vpx/vp9/common/vp9_reconinter.h

107 lines
4.4 KiB
C
Raw Normal View History

2010-05-18 17:58:33 +02:00
/*
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
2010-05-18 17:58:33 +02:00
*
* 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.
2010-05-18 17:58:33 +02:00
*/
#ifndef VP9_COMMON_VP9_RECONINTER_H_
#define VP9_COMMON_VP9_RECONINTER_H_
2010-05-18 17:58:33 +02:00
#include "vp9/common/vp9_filter.h"
#include "vp9/common/vp9_onyxc_int.h"
#include "vpx/vpx_integer.h"
#include "vpx_dsp/vpx_filter.h"
#ifdef __cplusplus
extern "C" {
#endif
static INLINE void inter_predictor(const uint8_t *src, int src_stride,
uint8_t *dst, int dst_stride,
const int subpel_x, const int subpel_y,
const struct scale_factors *sf, int w, int h,
int ref, const InterpKernel *kernel, int xs,
int ys) {
sf->predict[subpel_x != 0][subpel_y != 0][ref](
src, src_stride, dst, dst_stride, kernel[subpel_x], xs, kernel[subpel_y],
ys, w, h);
}
Try again to merge branch 'frame-parallel' into master branch. In frame parallel decode, libvpx decoder decodes several frames on all cpus in parallel fashion. If not being flushed, it will only return frame when all the cpus are busy. If getting flushed, it will return all the frames in the decoder. Compare with current serial decode mode in which libvpx decoder is idle between decode calls, libvpx decoder is busy between decode calls. Current frame parallel decode will only speed up the decoding for frame parallel encoded videos. For non frame parallel encoded videos, frame parallel decode is slower than serial decode due to lack of loopfilter worker thread. There are still some known issues that need to be addressed. For example: decode frame parallel videos with segmentation enabled is not right sometimes. * frame-parallel: Add error handling for frame parallel decode and unit test for that. Fix a bug in frame parallel decode and add a unit test for that. Add two test vectors to test frame parallel decode. Add key frame seeking to webmdec and webm_video_source. Implement frame parallel decode for VP9. Increase the thread test range to cover 5, 6, 7, 8 threads. Fix a bug in adding frame parallel unit test. Add VP9 frame-parallel unit test. Manually pick "Make the api behavior conform to api spec." from master branch. Move vp9_dec_build_inter_predictors_* to decoder folder. Add segmentation map array for current and last frame segmentation. Include the right header for VP9 worker thread. Move vp9_thread.* to common. ctrl_get_reference does not need user_priv. Seperate the frame buffers from VP9 encoder/decoder structure. Revert "Revert "Revert "Revert 3 patches from Hangyu to get Chrome to build:""" Conflicts: test/codec_factory.h test/decode_test_driver.cc test/decode_test_driver.h test/invalid_file_test.cc test/test-data.sha1 test/test.mk test/test_vectors.cc vp8/vp8_dx_iface.c vp9/common/vp9_alloccommon.c vp9/common/vp9_entropymode.c vp9/common/vp9_loopfilter_thread.c vp9/common/vp9_loopfilter_thread.h vp9/common/vp9_mvref_common.c vp9/common/vp9_onyxc_int.h vp9/common/vp9_reconinter.c vp9/decoder/vp9_decodeframe.c vp9/decoder/vp9_decodeframe.h vp9/decoder/vp9_decodemv.c vp9/decoder/vp9_decoder.c vp9/decoder/vp9_decoder.h vp9/encoder/vp9_encoder.c vp9/encoder/vp9_pickmode.c vp9/encoder/vp9_rdopt.c vp9/vp9_cx_iface.c vp9/vp9_dx_iface.c This reverts commit a18da9760a74d9ce6fb9f875706dc639c95402f5. Change-Id: I361442ffec1586d036ea2e0ee97ce4f077585f02
2015-01-27 21:26:28 +01:00
#if CONFIG_VP9_HIGHBITDEPTH
static INLINE void highbd_inter_predictor(
const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride,
const int subpel_x, const int subpel_y, const struct scale_factors *sf,
