mlsanityData to 7 Oct 2026

Fast Convolution based on Winograd Minimum Filtering: Introduction and Development

arXiv 2111.00977 ↗First posted 1 Nov 2021cs.AI cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Network (CNN) has been widely used in various fields and played an important role. Convolution operators are the fundamental component of convolutional neural networks, and it is also the most time-consuming part of network training and inference. In recent years, researchers have proposed several fast convolution algorithms including FFT and Winograd. Among them, Winograd convolution significantly reduces the multiplication operations in convolution, and it also takes up less memory space than FFT convolution. Therefore, Winograd convolution has quickly become the first choice for fast convolution implementation within a few years. At present, there is no systematic summary of the convolution algorithm. This article aims to fill this gap and provide detailed references for follow-up researchers. This article summarizes the development of Winograd convolution from the three aspects of algorithm expansion, algorithm optimization, implementation, and application, and finally makes a simple outlook on the possible future directions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 97 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

31 of 97 references.

References · 31

  1. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  2. 2013Fast Training of Convolutional Networks through FFTscited by 89
  3. 2018Efficient Sparse-Winograd Convolutional Neural Networkscited by 20
  4. 2017An OpenCL(TM) Deep Learning Accelerator on Arria 10cited by 11
  5. 2020Searching for Winograd-aware Quantized Networkscited by 11
  6. 2016Caffeinated FPGAs: FPGA Framework For Convolutional Neural Networkscited by 8
  7. 2020HybridDNN: A Framework for High-Performance Hybrid DNN Accelerator Design and Implementationcited by 8
  8. 2017Enabling Sparse Winograd Convolution by Native Pruningcited by 6
  9. 2019Efficient Winograd Convolution via Integer Arithmeticcited by 6
  10. 2018Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networkscited by 5
  11. 2019Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUscited by 5
  12. 2020DWM: A Decomposable Winograd Method for Convolution Accelerationcited by 5
19 more
  1. 2020Efficient Residue Number System Based Winograd Convolutioncited by 5
  2. 2020INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devicescited by 5
  3. 2021WinoCNN: Kernel Sharing Winograd Systolic Array for Efficient Convolutional Neural Network Acceleration on FPGAscited by 5
  4. 2018Sparse Winograd Convolutional neural networks on small-scale systolic arrayscited by 4
  5. 2019Winograd Convolution for DNNs: Beyond linear polynomialscited by 4
  6. 2020LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Unitscited by 4
  7. 2021Winograd Algorithm for AdderNetcited by 4
  8. 2016Deep Tensor Convolution on Multicorescited by 3
  9. 2018Face Recognition with Hybrid Efficient Convolution Algorithms on FPGAscited by 3
  10. 2020Quantaized Winograd/Toom-Cook Convolution for DNNs: Beyond Canonical Polynomials Basecited by 3
  11. 2018Hardware-Efficient Structure of the Accelerating Module for Implementation of Convolutional Neural Network Basic Operationcited by 2
  12. 2019Spatial-Winograd Pruning Enabling Sparse Winograd Convolutioncited by 2
  13. 2019Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domainscited by 2
  14. 2019Derivation and Analysis of Fast Bilinear Algorithms for Convolutioncited by 2
  15. 2016cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCLcited by 1
  16. 2019Towards Design Space Exploration and Optimization of Fast Algorithms for Convolutional Neural Networks (CNNs) on FPGAscited by 1
  17. 2019L3 Fusion: Fast Transformed Convolutions on CPUscited by 1
  18. 2020Minimal Filtering Algorithms for Convolutional Neural Networkscited by 1
  19. 2021Accelerating Large Kernel Convolutions with Nested Winograd Transformation.pdfcited by 1

Built on by

Not cited yet.