mlsanityData to 7 Oct 2026

Supporting Massive DLRM Inference Through Software Defined Memory

arXiv 2110.11489 ↗First posted 21 Oct 2021cs.AR cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in terabytes range, leveraging Storage ClassMemory (SCM) for inference enables lower power consumption and cost. This paper evaluates the major challenges in extending the memory hierarchy to SCM for DLRM, and presents different techniques to improve performance through a Software Defined Memory. We show how underlying technologies such as Nand Flash and 3DXP differentiate, and relate to real world scenarios, enabling from 5% to 29% power savings.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 15 of its 33 references that are in the map. First posted on arXiv 21 Oct 2021.

Builds on

15 of 33 references.

References · 15

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2016Wide & Deep Learning for Recommender Systemscited by 745
  3. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  4. 2019The Architectural Implications of Facebook's DNN-based Personalized Recommendationcited by 83
  5. 2020Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systemscited by 59
  6. 2021FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inferencecited by 40
  7. 2020Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systemscited by 37
  8. 2018Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implicationscited by 35
  9. 2021RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inferencecited by 35
  10. 2020Understanding Capacity-Driven Scale-Out Neural Recommendation Inferencecited by 29
  11. 2019Post-Training 4-bit Quantization on Embedding Tablescited by 21
  12. 2020Learning from eXtreme Bandit Feedbackcited by 17
3 more
  1. 2018Bandana: Using Non-volatile Memory for Storing Deep Learning Modelscited by 14
  2. 2021JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baiducited by 10
  3. 2021First-Generation Inference Accelerator Deployment at Facebookcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 2.

5 papers.

  1. 2025Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updatescited by 1
  2. 2023MTrainS: Improving DLRM training efficiency using heterogeneous memoriescited by 0
  3. 2024ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation Systemcited by 0
  4. 2024ElasticRec: A Microservice-based Model Serving Architecture Enabling Elastic Resource Scaling for Recommendation Modelscited by 0
  5. 2025Faster Distributed Inference-Only Recommender Systems via Bounded Lag Synchronous Collectivescited by 0