Abstract: The disclosure describes video decoding techniques that utilize parallel processor technology in order to accelerate the decoding processes of image frames. The techniques include defining batches of video blocks to be decoded in parallel with one another. According to this disclosure, a method may comprise defining a first batch of video blocks of an image frame, decoding the first batch of video blocks in a serial manner, defining a second batch of video blocks and a third batch of video blocks relative to the first batch of video blocks, and decoding the second and third batches of video blocks in parallel with one another.

Abstract: The disclosure describes video decoding techniques that utilize parallel processor technology in order to accelerate the decoding processes of image frames. The techniques include defining batches of video blocks to be decoded in parallel with one another. According to this disclosure, a method may comprise defining a first batch of video blocks of an image frame, decoding the first batch of video blocks in a serial manner, defining a second batch of video blocks and a third batch of video blocks relative to the first batch of video blocks, and decoding the second and third batches of video blocks in parallel with one another.

Abstract: A video stream (for example, H.264 video) includes intra-encoded portions. Decoding an intra-encoded portion utilizes the result of decoding one or more other portions (called predecessors) in the frame. Frame reconstruction involves identifying a portion that has no predecessor portions that have not been decoded and then initiating decoding of the identified portion(s). When the decoding of a portion is substantially complete, then the remaining portions to be decoded are examined to identify portions that have no predecessors that have not been decoded. By carrying out this method, multiple portions may be decoded simultaneously. Each can be decoded on a different work entity, thereby increasing the rate of decoding of the overall frame. Because deblock filtering a predecessor destroys information needed in the intra-decoding of other portions, prefiltered predecessor information is stored in a buffer for subsequent use during intra-decoding, thereby facilitating simultaneous decoding of multiple portions.