SDA:大规模深度神经网络系统的软件定义加速器

2014 IEEE Hot Chips 26 Symposium (HCS) Pub Date : 2014-08-01 DOI:10.1109/HOTCHIPS.2014.7478821

Jian Ouyang, Shiding Lin, Wei Qi, Yong Wang, Bo Yu, Song Jiang

{"title":"SDA:大规模深度神经网络系统的软件定义加速器","authors":"Jian Ouyang, Shiding Lin, Wei Qi, Yong Wang, Bo Yu, Song Jiang","doi":"10.1109/HOTCHIPS.2014.7478821","DOIUrl":null,"url":null,"abstract":"This article consists of a collection of slides from the author's conference presentation on the special features, system design and architectures, processing capabilities, and targeted markets for Baidu's family of software defined accelerator products (SDA) for large scale deep neural network (DNN) systems.","PeriodicalId":299263,"journal":{"name":"2014 IEEE Hot Chips 26 Symposium (HCS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"111","resultStr":"{\"title\":\"SDA: Software-defined accelerator for large-scale DNN systems\",\"authors\":\"Jian Ouyang, Shiding Lin, Wei Qi, Yong Wang, Bo Yu, Song Jiang\",\"doi\":\"10.1109/HOTCHIPS.2014.7478821\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article consists of a collection of slides from the author's conference presentation on the special features, system design and architectures, processing capabilities, and targeted markets for Baidu's family of software defined accelerator products (SDA) for large scale deep neural network (DNN) systems.\",\"PeriodicalId\":299263,\"journal\":{\"name\":\"2014 IEEE Hot Chips 26 Symposium (HCS)\",\"volume\":\"86 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"111\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 IEEE Hot Chips 26 Symposium (HCS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HOTCHIPS.2014.7478821\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE Hot Chips 26 Symposium (HCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HOTCHIPS.2014.7478821","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 111

摘要

本文由作者在会议上的演讲幻灯片组成，内容涉及百度用于大规模深度神经网络(DNN)系统的软件定义加速器产品(SDA)系列的特殊功能、系统设计和架构、处理能力和目标市场。

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

SDA: Software-defined accelerator for large-scale DNN systems

This article consists of a collection of slides from the author's conference presentation on the special features, system design and architectures, processing capabilities, and targeted markets for Baidu's family of software defined accelerator products (SDA) for large scale deep neural network (DNN) systems.

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

2014 IEEE Hot Chips 26 Symposium (HCS)

自引率

0.00%

发文量