mlsanityData to 7 Oct 2026

Multiply-and-Fire (MNF): An Event-driven Sparse Neural Network Accelerator

arXiv 2204.09797 ↗First posted 20 Apr 2022cs.AR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning, particularly deep neural network inference, has become a vital workload for many computing systems, from data centers and HPC systems to edge-based computing. As advances in sparsity have helped improve the efficiency of AI acceleration, there is a continued need for improved system efficiency for both high-performance and system-level acceleration. This work takes a unique look at sparsity with an event (or activation-driven) approach to ANN acceleration that aims to minimize useless work, improve utilization, and increase performance and energy efficiency. Our analytical and experimental results show that this event-driven solution presents a new direction to enable highly efficient AI inference for both CNN and MLP workloads. This work demonstrates state-of-the-art energy efficiency and performance centring on activation-based sparsity and a highly-parallel dataflow method that improves the overall functional unit utilization (at 30 fps). This work enhances energy efficiency over a state-of-the-art solution by 1.46×. Taken together, this methodology presents a novel, new direction to achieve high-efficiency, high-performance designs for next-generation AI acceleration platforms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 64 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

24 of 64 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  12. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
12 more
  1. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  2. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  3. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  4. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  5. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
  6. 2013Predicting Parameters in Deep Learningcited by 223
  7. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  8. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  9. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 132
  10. 2017NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Mapscited by 39
  11. 2021DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Eracited by 27
  12. 2020You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracycited by 4

Built on by

Not cited yet.