Drift: Leveraging Distribution-based Dynamic Precision Quantization for Efficient Deep Neural Network Acceleration
Lian Liu, Xu Zhaohui, Yintao He, Ying Wang, Huawei Li, Xiaowei Li, Yinhe Han · 2024
Quantization is one of the most hardware-efficient ways to reduce inference costs for deep neural network (DNN) models. Nevertheless, with the continuous increase of DNN model sizes (240× in two years) and the emergence of large language models, existing static quantization methods fail to utilize the sparsity and redundancy of models sufficiently. Motivated by the pervasive dynamism in data tensors across DNN models, we propose a dynamic precision quantization algorithm to further reduce computational costs beyond statically quantized DNN models. Furthermore, we find that existing precision-flexible accelerators cannot support the DNN models with dynamic precision. To this end, we design a novel accelerator, Drift, and achieve online scheduling to efficiently support dynamic precision execution. We conduct experiments with various DNN models, including CNN-based and Transformer-based models. Evaluation results show that Drift achieves 2.85× speedup and 3.12× energy saving compared to existing precision-flexible accelerators with statically quantized models.