Recpipe: Co-designing models and hardware to jointly optimize recommendation quality and performance

U Gupta, S Hsia, J Zhang, M Wilkening… - MICRO-54: 54th Annual …, 2021 - dl.acm.org
Deep learning recommendation systems must provide high quality, personalized content
under strict tail-latency targets and high system loads. This paper presents RecPipe, a …

Deeprecsys: A system for optimizing end-to-end at-scale neural recommendation inference

U Gupta, S Hsia, V Saraph, X Wang… - 2020 ACM/IEEE 47th …, 2020 - ieeexplore.ieee.org
Neural personalized recommendation is the cornerstone of a wide collection of cloud
services and products, constituting significant compute demand of cloud infrastructure. Thus …

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

Y Zhang, L Chen, S Yang, M Yuan, H Yi… - 2022 IEEE 38th …, 2022 - ieeexplore.ieee.org
The development of personalized recommendation has significantly improved the accuracy
of information matching and the revenue of e-commerce platforms. Recently, it has two …

A GPU-specialized inference parameter server for large-scale deep recommendation models

Y Wei, M Langer, F Yu, M Lee, J Liu, J Shi… - Proceedings of the 16th …, 2022 - dl.acm.org
Recommendation systems are of crucial importance for a variety of modern apps and web
services, such as news feeds, social networks, e-commerce, search, etc. To achieve peak …

Cross-stack workload characterization of deep recommendation systems

S Hsia, U Gupta, M Wilkening, CJ Wu… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
Deep learning based recommendation systems form the backbone of most personalized
cloud services. Though the computer architecture community has recently started to take …

RecFlex: Enabling Feature Heterogeneity-Aware Optimization for Deep Recommendation Models with Flexible Schedules

Z Pan, Z Zheng, F Zhang, B Xie, R Wu… - … Conference for High …, 2024 - ieeexplore.ieee.org
Industrial recommendation models typically involve numerous feature fields. The embedding
computation workloads are heterogeneous across these fields, thus requiring varied optimal …

Enabling efficient large recommendation model training with near cxl memory processing

H Liu, L Zheng, Y Huang, J Zhou, C Liu… - 2024 ACM/IEEE 51st …, 2024 - ieeexplore.ieee.org
Personalized recommendation systems have become one of the most important Internet
services nowadays. A critical challenge of training and deploying the recommendation …

InTune: Reinforcement learning-based data pipeline optimization for deep recommendation models

K Nagrecha, L Liu, P Delgado… - Proceedings of the 17th …, 2023 - dl.acm.org
Deep learning-based recommender models (DLRMs) have become an essential component
of many modern recommender systems. Several companies are now building large compute …

Hercules: Heterogeneity-aware inference serving for at-scale personalized recommendation

L Ke, U Gupta, M Hempstead, CJ Wu… - … Symposium on High …, 2022 - ieeexplore.ieee.org
Personalized recommendation is an important class of deep-learning applications that
powers a large collection of internet services and consumes a considerable amount of …

Optimizing cpu performance for recommendation systems at-scale

R Jain, S Cheng, V Kalagi, V Sanghavi, S Kaul… - Proceedings of the 50th …, 2023 - dl.acm.org
Deep Learning Recommendation Models (DLRMs) are very popular in personalized
recommendation systems and are a major contributor to the data-center AI cycles. Due to the …