展台融合:有效的位融合乘数与展台编码

2020 International SoC Design Conference (ISOCC) Pub Date : 2020-10-21 DOI:10.1109/ISOCC50952.2020.9332943

Seokho Lee, Youngmin Kim

{"title":"展台融合:有效的位融合乘数与展台编码","authors":"Seokho Lee, Youngmin Kim","doi":"10.1109/ISOCC50952.2020.9332943","DOIUrl":null,"url":null,"abstract":"Recently, several attempts have been made to optimize Deep Neural Networks (DNNs) through various hardware acceleration methods. Among them, Bit Fusion, the dynamic bit-level fusion/decomposition hardware architecture, was noted. We introduce a new model structure, Booth Fusion, which makes dynamic bit-level operations more efficient by implementing Bit Fusion with booth encoding. Our design shows improvements in 16.4% for the number of LUT and 14.2% for throughput.","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":"1","resultStr":"{\"title\":\"Booth Fusion: Efficient Bit Fusion Multiplier with Booth Encoding\",\"authors\":\"Seokho Lee, Youngmin Kim\",\"doi\":\"10.1109/ISOCC50952.2020.9332943\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, several attempts have been made to optimize Deep Neural Networks (DNNs) through various hardware acceleration methods. Among them, Bit Fusion, the dynamic bit-level fusion/decomposition hardware architecture, was noted. We introduce a new model structure, Booth Fusion, which makes dynamic bit-level operations more efficient by implementing Bit Fusion with booth encoding. Our design shows improvements in 16.4% for the number of LUT and 14.2% for throughput.\",\"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\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International SoC Design Conference (ISOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISOCC50952.2020.9332943\",\"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/ISOCC50952.2020.9332943","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

近年来，人们尝试通过各种硬件加速方法来优化深度神经网络(dnn)。其中，Bit Fusion是一种动态比特级融合/分解硬件架构。我们引入了一种新的模型结构，Booth Fusion，它通过实现Bit Fusion和Booth编码来提高动态比特级操作的效率。我们的设计显示LUT的数量提高了16.4%，吞吐量提高了14.2%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Booth Fusion: Efficient Bit Fusion Multiplier with Booth Encoding

Recently, several attempts have been made to optimize Deep Neural Networks (DNNs) through various hardware acceleration methods. Among them, Bit Fusion, the dynamic bit-level fusion/decomposition hardware architecture, was noted. We introduce a new model structure, Booth Fusion, which makes dynamic bit-level operations more efficient by implementing Bit Fusion with booth encoding. Our design shows improvements in 16.4% for the number of LUT and 14.2% for throughput.

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