An FPGA-based fast two-symbol processing architecture for JPEG 2000 arithmetic coding

Nandini Ramesh Kumar, Wei Xiang, Yafeng Wang

Abstract: In this paper, a field-programmable gate array (FPGA) based enhanced architecture of the arithmetic coder is proposed, which processes two symbols per clock cycle as compared to the conventional architecture that processes only one symbol per clock. The input to the arithmetic coder is from the bit-plane coder, which generates more than two context-decision pairs per clock cycle. But due to the slow processing speed of the arithmetic coder, the overall encoding becomes slow. Hence, to overcome this bottleneck and speed up the process, a two-symbol architecture is proposed which not only doubles the throughput, but also can be operated at frequencies greater than 100 MHz. This architecture achieves a throughput of 210 Msymbols/sec and the critical path is at 9.457 ns.