Joonsang Yu, Junki Park, Seongmin Park, Minsoo Kim, Sihwa Lee, Dong Hyun Lee, Jungwook Choi
2022 Proceedings of the 59th ACM/IEEE Design Automation Conference  
Non-linear operations such as GELU, Layer normalization, and Softmax are essential yet costly building blocks of Transformer models. Several prior works simplified these operations with look-up tables or integer computations, but such approximations suffer inferior accuracy or considerable hardware cost with long latency. This paper proposes an accurate and hardware-friendly approximation framework for efficient Transformer inference. Our framework employs a simple neural network as a universal
more » ... approximator with its structure equivalently transformed into a Look-up table(LUT). The proposed framework called Neural network generated LUT(NN-LUT ) can accurately replace all the non-linear operations in popular BERT models with significant reductions in area, power consumption, and latency.
doi:10.1145/3489517.3530505 fatcat:rmhxntcylzcehm7euxvyv7cszu