1. Introduction
High Efficiency Video Coding (HEVC), developed by the Joint Collaborative Team on Video Coding (JCT-VC) as the latest video compression standard, was approved as an ITU-T/ISO standard in early 2013 [1]. HEVC achieves 2x higher coding efficiency than it's predecessor H.264/AVC, and supports resolutions up to 4320p, or 8K Ultra-HD (UHD) [2]. HEVC uses Context Adaptive Binary Arithmetic Coding (CABAC), a form of entropy coding, to achieve high coding efficiency [3]. However, CABAC is a well-known throughput bottleneck in H.264/AVC codecs, particularly in the decoder due to the highly serial dependencies caused by several feedback loops within the decoding flow. Efforts have been made to revise the CABAC in HEVC with many throughput-aware improvements, such as reduced memory requirements, reduced context-coded bins and grouping of bypass bins [4]. This work will describe an architecture that fully leverages these features to achieve a high-throughput CABAC decoder.