一种将卷积网络映射到具有内存计算节点的片上网络的新方案

2020 International SoC Design Conference (ISOCC) Pub Date : 2020-10-21 DOI:10.1109/ISOCC50952.2020.9332940

Jiayi Liu, Kejie Huang

{"title":"一种将卷积网络映射到具有内存计算节点的片上网络的新方案","authors":"Jiayi Liu, Kejie Huang","doi":"10.1109/ISOCC50952.2020.9332940","DOIUrl":null,"url":null,"abstract":"Computing-In Memory (CIM) has been widely used to accelerate the inferencing speed of deep learning. Network-on-Chips (NoCs) are usually used together with CIM to enable the versatile ability of the hardware. This paper proposes a bandwidth aware mapping scheme to minimize both hops and bandwidth requirement. The simulation results show that the proposed scheme could reduce the hops and bandwidth requirements by more than 33.57% and 46.13%, respectively.","PeriodicalId":270577,"journal":{"name":"2020 International SoC Design Conference (ISOCC)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"A Novel Scheme to Map Convolutional Networks to Network-on-Chip with Computing-In-Memory Nodes\",\"authors\":\"Jiayi Liu, Kejie Huang\",\"doi\":\"10.1109/ISOCC50952.2020.9332940\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Computing-In Memory (CIM) has been widely used to accelerate the inferencing speed of deep learning. Network-on-Chips (NoCs) are usually used together with CIM to enable the versatile ability of the hardware. This paper proposes a bandwidth aware mapping scheme to minimize both hops and bandwidth requirement. The simulation results show that the proposed scheme could reduce the hops and bandwidth requirements by more than 33.57% and 46.13%, respectively.\",\"PeriodicalId\":270577,\"journal\":{\"name\":\"2020 International SoC Design Conference (ISOCC)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-10-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International SoC Design Conference (ISOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISOCC50952.2020.9332940\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International SoC Design Conference (ISOCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISOCC50952.2020.9332940","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

内存计算(CIM)被广泛用于提高深度学习的推理速度。片上网络(noc)通常与CIM一起使用，以实现硬件的多功能。本文提出了一种带宽感知映射方案，以最小化跳数和带宽需求。仿真结果表明，该方案可将跳数和带宽要求分别降低33.57%和46.13%以上。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

A Novel Scheme to Map Convolutional Networks to Network-on-Chip with Computing-In-Memory Nodes

Computing-In Memory (CIM) has been widely used to accelerate the inferencing speed of deep learning. Network-on-Chips (NoCs) are usually used together with CIM to enable the versatile ability of the hardware. This paper proposes a bandwidth aware mapping scheme to minimize both hops and bandwidth requirement. The simulation results show that the proposed scheme could reduce the hops and bandwidth requirements by more than 33.57% and 46.13%, respectively.

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

2020 International SoC Design Conference (ISOCC)

自引率

0.00%

发文量