Enhanced memory architecture for massively parallel vision chip

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.

[1]  Wancheng Zhang,et al.  A Programmable SIMD Vision Chip for Real-Time Vision Applications , 2008, IEEE Journal of Solid-State Circuits.

[2]  Hongbo Zhu,et al.  A real-time motion-feature-extraction image processor employing digital-pixel-sensor-based parallel architecture , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[3]  Piotr Dudek,et al.  A SIMD Cellular Processor Array Vision Chip With Asynchronous Processing Capabilities , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Wancheng Zhang,et al.  A Programmable Vision Chip Based on Multiple Levels of Parallel Processors , 2011, IEEE Journal of Solid-State Circuits.

[5]  Bernabé Linares-Barranco,et al.  A 3.6 $\mu$ s Latency Asynchronous Frame-Free Event-Driven Dynamic-Vision-Sensor , 2011, IEEE Journal of Solid-State Circuits.

[6]  Liyuan Liu,et al.  7.3 A 1000fps vision chip based on a dynamically reconfigurable hybrid architecture comprising a PE array and self-organizing map neural network , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[7]  Wancheng Zhang,et al.  A 1,000 Frames/s Programmable Vision Chip with Variable Resolution and Row-Pixel-Mixed Parallel Image Processors , 2009, Sensors.

[8]  Zhe Chen,et al.  A novel architecture of local memory for programmable SIMD vision chip , 2013, 2013 IEEE 10th International Conference on ASIC.

[9]  Jaehyuk Choi,et al.  A 3.4-$\mu$ W Object-Adaptive CMOS Image Sensor With Embedded Feature Extraction Algorithm for Motion-Triggered Object-of-Interest Imaging , 2014, IEEE Journal of Solid-State Circuits.

[10]  Piotr Dudek,et al.  A general-purpose vision processor with 160×80 pixel-parallel SIMD processor array , 2013, Proceedings of the IEEE 2013 Custom Integrated Circuits Conference.