A high speed and efficient architecture of VLD for AVS HD video decoder

PCS(2012)

引用 0|浏览9
暂无评分
摘要
In this paper, we present a high speed and efficient architecture of Variable Length Decoder for AVS video standard targeted for all-hardware implementation. Besides the regular operations of decoding Fixed Length Code, unsigned or signed k-th Exp-Golomb Code and 2D Variable Length Code, the proposed design provides other functions such as de-stuffing or pre-fetching the Bitstream. It can perform decoding syntax elements of sequence, frame, slice, and macro block. The complete architecture has been described in Verilog HDL, simulated with Modelsim SE 6.3c simulator, implemented using FPGA of Xinlinx Vertex 5 VLX330. Without any strict constraint, the design can achieve a working frequency at 190 MHz after synthesis with Synplify_pro 9.4, and the critical path is less than 6.5ns after place & route. The throughput of the design is 1 codeword per clock. In all, the architecture fully meets the demands of AVS HD decoder. It can support real-time decoding for 1080P @ 30 frame/s or 1080i @ 60 field/s videos. Inevitably, the cost for such a high speed design is consuming more hardware resources. Report of Place & Route shows about 9.1K LUTs (4% of the total LUTs in FPGA chip) are consumed by our design. Although the VLD architecture was originally designed for AVS video standard, the idea of the design can be easily adapted to other video standards.
更多
查看译文
关键词
prefetching,variable length decoder,variable length codes,destuffing,frequency 190 mhz,syntax element,modelsim se 6.3c simulator,2d variable length code,video coding,synplify_pro 9.4,avs video standard,fpga,vld,avs hd video decoder,field programmable gate arrays,fixed length code,verilog hdl,xinlinx vertex 5 vlx330,k-th exp-golomb code,decoding,critical path,chip,variable length code,real time
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要