Motion compensation calculation of video decoder frequently access the video data which are stored in external memory, thus efficient memory access is critical in the design of decoder. An advanced parallel multi-pipe...
详细信息
ISBN:
(纸本)9783642319679
Motion compensation calculation of video decoder frequently access the video data which are stored in external memory, thus efficient memory access is critical in the design of decoder. An advanced parallel multi-pipe line architecture of Motion compensation is proposed in this paper, which fulfilled different of picture prediction modes employed by multi standard video decoder. In this architecture, buffering mechanism for the referencedata is used to reduce external memory access, and DMA is used to control data transformation between modules. Compared with traditional memory fetch module, the proposed architecture reduces 30%similar to 40% video decoding cycle in H.264 decoding. Synthetically result shows that timing and the area of this design are both satisfied the requirement of video decoder.
To improve the performance of the real-time video decoding under the power-constrained environment, an efficient memory fetch architecture for accessing the motion compensation memory is proposed. According to the fea...
详细信息
To improve the performance of the real-time video decoding under the power-constrained environment, an efficient memory fetch architecture for accessing the motion compensation memory is proposed. According to the feature of accessing the motion compensation memory, the architecture adopts the cache mechanism to buffer the referencedata and chooses DMA to access external memories. The architecture can be applied for H.264/AVC, MPEG-4, AVS and other video decoding systems. Compared to the conventional memory fetch module, experimental results show that the proposed architecture reduces 12.8%~16.7% video decoding cycles in H.264 decoding. The timing and the area of this design are both satisfied after synthesized.
暂无评论