# Efficient Residue Number System Based Winograd Convolution

arXiv: https://arxiv.org/abs/2007.12216 · HTML: https://mlsanity.com/paper/2007.12216/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [QONNX: Representing Arbitrary-Precision Quantized Neural Networks](https://mlsanity.com/paper/2206.07527/) (2022)
- [Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques](https://mlsanity.com/paper/2112.15131/) (2021)
- [Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile](https://mlsanity.com/paper/2209.12982/) (2022)
- [SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic](https://mlsanity.com/paper/2407.02913/) (2024)
- [Fast Convolution based on Winograd Minimum Filtering: Introduction and Development](https://mlsanity.com/paper/2111.00977/) (2021)

## Abstract (arXiv)

Prior research has shown that Winograd algorithm can reduce the computational complexity of convolutional neural networks (CNN) with weights and activations represented in floating point. However it is difficult to apply the scheme to the inference of low-precision quantized (e.g. INT8) networks. Our work extends the Winograd algorithm to Residue Number System (RNS). The minimal complexity convolution is computed precisely over large transformation tile (e.g. 10 x 10 to 16 x 16) of filters and activation patches using the Winograd transformation and low cost (e.g. 8-bit) arithmetic without degrading the prediction accuracy of the networks during inference. The arithmetic complexity reduction is up to 7.03x while the performance improvement is up to 2.30x to 4.69x for 3 x 3 and 5 x 5 filters respectively.