mlsanityData to 7 Oct 2026

AI Accelerator Survey and Trends

arXiv 2109.08957 ↗First posted 18 Sep 2021cs.AR cs.DC cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Over the past several years, new machine learning accelerators were being announced and released every month for a variety of applications from speech recognition, video object detection, assisted driving, and many data center applications. This paper updates the survey of AI accelerators and processors from past two years. This paper collects and summarizes the current commercial accelerators that have been publicly announced with peak performance and power consumption numbers. The performance and power values are plotted on a scatter graph, and a number of dimensions and observations from the trends on this plot are again discussed and analyzed. This year, we also compile a list of benchmarking performance results and compute the computational efficiency with respect to peak performance.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 10 of its 134 references that are in the map. First posted on arXiv 18 Sep 2021.

Builds on

10 of 134 references.

References · 10

  1. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  2. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
  3. 2019MLPerf Inference Benchmarkcited by 195
  4. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  5. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 68
  6. 2020Survey of Machine Learning Acceleratorscited by 29
  7. 2018DLA: Compiler and FPGA Overlay for Neural Network Inference Accelerationcited by 13
  8. 2019Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Goingcited by 13
  9. 2014Kickstarting High-performance Energy-efficient Manycore Architectures with Epiphanycited by 1
  10. 2016Epiphany-V: A 1024 processor 64-bit RISC System-On-Chipcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 8; 2024: 1; 2025: 2; 2026: 1.

17 papers.

Sort:

By area:

  1. 2023Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based acceleratorscited by 42
  2. 2022Intelligent Computing: The Latest Advances, Challenges and Futurecited by 6
  3. 2022The MIT Supercloud Workload Classification Challengecited by 3
  4. 2023Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inferencecited by 3
  5. 2022PINCH: An Adversarial Extraction Attack Framework for Deep Learning Modelscited by 2
  6. 2022Statistical Modeling of Soft Error Influence on Neural Networkscited by 2
  7. 2023One-Shot Online Testing of Deep Neural Networks Based on Distribution Shift Detectioncited by 2
  8. 2023Lincoln AI Computing Survey (LAICS) Updatecited by 2
  9. 2023AI-assisted Automated Workflow for Real-time X-ray Ptychography Data Analysis via Federated Resourcescited by 1
  10. 2023Energy Estimates Across Layers of Computing: From Devices to Large-Scale Applications in Machine Learning for Natural Language Processing, Scientific Computing, and Cryptocurrency Miningcited by 1
  11. 2023GreenLightningAI: An Efficient AI System with Decoupled Structural and Quantitative Knowledgecited by 1
  12. 2021Machines & Influence: An Information Systems Lenscited by 0
5 more
  1. 2023Perspectives on AI Architectures and Co-design for Earth System Predictabilitycited by 0
  2. 2024Optimizing DNN Inference on Multi-Accelerator SoCs at Training-timecited by 0
  3. 2025Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directionscited by 0
  4. 2025DCO: Dynamic Cache Orchestration for LLM Accelerators through Predictive Managementcited by 0
  5. 2026A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Modelcited by 0