Enhanced memory architecture for massively parallel vision chip

Zhe Chen, Jie Yang, Liyuan Liu, Nanjian WuProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2015 · DOI

Abstract

Local memory architecture plays an important role in high performance massively parallel vision chip. In this paper, we propose an enhanced memory architecture with compact circuit area designed in a full-custom flow. The memory consists of separate master-stage static latches and shared slave-stage dynamic latches. We use split transmission transistors on the input data path to enhance tolerance for charge sharing and to achieve random read/write capabilities. The memory is designed in a 0.18 &mu;m CMOS process. The area overhead of the memory achieves 16.6 &mu;m<sup>2</sup>/bit. Simulation results show that the maximum operating frequency reaches 410 MHz and the corresponding peak dynamic power consumption for a 64-bit memory unit is 190 &mu;W under 1.8 V supply voltage.
BibTeX
@inproceedings{chen2015enhanced,
  author = {Zhe Chen and Jie Yang and Liyuan Liu and Nanjian Wu},
  title = {{Enhanced memory architecture for massively parallel vision chip}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2015},
  doi = {10.1117/12.2179447},
}

Loading related content...

Figure