Abstract: In general, in one aspect, a decode order for a group of picture (GOP) frame structure for a video stream is modified to include regenerated P frames. The modified decode order includes a regenerated P frame of a P frame decoded prior to a sequence of B frames after last B frame in the sequence of B frames and before next I or P frame. The frames are decoded in modified decode order by a decode engine. The decoded frames are post processed in a display order (only includes regenerated P frames and does not include initial P frames defined in the decode order) by a post processing engine. The post processing engine may ignore the initial P frames or the decode engine may not forward the initial P frames to the post processing engine. The post processed frames may be prepared for presentation by a display engine.

Abstract: Described herein are techniques related to power efficient encoder architecture during static frame or sub-frame detection. In particular, a method of implementing a power savings algorithm is described upon detection of the static frame or sub-frame by the encoder architecture.

Abstract: In general, in one aspect, a graphics driver receives information related to where eyes of a user watching a video are focused, determine if the user is focusing their attention on a particular location of the video, and generates post processing instructions for pixel macro blocks of decoded video frames. The instructions are based on whether it is determined that the user is focused. The graphics driver is further to determine a focus area associated with the particular location the user is focusing their attention on, determine a peripheral area around the focus area, generate a first set of post processing instructions for pixel macro blocks within the focus area, generate a second set of post processing instructions for pixel macro blocks within the peripheral area, and generate a third set of post processing instructions for pixel macro blocks not within either area.

Abstract: Systems and methods are described including dynamically configuring a shared buffer to support processing of at least two video read streams associated with different video codec formats. The methods may include determining a buffer write address within the shared buffer in response to a memory request associated with one read stream, and determining a different buffer write address within the shared buffer in response to a memory request associated with the other read stream.

Abstract: In accordance with some embodiments, a fixed function media accelerator may be preempted in the middle of processing one frame of data and still be able to resume operation later without the need to save an internal state. This ability to be preempted, without saving an internal state, may be important for supporting page fault and increasing the responsiveness of fixed function engines. Enabling preemption without the need to save the entire state reduces the complexity of the implementation in some embodiments.

Abstract: Context-adaptive variable length bitstream decoding performance may be improved and power consumption reduced by pushing the variable length decoding beyond one syntax element per clock pulse.

Abstract: CABAC coefficient decoding may be increased to two bins per clock. Since coefficients comprise most of the bitstream, this improvement almost doubles the CABAC decoding for a low quantization parameter bitstream (with lots of coefficients).

Abstract: Systems and methods are described including dynamically configuring a shared buffer to support processing of at least two video read streams associated with different video codec formats. The methods may include determining a buffer write address within the shared buffer in response to a memory request associated with one read stream, and determining a different buffer write address within the shared buffer in response to a memory request associated with the other read stream.

Abstract: A camera input can be used by the computer to support audio spatialization or to improve audio spatialization of an application that already supports it. A computer system may to support audio spatialization, for example, by modifying the relative latency or relative amplitude of the rendered audio packets. If a sound is intended, for example, to be located on the left side of the user, then the audio channel that is rendered on the headset speaker located on the user's left ear may have a somewhat decreased latency and increased amplitude compared to the other audio channel.

Abstract: Systems and methods are described including dynamically configuring a shared buffer to support processing of at least two video read streams associated with different video codec formats. The methods may include determining a buffer write address within the shared buffer in response to a memory request associated with one read stream, and determining a different buffer write address within the shared buffer in response to a memory request associated with the other read stream.

Abstract: Techniques are disclosed that involve the processing of audio streams. For instance, a host processing platform may receive a content stream that includes an encoded audio stream. In turn, a graphics engine produces from it a decoded audio stream. This producing may involve the graphics engine performing various operations, such as an entropy decoding operation, an inverse quantization operation, and an inverse discrete cosine transform operation. In embodiments, the content stream may further include an encoded video stream. Thus the graphics engine may produce from it a decoded video stream. This audio and video decoding may be performed in parallel.