/* * Copyright (c) 2010 The WebM project authors. All Rights Reserved. * * Use of this source code is governed by a BSD-style license * that can be found in the LICENSE file in the root of the source * tree. An additional intellectual property rights grant can be found * in the file PATENTS. All contributing project authors may * be found in the AUTHORS file in the root of the source tree. */ #if !defined(WIN32) && CONFIG_OS_SUPPORT == 1# include <unistd.h>#endif#include "onyxd_int.h"#include "vpx_mem/vpx_mem.h"#include "vp8/common/threading.h" #include "vp8/common/loopfilter.h"#include "vp8/common/extend.h"#include "vpx_ports/vpx_timer.h"#include "detokenize.h"#include "vp8/common/reconinter.h"#include "reconintra_mt.h"#if CONFIG_ERROR_CONCEALMENT#include "error_concealment.h"#endif extern void mb_init_dequantizer(VP8D_COMP *pbi, MACROBLOCKD *xd);extern void clamp_mvs(MACROBLOCKD *xd);extern void vp8_build_uvmvs(MACROBLOCKD *x, int fullpixel); #if CONFIG_RUNTIME_CPU_DETECT#define RTCD_VTABLE(x) (&(pbi)->common.rtcd.x)#else#define RTCD_VTABLE(x) NULL#endif static void setup_decoding_thread_data(VP8D_COMP *pbi, MACROBLOCKD *xd, MB_ROW_DEC *mbrd, int count){ VP8_COMMON *const pc = & pbi->common; int i, j; for (i = 0; i < count; i++) { MACROBLOCKD *mbd = &mbrd[i].mbd;#if CONFIG_RUNTIME_CPU_DETECT mbd->rtcd = xd->rtcd;#endif mbd->subpixel_predict = xd->subpixel_predict; mbd->subpixel_predict8x4 = xd->subpixel_predict8x4; mbd->subpixel_predict8x8 = xd->subpixel_predict8x8; mbd->subpixel_predict16x16 = xd->subpixel_predict16x16; mbd->mode_info_context = pc->mi + pc->mode_info_stride * (i + 1); mbd->mode_info_stride = pc->mode_info_stride; mbd->frame_type = pc->frame_type; mbd->frames_since_golden = pc->frames_since_golden; mbd->frames_till_alt_ref_frame = pc->frames_till_alt_ref_frame; mbd->pre = pc->yv12_fb[pc->lst_fb_idx]; mbd->dst = pc->yv12_fb[pc->new_fb_idx]; vp8_setup_block_dptrs(mbd); vp8_build_block_doffsets(mbd); mbd->segmentation_enabled = xd->segmentation_enabled; mbd->mb_segement_abs_delta = xd->mb_segement_abs_delta; vpx_memcpy(mbd->segment_feature_data, xd->segment_feature_data, sizeof(xd->segment_feature_data)); /*signed char ref_lf_deltas[MAX_REF_LF_DELTAS];*/ vpx_memcpy(mbd->ref_lf_deltas, xd->ref_lf_deltas, sizeof(xd->ref_lf_deltas)); /*signed char mode_lf_deltas[MAX_MODE_LF_DELTAS];*/ vpx_memcpy(mbd->mode_lf_deltas, xd->mode_lf_deltas, sizeof(xd->mode_lf_deltas)); /*unsigned char mode_ref_lf_delta_enabled; unsigned char mode_ref_lf_delta_update;*/ mbd->mode_ref_lf_delta_enabled = xd->mode_ref_lf_delta_enabled; mbd->mode_ref_lf_delta_update = xd->mode_ref_lf_delta_update; mbd->current_bc = &pbi->bc2; for (j = 0; j < 25; j++) { mbd->block[j].dequant = xd->block[j].dequant; } } for (i=0; i< pc->mb_rows; i++) pbi->mt_current_mb_col[i]=-1;} static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int mb_col){ int eobtotal = 0; int i, do_clamp = xd->mode_info_context->mbmi.need_to_clamp_mvs; if (xd->mode_info_context->mbmi.mb_skip_coeff) { vp8_reset_mb_tokens_context(xd); } else { eobtotal = vp8_decode_mb_tokens(pbi, xd); } /* Perform temporary clamping of the MV to be used for prediction */ if (do_clamp) { clamp_mvs(xd); } eobtotal |= (xd->mode_info_context->mbmi.mode == B_PRED || xd->mode_info_context->mbmi.mode == SPLITMV); if (!eobtotal) { /* Special case: Force the loopfilter to skip when eobtotal and * mb_skip_coeff are zero. * */ xd->mode_info_context->mbmi.mb_skip_coeff = 1; /*mt_skip_recon_mb(pbi, xd, mb_row, mb_col);*/ if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) { vp8mt_build_intra_predictors_mbuv_s(pbi, xd, mb_row, mb_col); vp8mt_build_intra_predictors_mby_s(pbi, xd, mb_row, mb_col); } else { vp8_build_inter16x16_predictors_mb(xd, xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, xd->dst.y_stride, xd->dst.uv_stride); } return; } if (xd->segmentation_enabled) mb_init_dequantizer(pbi, xd); /* do prediction */ if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) { vp8mt_build_intra_predictors_mbuv(pbi, xd, mb_row, mb_col); if (xd->mode_info_context->mbmi.mode != B_PRED) { vp8mt_build_intra_predictors_mby(pbi, xd, mb_row, mb_col); } else { vp8mt_intra_prediction_down_copy(pbi, xd, mb_row, mb_col); } } else { vp8_build_inter_predictors_mb(xd); } #if CONFIG_ERROR_CONCEALMENT if (pbi->ec_enabled && (mb_row * pbi->common.mb_cols + mb_col >= pbi->mvs_corrupt_from_mb || vp8dx_bool_error(xd->current_bc))) { /* MB with corrupt residuals or corrupt mode/motion vectors. * Better to use the predictor as reconstruction. */ vpx_memset(xd->qcoeff, 0, sizeof(xd->qcoeff)); vp8_conceal_corrupt_mb(xd); return; }#endif /* dequantization and idct */ if (xd->mode_info_context->mbmi.mode != B_PRED && xd->mode_info_context->mbmi.mode != SPLITMV) { BLOCKD *b = &xd->block[24]; DEQUANT_INVOKE(&pbi->dequant, block)(b); /* do 2nd order transform on the dc block */ if (xd->eobs[24] > 1) { IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh16)(&b->dqcoeff[0], b->diff); ((int *)b->qcoeff)[0] = 0; ((int *)b->qcoeff)[1] = 0; ((int *)b->qcoeff)[2] = 0; ((int *)b->qcoeff)[3] = 0; ((int *)b->qcoeff)[4] = 0; ((int *)b->qcoeff)[5] = 0; ((int *)b->qcoeff)[6] = 0; ((int *)b->qcoeff)[7] = 0; } else { IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh1)(&b->dqcoeff[0], b->diff); ((int *)b->qcoeff)[0] = 0; } DEQUANT_INVOKE (&pbi->dequant, dc_idct_add_y_block) (xd->qcoeff, xd->block[0].dequant, xd->predictor, xd->dst.y_buffer, xd->dst.y_stride, xd->eobs, xd->block[24].diff); } else if (xd->mode_info_context->mbmi.mode == B_PRED) { for (i = 0; i < 16; i++) { BLOCKD *b = &xd->block[i]; vp8mt_predict_intra4x4(pbi, xd, b->bmi.as_mode, b->predictor, mb_row, mb_col, i); if (xd->eobs[i] > 1) { DEQUANT_INVOKE(&pbi->dequant, idct_add) (b->qcoeff, b->dequant, b->predictor, *(b->base_dst) + b->dst, 16, b->dst_stride); } else { IDCT_INVOKE(RTCD_VTABLE(idct), idct1_scalar_add) (b->qcoeff[0] * b->dequant[0], b->predictor, *(b->base_dst) + b->dst, 16, b->dst_stride); ((int *)b->qcoeff)[0] = 0; } } } else { DEQUANT_INVOKE (&pbi->dequant, idct_add_y_block) (xd->qcoeff, xd->block[0].dequant, xd->predictor, xd->dst.y_buffer, xd->dst.y_stride, xd->eobs); } DEQUANT_INVOKE (&pbi->dequant, idct_add_uv_block) (xd->qcoeff+16*16, xd->block[16].dequant, xd->predictor+16*16, xd->dst.u_buffer, xd->dst.v_buffer, xd->dst.uv_stride, xd->eobs+16);} static THREAD_FUNCTION thread_decoding_proc(void *p_data){ int ithread = ((DECODETHREAD_DATA *)p_data)->ithread; VP8D_COMP *pbi = (VP8D_COMP *)(((DECODETHREAD_DATA *)p_data)->ptr1); MB_ROW_DEC *mbrd = (MB_ROW_DEC *)(((DECODETHREAD_DATA *)p_data)->ptr2); ENTROPY_CONTEXT_PLANES mb_row_left_context; while (1) { if (pbi->b_multithreaded_rd == 0) break; /*if(WaitForSingleObject(pbi->h_event_start_decoding[ithread], INFINITE) == WAIT_OBJECT_0)*/ if (sem_wait(&pbi->h_event_start_decoding[ithread]) == 0) { if (pbi->b_multithreaded_rd == 0) break; else { VP8_COMMON *pc = &pbi->common; MACROBLOCKD *xd = &mbrd->mbd; int mb_row; int num_part = 1 << pbi->common.multi_token_partition; volatile int *last_row_current_mb_col; int nsync = pbi->sync_range; for (mb_row = ithread+1; mb_row < pc->mb_rows; mb_row += (pbi->decoding_thread_count + 1)) { int i; int recon_yoffset, recon_uvoffset; int mb_col; int ref_fb_idx = pc->lst_fb_idx; int dst_fb_idx = pc->new_fb_idx; int recon_y_stride = pc->yv12_fb[ref_fb_idx].y_stride; int recon_uv_stride = pc->yv12_fb[ref_fb_idx].uv_stride; int filter_level; loop_filter_info_n *lfi_n = &pc->lf_info; pbi->mb_row_di[ithread].mb_row = mb_row; pbi->mb_row_di[ithread].mbd.current_bc = &pbi->mbc[mb_row%num_part]; last_row_current_mb_col = &pbi->mt_current_mb_col[mb_row -1]; recon_yoffset = mb_row * recon_y_stride * 16; recon_uvoffset = mb_row * recon_uv_stride * 8; /* reset above block coeffs */ xd->above_context = pc->above_context; xd->left_context = &mb_row_left_context; vpx_memset(&mb_row_left_context, 0, sizeof(mb_row_left_context)); xd->up_available = (mb_row != 0); xd->mb_to_top_edge = -((mb_row * 16)) << 3; xd->mb_to_bottom_edge = ((pc->mb_rows - 1 - mb_row) * 16) << 3; for (mb_col = 0; mb_col < pc->mb_cols; mb_col++) { if ((mb_col & (nsync-1)) == 0) { while (mb_col > (*last_row_current_mb_col - nsync) && *last_row_current_mb_col != pc->mb_cols - 1) { x86_pause_hint(); thread_sleep(0); } } update_blockd_bmi(xd); /* Distance of MB to the various image edges. * These are specified to 8th pel as they are always * compared to values that are in 1/8th pel units. */ xd->mb_to_left_edge = -((mb_col * 16) << 3); xd->mb_to_right_edge = ((pc->mb_cols - 1 - mb_col) * 16) << 3; #if CONFIG_ERROR_CONCEALMENT if (pbi->ec_enabled && (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) && vp8dx_bool_error(xd->current_bc)) { /* We have an intra block with corrupt coefficients, * better to conceal with an inter block. * Interpolate MVs from neighboring MBs * * Note that for the first mb with corrupt residual * in a frame, we might not discover that before * decoding the residual. That happens after this * check, and therefore no inter concealment will be * done. */ vp8_interpolate_motion(xd, mb_row, mb_col, pc->mb_rows, pc->mb_cols, pc->mode_info_stride); }#endif xd->dst.y_buffer = pc->yv12_fb[dst_fb_idx].y_buffer + recon_yoffset; xd->dst.u_buffer = pc->yv12_fb[dst_fb_idx].u_buffer + recon_uvoffset; xd->dst.v_buffer = pc->yv12_fb[dst_fb_idx].v_buffer + recon_uvoffset; xd->left_available = (mb_col != 0); /* Select the appropriate reference frame for this MB */ if (xd->mode_info_context->mbmi.ref_frame == LAST_FRAME) ref_fb_idx = pc->lst_fb_idx; else if (xd->mode_info_context->mbmi.ref_frame == GOLDEN_FRAME) ref_fb_idx = pc->gld_fb_idx; else ref_fb_idx = pc->alt_fb_idx; xd->pre.y_buffer = pc->yv12_fb[ref_fb_idx].y_buffer + recon_yoffset; xd->pre.u_buffer = pc->yv12_fb[ref_fb_idx].u_buffer + recon_uvoffset; xd->pre.v_buffer = pc->yv12_fb[ref_fb_idx].v_buffer + recon_uvoffset; vp8_build_uvmvs(xd, pc->full_pixel); decode_macroblock(pbi, xd, mb_row, mb_col); if (pbi->common.filter_level) { int skip_lf = (xd->mode_info_context->mbmi.mode != B_PRED && xd->mode_info_context->mbmi.mode != SPLITMV && xd->mode_info_context->mbmi.mb_skip_coeff); const int mode_index = lfi_n->mode_lf_lut[xd->mode_info_context->mbmi.mode]; const int seg = xd->mode_info_context->mbmi.segment_id; const int ref_frame = xd->mode_info_context->mbmi.ref_frame; filter_level = lfi_n->lvl[seg][ref_frame][mode_index]; if( mb_row != pc->mb_rows-1 ) { /* Save decoded MB last row data for next-row decoding */ vpx_memcpy((pbi->mt_yabove_row[mb_row + 1] + 32 + mb_col*16), (xd->dst.y_buffer + 15 * recon_y_stride), 16); vpx_memcpy((pbi->mt_uabove_row[mb_row + 1] + 16 + mb_col*8), (xd->dst.u_buffer + 7 * recon_uv_stride), 8); vpx_memcpy((pbi->mt_vabove_row[mb_row + 1] + 16 + mb_col*8), (xd->dst.v_buffer + 7 * recon_uv_stride), 8); } /* save left_col for next MB decoding */ if(mb_col != pc->mb_cols-1) { MODE_INFO *next = xd->mode_info_context +1; if (next->mbmi.ref_frame == INTRA_FRAME) { for (i = 0; i < 16; i++) pbi->mt_yleft_col[mb_row][i] = xd->dst.y_buffer [i* recon_y_stride + 15]; for (i = 0; i < 8; i++) { pbi->mt_uleft_col[mb_row][i] = xd->dst.u_buffer [i* recon_uv_stride + 7]; pbi->mt_vleft_col[mb_row][i] = xd->dst.v_buffer [i* recon_uv_stride + 7]; } } } /* loopfilter on this macroblock. */ if (filter_level) { if(pc->filter_type == NORMAL_LOOPFILTER) { loop_filter_info lfi; FRAME_TYPE frame_type = pc->frame_type; const int hev_index = lfi_n->hev_thr_lut[frame_type][filter_level]; lfi.mblim = lfi_n->mblim[filter_level]; lfi.blim = lfi_n->blim[filter_level]; lfi.lim = lfi_n->lim[filter_level]; lfi.hev_thr = lfi_n->hev_thr[hev_index]; if (mb_col > 0) LF_INVOKE(&pc->rtcd.loopfilter, normal_mb_v) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, normal_b_v) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); /* don't apply across umv border */ if (mb_row > 0) LF_INVOKE(&pc->rtcd.loopfilter, normal_mb_h) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, normal_b_h) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); } else { if (mb_col > 0) LF_INVOKE(&pc->rtcd.loopfilter, simple_mb_v) (xd->dst.y_buffer, recon_y_stride, lfi_n->mblim[filter_level]); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, simple_b_v) (xd->dst.y_buffer, recon_y_stride, lfi_n->blim[filter_level]); /* don't apply across umv border */ if (mb_row > 0) LF_INVOKE(&pc->rtcd.loopfilter, simple_mb_h) (xd->dst.y_buffer, recon_y_stride, lfi_n->mblim[filter_level]); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, simple_b_h) (xd->dst.y_buffer, recon_y_stride, lfi_n->blim[filter_level]); } } } recon_yoffset += 16; recon_uvoffset += 8; ++xd->mode_info_context; /* next mb */ xd->above_context++; /*pbi->mb_row_di[ithread].current_mb_col = mb_col;*/ pbi->mt_current_mb_col[mb_row] = mb_col; } /* adjust to the next row of mbs */ if (pbi->common.filter_level) { if(mb_row != pc->mb_rows-1) { int lasty = pc->yv12_fb[ref_fb_idx].y_width + VP8BORDERINPIXELS; int lastuv = (pc->yv12_fb[ref_fb_idx].y_width>>1) + (VP8BORDERINPIXELS>>1); for (i = 0; i < 4; i++) { pbi->mt_yabove_row[mb_row +1][lasty + i] = pbi->mt_yabove_row[mb_row +1][lasty -1]; pbi->mt_uabove_row[mb_row +1][lastuv + i] = pbi->mt_uabove_row[mb_row +1][lastuv -1]; pbi->mt_vabove_row[mb_row +1][lastuv + i] = pbi->mt_vabove_row[mb_row +1][lastuv -1]; } } } else vp8_extend_mb_row(&pc->yv12_fb[dst_fb_idx], xd->dst.y_buffer + 16, xd->dst.u_buffer + 8, xd->dst.v_buffer + 8); ++xd->mode_info_context; /* skip prediction column */ /* since we have multithread */ xd->mode_info_context += xd->mode_info_stride * pbi->decoding_thread_count; } } } /* add this to each frame */ if ((mbrd->mb_row == pbi->common.mb_rows-1) || ((mbrd->mb_row == pbi->common.mb_rows-2) && (pbi->common.mb_rows % (pbi->decoding_thread_count+1))==1)) { /*SetEvent(pbi->h_event_end_decoding);*/ sem_post(&pbi->h_event_end_decoding); } } return 0 ;} void vp8_decoder_create_threads(VP8D_COMP *pbi){Lines 1–500 of 980. Load more
