Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

• Main Authors: Park, Jongsoo, Naumov, Maxim, Basu, Protonu, Deng, Summer, Kalaiah, Aravind, Khudia, Daya, Law, James, Malani, Parth, Malevich, Andrey, Nadathur, Satish, Pino, Juan, Schatz, Martin, Sidorov, Alexander, Sivakumar, Viswanath, Tulloch, Andrew, Wang, Xiaodong, Wu, Yiming, Yuen, Hector, Diril, Utku, Dzhulgakov, Dmytro, Hazelwood, Kim, Jia, Bill, Jia, Yangqing, Qiao, Lin, Rao, Vijay, Rotem, Nadav, Yoo, Sungjoo, Smelyanskiy, Mikhail
• Format: Journal Article
• Language: English
• Published: 24.11.2018
• Subjects: Computer Science - Learning; Statistics - Machine Learning

The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models used in many Facebook social network services. We present computational characteristics of our models, describe high pe...