公开(公告)号：WO2007006181A1

公开(公告)日：2007-01-18

申请号：PCT/CN2005/001047

申请日：2005-07-14

Applicant: INTEL CORPORATION ,  WU, Haihua ,  ZHOU, Zhenghua

Inventor： WU, Haihua ,  ZHOU, Zhenghua

IPC: H04N7/50

CPC classification number: H04N19/152 ,  H04N19/124 ,  H04N19/132 ,  H04N19/172 ,  H04N19/61

Abstract: A rate control method comprises determining a target buffer fullness for each frame of a plurality of frames, obtaining a real buffer fullness for a previous frame of the plurality of frames; determining a target allocation for a current frame based on the real buffer fullness and target buffer fullness for the previous frame, wherein at least two frames of the plurality of frames have different target buffer fullness.

Abstract translation: 速率控制方法包括：确定多个帧中的每个帧的目标缓冲器充满度，获得所述多个帧中的先前帧的实际缓冲区饱和度; 基于前一帧的实际缓冲区充满度和目标缓冲区饱和度来确定当前帧的目标分配，其中多个帧中的至少两个帧具有不同的目标缓冲区饱和度。

公开(公告)号：WO2016094062A1

公开(公告)日：2016-06-16

申请号：PCT/US2015/061918

申请日：2015-11-20

Applicant: INTEL CORPORATION

Inventor： WU, Haihua ,  GOULD, Julia

IPC: G06T1/20

CPC classification number: G06T1/20 ,  G06F9/3009 ,  G06F9/3851 ,  G06F9/4881 ,  H04N19/70

Abstract: Techniques to dispatch threads of a graphics kernel for execution to increase the interval between dependent threads and the associated are disclosed. The dispatch interval may be increased by dispatching associated threads, followed by threads without any dependencies, followed by threads dependent on the earlier dispatched associated threads. As such, the interval between dependent threads and their associated threads can be increased, leading to increased parallelism.

Abstract translation: 公开了分配用于执行的图形内核的线程以增加从属线程与相关联的间隔的技术。 可以通过调度相关联的线程来增加调度间隔，随后是没有任何依赖性的线程，后跟线程依赖于较早调度的相关线程。 因此，可以增加从属线程及其相关线程之间的间隔，从而增加并行性。

公开(公告)号：WO2016105842A1

公开(公告)日：2016-06-30

申请号：PCT/US2015/062722

申请日：2015-11-25

Applicant: INTEL CORPORATION

Inventor： FU, Fangwen ,  WU, Haihua ,  PIEL, Tuyet-Trang Lam

IPC: H04N19/14 ,  H04N19/91 ,  H04N19/463

CPC classification number: H04N19/13 ,  H04N19/146 ,  H04N19/184 ,  H04N19/70

Abstract: Techniques related to entropy coding with look-up-table based probability updating for video coding.

Abstract translation: 与基于查找表的视频编码概率更新熵编码相关的技术。

公开(公告)号：WO2016093978A1

公开(公告)日：2016-06-16

申请号：PCT/US2015/058573

申请日：2015-11-02

Applicant: INTEL CORPORATION

Inventor： WU, Haihua ,  GOULD, Julia A.

IPC: H04N19/44 ,  H04N19/176

CPC classification number: H04N19/436 ,  H04N19/117 ,  H04N19/82 ,  H04N19/86 ,  H04N19/865

Abstract: A thread dependency scheme may significantly reduce the dependency penalty and improve the parallelism efficiency in some embodiments in video compression techniques with relatively high dependencies, such as VP9. One fundamental feature is to split an individual large kernel into multiple, less dependent, smaller kernels, thereby significantly increasing the number of software threads that can potentially run in parallel. Another feature is to define the larger number of thread dependencies (superset of all the dependency candidates for each thread), with the specific thread's spatial position and associated context, and mask out some of the unnecessary thread dependencies.

Abstract translation: 线程依赖方案可以显着地减少依赖性损失并且在一些实施例中提高具有较高依赖性的视频压缩技术（例如VP9）中的并行性效率。 一个基本特征是将单个大型内核分解成多个较少依赖的较小内核，从而显着增加可能并行运行的软件线程数。 另一个特点是定义更多数量的线程依赖性（每个线程的所有依赖候选项的超集），以及特定线程的空间位置和关联的上下文，并且屏蔽一些不必要的线程依赖关系。