/* * Copyright (c) 2010 The WebM project authors. All Rights Reserved. * * Use of this source code is governed by a BSD-style license * that can be found in the LICENSE file in the root of the source * tree. An additional intellectual property rights grant can be found * in the file PATENTS. All contributing project authors may * be found in the AUTHORS file in the root of the source tree. */ #if !defined(WIN32) && CONFIG_OS_SUPPORT == 1 # include <unistd.h> #endif #include "onyxd_int.h" #include "vpx_mem/vpx_mem.h" #include "vp8/common/threading.h" #include "vp8/common/loopfilter.h" #include "vp8/common/extend.h" #include "vpx_ports/vpx_timer.h" #include "detokenize.h" #include "vp8/common/reconinter.h" #include "reconintra_mt.h" #if CONFIG_ERROR_CONCEALMENT #include "error_concealment.h" #endif extern void mb_init_dequantizer(VP8D_COMP *pbi, MACROBLOCKD *xd); extern void clamp_mvs(MACROBLOCKD *xd); extern void vp8_build_uvmvs(MACROBLOCKD *x, int fullpixel); #if CONFIG_RUNTIME_CPU_DETECT #define RTCD_VTABLE(x) (&(pbi)->common.rtcd.x) #else #define RTCD_VTABLE(x) NULL #endif static void setup_decoding_thread_data(VP8D_COMP *pbi, MACROBLOCKD *xd, MB_ROW_DEC *mbrd, int count) { VP8_COMMON *const pc = & pbi->common; int i, j; for (i = 0; i < count; i++) { MACROBLOCKD *mbd = &mbrd[i].mbd; #if CONFIG_RUNTIME_CPU_DETECT mbd->rtcd = xd->rtcd; #endif mbd->subpixel_predict = xd->subpixel_predict; mbd->subpixel_predict8x4 = xd->subpixel_predict8x4; mbd->subpixel_predict8x8 = xd->subpixel_predict8x8; mbd->subpixel_predict16x16 = xd->subpixel_predict16x16; mbd->mode_info_context = pc->mi + pc->mode_info_stride * (i + 1); mbd->mode_info_stride = pc->mode_info_stride; mbd->frame_type = pc->frame_type; mbd->frames_since_golden = pc->frames_since_golden; mbd->frames_till_alt_ref_frame = pc->frames_till_alt_ref_frame; mbd->pre = pc->yv12_fb[pc->lst_fb_idx]; mbd->dst = pc->yv12_fb[pc->new_fb_idx]; vp8_setup_block_dptrs(mbd); vp8_build_block_doffsets(mbd); mbd->segmentation_enabled = xd->segmentation_enabled; mbd->mb_segement_abs_delta = xd->mb_segement_abs_delta; vpx_memcpy(mbd->segment_feature_data, xd->segment_feature_data, sizeof(xd->segment_feature_data)); /*signed char ref_lf_deltas[MAX_REF_LF_DELTAS];*/ vpx_memcpy(mbd->ref_lf_deltas, xd->ref_lf_deltas, sizeof(xd->ref_lf_deltas)); /*signed char mode_lf_deltas[MAX_MODE_LF_DELTAS];*/ vpx_memcpy(mbd->mode_lf_deltas, xd->mode_lf_deltas, sizeof(xd->mode_lf_deltas)); /*unsigned char mode_ref_lf_delta_enabled; unsigned char mode_ref_lf_delta_update;*/ mbd->mode_ref_lf_delta_enabled = xd->mode_ref_lf_delta_enabled; mbd->mode_ref_lf_delta_update = xd->mode_ref_lf_delta_update; mbd->current_bc = &pbi->bc2; for (j = 0; j < 25; j++) { mbd->block[j].dequant = xd->block[j].dequant; } } for (i=0; i< pc->mb_rows; i++) pbi->mt_current_mb_col[i]=-1; } static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int mb_col) { int eobtotal = 0; int i, do_clamp = xd->mode_info_context->mbmi.need_to_clamp_mvs; if (xd->mode_info_context->mbmi.mb_skip_coeff) { vp8_reset_mb_tokens_context(xd); } else { eobtotal = vp8_decode_mb_tokens(pbi, xd); } /* Perform temporary clamping of the MV to be used for prediction */ if (do_clamp) { clamp_mvs(xd); } eobtotal |= (xd->mode_info_context->mbmi.mode == B_PRED || xd->mode_info_context->mbmi.mode == SPLITMV); if (!eobtotal) { /* Special case: Force the loopfilter to skip when eobtotal and * mb_skip_coeff are zero. * */ xd->mode_info_context->mbmi.mb_skip_coeff = 1; /*mt_skip_recon_mb(pbi, xd, mb_row, mb_col);*/ if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) { vp8mt_build_intra_predictors_mbuv_s(pbi, xd, mb_row, mb_col); vp8mt_build_intra_predictors_mby_s(pbi, xd, mb_row, mb_col); } else { vp8_build_inter16x16_predictors_mb(xd, xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, xd->dst.y_stride, xd->dst.uv_stride); } return; } if (xd->segmentation_enabled) mb_init_dequantizer(pbi, xd); /* do prediction */ if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) { vp8mt_build_intra_predictors_mbuv(pbi, xd, mb_row, mb_col); if (xd->mode_info_context->mbmi.mode != B_PRED) { vp8mt_build_intra_predictors_mby(pbi, xd, mb_row, mb_col); } else { vp8mt_intra_prediction_down_copy(pbi, xd, mb_row, mb_col); } } else { vp8_build_inter_predictors_mb(xd); } #if CONFIG_ERROR_CONCEALMENT if (pbi->ec_enabled && (mb_row * pbi->common.mb_cols + mb_col >= pbi->mvs_corrupt_from_mb || vp8dx_bool_error(xd->current_bc))) { /* MB with corrupt residuals or corrupt mode/motion vectors. * Better to use the predictor as reconstruction. */ vpx_memset(xd->qcoeff, 0, sizeof(xd->qcoeff)); vp8_conceal_corrupt_mb(xd); return; } #endif /* dequantization and idct */ if (xd->mode_info_context->mbmi.mode != B_PRED && xd->mode_info_context->mbmi.mode != SPLITMV) { BLOCKD *b = &xd->block[24]; DEQUANT_INVOKE(&pbi->dequant, block)(b); /* do 2nd order transform on the dc block */ if (xd->eobs[24] > 1) { IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh16)(&b->dqcoeff[0], b->diff); ((int *)b->qcoeff)[0] = 0; ((int *)b->qcoeff)[1] = 0; ((int *)b->qcoeff)[2] = 0; ((int *)b->qcoeff)[3] = 0; ((int *)b->qcoeff)[4] = 0; ((int *)b->qcoeff)[5] = 0; ((int *)b->qcoeff)[6] = 0; ((int *)b->qcoeff)[7] = 0; } else { IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh1)(&b->dqcoeff[0], b->diff); ((int *)b->qcoeff)[0] = 0; } DEQUANT_INVOKE (&pbi->dequant, dc_idct_add_y_block) (xd->qcoeff, xd->block[0].dequant, xd->predictor, xd->dst.y_buffer, xd->dst.y_stride, xd->eobs, xd->block[24].diff); } else if (xd->mode_info_context->mbmi.mode == B_PRED) { for (i = 0; i < 16; i++) { BLOCKD *b = &xd->block[i]; vp8mt_predict_intra4x4(pbi, xd, b->bmi.as_mode, b->predictor, mb_row, mb_col, i); if (xd->eobs[i] > 1) { DEQUANT_INVOKE(&pbi->dequant, idct_add) (b->qcoeff, b->dequant, b->predictor, *(b->base_dst) + b->dst, 16, b->dst_stride); } else { IDCT_INVOKE(RTCD_VTABLE(idct), idct1_scalar_add) (b->qcoeff[0] * b->dequant[0], b->predictor, *(b->base_dst) + b->dst, 16, b->dst_stride); ((int *)b->qcoeff)[0] = 0; } } } else { DEQUANT_INVOKE (&pbi->dequant, idct_add_y_block) (xd->qcoeff, xd->block[0].dequant, xd->predictor, xd->dst.y_buffer, xd->dst.y_stride, xd->eobs); } DEQUANT_INVOKE (&pbi->dequant, idct_add_uv_block) (xd->qcoeff+16*16, xd->block[16].dequant, xd->predictor+16*16, xd->dst.u_buffer, xd->dst.v_buffer, xd->dst.uv_stride, xd->eobs+16); } static THREAD_FUNCTION thread_decoding_proc(void *p_data) { int ithread = ((DECODETHREAD_DATA *)p_data)->ithread; VP8D_COMP *pbi = (VP8D_COMP *)(((DECODETHREAD_DATA *)p_data)->ptr1); MB_ROW_DEC *mbrd = (MB_ROW_DEC *)(((DECODETHREAD_DATA *)p_data)->ptr2); ENTROPY_CONTEXT_PLANES mb_row_left_context; while (1) { if (pbi->b_multithreaded_rd == 0) break; /*if(WaitForSingleObject(pbi->h_event_start_decoding[ithread], INFINITE) == WAIT_OBJECT_0)*/ if (sem_wait(&pbi->h_event_start_decoding[ithread]) == 0) { if (pbi->b_multithreaded_rd == 0) break; else { VP8_COMMON *pc = &pbi->common; MACROBLOCKD *xd = &mbrd->mbd; int mb_row; int num_part = 1 << pbi->common.multi_token_partition; volatile int *last_row_current_mb_col; int nsync = pbi->sync_range; for (mb_row = ithread+1; mb_row < pc->mb_rows; mb_row += (pbi->decoding_thread_count + 1)) { int i; int recon_yoffset, recon_uvoffset; int mb_col; int ref_fb_idx = pc->lst_fb_idx; int dst_fb_idx = pc->new_fb_idx; int recon_y_stride = pc->yv12_fb[ref_fb_idx].y_stride; int recon_uv_stride = pc->yv12_fb[ref_fb_idx].uv_stride; int filter_level; loop_filter_info_n *lfi_n = &pc->lf_info; pbi->mb_row_di[ithread].mb_row = mb_row; pbi->mb_row_di[ithread].mbd.current_bc = &pbi->mbc[mb_row%num_part]; last_row_current_mb_col = &pbi->mt_current_mb_col[mb_row -1]; recon_yoffset = mb_row * recon_y_stride * 16; recon_uvoffset = mb_row * recon_uv_stride * 8; /* reset above block coeffs */ xd->above_context = pc->above_context; xd->left_context = &mb_row_left_context; vpx_memset(&mb_row_left_context, 0, sizeof(mb_row_left_context)); xd->up_available = (mb_row != 0); xd->mb_to_top_edge = -((mb_row * 16)) << 3; xd->mb_to_bottom_edge = ((pc->mb_rows - 1 - mb_row) * 16) << 3; for (mb_col = 0; mb_col < pc->mb_cols; mb_col++) { if ((mb_col & (nsync-1)) == 0) { while (mb_col > (*last_row_current_mb_col - nsync) && *last_row_current_mb_col != pc->mb_cols - 1) { x86_pause_hint(); thread_sleep(0); } } update_blockd_bmi(xd); /* Distance of MB to the various image edges. * These are specified to 8th pel as they are always * compared to values that are in 1/8th pel units. */ xd->mb_to_left_edge = -((mb_col * 16) << 3); xd->mb_to_right_edge = ((pc->mb_cols - 1 - mb_col) * 16) << 3; #if CONFIG_ERROR_CONCEALMENT if (pbi->ec_enabled && (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME) && vp8dx_bool_error(xd->current_bc)) { /* We have an intra block with corrupt coefficients, * better to conceal with an inter block. * Interpolate MVs from neighboring MBs * * Note that for the first mb with corrupt residual * in a frame, we might not discover that before * decoding the residual. That happens after this * check, and therefore no inter concealment will be * done. */ vp8_interpolate_motion(xd, mb_row, mb_col, pc->mb_rows, pc->mb_cols, pc->mode_info_stride); } #endif xd->dst.y_buffer = pc->yv12_fb[dst_fb_idx].y_buffer + recon_yoffset; xd->dst.u_buffer = pc->yv12_fb[dst_fb_idx].u_buffer + recon_uvoffset; xd->dst.v_buffer = pc->yv12_fb[dst_fb_idx].v_buffer + recon_uvoffset; xd->left_available = (mb_col != 0); /* Select the appropriate reference frame for this MB */ if (xd->mode_info_context->mbmi.ref_frame == LAST_FRAME) ref_fb_idx = pc->lst_fb_idx; else if (xd->mode_info_context->mbmi.ref_frame == GOLDEN_FRAME) ref_fb_idx = pc->gld_fb_idx; else ref_fb_idx = pc->alt_fb_idx; xd->pre.y_buffer = pc->yv12_fb[ref_fb_idx].y_buffer + recon_yoffset; xd->pre.u_buffer = pc->yv12_fb[ref_fb_idx].u_buffer + recon_uvoffset; xd->pre.v_buffer = pc->yv12_fb[ref_fb_idx].v_buffer + recon_uvoffset; vp8_build_uvmvs(xd, pc->full_pixel); decode_macroblock(pbi, xd, mb_row, mb_col); if (pbi->common.filter_level) { int skip_lf = (xd->mode_info_context->mbmi.mode != B_PRED && xd->mode_info_context->mbmi.mode != SPLITMV && xd->mode_info_context->mbmi.mb_skip_coeff); const int mode_index = lfi_n->mode_lf_lut[xd->mode_info_context->mbmi.mode]; const int seg = xd->mode_info_context->mbmi.segment_id; const int ref_frame = xd->mode_info_context->mbmi.ref_frame; filter_level = lfi_n->lvl[seg][ref_frame][mode_index]; if( mb_row != pc->mb_rows-1 ) { /* Save decoded MB last row data for