13 April 2015 Enhanced memory architecture for massively parallel vision chip
Author Affiliations +
Proceedings Volume 9522, Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics 2014, Part II; 95220U (2015) https://doi.org/10.1117/12.2179447
Event: Selected Proceedings of the Photoelectronic Technology Committee Conferences held August-October 2014, 2014, China, China
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 μm CMOS process. The area overhead of the memory achieves 16.6 μm2/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 μW under 1.8 V supply voltage.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhe Chen, Zhe Chen, Jie Yang, Jie Yang, Liyuan Liu, Liyuan Liu, Nanjian Wu, Nanjian Wu, } "Enhanced memory architecture for massively parallel vision chip", Proc. SPIE 9522, Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics 2014, Part II, 95220U (13 April 2015); doi: 10.1117/12.2179447; https://doi.org/10.1117/12.2179447
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

The Use Of A Priori Knowledge In Image Processing
Proceedings of SPIE (April 16 1973)
Spectral Extrapolation With Spatial Constraints
Proceedings of SPIE (December 07 1978)
Airborne Video Image Enhancement
Proceedings of SPIE (December 24 1980)

Back to Top