OpenCNN: A Winograd Minimal Filtering Algorithm Implementation in CUDA

Roberto L. Castro, Diego Andrade and Basilio B. Fraguela
Additional contact information
Roberto L. Castro: Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, 15071 A Coruña, Spain
Diego Andrade: Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, 15071 A Coruña, Spain
Basilio B. Fraguela: Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, 15071 A Coruña, Spain

Mathematics, 2021, vol. 9, issue 17, 1-19

Abstract: Improving the performance of the convolution operation has become a key target for High Performance Computing (HPC) developers due to its prevalence in deep learning applied mainly to video processing. The improvement is being pushed by algorithmic and implementation innovations. Algorithmically, the convolution can be solved as it is mathematically enunciated, but other methods allow to transform it into a Fast Fourier Transform (FFT) or a GEneral Matrix Multiplication (GEMM). In this latter group, the Winograd algorithm is a state-of-the-art variant that is specially suitable for smaller convolutions. In this paper, we present openCNN, an optimized CUDA C++ implementation of the Winograd convolution algorithm. Our approach achieves speedups of up to 1.76 × on Turing RTX 2080Ti and up to 1.85 × on Ampere RTX 3090 with respect to Winograd convolution in cuDNN 8.2.0. OpenCNN is released as open-source software.

Keywords: deep learning; convolution; Winograd; CUDA (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/17/2033/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/17/2033/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:17:p:2033-:d:620895

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().