Haoran Qiu, Weichao Mao, et al.
ASPLOS 2024
Recent advancements in AI hardware highlight the potential of mixed-signal accelerators, which integrate analog computation for matrix multiplications with reduced-precision digital operations to achieve superior performance and energy efficiency. In this paper, we present a framework designed to perform hardware-aware training of and to evaluate neural networks (NNs) on such accelerators. This framework extends an existing framework, the IBM Analog AI Hardware Kit (AIHWKit), using a quantization library, enabling flexible layer-wise deployment in either analog or digital units, the latter with configurable precision. Our combined framework supports simultaneous quantization- and analog-aware training. It can also evaluate the accuracy of NNs when deployed on mixed-signal accelerators. We demonstrate the effectiveness of this combined training approach through extensive ablation studies on a ResNet-based vision model and a BERT-based language model, highlighting its importance for maximizing accuracy. Our contribution will be open-sourced as part of the core code of AIHWKit.
Haoran Qiu, Weichao Mao, et al.
ASPLOS 2024
Deming Chen, Alaa Youssef, et al.
arXiv
Jose Manuel Bernabe' Murcia, Eduardo Canovas Martinez, et al.
MobiSec 2024
Sahil Suneja, Yufan Zhuang, et al.
ACM TOSEM