Towards Data-center Level Carbon Modeling and Optimization for Deep Learning Inference

• DOI: 10.48550/arxiv.2403.04976
• Publication Date: 2024-03-07
• Authors: Shixin Ji; Zhuoping Yang; Xingzhen Chen; Jingtong Hu; Yiyu Shi; Alex K. Jones; Peipei Zhou
• Keywords: Center (category theory)

Recently, the increasing need for computing resources has led to prosperity of data centers, which poses challenges environmental impacts and calls improvements in center provisioning strategies. In this work, we show a comprehensive analysis based on profiling variety deep-learning inference applications different generations GPU servers. Our reveals several critical factors can largely affect design space strategies including hardware embodied cost estimation, application-specific features, distribution carbon each year, prior works have omitted. Based observations, further present first-order modeling optimization tool scheduling highlight importance from management.