Research Of Storage Resource Assignment On The Blackfin DSP Platform

H.264 is an advanced and popular video compression standard. Many companies and research institutions try their best to explore the real-time solution of H.264 Encoder in DSP (Digital Signal Processor) platform. However, as the high complexity and the resources limitation of DSP, there was no good solution up to now.The optimization of storage resource assignment based on the analysis of Blackfin561 architecture and H.264 encoding algorithm characteristics. The conflict of accessing memory is reduced by Abstracting data structures of H.264 algorithm, analyzing data size and operation frequency, and distributing corresponding memory level for the data. A dual-core synchronization method is designed for video capture, and buffers are distributed to different sub-banks, so the time of waiting video data is reduced. By calculating cache miss rate and average time of accessing memory, optimal Cache capacity is allocated, and appropriate write-back strategy is chosen for different part of data structures. By calculating additional spending of DMA transfer, fix up appropriate number of blocks transferred by one DMA transfer, and what is the optimal register value of DMA traffic. Branch and circle also have a great impact on storage performance, so optimize them by means of adding compiler option.Experiments on the Blackfin561 are conducted to evaluate and compare different techniques. After optimization, the cost time of video capture framework is reduced. The optimized H.264 Encoder achieve higher encoding frame rate (up to 22 fps) for the real-time video. For standard video sequences, results also suggest that storage resource assignment optimization improves the encoding rate.