TY - GEN
T1 - Mapping Binary ResNets on Computing-In-Memory Hardware with Low-bit ADCs
AU - Kim, Yulhwa
AU - Kim, Hyungjun
AU - Park, Jihoon
AU - Oh, Hyunmyung
AU - Kim, Jae Joon
N1 - Publisher Copyright:
© 2021 EDAA.
PY - 2021/2/1
Y1 - 2021/2/1
N2 - Implementing binary neural networks (BNNs) on computing-in-memory (CIM) hardware has several attractive features such as small memory requirement and minimal overhead in peripheral circuits such as analog-to-digital converters (ADCs). On the other hand, one of the downsides of using BNNs is that it degrades the classification accuracy. Recently, ResNet-style BNNs are gaining popularity with higher accuracy than conventional BNNs. The accuracy improvement comes from the high-resolution skip connection which binary ResNets use to compensate the information loss caused by binarization. However, the high-resolution skip connection forces the CIM hardware to use high-bit ADCs again so that area and energy overhead becomes larger. In this paper, we demonstrate that binary ResNets can be also mapped on CIM with low-bit ADCs via aggressive partial sum quantization and input-splitting combined with retraining. As a result, the key advantages of BNN CIM such as small area and energy consumption can be preserved with higher accuracy.
AB - Implementing binary neural networks (BNNs) on computing-in-memory (CIM) hardware has several attractive features such as small memory requirement and minimal overhead in peripheral circuits such as analog-to-digital converters (ADCs). On the other hand, one of the downsides of using BNNs is that it degrades the classification accuracy. Recently, ResNet-style BNNs are gaining popularity with higher accuracy than conventional BNNs. The accuracy improvement comes from the high-resolution skip connection which binary ResNets use to compensate the information loss caused by binarization. However, the high-resolution skip connection forces the CIM hardware to use high-bit ADCs again so that area and energy overhead becomes larger. In this paper, we demonstrate that binary ResNets can be also mapped on CIM with low-bit ADCs via aggressive partial sum quantization and input-splitting combined with retraining. As a result, the key advantages of BNN CIM such as small area and energy consumption can be preserved with higher accuracy.
KW - analog computing
KW - computing in memory
KW - hardware-Nn co-design
KW - NN accelerator
UR - https://www.scopus.com/pages/publications/85111012441
U2 - 10.23919/DATE51398.2021.9474056
DO - 10.23919/DATE51398.2021.9474056
M3 - Conference contribution
AN - SCOPUS:85111012441
T3 - Proceedings -Design, Automation and Test in Europe, DATE
SP - 856
EP - 861
BT - Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021
Y2 - 1 February 2021 through 5 February 2021
ER -