next-row decoding */ vpx_memcpy((pbi->mt_yabove_row[mb_row + 1] + 32 + mb_col*16), (xd->dst.y_buffer + 15 * recon_y_stride), 16); vpx_memcpy((pbi->mt_uabove_row[mb_row + 1] + 16 + mb_col*8), (xd->dst.u_buffer + 7 * recon_uv_stride), 8); vpx_memcpy((pbi->mt_vabove_row[mb_row + 1] + 16 + mb_col*8), (xd->dst.v_buffer + 7 * recon_uv_stride), 8); } /* save left_col for next MB decoding */ if(mb_col != pc->mb_cols-1) { MODE_INFO *next = xd->mode_info_context +1; if (next->mbmi.ref_frame == INTRA_FRAME) { for (i = 0; i < 16; i++) pbi->mt_yleft_col[mb_row][i] = xd->dst.y_buffer [i* recon_y_stride + 15]; for (i = 0; i < 8; i++) { pbi->mt_uleft_col[mb_row][i] = xd->dst.u_buffer [i* recon_uv_stride + 7]; pbi->mt_vleft_col[mb_row][i] = xd->dst.v_buffer [i* recon_uv_stride + 7]; } } } /* loopfilter on this macroblock. */ if (filter_level) { if(pc->filter_type == NORMAL_LOOPFILTER) { loop_filter_info lfi; FRAME_TYPE frame_type = pc->frame_type; const int hev_index = lfi_n->hev_thr_lut[frame_type][filter_level]; lfi.mblim = lfi_n->mblim[filter_level]; lfi.blim = lfi_n->blim[filter_level]; lfi.lim = lfi_n->lim[filter_level]; lfi.hev_thr = lfi_n->hev_thr[hev_index]; if (mb_col > 0) LF_INVOKE(&pc->rtcd.loopfilter, normal_mb_v) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, normal_b_v) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); /* don't apply across umv border */ if (mb_row > 0) LF_INVOKE(&pc->rtcd.loopfilter, normal_mb_h) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, normal_b_h) (xd->dst.y_buffer, xd->dst.u_buffer, xd->dst.v_buffer, recon_y_stride, recon_uv_stride, &lfi); } else { if (mb_col > 0) LF_INVOKE(&pc->rtcd.loopfilter, simple_mb_v) (xd->dst.y_buffer, recon_y_stride, lfi_n->mblim[filter_level]); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, simple_b_v) (xd->dst.y_buffer, recon_y_stride, lfi_n->blim[filter_level]); /* don't apply across umv border */ if (mb_row > 0) LF_INVOKE(&pc->rtcd.loopfilter, simple_mb_h) (xd->dst.y_buffer, recon_y_stride, lfi_n->mblim[filter_level]); if (!skip_lf) LF_INVOKE(&pc->rtcd.loopfilter, simple_b_h) (xd->dst.y_buffer, recon_y_stride, lfi_n->blim[filter_level]); } } } recon_yoffset += 16; recon_uvoffset += 8; ++xd->mode_info_context; /* next mb */ xd->above_context++; /*pbi->mb_row_di[ithread].current_mb_col = mb_col;*/ pbi->mt_current_mb_col[mb_row] = mb_col; } /* adjust to the next row of mbs */ if (pbi->common.filter_level) { if(mb_row != pc->mb_rows-1) { int lasty = pc->yv12_fb[ref_fb_idx].y_width + VP8BORDERINPIXELS; int lastuv = (pc->yv12_fb[ref_fb_idx].y_width>>1) + (VP8BORDERINPIXELS>>1); for (i = 0; i < 4; i++) { pbi->mt_yabove_row[mb_row +1][lasty + i] = pbi->mt_yabove_row[mb_row +1][lasty -1]; pbi->mt_uabove_row[mb_row +1][lastuv + i] = pbi->mt_uabove_row[mb_row +1][lastuv -1]; pbi->mt_vabove_row[mb_row +1][lastuv + i] = pbi->mt_vabove_row[mb_row +1][lastuv -1]; } } } else vp8_extend_mb_row(&pc->yv12_fb[dst_fb_idx], xd->dst.y_buffer + 16, xd->dst.u_buffer + 8, xd->dst.v_buffer + 8); ++xd->mode_info_context; /* skip prediction column */ /* since we have multithread */ xd->mode_info_context += xd->mode_info_stride * pbi->decoding_thread_count; } } } /* add this to each frame */ if ((mbrd->mb_row == pbi->common.mb_rows-1) || ((mbrd->mb_row == pbi->common.mb_rows-2) && (pbi->common.mb_rows % (pbi->decoding_thread_count+1))==1)) { /*SetEvent(pbi->h_event_end_decoding);*/ sem_post(&pbi->h_event_end_decoding); } } return 0 ; } void vp8_decoder_create_threads(VP8D_COMP *pbi) {