mlsanityData to 14 Oct 2026

FPGA Resource-aware Structured Pruning for Real-Time Neural Networks

arXiv 2308.05170 ↗First posted 9 Aug 2023cs.AR cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Neural networks achieve state-of-the-art performance in image classification, speech recognition, scientific analysis and many more application areas. Due to the high computational complexity and memory footprint of neural networks, various compression techniques, such as pruning and quantization, have been proposed in literature. Pruning sparsifies a neural network, reducing the number of multiplications and memory. However, pruning often fails to capture properties of the underlying hardware, causing unstructured sparsity and load-balance inefficiency, thus bottlenecking resource improvements. We propose a hardware-centric formulation of pruning, by formulating it as a knapsack problem with resource-aware tensor structures. Evaluated on a range of tasks, including sub-microsecond particle classification at CERN's Large Hadron Collider and fast image classification, the proposed method achieves reductions ranging between 55% and 92% in the DSP utilization and up to 81% in BRAM utilization.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 9 Aug 2023.

Builds on

28 of 46 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  5. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  6. 2020What is the State of Neural Network Pruning?cited by 583
  7. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  8. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
  9. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 150
  10. 2018Fast inference of deep neural networks in FPGAs for particle physicscited by 133
  11. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 94
  12. 2020Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorscited by 80
16 more
  1. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 76
  2. 2018FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networkscited by 56
  3. 2020Methods for Pruning Deep Neural Networkscited by 49
  4. 2018ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multiplierscited by 42
  5. 2020Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4MLcited by 42
  6. 2021Fast convolutional neural networks on FPGAs with hls4mlcited by 42
  7. 2022Structural Pruning via Latency-Saliency Knapsackcited by 41
  8. 2020Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physicscited by 34
  9. 2019LUTNet: Rethinking Inference in FPGA Soft Logiccited by 28
  10. 2018Accelerator-Aware Pruning for Convolutional Neural Networkscited by 22
  11. 2022Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4mlcited by 14
  12. 2022Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4mlcited by 11
  13. 2020PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Acceleratorscited by 9
  14. 2020Joint Pruning & Quantization for Extremely Sparse Neural Networkscited by 9
  15. 2021HALP: Hardware-Aware Latency Pruningcited by 8
  16. 2021Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inferencecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2024HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAscited by 9
  2. 2025hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardwarecited by 9
  3. 2025da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAscited by 8
  4. 2024Optimal Gradient Checkpointing for Sparse and Recurrent Architectures using Off-Chip Memorycited by 3
  5. 2026HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inferencecited by 1
  6. 2026PQuantML: A Tool for End-to-End Hardware-aware Model Compressioncited by 0
  7. 2026Hardware-aware Graph Neural Networks prunning for embedded event-based visioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms
  2. 2021Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities
  3. 2021Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference
  4. 2026Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators
  5. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Survey
  6. 2026Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
  7. 2023Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization
  8. 2025Structured Pruning and Quantization for Learned Image Compression