PROJECT TITLE :
HEVC Encoding Optimization Using Multicore CPUs and GPUs
Although the High Potency Video Coding (HEVC) commonplace considerably improves the coding efficiency of video compression, it is unacceptable even in offline applications to spend several hours compressing 10 s of high-definition video. In this paper, we tend to propose employing a multicore central processing unit (CPU) and an off-the-shelf graphics processing unit (GPU) with 3072 streaming processors (SPs) for HEVC fast encoding, therefore that the speed optimization does not result in loss of coding potency. There are two key technical contributions during this paper. 1st, we propose an algorithm that is each parallel and quick for the GPU, which will utilize 3072 SPs in parallel to estimate the motion vector (MV) of each prediction unit (PU) in each combination of the coding unit (CU) and PU partitions. Furthermore, the proposed GPU algorithm can avoid coding efficiency loss caused by the dearth of a MV predictor (MVP). Second, we propose a quick algorithm for the CPU, that will totally utilize the results from the GPU to considerably scale back the amount of possible CU and PU partitions without any coding potency loss. Our experimental results show that compared with the reference software, we have a tendency to can encode high-resolution video that consumes 1.9p.c of the CPU time and one.zero% of the GPU time, with solely a 1.4percent rate increase.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here