Paper Info
Title
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications.
Abstract
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 performance optimizations targeting existing systems, point out their limitations and make suggestions for the future general-purpose/accelerated inference hardware. Also, we highlight the need for better co-design of algorithms, numerics and computing platforms to address the challenges of workloads often run in data centers.
Year
Venue
DocType
2018
arXiv: Learning
Journal
Volume
Citations 
PageRank 
abs/1811.09886
4
0.39
References 
Authors
31
28
Name
Order
Citations
PageRank
Jongsoo Park11039.49
Maxim Naumov26810.29
Protonu Basu340.39
Summer Deng480.83
Aravind Kalaiah5964.10
Daya Shanker Khudia640.39
James Law782.90
Parth Malani840.39
Andrey Malevich9100.80
Nadathur Satish10202099.88
Juan Pino112112.63
Martin Schatz1240.39
Alexander Sidorov1340.39
Viswanath Sivakumar1440.72
Andrew Tulloch152397.52
Xiaodong Wang161266.24
Yiming Wu17173.04
Hector Yuen1861.10
Utku Diril1940.72
Dmytro Dzhulgakov20100.79
Kim M. Hazelwood212465110.46
Bill Jia221265.90
Yangqing Jia237563351.84
Lin Qiao24472.61
Vijay Rao25100.79
Nadav Rotem2680.83
Sungjoo Yoo27696.90
Mikhail Smelyanskiy2841.06