Despite that current fully Complementary Metal-Oxide-Semiconductor (CMOS) implementations of neuromorphic platforms have shown remarkable performance in terms of power efficiency and classification accuracy, there are still some bottlenecks hindering the design of embedded sensing and processing systems. First, the memory used is typically Static Random Access Memory (SRAM), which has very low static power consumption, but it is a large element (six transistors per cell) and it is volatile. The latter feature implies that the information about the network configuration has to be stored elsewhere and transferred to the system at its startup. For large networks, it may take tens of minutes before the system is ready for normal operation. Second, always-on adaptive systems need to work with time constants that have the same time-span of the task that is being learned (e.g., longer than seconds). Implementing such long time constants in neuromorphic CMOS circuits is impractical, since it requires large area capacitors.
The first one is the co-integration of non-volatile memristive devices with some peripheral circuits (Hirtzlin et al., 2020) and to implement some logic and multiply-and-accumulate (MAC) operations (Chen et al., 2019), which reaches the maturity with the demonstration of a fully co-integrated SNN with analog neurons and memristive synapses (Valentian et al., 2019). The second phase is the co-integration of different technologies. Despite this approach results in higher fabrication costs, it presents several advantages in terms of system performance, which can be more compact and potentially more power efficient. In particular, the co-integration of non-volatile and volatile memristive devices can lead to a fully memristive approach. As an example, Wang et al. (2018c) exploit volatile memristive devices to emulate stochastic neurons and non-volatile memristive devices to store the synaptic weights on the same chip, thus demonstrating the feasibility and the advantages of the dual technology co-integration process. Eventually, the final step which has to be taken in the development of a dedicated ASIC for wearable edge computing is the co-integration of sensors and memristive-based systems. Shulaker et al. (2017) tackled this challenge by designing and fabricating a gas sensing system able of gas classification. The system uses RRAM arrays as memory, Carbon Nanotube Field Effect Transistor (CNFET) for computation and gas sensing, both 3D monolithically integrated on CMOS circuits, which carry out computation and allow memory access.
Essentials Of Vlsi Circuits And Systems By Kamran Eshraghian Pdf 222
2ff7e9595c
Comments