PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems

by   Yuanxing Zhang, et al.

The development of personalized recommendation has significantly improved the accuracy of information matching and the revenue of e-commerce platforms. Recently, it has 2 trends: 1) recommender systems must be trained timely to cope with ever-growing new products and ever-changing user interests from online marketing and social network; 2) SOTA recommendation models introduce DNN modules to improve prediction accuracy. Traditional CPU-based recommender systems cannot meet these two trends, and GPU- centric training has become a trending approach. However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas. This issue can be explained by two characteristics of these recommendation models: First, they contain up to a thousand input feature fields, introducing fragmentary and memory-intensive operations; Second, the multiple constituent feature interaction submodules introduce substantial small-sized compute kernels. To remove this roadblock to the development of recommender systems, we propose a novel framework named PICASSO to accelerate the training of recommendation models on commodity hardware. Specifically, we conduct a systematic analysis to reveal the bottlenecks encountered in training recommendation models. We leverage the model structure and data distribution to unleash the potential of hardware through our packing, interleaving, and caching optimization. Experiments show that PICASSO increases the hardware utilization by an order of magnitude on the basis of SOTA baselines and brings up to 6x throughput improvement for a variety of industrial recommendation models. Using the same hardware budget in production, PICASSO on average shortens the walltime of daily training tasks by 7 hours, significantly reducing the delay of continuous delivery.


page 1

page 6

page 10


Mobile recommender systems: Identifying the major concepts

This paper identifies the factors that have an impact on mobile recommen...

Recommender Systems in the Era of Large Language Models (LLMs)

With the prosperity of e-commerce and web applications, Recommender Syst...

Understanding Echo Chambers in E-commerce Recommender Systems

Personalized recommendation benefits users in accessing contents of inte...

Accelerating Recommender Systems via Hardware "scale-in"

In today's era of "scale-out", this paper makes the case that a speciali...

Simulations for novel problems in recommendation: analyzing misinformation and data characteristics

In this position paper, we discuss recent applications of simulation app...

Deep Autoencoder for Recommender Systems: Parameter Influence Analysis

Recommender systems have recently attracted many researchers in the deep...

Forgetting Fast in Recommender Systems

Users of a recommender system may want part of their data being deleted,...

Please sign up or login with your details

Forgot password? Click here to reset