Suppr超能文献

用于高性能计算系统的光互连网络。

Optical interconnection networks for high-performance computing systems.

机构信息

Lightwave Research Laboratory, Department of Electrical Engineering, Columbia University, 1300 Seeley W Mudd, 500 West 120th Street, New York 10027, USA.

出版信息

Rep Prog Phys. 2012 Apr;75(4):046402. doi: 10.1088/0034-4885/75/4/046402. Epub 2012 Mar 13.

Abstract

Enabled by silicon photonic technology, optical interconnection networks have the potential to be a key disruptive technology in computing and communication industries. The enduring pursuit of performance gains in computing, combined with stringent power constraints, has fostered the ever-growing computational parallelism associated with chip multiprocessors, memory systems, high-performance computing systems and data centers. Sustaining these parallelism growths introduces unique challenges for on- and off-chip communications, shifting the focus toward novel and fundamentally different communication approaches. Chip-scale photonic interconnection networks, enabled by high-performance silicon photonic devices, offer unprecedented bandwidth scalability with reduced power consumption. We demonstrate that the silicon photonic platforms have already produced all the high-performance photonic devices required to realize these types of networks. Through extensive empirical characterization in much of our work, we demonstrate such feasibility of waveguides, modulators, switches and photodetectors. We also demonstrate systems that simultaneously combine many functionalities to achieve more complex building blocks. We propose novel silicon photonic devices, subsystems, network topologies and architectures to enable unprecedented performance of these photonic interconnection networks. Furthermore, the advantages of photonic interconnection networks extend far beyond the chip, offering advanced communication environments for memory systems, high-performance computing systems, and data centers.

摘要

在硅光子技术的推动下,光互连网络有可能成为计算和通信行业的一项关键颠覆性技术。计算性能不断提高的持久追求,加上严格的功耗限制,催生了与芯片多处理器、内存系统、高性能计算系统和数据中心相关的计算并行性的不断增长。维持这些并行性增长为片上和片外通信带来了独特的挑战,促使人们转向新颖的、根本不同的通信方法。由高性能硅光子器件支持的芯片级光子互连网络提供了前所未有的带宽可扩展性,同时降低了功耗。我们证明了硅光子平台已经生产出实现这些类型网络所需的所有高性能光子器件。通过我们的大量工作中的广泛经验特征化,我们证明了波导、调制器、开关和光电探测器的这种可行性。我们还展示了同时结合多种功能以实现更复杂构建块的系统。我们提出了新颖的硅光子器件、子系统、网络拓扑和架构,以实现这些光子互连网络的前所未有的性能。此外,光子互连网络的优势远远超出了芯片范围,为内存系统、高性能计算系统和数据中心提供了先进的通信环境。

相似文献

1
Optical interconnection networks for high-performance computing systems.
Rep Prog Phys. 2012 Apr;75(4):046402. doi: 10.1088/0034-4885/75/4/046402. Epub 2012 Mar 13.
2
Scaling silicon photonic switch fabrics for data center interconnection networks.
Opt Express. 2015 Jan 26;23(2):1159-75. doi: 10.1364/OE.23.001159.
3
A scalable silicon photonic chip-scale optical switch for high performance computing systems.
Opt Express. 2013 Dec 30;21(26):32655-67. doi: 10.1364/OE.21.032655.
5
Locality-based control algorithms for reconfigurable optical interconnection networks.
Appl Opt. 1994 Mar 10;33(8):1528-37. doi: 10.1364/AO.33.001528.
6
On-chip silicon photonic signaling and processing: a review.
Sci Bull (Beijing). 2018 Oct 15;63(19):1267-1310. doi: 10.1016/j.scib.2018.05.038. Epub 2018 Jul 12.
7
First demonstration of long-haul transmission using silicon microring modulators.
Opt Express. 2010 Jul 19;18(15):15544-52. doi: 10.1364/OE.18.015544.
8
Integrating photonics with silicon nanoelectronics for the next generation of systems on a chip.
Nature. 2018 Apr;556(7701):349-354. doi: 10.1038/s41586-018-0028-z. Epub 2018 Apr 18.
9
Ultra-efficient 10 Gb/s hybrid integrated silicon photonic transmitter and receiver.
Opt Express. 2011 Mar 14;19(6):5172-86. doi: 10.1364/OE.19.005172.
10
Silicon-chip-based ultrafast optical oscilloscope.
Nature. 2008 Nov 6;456(7218):81-4. doi: 10.1038/nature07430.

引用本文的文献

1
Anisotropic metamaterials for scalable photonic integrated circuits: a review on subwavelength gratings for high-density integration.
Nanophotonics. 2025 Mar 31;14(9):1311-1331. doi: 10.1515/nanoph-2024-0627. eCollection 2025 Apr.
2
Polarization and wavelength routers based on diffractive neural network.
Front Optoelectron. 2024 Jul 16;17(1):22. doi: 10.1007/s12200-024-00126-2.
3
Automated Nanoscale Absolute Accuracy Alignment System for Transfer Printing.
ACS Appl Nano Mater. 2020 Oct 23;3(10):10326-10332. doi: 10.1021/acsanm.0c02224. Epub 2020 Sep 23.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验