0% 63.0% 24.0% * */ if( h->param.i_bframe && h->stat.i_frame_count[SLICE_TYPE_B] ) { //B帧相关信息 char *p = buf; int den = 0; // weight by number of frames (including the I/P-frames) that are in a sequence of N B-frames for( int i = 0; i <= h->param.i_bframe; i++ ) den += (i+1) * h->stat.i_consecutive_bframes[i]; for( int i = 0; i <= h->param.i_bframe; i++ ) p += sprintf( p, " %4.1f%%", 100. * (i+1) * h->stat.i_consecutive_bframes[i] / den ); x264_log( h, X264_LOG_INFO, "consecutive B-frames:%s\n", buf ); } for( int i_type = 0; i_type < 2; i_type++ ) for( int i = 0; i < X264_PARTTYPE_MAX; i++ ) { if( i == D_DIRECT_8x8 ) continue; /* direct is counted as its own type */ i_mb_count_size[i_type][x264_mb_partition_pixel_table[i]] += h->stat.i_mb_partition[i_type][i]; } /* MB types used */ /* 示例 * x264 [info]: mb I I16..4: 15.3% 37.5% 47.3% * x264 [info]: mb P I16..4: 0.6% 0.4% 0.2% P16..4: 34.6% 21.2% 12.7% 0.0% 0.0% skip:30.4% * x264 [info]: mb B I16..4: 0.0% 0.0% 0.0% B16..8: 21.2% 4.1% 0.7% direct: 0.8% skip:73.1% L0:28.7% L1:53.0% BI:18.3% */ if( h->stat.i_frame_count[SLICE_TYPE_I] > 0 ) { int64_t *i_mb_count = h->stat.i_mb_count[SLICE_TYPE_I]; double i_count = h->stat.i_frame_count[SLICE_TYPE_I] * h->mb.i_mb_count / 100.0; //Intra宏块信息-存于buf //从左到右3个信息，依次为I16x16,I8x8,I4x4 x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); x264_log( h, X264_LOG_INFO, "mb I %s\n", buf ); } if( h->stat.i_frame_count[SLICE_TYPE_P] > 0 ) { int64_t *i_mb_count = h->stat.i_mb_count[SLICE_TYPE_P]; double i_count = h->stat.i_frame_count[SLICE_TYPE_P] * h->mb.i_mb_count / 100.0; int64_t *i_mb_size = i_mb_count_size[SLICE_TYPE_P]; //Intra宏块信息-存于buf x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); //Intra宏块信息-放在最前面 //后面添加P宏块信息 //从左到右6个信息，依次为P16x16, P16x8+P8x16, P8x8, P8x4+P4x8, P4x4, PSKIP x264_log( h, X264_LOG_INFO, "mb P %s P16..4: %4.1f%% %4.1f%% %4.1f%% %4.1f%% %4.1f%% skip:%4.1f%%\n", buf, i_mb_size[PIXEL_16x16] / (i_count*4), (i_mb_size[PIXEL_16x8] + i_mb_size[PIXEL_8x16]) / (i_count*4), i_mb_size[PIXEL_8x8] / (i_count*4), (i_mb_size[PIXEL_8x4] + i_mb_size[PIXEL_4x8]) / (i_count*4), i_mb_size[PIXEL_4x4] / (i_count*4), i_mb_count[P_SKIP] / i_count ); } if( h->stat.i_frame_count[SLICE_TYPE_B] > 0 ) { int64_t *i_mb_count = h->stat.i_mb_count[SLICE_TYPE_B]; double i_count = h->stat.i_frame_count[SLICE_TYPE_B] * h->mb.i_mb_count / 100.0; double i_mb_list_count; int64_t *i_mb_size = i_mb_count_size[SLICE_TYPE_B]; int64_t list_count[3] = {0}; /* 0 == L0, 1 == L1, 2 == BI */ //Intra宏块信息 x264_print_intra( i_mb_count, i_count, b_print_pcm, buf ); for( int i = 0; i < X264_PARTTYPE_MAX; i++ ) for( int j = 0; j < 2; j++ ) { int l0 = x264_mb_type_list_table[i][0][j]; int l1 = x264_mb_type_list_table[i][1][j]; if( l0 || l1 ) list_count[l1+l0*l1] += h->stat.i_mb_count[SLICE_TYPE_B][i] * 