int w, int h, int ref, const InterpKernel *kernel, int xs, int ys, int bd) {
sf->highbd_predict[subpel_x != 0][subpel_y != 0][ref](
src, src_stride, dst, dst_stride, kernel[subpel_x], xs, kernel[subpel_y],
ys, w, h, bd);
}
Try again to merge branch 'frame-parallel' into master branch. In frame parallel decode, libvpx decoder decodes several frames on all cpus in parallel fashion. If not being flushed, it will only return frame when all the cpus are busy. If getting flushed, it will return all the frames in the decoder. Compare with current serial decode mode in which libvpx decoder is idle between decode calls, libvpx decoder is busy between decode calls. Current frame parallel decode will only speed up the decoding for frame parallel encoded videos. For non frame parallel encoded videos, frame parallel decode is slower than serial decode due to lack of loopfilter worker thread. There are still some known issues that need to be addressed. For example: decode frame parallel videos with segmentation enabled is not right sometimes. * frame-parallel: Add error handling for frame parallel decode and unit test for that. Fix a bug in frame parallel decode and add a unit test for that. Add two test vectors to test frame parallel decode. Add key frame seeking to webmdec and webm_video_source. Implement frame parallel decode for VP9. Increase the thread test range to cover 5, 6, 7, 8 threads. Fix a bug in adding frame parallel unit test. Add VP9 frame-parallel unit test. Manually pick "Make the api behavior conform to api spec." from master branch. Move vp9_dec_build_inter_predictors_* to decoder folder. Add segmentation map array for current and last frame segmentation. Include the right header for VP9 worker thread. Move vp9_thread.* to common. ctrl_get_reference does not need user_priv. Seperate the frame buffers from VP9 encoder/decoder structure. Revert "Revert "Revert "Revert 3 patches from Hangyu to get Chrome to build:""" Conflicts: test/codec_factory.h test/decode_test_driver.cc test/decode_test_driver.h test/invalid_file_test.cc test/test-data.sha1 test/test.mk test/test_vectors.cc vp8/vp8_dx_iface.c vp9/common/vp9_alloccommon.c vp9/common/vp9_entropymode.c vp9/common/vp9_loopfilter_thread.c vp9/common/vp9_loopfilter_thread.h vp9/common/vp9_mvref_common.c vp9/common/vp9_onyxc_int.h vp9/common/vp9_reconinter.c vp9/decoder/vp9_decodeframe.c vp9/decoder/vp9_decodeframe.h vp9/decoder/vp9_decodemv.c vp9/decoder/vp9_decoder.c vp9/decoder/vp9_decoder.h vp9/encoder/vp9_encoder.c vp9/encoder/vp9_pickmode.c vp9/encoder/vp9_rdopt.c vp9/vp9_cx_iface.c vp9/vp9_dx_iface.c This reverts commit a18da9760a74d9ce6fb9f875706dc639c95402f5. Change-Id: I361442ffec1586d036ea2e0ee97ce4f077585f02
2015-01-27 21:26:28 +01:00
#endif // CONFIG_VP9_HIGHBITDEPTH
MV average_split_mvs(const struct macroblockd_plane *pd, const MODE_INFO *mi,
int ref, int block);
MV clamp_mv_to_umv_border_sb(const MACROBLOCKD *xd, const MV *src_mv, int bw,
int bh, int ss_x, int ss_y);
Try again to merge branch 'frame-parallel' into master branch. In frame parallel decode, libvpx decoder decodes several frames on all cpus in parallel fashion. If not being flushed, it will only return frame when all the cpus are busy. If getting flushed, it will return all the frames in the decoder. Compare with current serial decode mode in which libvpx decoder is idle between decode calls, libvpx decoder is busy between decode calls. Current frame parallel decode will only speed up the decoding for frame parallel encoded videos. For non frame parallel encoded videos, frame parallel decode is slower than serial decode due to lack of loopfilter worker thread. There are still some known issues that need to be addressed. For example: