The Architectural Implications of Facebook's DNN-Based Personalized Recommendation
Abstrak
The widespread application of deep learning has changed the landscape of computation in data centers. In particular, personalized recommendation for content ranking is now largely accomplished using deep neural networks. However, despite their importance and the amount of compute cycles they consume, relatively little research attention has been devoted to recommendation systems. To facilitate research and advance the understanding of these workloads, this paper presents a set of real-world, production-scale DNNs for personalized recommendation coupled with relevant performance metrics for evaluation. In addition to releasing a set of open-source workloads, we conduct in-depth analysis that underpins future system design and optimization for at-scale recommendation: Inference latency varies by 60% across three Intel server generations, batching and co-location of inference jobs can drastically improve latency-bounded throughput, and diversity across recommendation models leads to different optimization strategies.
Topik & Kata Kunci
Penulis (15)
Udit Gupta
Xiaodong Wang
M. Naumov
Carole-Jean Wu
Brandon Reagen
D. Brooks
Bradford Cottel
K. Hazelwood
Bill Jia
Hsien-Hsin S. Lee
A. Malevich
Dheevatsa Mudigere
M. Smelyanskiy
Liang Xiong
Xuan Zhang
Akses Cepat
- Tahun Terbit
- 2019
- Bahasa
- en
- Total Sitasi
- 322×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/HPCA47549.2020.00047
- Akses
- Open Access ✓