Prof Chu Xiaowen and his team win the Best Paper Award in GreenCom 2020

Professor Chu Xiaowen and Dr Wang Qiang, Professor and Research Assistant Professor of the Department of Computer Science and PhD student Wang Yuxin received the Best Paper Award for their co-authored paper “Energy-Efficient Inference Service of Transformer-Based Deep Learning Models on GPUs“ at the 16th IEEE International Conference on Green Computing and Communications (GreenCom 2020).

The award-winning paper has aimed to address how to improve the energy efficiency of Inference-as-a-service (IAAS), especially the language translation service based on the Transformer Sequence Transduction model, without violating the service-level agreement (SLA) in the cloud environment. Although Transformer has achieved the state-of-the-art performance in many natural language processing tasks, it consumes a significant amount of energy due to the large model size and tremendous computations. In this work, they have conducted a comprehensive study on the inference performance and energy efficiency of a Transformer model trained for the language translation service. Their findings provide a full scope of Transformer inference, and suggest that the workload balancing and scheduling have great potentials to offer energy-efficient Transformer inference services.