mlsanityData to 7 Oct 2026

MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores

arXiv 2104.13997 ↗First posted 28 Apr 2021cs.AR cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

As Deep Learning continues to drive a variety of applications in edge and cloud data centers, there is a growing trend towards building large accelerators with several sub-accelerator cores/chiplets. This work looks at the problem of supporting multi-tenancy on such accelerators. In particular, we focus on the problem of mapping jobs from several DNNs simultaneously on an accelerator. Given the extremely large search space, we formulate the search as an optimization problem and develop an optimization framework called M3E. In addition, we develop a specialized optimization algorithm called MAGMA with custom operators to enable structured sample-efficient exploration. We quantitatively compare MAGMA with several state-of-the-art methods, black-box optimization, and reinforcement learning methods across different accelerator settings (large/small accelerators) and different sub-accelerator configurations (homogeneous/heterogeneous), and observe MAGMA can consistently find better mappings.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 45 of its 110 references that are in the map. First posted on arXiv 28 Apr 2021.

Builds on

45 of 110 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2017Proximal Policy Optimization Algorithmscited by 14,441
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  11. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  12. 2018Deep contextualized word representationscited by 2,285
33 more
  1. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  2. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  3. 2020Reformer: The Efficient Transformercited by 1,658
  4. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  5. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  6. 2017Neural Collaborative Filteringcited by 1,108
  7. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  8. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  9. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  10. 2020Efficient Transformers: A Surveycited by 784
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  12. 2016Wide & Deep Learning for Recommender Systemscited by 745
  13. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 696
  14. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  15. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  16. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  17. 2019CamemBERT: a Tasty French Language Modelcited by 368
  18. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 336
  19. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  20. 2019FlauBERT: Unsupervised Language Model Pre-training for Frenchcited by 153
  21. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 148
  22. 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 133
  23. 2017Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agentscited by 107
  24. 2018Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractionscited by 84
  25. 2020DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inferencecited by 54
  26. 2018Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implicationscited by 35
  27. 2020ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learningcited by 35
  28. 2019PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Unitscited by 30
  29. 2016Maximizing CNN Accelerator Efficiency Through Resource Partitioningcited by 29
  30. 2020Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendationscited by 21
  31. 2019Optimally Scheduling CNN Convolutions for Efficient Memory Accesscited by 10
  32. 2018Genetic-Gated Networks for Deep Reinforcementcited by 7
  33. 2019Heterogeneous Dataflow Accelerators for Multi-DNN Workloadscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 5; 2025: 1; 2026: 3.

15 papers.

Sort:

By area:

  1. 2022DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloadscited by 8
  2. 2023MoCA: Memory-Centric, Adaptive Execution for Multi-Tenant Deep Neural Networkscited by 8
  3. 2023Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloadscited by 6
  4. 2024SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Acceleratorscited by 6
  5. 2023Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chipscited by 5
  6. 2024Deep Reinforcement Learning based Online Scheduling Policy for Deep Neural Network Multi-Tenant Multi-Accelerator Systemscited by 4
  7. 2024Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platformscited by 3
  8. 2022Demystifying Map Space Exploration for NPUscited by 2
  9. 2023MARS: Exploiting Multi-Level Parallelism for DNN Workloads on Adaptive Multi-Accelerator Systemscited by 1
  10. 2024Obsidian: Cooperative State-Space Exploration for Performant Inference on Secure ML Acceleratorscited by 1
  11. 2024Towards Fair and Firm Real-Time Scheduling in DNN Multi-Tenant Multi-Accelerator Systems via Reinforcement Learningcited by 0
  12. 2025CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUscited by 0
3 more
  1. 2026Compiler-Assisted Speculative Sampling for Accelerated LLM Inference on Heterogeneous Edge Devicescited by 0
  2. 2026Orchestrating Multimodal DNN Workloads in Wireless Neural Processingcited by 0
  3. 2026Terastal: Layer-Variant-based Scheduling for Real-Time Multi-DNN Workloads on Heterogeneous Acceleratorscited by 0