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 incursworkflow (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, theepilogue-fuseddesign integrates recurring output reconstruction postprocessing into the implicit GEMM epilogue to reduce auxiliary kernels and intermediate traffic. Second, theoperation-reordereddesign 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, theunifieddesign 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, theepilogue-fused,operation-reordered, andunifieddesigns reduce the normalized end-to-end runtime by 7.6%, 10.1%, and 27.8% relative tobaseline, respectively, with theunifieddesign consistently achieving the largest improvement across the evaluated models.