高性能快速单流量子位片算术逻辑单元

IF 5.6 Q1 ENGINEERING, ELECTRICAL & ELECTRONIC
Jing Ren , Pei-Yao Qu , Jia-Hong Yang , Xiang-Yu Zheng , Hui Zhang , Jie Ren , Guang-Ming Tang
{"title":"高性能快速单流量子位片算术逻辑单元","authors":"Jing Ren ,&nbsp;Pei-Yao Qu ,&nbsp;Jia-Hong Yang ,&nbsp;Xiang-Yu Zheng ,&nbsp;Hui Zhang ,&nbsp;Jie Ren ,&nbsp;Guang-Ming Tang","doi":"10.1016/j.supcon.2024.100116","DOIUrl":null,"url":null,"abstract":"<div><p>Two optimization technologies, namely, bypass and carry-control optimization, were demonstrated for enhancing the performance of a bit-slice Arithmetic Logic Unit (ALU) in 2<sup><em>n</em></sup>-bit Rapid Single-Flux-Quantum (RSFQ) microprocessors. These technologies can not only shorten the calculation time but also solve data hazards. Among them, the proposed bypass technology is applicable to any 2<sup><em>n</em></sup>-bit ALU, whether it is bit-serial, bit-slice or bit-parallel. The high performance bit-slice ALU was implemented using the 6 <em>k</em>A/cm<sup>2</sup> Nb/AlO<sub><em>x</em></sub>/Nb junction fabrication process from Superconducting Electronics Facility of Shanghai Institute of Microsystem and Information Technology. It consists of 1693 Josephson junctions with an area of 2.46 <span><math><mrow><mo>×</mo></mrow></math></span> 0.81 mm<sup>2</sup>. All ALU operations of the MIPS32 instruction set are implemented, including two extended instructions, i.e., addition with carry (ADDC) and subtraction with borrow (SUBB). All the ALU operations were successfully obtained in SFQ testing based on OCTOPUX and the measured DC bias current margin can reach 86<span><math><mrow><mo>%</mo></mrow></math></span> - 104<span><math><mrow><mo>%</mo></mrow></math></span>. The ALU achieves a 100<span><math><mrow><mo>%</mo></mrow></math></span> utilization rate, regardless of carry/borrow read-after-write correlations between instructions.</p></div>","PeriodicalId":101185,"journal":{"name":"Superconductivity","volume":"11 ","pages":"Article 100116"},"PeriodicalIF":5.6000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772830724000334/pdfft?md5=96f792fb9935383fe687678b7f003e24&pid=1-s2.0-S2772830724000334-main.pdf","citationCount":"0","resultStr":"{\"title\":\"High performance rapid single-flux-quantum bit-slice arithmetic logic unit\",\"authors\":\"Jing Ren ,&nbsp;Pei-Yao Qu ,&nbsp;Jia-Hong Yang ,&nbsp;Xiang-Yu Zheng ,&nbsp;Hui Zhang ,&nbsp;Jie Ren ,&nbsp;Guang-Ming Tang\",\"doi\":\"10.1016/j.supcon.2024.100116\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Two optimization technologies, namely, bypass and carry-control optimization, were demonstrated for enhancing the performance of a bit-slice Arithmetic Logic Unit (ALU) in 2<sup><em>n</em></sup>-bit Rapid Single-Flux-Quantum (RSFQ) microprocessors. These technologies can not only shorten the calculation time but also solve data hazards. Among them, the proposed bypass technology is applicable to any 2<sup><em>n</em></sup>-bit ALU, whether it is bit-serial, bit-slice or bit-parallel. The high performance bit-slice ALU was implemented using the 6 <em>k</em>A/cm<sup>2</sup> Nb/AlO<sub><em>x</em></sub>/Nb junction fabrication process from Superconducting Electronics Facility of Shanghai Institute of Microsystem and Information Technology. It consists of 1693 Josephson junctions with an area of 2.46 <span><math><mrow><mo>×</mo></mrow></math></span> 0.81 mm<sup>2</sup>. All ALU operations of the MIPS32 instruction set are implemented, including two extended instructions, i.e., addition with carry (ADDC) and subtraction with borrow (SUBB). All the ALU operations were successfully obtained in SFQ testing based on OCTOPUX and the measured DC bias current margin can reach 86<span><math><mrow><mo>%</mo></mrow></math></span> - 104<span><math><mrow><mo>%</mo></mrow></math></span>. The ALU achieves a 100<span><math><mrow><mo>%</mo></mrow></math></span> utilization rate, regardless of carry/borrow read-after-write correlations between instructions.</p></div>\",\"PeriodicalId\":101185,\"journal\":{\"name\":\"Superconductivity\",\"volume\":\"11 \",\"pages\":\"Article 100116\"},\"PeriodicalIF\":5.6000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2772830724000334/pdfft?md5=96f792fb9935383fe687678b7f003e24&pid=1-s2.0-S2772830724000334-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Superconductivity\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2772830724000334\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Superconductivity","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772830724000334","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

为提高 2n 位快速单流量子(RSFQ)微处理器中位片算术逻辑单元(ALU)的性能,展示了两种优化技术,即旁路优化和进位控制优化。这些技术不仅能缩短计算时间,还能解决数据隐患。其中,所提出的旁路技术适用于任何 2n 位 ALU,无论是位串行、位片还是位并行。高性能位片 ALU 是利用上海微系统与信息技术研究所超导电子设施的 6 kA/cm2 Nb/AlOx/Nb 结制造工艺实现的。它由 1693 个约瑟夫森结组成,面积为 2.46 × 0.81 mm2。它实现了 MIPS32 指令集的所有 ALU 运算,包括两条扩展指令,即带进位的加法(ADDC)和带借位的减法(SUBB)。在基于 OCTOPUX 的 SFQ 测试中,成功实现了所有 ALU 操作,测得的直流偏置电流裕度可达 86% - 104%。无论指令之间的进位/借位读写关联如何,ALU 的利用率都达到了 100%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
High performance rapid single-flux-quantum bit-slice arithmetic logic unit

Two optimization technologies, namely, bypass and carry-control optimization, were demonstrated for enhancing the performance of a bit-slice Arithmetic Logic Unit (ALU) in 2n-bit Rapid Single-Flux-Quantum (RSFQ) microprocessors. These technologies can not only shorten the calculation time but also solve data hazards. Among them, the proposed bypass technology is applicable to any 2n-bit ALU, whether it is bit-serial, bit-slice or bit-parallel. The high performance bit-slice ALU was implemented using the 6 kA/cm2 Nb/AlOx/Nb junction fabrication process from Superconducting Electronics Facility of Shanghai Institute of Microsystem and Information Technology. It consists of 1693 Josephson junctions with an area of 2.46 × 0.81 mm2. All ALU operations of the MIPS32 instruction set are implemented, including two extended instructions, i.e., addition with carry (ADDC) and subtraction with borrow (SUBB). All the ALU operations were successfully obtained in SFQ testing based on OCTOPUX and the measured DC bias current margin can reach 86% - 104%. The ALU achieves a 100% utilization rate, regardless of carry/borrow read-after-write correlations between instructions.

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
CiteScore
3.90
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信