Neuromorphic hardware accelerator for SNN inference based on STT-RAM crossbar arrays
Document Type
Conference Proceeding
Publication Date
11-1-2019
Abstract
In this paper, we propose a Spin Transfer Torque RAM (STT-RAM) based neurosynaptic core to implement a hardware accelerator for Spiking Neural Networks (SNNs), which mimic the time-based signal encoding and processing mechanisms of the human brain. The computational core consists of a crossbar array of non-volatile STT-RAMs, read/write peripheral circuits, and digital logic for the spiking neurons. Inter-core communication is realized through on-chip routing network by sending/receiving spike packets. Unlike prior works that use multi-level states of non-volatile memory (NVM) devices for the synaptic weights, we use the technologically-mature STT-RAM devices for binary data storage. The design studies are conducted using a compact model for STT-RAM devices, tuned to capture the state-of-the-art experimental results. Our design avoids the need for expensive ADCs and DACs, enabling instantiation of large NVM arrays for our core. We show that the STT-RAM based neurosynaptic core designed in 28 nm technology node has approximately 6× higher throughput per unit Watt and unit area than an equivalent SRAM based design. Our design also achieves ∼ 2× higher performance per Watt compared to other memristive neural network accelerator designs in the literature.
Identifier
85079196851 (Scopus)
ISBN
[9781728109961]
Publication Title
2019 26th IEEE International Conference on Electronics Circuits and Systems Icecs 2019
External Full Text Location
https://doi.org/10.1109/ICECS46596.2019.8964886
First Page
438
Last Page
441
Grant
2016-SD-2717
Fund Ref
Semiconductor Research Corporation
Recommended Citation
Kulkarni, Shruti R.; Kadetotad, Deepak Vinayak; Yin, Shihui; Seo, Jae Sun; and Rajendran, Bipin, "Neuromorphic hardware accelerator for SNN inference based on STT-RAM crossbar arrays" (2019). Faculty Publications. 7235.
https://digitalcommons.njit.edu/fac_pubs/7235
