{"title":"英特尔Geneseo项目","authors":"Ajay V. Bhatt","doi":"10.1109/FPL.2007.4380613","DOIUrl":null,"url":null,"abstract":"Summary form only given. Moore's law has enabled the current trend toward multi-core computing that is dramatically increasing performance and power efficiency. I/O interconnects are on a similar growth path of increasing performance and efficiency. As computing requirements become more complex, new strategies evolve to provide the performance necessary for data-and calculation-intensive applications. A growing such strategy is the use of specialized accelerators to enhance the performance of specific tasks or functions. Broadly speaking, an accelerator is a device that attaches to a computing system, providing optimal performance at reduced cost and/or power for a specialized task. Examples of emerging applications for which accelerators may be suitable are photorealistic graphics, financial simulation, and climate modeling. The development of specialized application accelerators is happening today. However, they do not share a common attach point, and have no common architecture or programming model. An industry framework that economically and efficiently enables specialized acceleration is highly desirable. This talk will focus on a new architectural framework for the attached application accelerators called Geneseo. The talk will provide an overview of the Geneseo interconnect and software architecture and provide insight in to proposed improvements in available bandwidth, latency, efficiency and software interface.","PeriodicalId":93570,"journal":{"name":"International Conference on Field-programmable Logic and Applications : [proceedings]. International Conference on Field-Programmable Logic and Applications","volume":"22 1","pages":"1"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The Intel Geneseo Project\",\"authors\":\"Ajay V. Bhatt\",\"doi\":\"10.1109/FPL.2007.4380613\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Summary form only given. Moore's law has enabled the current trend toward multi-core computing that is dramatically increasing performance and power efficiency. I/O interconnects are on a similar growth path of increasing performance and efficiency. As computing requirements become more complex, new strategies evolve to provide the performance necessary for data-and calculation-intensive applications. A growing such strategy is the use of specialized accelerators to enhance the performance of specific tasks or functions. Broadly speaking, an accelerator is a device that attaches to a computing system, providing optimal performance at reduced cost and/or power for a specialized task. Examples of emerging applications for which accelerators may be suitable are photorealistic graphics, financial simulation, and climate modeling. The development of specialized application accelerators is happening today. However, they do not share a common attach point, and have no common architecture or programming model. An industry framework that economically and efficiently enables specialized acceleration is highly desirable. This talk will focus on a new architectural framework for the attached application accelerators called Geneseo. The talk will provide an overview of the Geneseo interconnect and software architecture and provide insight in to proposed improvements in available bandwidth, latency, efficiency and software interface.\",\"PeriodicalId\":93570,\"journal\":{\"name\":\"International Conference on Field-programmable Logic and Applications : [proceedings]. International Conference on Field-Programmable Logic and Applications\",\"volume\":\"22 1\",\"pages\":\"1\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-11-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Field-programmable Logic and Applications : [proceedings]. International Conference on Field-Programmable Logic and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/FPL.2007.4380613\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Field-programmable Logic and Applications : [proceedings]. International Conference on Field-Programmable Logic and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FPL.2007.4380613","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

只提供摘要形式。摩尔定律使当前的多核计算趋势成为可能,这极大地提高了性能和能效。I/O互连也处于提高性能和效率的类似增长路径上。随着计算需求变得越来越复杂,新的策略不断发展,以提供数据和计算密集型应用程序所需的性能。越来越多的这种策略是使用专门的加速器来提高特定任务或功能的性能。从广义上讲,加速器是一种连接到计算系统的设备,以更低的成本和/或功耗为特定任务提供最佳性能。加速器可能适合的新兴应用示例有逼真的图形、金融模拟和气候建模。目前正在开发专门的应用程序加速器。然而,它们没有共享一个公共的附加点,也没有公共的体系结构或编程模型。一个经济有效地实现专业化加速的行业框架是非常可取的。本次演讲将重点介绍一个用于附加应用程序加速器的新架构框架Geneseo。本次演讲将概述Geneseo互连和软件架构,并对可用带宽、延迟、效率和软件接口的改进提出见解。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
The Intel Geneseo Project
Summary form only given. Moore's law has enabled the current trend toward multi-core computing that is dramatically increasing performance and power efficiency. I/O interconnects are on a similar growth path of increasing performance and efficiency. As computing requirements become more complex, new strategies evolve to provide the performance necessary for data-and calculation-intensive applications. A growing such strategy is the use of specialized accelerators to enhance the performance of specific tasks or functions. Broadly speaking, an accelerator is a device that attaches to a computing system, providing optimal performance at reduced cost and/or power for a specialized task. Examples of emerging applications for which accelerators may be suitable are photorealistic graphics, financial simulation, and climate modeling. The development of specialized application accelerators is happening today. However, they do not share a common attach point, and have no common architecture or programming model. An industry framework that economically and efficiently enables specialized acceleration is highly desirable. This talk will focus on a new architectural framework for the attached application accelerators called Geneseo. The talk will provide an overview of the Geneseo interconnect and software architecture and provide insight in to proposed improvements in available bandwidth, latency, efficiency and software interface.
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
期刊最新文献
Performance-Driven System Generation for Distributed Vertex-Centric Graph Processing on Multi-FPGA Systems "All programmable FPGA, providing hardware efficiency to software programmers" The evolution of architecture exploration of programmable devices Virtex-6 and Spartan-6, plus a look into the future In search of agile hardware
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1