paper-with-me

홈 › Papers

Deep Recommender Models Inference: Automatic Asymmetric Data Flow Optimization

2025-07-02 · Giuseppe Ruggeri, Renzo Andri, Daniele Jahier Pagliari, Lukas Cavigelli arxiv

Deep Recommender Models (DLRMs) inference is a fundamental AI workload accounting for more than 79% of the total AI workload in Meta's data centers. DLRMs' performance bottleneck is found in the embedding layers, which perform many random memory accesses to retrieve small embedding vectors from tables of various sizes. We propose the design of tailored data flows to speedup embedding look-ups. Namely, we propose four strategies to look up an embedding table effectively on one core, and a framework to automatically map the tables asymmetrically to the multiple cores of a SoC. We assess the effectiveness of our method using the Huawei Ascend AI accelerators, comparing it with the default Ascend compiler, and we perform high-level comparisons with Nvidia A100. Results show a speed-up varying from 1.5x up to 6.5x for real workload distributions, and more than 20x for extremely unbalanced distributions. Furthermore, the method proves to be much more independent of the query distribution than the baseline.

📄 PDF Abstract BibTeX arXiv:2507.01676

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

2021-03-14 · Martin Mladenov, Chih-Wei Hsu, Vihan Jain, Eugene Ie 외

The development of recommender systems that optimize multi-turn interaction with users, and model the interactions of different agents (e.g., users, content providers, vendors) in the recommender ecosystem have drawn inc…

counterfactualProbabilistic ProgrammingRecommendation Systems

Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

2018-06-04 · NeurIPS 2018 12 · Simon S. Du, Wei Hu, Jason D. Lee

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReL…

Scalable Hyperbolic Recommender Systems

2019-02-22 · Benjamin Paul Chamberlain, Stephen R. Hardwick, David R. Wardrope, Fabon Dzogang 외

We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we …

Recommendation Systems

Efficient Maximum-Likelihood Inference For The Isolation-With-Initial-Migration Model With Potentially Asymmetric Gene Flow

2016-01-14

The isolation-with-migration (IM) model is a common tool to make inferences about the presence of gene flow during speciation, using polymorphism data. However, Becquet and Przeworski (2009) report that the parameter est…

Flow-Transformed Implicit Processes for Function-Space Variational Inference

2026-06-01 · Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen arxiv

Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors i…