2; } list_count[0] += h->stat.i_mb_partition[SLICE_TYPE_B][D_L0_8x8]; list_count[1] += h->stat.i_mb_partition[SLICE_TYPE_B][D_L1_8x8]; list_count[2] += h->stat.i_mb_partition[SLICE_TYPE_B][D_BI_8x8]; i_mb_count[B_DIRECT] += (h->stat.i_mb_partition[SLICE_TYPE_B][D_DIRECT_8x8]+2)/4; i_mb_list_count = (list_count[0] + list_count[1] + list_count[2]) / 100.0; //Intra宏块信息-放在最前面 //后面添加B宏块信息 //从左到右5个信息，依次为B16x16, B16x8+B8x16, B8x8, BDIRECT, BSKIP // //SKIP和DIRECT区别 //P_SKIP的CBP为0,无像素残差，无运动矢量残 //B_SKIP宏块的模式为B_DIRECT且CBP为0,无像素残差，无运动矢量残 //B_DIRECT的CBP不为0,有像素残差，无运动矢量残 sprintf( buf + strlen(buf), " B16..8: %4.1f%% %4.1f%% %4.1f%% direct:%4.1f%% skip:%4.1f%%", i_mb_size[PIXEL_16x16] / (i_count*4), (i_mb_size[PIXEL_16x8] + i_mb_size[PIXEL_8x16]) / (i_count*4), i_mb_size[PIXEL_8x8] / (i_count*4), i_mb_count[B_DIRECT] / i_count, i_mb_count[B_SKIP] / i_count ); if( i_mb_list_count != 0 ) sprintf( buf + strlen(buf), " L0:%4.1f%% L1:%4.1f%% BI:%4.1f%%", list_count[0] / i_mb_list_count, list_count[1] / i_mb_list_count, list_count[2] / i_mb_list_count ); x264_log( h, X264_LOG_INFO, "mb B %s\n", buf ); } //码率控制信息 /* 示例 * x264 [info]: final ratefactor: 20.01 */ x264_ratecontrol_summary( h ); if( h->stat.i_frame_count[SLICE_TYPE_I] + h->stat.i_frame_count[SLICE_TYPE_P] + h->stat.i_frame_count[SLICE_TYPE_B] > 0 ) { #define SUM3(p) (p[SLICE_TYPE_I] + p[SLICE_TYPE_P] + p[SLICE_TYPE_B]) #define SUM3b(p,o) (p[SLICE_TYPE_I][o] + p[SLICE_TYPE_P][o] + p[SLICE_TYPE_B][o]) int64_t i_i8x8 = SUM3b( h->stat.i_mb_count, I_8x8 ); int64_t i_intra = i_i8x8 + SUM3b( h->stat.i_mb_count, I_4x4 ) + SUM3b( h->stat.i_mb_count, I_16x16 ); int64_t i_all_intra = i_intra + SUM3b( h->stat.i_mb_count, I_PCM); int64_t i_skip = SUM3b( h->stat.i_mb_count, P_SKIP ) + SUM3b( h->stat.i_mb_count, B_SKIP ); const int i_count = h->stat.i_frame_count[SLICE_TYPE_I] + h->stat.i_frame_count[SLICE_TYPE_P] + h->stat.i_frame_count[SLICE_TYPE_B]; int64_t i_mb_count = (int64_t)i_count * h->mb.i_mb_count; int64_t i_inter = i_mb_count - i_skip - i_intra; const double duration = h->stat.f_frame_duration[SLICE_TYPE_I] + h->stat.f_frame_duration[SLICE_TYPE_P] + h->stat.f_frame_duration[SLICE_TYPE_B]; float f_bitrate = SUM3(h->stat.i_frame_size) / duration / 125; //隔行 if( PARAM_INTERLACED ) { char *fieldstats = buf; fieldstats[0] = 0; if( i_inter ) fieldstats += sprintf( fieldstats, " inter:%.1f%%", h->stat.i_mb_field[1] * 100.0 / i_inter ); if( i_skip ) fieldstats += sprintf( fieldstats, " skip:%.1f%%", h->stat.i_mb_field[2] * 100.0 / i_skip ); x264_log( h, X264_LOG_INFO, "field mbs: intra: %.1f%%%s\n", h->stat.i_mb_field[0] * 100.0 / i_intra, buf ); } //8x8DCT信息 if( h->pps->b_transform_8x8_mode ) { buf[0] = 0; if( h->stat.i_mb_count_8x8dct[0] ) sprintf( buf, " inter:%.1f%%", 100. * h->stat.i_mb_count_8x8dct[1] / h->stat.i_mb_count_8x8dct[0] ); x264_log( h, X264_LOG_INFO, "8x8 transform intra:%.1f%%%s\n", 100. * i_i8x8 / i_intra, buf ); } if( (h->param.analyse.i_direct_mv_pred == X264_DIRECT_PRED_AUTO || (h->stat.i_direct_frames[0] && h->stat.i_direct_frames[1])) && h->stat.i_frame_count[SLICE_TYPE_B] ) { x264_log( h, X264_LOG_INFO, "direct mvs spatial:%.1f%% temporal:%.1f%%\n", h->stat.i_direct_frames[1] * 100. / h->stat.i_frame_count[SLICE_TYPE_B], h->stat.i_direct_frames[0] * 100. / h->stat.i_frame_count[SLICE_TYPE_B] ); } buf[0] = 0; int csize = CHROMA444 ? 