# Efficient Winograd Convolution via Integer Arithmetic

arXiv: https://arxiv.org/abs/1901.01965 · HTML: https://mlsanity.com/paper/1901.01965/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2019.

## Built on by (most cited first, 6 of 6)

- [Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile](https://mlsanity.com/paper/2209.12982/) (2022)
- [Low-Rank Winograd Transformation for 3D Convolutional Neural Networks](https://mlsanity.com/paper/2301.11180/) (2023)
- [YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs](https://mlsanity.com/paper/2310.00574/) (2023)
- [Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales](https://mlsanity.com/paper/2412.19867/) (2024)
- [Fast Convolution based on Winograd Minimum Filtering: Introduction and Development](https://mlsanity.com/paper/2111.00977/) (2021)
- [Benchmarking Deep Learning Convolutions on Energy-constrained CPUs](https://mlsanity.com/paper/2509.26217/) (2025)

## Abstract (arXiv)

Convolution is the core operation for many deep neural networks. The Winograd convolution algorithms have been shown to accelerate the widely-used small convolution sizes. Quantized neural networks can effectively reduce model sizes and improve inference speed, which leads to a wide variety of kernels and hardware accelerators that work with integer data. The state-of-the-art Winograd algorithms pose challenges for efficient implementation and execution by the integer kernels and accelerators. We introduce a new class of Winograd algorithms by extending the construction to the field of complex and propose optimizations that reduce the number of general multiplications. The new algorithm achieves an arithmetic complexity reduction of 3.13x over the direct method and an efficiency gain up to 17.37% over the rational algorithms. Furthermore, we design and implement an integer-based filter scaling scheme to effectively reduce the filter bit width by 30.77% without any significant accuracy loss.