.png){kind=icon}
.png){kind=icon}
Return
Efficient Discrete Temporal Coding Spike-Driven In-Memory Computing Macro for Deep Neural Network Based on Nonvolatile Memory
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSI.2022.3194918.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nonvolatile memory (NVM) based neural network can directly perform in situ computation in memory to significantly reduce energy consumption resulting from the data movement. However, the energy consumption by the analog-to-digital converter (ADC) restricts the efficiency of the mixed-signal in-memory computing macro. The rate coding spike-driven in-memory computing macro can increase the energy efficiency via eliminating the ADC, but the improvement is limited because substantial energy is consumed for the coding of multiple spikes. In this work, we propose a discrete temporal coding spike-driven in-memory computing macro, including input coding scheme, weight mapping method, and improved leaky integrate-and-fire (LIF) neuron circuit, to perform the efficient forward inference of deep neural networks based on NVM array. We then optimize the designment of the proposed in-memory computing macro to mitigate the neural network accuracy loss due to the nonlinearity of the LIF neuron and voltage drop caused by interconnect resistance. Because the temporal coding scheme reduces spike numbers and the improved-LIF circuit simultaneously integrates two bit-lines current corresponding to positive and negative weight, the proposed macro achieves 46.63TOPS/W energy efficiency and 1.92TOPS throughput for 3bit temporal coding precision.
Keywords:
Encoding
In-memory computing
Capacitors
Biological neural networks
Neurons
Delays
Nonvolatile memory
In-memory computing
deep neural network
non-volatile memory
discrete temporal coding
spike-driven macro
Journal
IF:
5.2
Papers:
9.7K
Citations:
2.2W