Exploiting Thread-Level Parallelism on HEVC by Employing a Reference Dependency Graph

Abstract

This paper presents an optimized parallel algorithm for the next-generation video codec HEVC. The proposed method provides maximized parallel scalability by exploiting two levels of parallelism: frame-level and tasklevel. Frame-level parallelism is exploited by using a graph that efficiently provides a parallel coding order of the frames with complex reference dependencies. The proposed Reference Dependency Graph is generated at runtime by a novel construction algorithm that dynamically analyzes the configuration of the HEVC codec.Task-level parallelism is exploited to provide further scalability to frame-level parallelization. A pipelined execution is allowed for independent tasks, which are defined by dividing and categorizing a single coding process into multiple types of tasks. The proposed parallel encoder and decoder do not suffer from loss in coding efficiency because neither constraints nor modification in coding options are required. The proposed parallel methods result in an average encoding speedup of 1.75 and the aggressive method that exploits additional frame-level parallelism achieved 6.52 speedup using eight physical cores.Abstract-This paper presents an optimized parallel algorithm for the next-generation video codec HEVC. The proposed method provides maximized parallel scalability by exploiting two levels of parallelism: frame-level and task-level. Frame-level parallelism is exploited by using a graph that efficiently provides a parallel coding order of the frames with complex reference dependencies. The proposed Reference Dependency Graph is generated at runtime by a novel construction algorithm that dynamically analyzes the configuration of the HEVC codec. Tasklevel parallelism is exploited to provide further scalability to frame-level parallelization. A pipelined execution is allowed for independent tasks, which are defined by dividing and categorizing a single coding process into multiple types of tasks. The proposed parallel encoder and decoder do not suffer from loss in coding efficiency because neither constraints nor modification in coding options are required. The proposed parallel methods result in an average encoding speedup of 1.75 and the aggressive method that exploits additional frame-level parallelism achieved 6.52 speedup using eight physical cores.

Context-adaptive based CU processing for 3D-HEVC

“…A number of fast coding algorithms [ 14 – 24 ] have been proposed to reduce the complexity of state-of-the-art video coding standard, HEVC. The optimized parallel structure which is designed to speed up HEVC encoders [ 14 ] includes two levels of parallelism: frame-level and task-level.…”

“…A number of fast coding algorithms [ 14 – 24 ] have been proposed to reduce the complexity of state-of-the-art video coding standard, HEVC. The optimized parallel structure which is designed to speed up HEVC encoders [ 14 ] includes two levels of parallelism: frame-level and task-level. A novel coding strategy is proposed in [ 15 ] to reduce the computation complexity in HEVC encoders by efficient selection of appropriate block-partitioning modes based on human visual features (HVF), and low complexity coding tree mechanism is proposed in [ 16 ] for HEVC fast CU encoding, which makes an in-depth study of the relationship among CU distribution, quantization parameter and content change.…”