Coarse-Grained Floorplanning for streaming CNN applications on Multi-Die FPGAs
Coarse-Grained Floorplanning for streaming CNN applications on Multi-Die FPGAs
复制标题
DOI：
10.1109/ispdc55340.2022.00014
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Danielle Tchuinkou Kwadjo;Erman Nghonda Tchinda;C. Bobda
中科院分区：
文献类型：
--
作者：
Danielle Tchuinkou Kwadjo;Erman Nghonda Tchinda;C. Bobda
随着FPGA在云中的广泛采用，有必要研究将CNN有效部署到多FPGA云基础设施中的架构和机制。然而，神经网络不断增长的规模和复杂性，加上通信和片外存储器瓶颈，使得多FPGA设计越来越难以实现高资源利用率。在这项工作中，我们引入了一个可扩展的框架，该框架支持将CNN应用程序有效地集成到云基础设施中，该基础设施将多芯片FPGA暴露给云开发人员。我们的框架配备了两种机制，以方便在FPGA上部署CNN推理。首先，我们提出了一个模型来找到参数，最大限度地提高资源预算内的并行性，同时保持层之间的平衡速率。然后，我们提出了一种高效的粗粒度图划分算法，用于在FPGA上放置CNN组件的高质量和可扩展的可路由性驱动。与在相同数量的FPGA上实现的基线实现相比，原型结果实现了总体37%的频率提高，资源使用量降低。
With the vast adoption of FPGAs in the cloud, it becomes necessary to investigate architectures and mechanisms for the efficient deployment of CNN into multi-FPGAs cloud Infrastructure. However, neural networks’ growing size and complexity, coupled with communication and off-chip memory bottlenecks, make it increasingly difficult for multi-FPGA designs to achieve high resource utilization. In this work, we introduce a scalable framework that supports the efficient integration of CNN applications into a cloud infrastructure that exposes multi-Die FPGAs to cloud developers. Our framework is equipped is with two mechanisms to facilitate the deployment of CNN inference on FPGA. First, we propose a model to find the parameters that maximize the parallelism within the resource budget while maintaining a balanced rate between the layers. Then, we propose an efficient Coarse-Grained graph partitioning algorithm for high-quality and scalable routability-drive placement of CNN’s components on the FPGAs. Prototyping results achieve an overall 37% higher frequency, with lower resource usage compared to a baseline implementation on the same number of FPGAs.