mlsanityData to 14 Oct 2026

Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network

arXiv 2306.09552 ↗First posted 15 Jun 2023cs.ARcited by 2

Not on the map. Why?

Abstract (arXiv)

EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to accelerate pruned and sparse neural networks and spawned many algorithm-hardware co-designs for model compression and acceleration, both in academia and commercial AI chips. In retrospect, we review the background of this project, summarize the pros and cons, and discuss new opportunities where pruning, sparsity, and low precision can accelerate emerging deep learning workloads.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

18 of 26 references.

References · 18

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  3. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 856
  4. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  5. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  6. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  7. 2020SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruningcited by 234
  8. 2021Accelerating Sparse Deep Neural Networkscited by 223
  9. 2022On-Device Training Under 256KB Memorycited by 160
  10. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 135
  11. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 89
  12. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 73
6 more
  1. 2016ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGAcited by 52
  2. 2022Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Modelscited by 45
  3. 2016Bit-pragmatic Deep Neural Network Computingcited by 32
  4. 2021PointAcc: Efficient Point Cloud Acceleratorcited by 24
  5. 2018UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetitioncited by 20
  6. 2022The Sparse Abstract Machinecited by 4

Built on by

Cited by year

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

2 papers.

  1. 2023ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Modelscited by 94
  2. 2024Adaptive Inference: Theoretical Limits and Unexplored Opportunitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021SparseDNN: Fast Sparse Deep Learning Inference on CPUs
  2. 2022FasterAI: A Lightweight Library for Creating Sparse Neural Networks
  3. 2022S4: a High-sparsity, High-performance AI Accelerator
  4. 2026Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
  5. 2025GoPrune: Accelerated Structured Pruning with ℓ2,p-Norm Optimization
  6. 2022Towards Hardware-Specific Automatic Compression of Neural Networks
  7. 2021Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
  8. 2024Neural Network Compression for Reinforcement Learning Tasks