Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/HPCA47549.2020.00047 | 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA) |
Keywords | DocType | ISSN |
data centers,personalized recommendation,content ranking,deep neural networks,recommendation systems,production-scale DNNs,open-source workloads,recommendation models,Facebook,deep learning,latency-bounded throughput | Conference | 1530-0897 |
ISBN | Citations | PageRank |
978-1-7281-6150-1 | 4 | 0.44 |
References | Authors | |
24 | 16 |
Name | Order | Citations | PageRank |
---|---|---|---|
Udit Gupta | 1 | 74 | 6.27 |
Carole-Jean Wu | 2 | 432 | 23.81 |
Xiaodong Wang | 3 | 126 | 6.24 |
Maxim Naumov | 4 | 68 | 10.29 |
Brandon Reagen | 5 | 210 | 13.90 |
David Brooks | 6 | 5518 | 422.08 |
Bradford Cottel | 7 | 4 | 0.44 |
Kim M. Hazelwood | 8 | 2465 | 110.46 |
Mark Hempstead | 9 | 980 | 81.39 |
Bill Jia | 10 | 126 | 5.90 |
Hsien-Hsin Sean Lee | 11 | 1657 | 102.66 |
Andrey Malevich | 12 | 4 | 0.44 |
Dheevatsa Mudigere | 13 | 289 | 19.84 |
Mikhail Smelyanskiy | 14 | 1160 | 65.96 |
Liang Xiong | 15 | 4 | 0.44 |
xuan zhang | 16 | 93 | 25.30 |