Fugaku and A64FX: the First Exascale Supercomputer and its Innovative Arm CPU

S. Matsuoka
{"title":"Fugaku and A64FX: the First Exascale Supercomputer and its Innovative Arm CPU","authors":"S. Matsuoka","doi":"10.23919/VLSICircuits52068.2021.9492415","DOIUrl":null,"url":null,"abstract":"Fugaku is the first exascale supercomputer in the world, designed and built primarily by Riken Center for Computational Science (R-CCS) and Fujitsu Ltd., but involving essentially all the major stakeholders in the Japanese HPC community. The name ‘Fugaku’ is an alternative name for Mt. Fuji, and was chosen to signify that the machine not only seeks very high performance, but also a broad base of users and applicability at the same time. The heart of Fugaku is the new Fujitsu A64FX Arm processor, which is 100% compliant to Aarch64 specifications, yet embodies technologies realized for the first time in a major server general-purpose CPU, such as 7nm process technology, on-package integrated HBM2 and terabyte-class SVE streaming capabilities, on-die embedded TOFU-D high-performance network including the network switch, and adoption of so-called ‘disaggregated architecture’ that allows separation and arbitrary combination of CPU core, memory, and network functions. Fugaku uses 158,974 A64FX CPUs in a single socket node configuration, making it the largest and fastest supercomputer ever created, signified by its groundbreaking achievements in major HPC benchmarks, as well as producing societal results in COVID-19 applications.","PeriodicalId":106356,"journal":{"name":"2021 Symposium on VLSI Circuits","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Symposium on VLSI Circuits","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/VLSICircuits52068.2021.9492415","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

Fugaku is the first exascale supercomputer in the world, designed and built primarily by Riken Center for Computational Science (R-CCS) and Fujitsu Ltd., but involving essentially all the major stakeholders in the Japanese HPC community. The name ‘Fugaku’ is an alternative name for Mt. Fuji, and was chosen to signify that the machine not only seeks very high performance, but also a broad base of users and applicability at the same time. The heart of Fugaku is the new Fujitsu A64FX Arm processor, which is 100% compliant to Aarch64 specifications, yet embodies technologies realized for the first time in a major server general-purpose CPU, such as 7nm process technology, on-package integrated HBM2 and terabyte-class SVE streaming capabilities, on-die embedded TOFU-D high-performance network including the network switch, and adoption of so-called ‘disaggregated architecture’ that allows separation and arbitrary combination of CPU core, memory, and network functions. Fugaku uses 158,974 A64FX CPUs in a single socket node configuration, making it the largest and fastest supercomputer ever created, signified by its groundbreaking achievements in major HPC benchmarks, as well as producing societal results in COVID-19 applications.
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
Fugaku和A64FX:第一台百亿亿级超级计算机及其创新Arm CPU
Fugaku是世界上第一台百亿亿次超级计算机,主要由理研计算科学中心(R-CCS)和富士通有限公司设计和建造,但基本上涉及日本高性能计算社区的所有主要利益相关者。“Fugaku”这个名字是富士山的另一个名字,被选中是为了表明这台机器不仅寻求非常高的性能,同时也有广泛的用户基础和适用性。Fugaku的核心是全新的Fujitsu A64FX Arm处理器,该处理器100%符合Aarch64规范,同时体现了首次在主要服务器通用CPU中实现的技术,如7nm制程技术,封装内集成HBM2和tb级SVE流功能,片上嵌入式TOFU-D高性能网络,包括网络交换机,采用所谓的“分解架构”,允许CPU核心、内存和网络功能的分离和任意组合。Fugaku在单个插槽节点配置中使用158,974个A64FX cpu,使其成为有史以来最大和最快的超级计算机,这标志着其在主要HPC基准测试中取得的突破性成就,以及在COVID-19应用程序中产生的社会成果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
PIMCA: A 3.4-Mb Programmable In-Memory Computing Accelerator in 28nm for On-Chip DNN Inference A 24–31 GHz Reference Oversampling ADPLL Achieving FoMjitter−N of -269.3 dB A 6.78 MHz Wireless Power Transfer System for Simultaneous Charging of Multiple Receivers with Maximum Efficiency using Adaptive Magnetic Field Distributor IC Enhanced Core Circuits for scaling DRAM: 0.7V VCC with Long Retention 138ms at 125°C and Random Row/Column Access Times Accelerated by 1.5ns A Sub-mW Dual-Engine ML Inference System-on-Chip for Complete End-to-End Face-Analysis at the Edge
×
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