Restructuring the Implicit GEMM Workflow for Complex-Valued Convolution
Open Access
- 20 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 61010-61024
Abstract
Complex-valued neural networks (CV-CNNs) are valuable in signal-centric domains because they preserve magnitude–phase structure that can be lost in purely real-valued representations. However, this benefit does not directly translate to efficient GPU inference. In common implementations, complex-valued convolution is typically decomposed into four real-valued terms, each executed via implicit GEMM. This fragmented execution incurs workflow (structural) overheads from repeated tensor preparation, output reconstruction, and fine-grained kernel launches beyond the core GEMM computation, increasing redundant memory movement and kernel-launch frequency and accounting for a substantial fraction of the end-to-end runtime of ComplexConv2d. This paper revisits the implicit GEMM execution structure of ComplexConv2d and proposes threeCV-CNN specialized restructurings that optimize the implicitGEMM workflow. First, the epilogue-fused design integrates recurring output reconstruction postprocessing into the implicit GEMM epilogue to reduce auxiliary kernels and intermediate traffic. Second, the operation-reordered design reorders the four real-valued convolution terms to increase reuse of already materialized real and imaginary input tensors within the implicit GEMM workflow, reducing repeated tensor preparation. Third, the unified design implements an implicit CGEMM kernel that directly consumes real and imaginary components through an integrated load path and performs complex accumulation within a consolidated execution flow, thereby substantially reducing these overheads. We evaluate the proposed designs across four representative CV-CNN backbones (ResNet18, ResNet50, VGG16, and VGG19). On average, the epilogue-fused, operation-reordered, and unified designs reduce the normalized end-to-end runtime by 7.6%, 10.1%, and 27.8% relative to baseline, respectively, with the unified design consistently achieving the largest improvement across the evaluated models.Keywords
Funding Information
- National Research Foundation of Korea (NRF) grant funded by the Korea Government [Ministry of Science and ICT (MSIT)] (RS-2025-02214322)
- National Research Foundation of Korea (NRF) grant funded by the Korea Government [Ministry of Science and ICT (MSIT)] (RS-2025-00553645)
This publication has 19 references indexed in Scilit:
- FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function2023
- Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN2022
- The Performance Analysis of Complex-Valued Neural Network in Radio Signal RecognitionIEEE Access, 2022
- Characterizing and Demystifying the Implicit Convolution Algorithm on Commercial Matrix-Multiplication Accelerators2021
- Analysis of deep complex‐valued convolutional neural networks for MRI reconstruction and phase‐focused applicationsMagnetic Resonance in Medicine, 2021
- Performance Evaluation of cuDNN Convolution Algorithms on NVIDIA Volta GPUsIEEE Access, 2019
- NVIDIA Tensor Core Programmability, Performance & Precision2018
- Parallel Multi Channel convolution using General Matrix Multiplication2017
- Deep Residual Learning for Image Recognition2016
- Complex-valued neural networks: The merits and their origins2009