DeepAI AI Chat
Log In Sign Up

The Architectural Implications of Facebook's DNN-based Personalized Recommendation

by   Udit Gupta, et al.

The widespread application of deep learning has changed the landscape of computation in the data center. In particular, personalized recommendation for content ranking is now largely accomplished leveraging deep neural networks. However, despite the importance of these models and the amount of compute cycles they consume, relatively little research attention has been devoted to systems for recommendation. To facilitate research and to 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 of inferences can drastically improve latency-bounded throughput, and the diverse composition of recommendation models leads to different optimization strategies.


page 1

page 3

page 6

page 9


DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference

Neural personalized recommendation is the corner-stone of a wide collect...

MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions

Deep neural networks are widely used in personalized recommendation syst...

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Personalized recommendation systems leverage deep learning models and ac...

RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performance

Deep learning recommendation systems must provide high quality, personal...

DisaggRec: Architecting Disaggregated Systems for Large-Scale Personalized Recommendation

Deep learning-based personalized recommendation systems are widely used ...

LLM-Rec: Personalized Recommendation via Prompting Large Language Models

We investigate various prompting strategies for enhancing personalized r...

Enhancing the Interactivity of Dataframe Queries by Leveraging Think Time

We propose opportunistic evaluation, a framework for accelerating intera...