• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于流水线光总线的并行算法与架构。

Parallel algorithms and architectures based on pipelined optical buses.

作者信息

Guo Z, Caulfield H J

出版信息

Appl Opt. 1995 Dec 10;34(35):8116-24. doi: 10.1364/AO.34.008116.

DOI:10.1364/AO.34.008116
PMID:21068926
Abstract

Optical signals have some unique properties, such as unidirectional propagation and precisely predictable path delays in waveguides, which are not shared with their electronic counterparts. By taking advantage of these unique properties, we can use optical interconnections to achieve speed improvements in single-instruction stream, multiple-data streams (SIMD) computations. We first show how optical buses can be utilized advantageously in SIMD architectures to obtain fast solutions to several computational problems, including integer addition, counting and logical XOR, sorting, and fast Fourier transforms. We then present a new implementation of the optical buses to meet the unique requirements in highperformance optical-electronic computing systems. Such an implementation allows the transmission of messages at speeds ideal for optics and, in the meantime, the processing of data at speeds ideal for electronics, dealing successfully with the speed limitation by electronics in optical-electronic computers. The primary effects of this bimodal optical bus are twofold: reduction of fiber lengths and reduction of system latency. Reduced latency is a unique advantage to an optical bimodal bus. Together, these observations make optical-bus-based architectures appear to be a promising approach to SIMD processing.

摘要

光信号具有一些独特的特性,比如单向传播以及在波导中可精确预测的路径延迟,而这些特性是其电子信号对应物所不具备的。利用这些独特特性,我们可以使用光互连来提高单指令流多数据流(SIMD)计算的速度。我们首先展示如何在SIMD架构中有利地利用光总线,以快速解决几个计算问题,包括整数加法、计数和逻辑异或、排序以及快速傅里叶变换。然后我们提出一种光总线的新实现方式,以满足高性能光电子计算系统的独特要求。这样的实现方式允许以光学理想的速度传输消息,同时以电子学理想的速度处理数据,成功应对光电子计算机中电子学的速度限制。这种双峰光总线的主要作用有两方面:减少光纤长度和减少系统延迟。减少延迟是光双峰总线的独特优势。综合来看,这些观察结果使基于光总线的架构似乎成为SIMD处理的一种有前景的方法。

相似文献

1
Parallel algorithms and architectures based on pipelined optical buses.基于流水线光总线的并行算法与架构。
Appl Opt. 1995 Dec 10;34(35):8116-24. doi: 10.1364/AO.34.008116.
2
Designing massively parallel optical computers: a case study.设计大规模并行光学计算机:一个案例研究。
Appl Opt. 1990 May 10;29(14):2187-200. doi: 10.1364/AO.29.002187.
3
Optical content-addressable parallel processor: architecture, algorithms, and design concepts.光学内容寻址并行处理器:架构、算法及设计概念。
Appl Opt. 1992 Jun 10;31(17):3241-58. doi: 10.1364/AO.31.003241.
4
Parallel electro-optical rule-based system for fast execution of expert systems.用于快速执行专家系统的并行电光规则基系统。
Appl Opt. 1993 Apr 10;32(11):1863-75. doi: 10.1364/AO.32.001863.
5
Area-time trade-offs in arrays with optical pipelined buses.
Appl Opt. 1996 Apr 10;35(11):1827-35. doi: 10.1364/AO.35.001827.
6
Demonstration of optical computing logics based on binary decision diagram.基于二元决策图的光学计算逻辑演示。
Opt Express. 2012 Jan 16;20(2):1378-84. doi: 10.1364/OE.20.001378.
7
Combinatorial logic based digital optical computing architectures.基于组合逻辑的数字光学计算架构。
Appl Opt. 1988 May 1;27(9):1661-73. doi: 10.1364/AO.27.001661.
8
Array processors using a quadratic residue number system.使用二次剩余数制的阵列处理器。
Appl Opt. 1989 Aug 15;28(16):3461-5. doi: 10.1364/AO.28.003461.
9
Optical interconnections for massively parallel architectures.用于大规模并行架构的光互连
Appl Opt. 1990 Mar 10;29(8):1077-93. doi: 10.1364/AO.29.001077.
10
Locality-based control algorithms for reconfigurable optical interconnection networks.用于可重构光互连网络的基于局部性的控制算法。
Appl Opt. 1994 Mar 10;33(8):1528-37. doi: 10.1364/AO.33.001528.