Extending Data Flow Architectures for Convolutional Neural Networks to Multiple FPGAs
Authors:
- 12 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 132-141
Abstract
Convolutional Neural Networks (CNNs) are the state-of-the-art Artificial Intelligence frameworks that are used for a variety of applications including autonomous driving, surveillance and object detection. Since CNNs are very compute intensive, Field-Programmable Gate Array (FPGA)-based accelerators such as HPIPE have been used to speed up CNN computations. Although such accelerators show significant improvements in CNN performance, large CNNs such as ResNet152 still pose a challenge due to their high compute and memory requirements. This article discusses how we augment and extend HPIPE, the state-of-the-art CNN inference accelerator for FPGAs. We propose an automated CAD flow to partition large CNNs across multiple FPGAs that communicate via 100 Gb Ethernet. We utilize this CAD flow to estimate the performance improvements when scaling HPIPE to multiple FPGAs on six different CNNs. Moreover, we demonstrate through a prototype system that doubling the number of FPGAs results in 2× performance improvement on three CNNs: MobileNet-V1, MobileNet-V2, and ResNet-50.Keywords
Funding Information
- VMware
This publication has 28 references indexed in Scilit:
- TGPA2018
- Low-Cost CNN Design for Intelligent Surveillance System2018
- A Configurable Cloud-Scale DNN Processor for Real-Time AI2018
- NVIDIA Tensor Core Programmability, Performance & Precision2018
- Latency-driven design for FPGA-based convolutional neural networks2017
- In-Datacenter Performance Analysis of a Tensor Processing UnitACM SIGARCH Computer Architecture News, 2017
- Performance Analysis of GPU-Based Convolutional Neural Networks2016
- Energy-Efficient CNN Implementation on a Deeply Pipelined FPGA Cluster2016
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009