Dynamic load balancing algorithm based on HEVC tiles for just-in-time video encoding for heterogeneous architectures

This paper proposes a novel algorithm for dynamic tile partitioning to achieve the optimal workload balance for parallel processing architectures in just-in-time HEVC encoding. Tile boundaries are dynamically shifted depending on the file cost, a value that denotes predicted computational complexity of a single tile in a frame. The overall cost of a tile is determined as a combination of costs of three computationally most expensive and resource-hungry operations in HEVC encoding: prediction, transformation, and entropy coding. The algorithm aims at exploiting different types of processing architectures, from homogeneous multicore CPU architectures to heterogeneous architectures in the actual conditions in which streaming servers operate. The experimental results show that the proposed algorithm outperforms uniform tiling, by up to 5.5% in processing time, while maintaining the same video quality and bitrate. Compared to the stateof-the-art algorithms, the proposed algorithm achieves up to 8.85% speedup depending on the number of videos that are being encoded concurrently on a video streaming server.