4 : 1; if( i_mb_count != i_all_intra ) sprintf( buf, " inter: %.1f%% %.1f%% %.1f%%", h->stat.i_mb_cbp[1] * 100.0 / ((i_mb_count - i_all_intra)*4), h->stat.i_mb_cbp[3] * 100.0 / ((i_mb_count - i_all_intra)*csize), h->stat.i_mb_cbp[5] * 100.0 / ((i_mb_count - i_all_intra)*csize) ); /* * 示例 * x264 [info]: coded y,uvDC,uvAC intra: 74.1% 83.3% 58.9% inter: 10.4% 6.6% 0.4% */ x264_log( h, X264_LOG_INFO, "coded y,%s,%s intra: %.1f%% %.1f%% %.1f%%%s\n", CHROMA444?"u":"uvDC", CHROMA444?"v":"uvAC", h->stat.i_mb_cbp[0] * 100.0 / (i_all_intra*4), h->stat.i_mb_cbp[2] * 100.0 / (i_all_intra*csize), h->stat.i_mb_cbp[4] * 100.0 / (i_all_intra*csize), buf ); /* * 帧内预测信息 * 从上到下分别为I16x16,I8x8,I4x4 * 从左到右顺序为Vertical, Horizontal, DC, Plane .... * * 示例 * * x264 [info]: i16 v,h,dc,p: 21% 25% 7% 48% * x264 [info]: i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 23% 13% 6% 5% 5% 6% 8% 10% * x264 [info]: i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 22% 20% 9% 7% 7% 8% 8% 7% 12% * x264 [info]: i8c dc,h,v,p: 43% 20% 27% 10% * */ int64_t fixed_pred_modes[4][9] = {{0}}; int64_t sum_pred_modes[4] = {0}; for( int i = 0; i <= I_PRED_16x16_DC_128; i++ ) { fixed_pred_modes[0][x264_mb_pred_mode16x16_fix[i]] += h->stat.i_mb_pred_mode[0][i]; sum_pred_modes[0] += h->stat.i_mb_pred_mode[0][i]; } if( sum_pred_modes[0] ) x264_log( h, X264_LOG_INFO, "i16 v,h,dc,p: %2.0f%% %2.0f%% %2.0f%% %2.0f%%\n", fixed_pred_modes[0][0] * 100.0 / sum_pred_modes[0], fixed_pred_modes[0][1] * 100.0 / sum_pred_modes[0], fixed_pred_modes[0][2] * 100.0 / sum_pred_modes[0], fixed_pred_modes[0][3] * 100.0 / sum_pred_modes[0] ); for( int i = 1; i <= 2; i++ ) { for( int j = 0; j <= I_PRED_8x8_DC_128; j++ ) { fixed_pred_modes[i][x264_mb_pred_mode4x4_fix(j)] += h->stat.i_mb_pred_mode[i][j]; sum_pred_modes[i] += h->stat.i_mb_pred_mode[i][j]; } if( sum_pred_modes[i] ) x264_log( h, X264_LOG_INFO, "i%d v,h,dc,ddl,ddr,vr,hd,vl,hu: %2.0f%% %2.0f%% %2.0f%% %2.0f%% %2.0f%% %2.0f%% %2.0f%% %2.0f%% %2.0f%%\n", (3-i)*4, fixed_pred_modes[i][0] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][1] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][2] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][3] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][4] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][5] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][6] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][7] * 100.0 / sum_pred_modes[i], fixed_pred_modes[i][8] * 100.0 / sum_pred_modes[i] ); } for( int i = 0; i <= I_PRED_CHROMA_DC_128; i++ ) { fixed_pred_modes[3][x264_mb_chroma_pred_mode_fix[i]] += h->stat.i_mb_pred_mode[3][i]; sum_pred_modes[3] += h->stat.i_mb_pred_mode[3][i]; } if( sum_pred_modes[3] && !CHROMA444 ) x264_log( h, X264_LOG_INFO, "i8c dc,h,v,p: %2.0f%% %2.0f%% %2.0f%% %2.0f%%\n", fixed_pred_modes[3][0] * 100.0 / sum_pred_modes[3], fixed_pred_modes[3][1] * 100.0 / sum_pred_modes[3], fixed_pred_modes[3][2] * 100.0 / sum_pred_modes[3], fixed_pred_modes[3][3] * 100.0 / sum_pred_modes[3] ); if( h->param.analyse.i_weighted_pred >= X264_WEIGHTP_SIMPLE && h->stat.i_frame_count[SLICE_TYPE_P] > 0 ) x264_log( h, X264_LOG_INFO, "Weighted P-Frames: Y:%.1f%% UV:%.1f%%\n", h->stat.i_wpred[0] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P], h->stat.i_wpred[1] * 100.0 / h->stat.i_frame_count[SLICE_TYPE_P] ); /* * 参考帧信息 * 从左到右依次为不同序号的参考帧 * * 示例 * * x264 [info]: ref P L0: 62.5% 19.7% 13.8% 4.0% * x264 [info]: ref B L0: 88.8% 9.4% 1.9% * x264 [info]: ref B L1: 92.6% 7.4% * */ for( int i_list = 0; i_list < 2; i_list++ ) for( int i_slice = 0; i_slice < 2; i_slice++ ) { char *p = buf; int64_t i_den = 0; int i_max = 0; for( int i = 0; i < X264_REF_MAX*2; i++ ) if( h->stat.i_mb_count_ref[i_slice][i_list][i] ) { i_den += h->stat.i_mb_count_ref[i_slice][i_list][i]; i_max = i; } if( i_max == 0 ) continue; for( int i = 0; i <= i_max; i++ ) p += sprintf( p, " %4.1f%%", 100. * h->stat.i_mb_count_ref[i_slice][i_list][i] / i_den ); x264_log( h, X264_LOG_INFO, "ref %c L%d:%s\n", "PB"[i_slice], i_list, buf ); } if( h->param.analyse.b_ssim ) { float ssim = SUM3( h->stat.f_ssim_mean_y ) / duration; x264_log( h, X264_LOG_INFO, "SSIM Mean Y:%.7f (%6.3fdb)\n", ssim, x264_ssim( ssim ) ); } /* * 示例 * * x264 [info]: PSNR Mean Y:42.967 U:47.163 V:47.000 Avg:43.950 Global:43.796 kb/s:339.67 * */ if( h->param.analyse.b_psnr ) { x264_log( h, X264_LOG_INFO, "PSNR Mean Y:%6.3f U:%6.3f V:%6.3f Avg:%6.3f Global:%6.3f kb/s:%.2f\n", SUM3( h->stat.f_psnr_mean_y ) / duration, SUM3( h->stat.f_psnr_mean_u ) / duration, SUM3( h->stat.f_psnr_mean_v ) / duration, SUM3( h->stat.f_psnr_average ) / duration, x264_psnr( SUM3( h->stat.f_ssd_global ), duration * i_yuv_size ), f_bitrate ); } else x264_log( h, X264_LOG_INFO, "kb/s:%.2f\n", f_bitrate ); } //各种释放 /* rc */ x264_ratecontrol_delete( h ); /* param */ if( h->param.rc.psz_stat_out ) free( h->param.rc.psz_stat_out ); if( h->param.rc.psz_stat_in ) free( h->param.rc.psz_stat_in ); x264_cqm_delete( h ); x264_free( h->nal_buffer ); x264_free( h->reconfig_h ); x264_analyse_free_costs( h ); if( h->i_thread_frames > 1 ) h = h->thread[h->i_thread_phase]; /* frames */ x264_frame_delete_list( h->frames.unused[0] ); x264_frame_delete_list( h->frames.unused[1] ); x264_frame_delete_list( h->frames.current ); x264_frame_delete_list( h->frames.blank_unused ); h = h->thread[0]; for( int i = 0; i < h->i_thread_frames; i++ ) if( h->thread[i]->b_thread_active ) for( int j = 0; j < h->thread[i]->i_ref[0]; j++ ) if( h->thread[i]->fref[0][j] && h->thread[i]->fref[0][j]->b_duplicate ) x264_frame_delete( h->thread[i]->fref[0][j] ); if( h->param.i_lookahead_threads > 1 ) for( int i = 0; i < h->param.i_lookahead_threads; i++ ) x264_free( h->lookahead_thread[i] ); for( int i = h->param.i_threads - 1; i >= 0; i-- ) { x264_frame_t **frame; if( !h->param.b_sliced_threads || i == 0 ) { for( frame = h->thread[i]->frames.reference; *frame; frame++ ) { assert( (*frame)->i_reference_count > 0 ); (*frame)->i_reference_count--; if( (*frame)->i_reference_count == 0 ) x264_frame_delete( *frame ); } frame = &h->thread[i]->fdec; if( *frame ) { assert( (*frame)->i_reference_count > 0 ); (*frame)->i_reference_count--; if( (*frame)->i_reference_count == 0 ) x264_frame_delete( *frame ); } x264_macroblock_cache_free( h->thread[i] ); } x264_macroblock_thread_free( h->thread[i], 0 ); x264_free( h->thread[i]->out.p_bitstream ); x264_free( h->thread[i]->out.nal ); x264_pthread_mutex_destroy( &h->thread[i]->mutex ); x264_pthread_cond_destroy( &h->thread[i]->cv ); x264_free( h->thread[i] ); } #if HAVE_OPENCL x264_opencl_close_library( ocl ); #endif }
从源代码可以看出，x264_encoder_close()主要用于输出编码的统计信息。源代码中已经做了比较充分的注释，就不再详细叙述了。其中输出日志的时候用到了libx264中输出日志的API函数libx264()，下面记录一下。
x264_log()
x264_log()用于输出日志。该函数的定义位于common\common.c，如下所示。
/**************************************************************************** * x264_log: ****************************************************************************/ //日志输出函数 void x264_log( x264_t *h, int i_level, const char *psz_fmt, ... ) { if( !h || i_level <= h->param.i_log_level ) { va_list arg; va_start( arg, psz_fmt ); if( !h ) x264_log_default( NULL, i_level, psz_fmt, arg );//默认日志输出函数 else h->param.pf_log( h->param.p_log_private, i_level, psz_fmt, arg ); va_end( arg ); } }
可以看出x264_log()再开始的时候做了一个判断：只有该条日志级别i_level小于当前系统的日志级别param.i_log_level的时候，才会输出日志。libx264中定义了下面几种日志级别，数值越小，代表日志越紧急。
/* Log level */ #define X264_LOG_NONE (-1) #define X264_LOG_ERROR 0 #define X264_LOG_WARNING 1 #define X264_LOG_INFO 2 #define X264_LOG_DEBUG 3
接 下来x264_log()会根据输入的结构体x264_t是否为空来决定是调用x264_log_default()或者是x264_t中的 param.pf_log()函数。假如都使用默认配置的话，param.pf_log()在x264_param_default()函数中也会被设置 为指向x264_log_default()。因此可以继续看一下x264_log_default()函数。
x264_log_default()
x264_log_default()是libx264默认的日志输出函数。该函数的定义如下所示。
//默认日志输出函数 static void x264_log_default( void *p_unused, int i_level, const char *psz_fmt, va_list arg ) { char *psz_prefix; //日志级别 switch( i_level ) { case X264_LOG_ERROR: psz_prefix = "error"; break; case X264_LOG_WARNING: psz_prefix = "warning"; break; case X264_LOG_INFO: psz_prefix = "info"; break; case X264_LOG_DEBUG: psz_prefix = "debug"; break; default: psz_prefix = "unknown"; break; } //日志级别两边加上"[]" //输出到stderr fprintf( stderr, "x264 [%s]: ", psz_prefix ); x264_vfprintf( stderr, psz_fmt, arg ); }
从源代码可以看出，x264_log_default()会在日志信息前面加上形如"x264 [日志级别]"的信息，然后将处理后的日志输出到stderr。
至 此，对x264中x264_encoder_open()，x264_encoder_headers()，和x264_encoder_close() 这三个函数的分析就完成了。下一篇文章继续记录x264编码器主干部分的x264_encoder_encode()函数。
