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.
Enhanced memory architecture for massively parallel vision chip
Selected Papers from Conferences of the Photoelectronic Technology Committee of the Chinese Society of Astronautics 2014, Part II ; 2014 ; China,China
Proc. SPIE ; 9522
2015-04-13
Conference paper
Electronic Resource
English
1ms target tracking system using massively parallel processing vision
British Library Online Contents | 1997
|The Massively Parallel Processor
AIAA | 1982
|A Massively Parallel Approach to Real-Time Vision-Based Road Markings Detection
British Library Conference Proceedings | 1995
|Team targets greater imaging capabilities - Designing massively parallel processing chip set
Online Contents | 1996