FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10

TL;DR

FeCaffe is a novel FPGA-enabled extension of the Caffe framework that supports deep learning training and inference on Intel Stratix 10, offering significant speedups and flexibility for CNN development.

Contribution

This work introduces FeCaffe, a hierarchical design methodology enabling FPGA support for mainline deep learning features in Caffe, including training and inference.

Findings

Supports almost full CNN training and inference features on FPGA

Achieves 6.4x and 8.4x average speedup for forward and backward passes on LeNet

Provides a flexible, extensible platform for FPGA-based deep learning development

Abstract

Deep learning and Convolutional Neural Network (CNN) have becoming increasingly more popular and important in both academic and industrial areas in recent years cause they are able to provide better accuracy and result in classification, detection and recognition areas, compared to traditional approaches. Currently, there are many popular frameworks in the market for deep learning development, such as Caffe, TensorFlow, Pytorch, and most of frameworks natively support CPU and consider GPU as the mainline accelerator by default. FPGA device, viewed as a potential heterogeneous platform, still cannot provide a comprehensive support for CNN development in popular frameworks, in particular to the training phase. In this paper, we firstly propose the FeCaffe, i.e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e.g. training and inference with Caffe. Furthermore, we provide some benchmarks with FeCaffe by taking some classical CNN networks as examples, and further analysis of kernel execution time in details accordingly. Finally, some optimization directions including FPGA kernel design, system pipeline, network architecture, user case application and heterogeneous platform levels, have been proposed gradually to improve FeCaffe performance and efficiency. The result demonstrates the proposed FeCaffe is capable of supporting almost full features during CNN network training and inference respectively with high degree of design flexibility, expansibility and reusability for deep learning development. Compared to prior studies, our architecture can support more network and training settings, and current configuration can achieve 6.4x and 8.4x average execution time improvement for forward and backward respectively for LeNet.