decode frame parallel videos with segmentation enabled is not right sometimes. * frame-parallel: Add error handling for frame parallel decode and unit test for that. Fix a bug in frame parallel decode and add a unit test for that. Add two test vectors to test frame parallel decode. Add key frame seeking to webmdec and webm_video_source. Implement frame parallel decode for VP9. Increase the thread test range to cover 5, 6, 7, 8 threads. Fix a bug in adding frame parallel unit test. Add VP9 frame-parallel unit test. Manually pick "Make the api behavior conform to api spec." from master branch. Move vp9_dec_build_inter_predictors_* to decoder folder. Add segmentation map array for current and last frame segmentation. Include the right header for VP9 worker thread. Move vp9_thread.* to common. ctrl_get_reference does not need user_priv. Seperate the frame buffers from VP9 encoder/decoder structure. Revert "Revert "Revert "Revert 3 patches from Hangyu to get Chrome to build:""" Conflicts: test/codec_factory.h test/decode_test_driver.cc test/decode_test_driver.h test/invalid_file_test.cc test/test-data.sha1 test/test.mk test/test_vectors.cc vp8/vp8_dx_iface.c vp9/common/vp9_alloccommon.c vp9/common/vp9_entropymode.c vp9/common/vp9_loopfilter_thread.c vp9/common/vp9_loopfilter_thread.h vp9/common/vp9_mvref_common.c vp9/common/vp9_onyxc_int.h vp9/common/vp9_reconinter.c vp9/decoder/vp9_decodeframe.c vp9/decoder/vp9_decodeframe.h vp9/decoder/vp9_decodemv.c vp9/decoder/vp9_decoder.c vp9/decoder/vp9_decoder.h vp9/encoder/vp9_encoder.c vp9/encoder/vp9_pickmode.c vp9/encoder/vp9_rdopt.c vp9/vp9_cx_iface.c vp9/vp9_dx_iface.c This reverts commit a18da9760a74d9ce6fb9f875706dc639c95402f5. Change-Id: I361442ffec1586d036ea2e0ee97ce4f077585f02
2015-01-27 21:26:28 +01:00
void vp9_build_inter_predictors_sby(MACROBLOCKD *xd, int mi_row, int mi_col,
BLOCK_SIZE bsize);
void vp9_build_inter_predictors_sbp(MACROBLOCKD *xd, int mi_row, int mi_col,
BLOCK_SIZE bsize, int plane);
void vp9_build_inter_predictors_sbuv(MACROBLOCKD *xd, int mi_row, int mi_col,
BLOCK_SIZE bsize);
void vp9_build_inter_predictors_sb(MACROBLOCKD *xd, int mi_row, int mi_col,
BLOCK_SIZE bsize);
void vp9_build_inter_predictor(const uint8_t *src, int src_stride, uint8_t *dst,
int dst_stride, const MV *mv_q3,
const struct scale_factors *sf, int w, int h,
int do_avg, const InterpKernel *kernel,
enum mv_precision precision, int x, int y);
#if CONFIG_VP9_HIGHBITDEPTH
void vp9_highbd_build_inter_predictor(
const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride,
const MV *mv_q3, const struct scale_factors *sf, int w, int h, int do_avg,
const InterpKernel *kernel, enum mv_precision precision, int x, int y,
int bd);
#endif
static INLINE int scaled_buffer_offset(int x_offset, int y_offset, int stride,
const struct scale_factors *sf) {
const int x = sf ? sf->scale_value_x(x_offset, sf) : x_offset;
const int y = sf ? sf->scale_value_y(y_offset, sf) : y_offset;
return y * stride + x;
}
static INLINE void setup_pred_plane(struct buf_2d *dst, uint8_t *src,
int stride, int mi_row, int mi_col,
const struct scale_factors *scale,
int subsampling_x, int subsampling_y) {
const int x = (MI_SIZE * mi_col) >> subsampling_x;
const int y = (MI_SIZE * mi_row) >> subsampling_y;
dst->buf = src + scaled_buffer_offset(x, y, stride, scale);
dst->stride = stride;
}
void vp9_setup_dst_planes(struct macroblockd_plane planes[MAX_MB_PLANE],
const YV12_BUFFER_CONFIG *src, int mi_row,
int mi_col);
void vp9_setup_pre_planes(MACROBLOCKD *xd, int idx,
const YV12_BUFFER_CONFIG *src, int mi_row, int mi_col,
const struct scale_factors *sf);
#ifdef __cplusplus
} // extern "C"
#endif
#endif // VP9_COMMON_VP9_RECONINTER_H_