mlsanityData to 14 Oct 2026

Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

arXiv 1811.09886 ↗First posted 24 Nov 2018cs.LG stat.MLcited by 36

Not on the map. Why?

Abstract (arXiv)

The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models used in many Facebook social network services. We present computational characteristics of our models, describe high performance optimizations targeting existing systems, point out their limitations and make suggestions for the future general-purpose/accelerated inference hardware. Also, we highlight the need for better co-design of algorithms, numerics and computing platforms to address the challenges of workloads often run in data centers.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 6; 2024: 4; 2025: 3; 2026: 1.

36 papers.

Sort:

By area:

  1. 2021Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Modelscited by 78
  2. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  3. 2021RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inferencecited by 35
  4. 2022NIPQ: Noise proxy-based Integrated Pseudo-Quantizationcited by 35
  5. 2022Aryl: An Elastic Cluster Scheduler for Deep Learningcited by 27
  6. 2021A Full-Stack Search Technique for Domain Optimized Deep Learning Acceleratorscited by 19
  7. 2024Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarioscited by 17
  8. 2021MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Corescited by 15
  9. 2023Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Servingcited by 15
  10. 2023SuperServe: Fine-Grained Inference Serving for Unpredictable Workloadscited by 12
  11. 2021SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learningcited by 11
  12. 2021JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baiducited by 10
24 more
  1. 2023MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendationcited by 9
  2. 2021Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systemscited by 7
  3. 2021Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scalecited by 7
  4. 2022Benchmarking Resource Usage for Efficient Distributed Deep Learningcited by 7
  5. 2022Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Visioncited by 6
  6. 2024SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Acceleratorscited by 6
  7. 2021Supporting Massive DLRM Inference Through Software Defined Memorycited by 5
  8. 2022Learning to Collide: Recommendation System Model Compression with Learned Hash Functionscited by 5
  9. 2023Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systemscited by 5
  10. 2022Adaptive Block Floating-Point for Analog Deep Learning Hardwarecited by 4
  11. 2021SMASH: Sparse Matrix Atomic Scratchpad Hashingcited by 3
  12. 2022Memory Planning for Deep Neural Networkscited by 3
  13. 2022The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)cited by 2
  14. 2021Demonstrating Analog Inference on the BrainScaleS-2 Mobile Systemcited by 1
  15. 2022RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instancescited by 1
  16. 2025Characterizing State Space Model and Hybrid Language Model Performance with Long Contextcited by 1
  17. 2022Dynamic Network Adaptation at Inferencecited by 0
  18. 2023Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendationscited by 0
  19. 2023Arithmetic Intensity Balancing Convolution for Hardware-aware Efficient Block Designcited by 0
  20. 2024ElasticRec: A Microservice-based Model Serving Architecture Enabling Elastic Resource Scaling for Recommendation Modelscited by 0
  21. 2024Inducing Semi-Structured Sparsity by Masking for Efficient Model Inference in Convolutional Networkscited by 0
  22. 2025Empowering Vector Architectures for ML: The CAMP Architecture for Matrix Multiplicationcited by 0
  23. 2025EPARA: Parallelizing Categorized AI Inference in Edge Cloudscited by 0
  24. 2026Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Acceleratorscited by 0