DCCVIVApr 10, 2024

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA

arXiv:2404.07188v14 citationsh-index: 7FCCM
Originality Incremental advance
AI Analysis

This work addresses the computational bottleneck for researchers and practitioners using GNNs in computer vision, offering a domain-specific hardware solution that is incremental but with strong performance gains.

The paper tackles the problem of accelerating GNN-based computer vision tasks by introducing GCV-Turbo, an FPGA-based accelerator with a novel hardware architecture and compiler, achieving an average latency reduction of 68.4x compared to CPUs and 4.1x compared to GPUs across six tasks.

Graph neural networks (GNNs) have recently empowered various novel computer vision (CV) tasks. In GNN-based CV tasks, a combination of CNN layers and GNN layers or only GNN layers are employed. This paper introduces GCV-Turbo, a domain-specific accelerator on FPGA for end-to-end acceleration of GNN-based CV tasks. GCV-Turbo consists of two key components: (1) a \emph{novel} hardware architecture optimized for the computation kernels in both CNNs and GNNs using the same set of computation resources. (2) a PyTorch-compatible compiler that takes a user-defined model as input, performs end-to-end optimization for the computation graph of a given GNN-based CV task, and produces optimized code for hardware execution. The hardware architecture and the compiler work synergistically to support a variety of GNN-based CV tasks. We implement GCV-Turbo on a state-of-the-art FPGA and evaluate its performance across six representative GNN-based CV tasks with diverse input data modalities (e.g., image, human skeleton, point cloud). Compared with state-of-the-art CPU (GPU) implementations, GCV-Turbo achieves an average latency reduction of $68.4\times$ ($4.1\times$) on these six GNN-based CV tasks. Moreover, GCV-Turbo supports the execution of the standalone CNNs or GNNs, achieving performance comparable to that of state-of-the-art CNN (GNN) accelerators for widely used CNN-only (GNN-only) models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes