A low-energy ASIP with flexible exponential Golomb codec for lossless data compression toward artificial vision systems

摘要

This paper proposes an application-domain specific instruction-set processor (ASIP) with dedicated instructions for lossless data compression and decompression process to be used in artificial vision systems. Proposed ASIP has dedicated instructions to accelerate the performance to codec operations of Exponential Golomb coding, where the coding parameter value can be set by the user in order to maximize the compression ratio. Experimental results through simulation show that the proposed ASIP reduces execution cycles by 88% for compression and 42% for decompression, and reduces energy consumption by 85% for compression and 40% for decompression, compared with the base reduced instruction set computer processor.