4K Real-Time and Parallel Software Video Decoder for Multi-layer HEVC Extensions
Résumé
Two High Efficiency Video Coding (HEVC) extensions, namely the Scalable HEVC extension (SHVC) and the multi-view HEVC extension (MV-HEVC), have been finalized in July 2014 by the MPEG and VCEG. These two extensions enable additional features not covered in the first version of the HEVC standard such as: spatial, fidelity, bit depth and color gamut scalability, as well as stereoscopic and multi-view representations. In this paper we propose a software parallel decoder architecture for the HEVC standard and its multi-layer extensions, including SHVC and MV-HEVC extensions. The decoder consists of multiple instances of the OpenHEVC decoder, one instance to decode each layer with a communication between dependent layers to perform inter-layer predictions. The proposed multi-layer HEVC decoder is parallel friendly and supports both wavefront parallelism to simultaneously process adjacent rows of the frame and frame-based parallelism to decode a set temporal and spatial frames in parallel. Moreover, the most time consuming operation introduced in the SHVC extension, namely the resampling of the inter-layer reference picture in spatial scalability, is optimized in SIMD for x86 platform. We assess the complexity of the multilayer HEVC decoder with respect to the simulcast configuration. The multi-layer decoder decoding two SHVC layers introduces in average 40%-71% additional complexity compared to the single layer HEVC decoder. Moreover, the low level optimizations with a hybrid parallel processing solution enable a real time decoding of 4Kp60 enhancement layer on a 6 cores Intel i7 processor running at 3.4 GHz.