Argus: An End-to-End Framework for Accelerating CNNs on FPGAs

摘要

In this article, we present Argus, an end-to-end framework for accelerating convolutional neural networks (CNNs) on field-programmable gate arrays (FPGAs) with minimum user effort. Argus uses state-of-the-art methods to auto-generate highly optimized CNN accelerator designs for FPGAs, and includes software for running an FPGA-backed CNN inference microservice.