综述FPGA加速卷积神经网络的方案与性能优化。
FPGA-based Acceleration for Convolutional Neural Networks: A Comprehensive Review
- 基于FPGA的并行计算与数据流优化提升CNN推理效率。
- 对比多种FPGA架构，涵盖延迟、吞吐量与能效表现。
- 适合关注硬件加速与嵌入式AI部署的研究者参考。
卷积神经网络（CNN）是深度学习的核心，广泛应用于各类场景。然而其复杂度持续增长，带来巨大的计算压力，亟需高效硬件加速器。现场可编程门阵列（FPGA）因其可重构性、并行处理能力与高能效比，成为主流解决方案。本文全面综述针对CNN设计的FPGA硬件加速器，总结现有研究中的性能评估框架，分析关键优化策略，包括并行计算、数据流优化及软硬件协同设计。同时，从延迟、吞吐量、计算效率、功耗和资源利用率等方面比较不同FPGA架构的性能表现。最后，指出未来挑战与机遇，强调该领域仍具持续创新潜力。
原文摘要 · Abstract (English)
Convolutional Neural Networks (CNNs) are fundamental to deep learning, driving applications across various domains. However, their growing complexity has significantly increased computational demands, necessitating efficient hardware accelerators. Field-Programmable Gate Arrays (FPGAs) have emerged as a leading solution, offering reconfigurability, parallelism, and energy efficiency. This paper provides a comprehensive review of FPGA-based hardware accelerators specifically designed for CNNs. It presents and summarizes the performance evaluation framework grounded in existing studies and explores key optimization strategies, such as parallel computing, dataflow optimization, and hardware-software co-design. It also compares various FPGA architectures in terms of latency, throughput, compute efficiency, power consumption, and resource utilization. Finally, the paper highlights future challenges and opportunities, emphasizing the potential for continued innovation in this field.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。