基于FPGA的灵活数据流CNN加速器

Haoran Li, Lei Gong, Chao Wang, Xuehai Zhou
{"title":"基于FPGA的灵活数据流CNN加速器","authors":"Haoran Li, Lei Gong, Chao Wang, Xuehai Zhou","doi":"10.1109/CCGridW59191.2023.00065","DOIUrl":null,"url":null,"abstract":"With the increasing diversity of neural networks, accelerators supporting multiple dataflows are more efficient than those only supporting a specific dataflow. However, due to different storage structures and transmission patterns in different dataflows, deploying an accelerator with multiple heterogeneous cores on FPGA that lacks resources is challenging. In this paper, we present an instruction-based CNN accelerator supporting flexible dataflow. Towards reducing the resource occupation of FPGA, we propose a novel architecture with a delicate data path reusing the storage module and the computing module. In addition, a special instruction mechanism is designed to control the data transmission. As a case study, we implement a prototype and test it on ResNet18 and MobileNetv1. Results show, compared to the multi-core accelerator that supports the flexible dataflow, we achieve 1.3-2.7x speedup.","PeriodicalId":341115,"journal":{"name":"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A flexible dataflow CNN accelerator on FPGA\",\"authors\":\"Haoran Li, Lei Gong, Chao Wang, Xuehai Zhou\",\"doi\":\"10.1109/CCGridW59191.2023.00065\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the increasing diversity of neural networks, accelerators supporting multiple dataflows are more efficient than those only supporting a specific dataflow. However, due to different storage structures and transmission patterns in different dataflows, deploying an accelerator with multiple heterogeneous cores on FPGA that lacks resources is challenging. In this paper, we present an instruction-based CNN accelerator supporting flexible dataflow. Towards reducing the resource occupation of FPGA, we propose a novel architecture with a delicate data path reusing the storage module and the computing module. In addition, a special instruction mechanism is designed to control the data transmission. As a case study, we implement a prototype and test it on ResNet18 and MobileNetv1. Results show, compared to the multi-core accelerator that supports the flexible dataflow, we achieve 1.3-2.7x speedup.\",\"PeriodicalId\":341115,\"journal\":{\"name\":\"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)\",\"volume\":\"35 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCGridW59191.2023.00065\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCGridW59191.2023.00065","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

随着神经网络多样性的增加,支持多个数据流的加速器比只支持特定数据流的加速器效率更高。然而,由于不同数据流的存储结构和传输模式不同,在缺乏资源的FPGA上部署具有多个异构核的加速器是一项挑战。本文提出了一种支持灵活数据流的基于指令的CNN加速器。为了减少FPGA对资源的占用,我们提出了一种新颖的架构,该架构具有巧妙的数据路径,重用存储模块和计算模块。此外,还设计了一种特殊的指令机制来控制数据的传输。作为案例研究,我们实现了一个原型,并在ResNet18和MobileNetv1上进行了测试。结果表明,与支持灵活数据流的多核加速器相比,我们实现了1.3-2.7倍的加速。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A flexible dataflow CNN accelerator on FPGA
With the increasing diversity of neural networks, accelerators supporting multiple dataflows are more efficient than those only supporting a specific dataflow. However, due to different storage structures and transmission patterns in different dataflows, deploying an accelerator with multiple heterogeneous cores on FPGA that lacks resources is challenging. In this paper, we present an instruction-based CNN accelerator supporting flexible dataflow. Towards reducing the resource occupation of FPGA, we propose a novel architecture with a delicate data path reusing the storage module and the computing module. In addition, a special instruction mechanism is designed to control the data transmission. As a case study, we implement a prototype and test it on ResNet18 and MobileNetv1. Results show, compared to the multi-core accelerator that supports the flexible dataflow, we achieve 1.3-2.7x speedup.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信