Optics for High-Performance Servers and Supercomputers

Benner, Alan F.; Kuchta, Daniel M.; Pepeljugoski, P.; Budd, R.; Hougham, Gareth; Fasano, Benjamin; Marston, K.; Bagheri, Harry; Seminaro, Edward J; Xu, Hui; Meadowcroft, David; Fields, Mitchell H.; McColloch, Larry; Robinson, Michael C.; Miller, Frederick W.; Kaneshiro, Ron; Granger, Russell; Childers, Darrell; Childers, Eric

doi:10.1364/ofc.2010.otuh1

Cited by 73 publications

(22 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For machines with peak performance beyond 10PF, optics will play a far more important role. For example, in the planned POWER7-IH systems [3], all the board-to-board interconnects, will be optical. A major change in the packaging tightly integrates the optics onto the chip-level package.…”

Section: Optics In Petascale Supercomputersmentioning

confidence: 99%

Optical Interconnects in Future Servers

Kash

Benner²,

Doany

et al. 2011

Optical Fiber Communication Conference/National Fiber Optic Engineers Conference 2011

Self Cite

View full text Add to dashboard Cite

Optical interconnects are common in today's petascale supercomputers, and will become pervasive at the exascale during this decade. Technologies that can meet the challenging technological and economic requirements for the exascale will be reviewed. Optics in Petascale SupercomputersIn 2008, Roadrunner[1], the first petaflop supercomputer (i.e., >10 15 floating point operations per second) was constructed. The large number of microprocessor cores in such petascale machines must be interconnected with a high capacity communications network to permit efficient computation. Higher interconnect bandwidth will generally result in more efficient use of the microprocessors in real calculations. Prior to 2005, this network used electrical interconnects in essentially all supercomputers. Communication bitrates increased beyond ~2Gb/s starting in about 2005. For distances greater than about 20m, electrical interconnects were impractical and optics began to be used for these longer rack-to-rack interconnects (e.g., ASCI Purple[2]). For cost reasons, however, the shorter rack-to-rack interconnect in this machine was still electrical. By 2008, communication bitrates had increased to 5Gb/s (InfiniBand DDR), and the practical reach of electrical interconnects was shorter. At the same time, the cost of optics had decreased. As a result, for Roadrunner, all node-to-node communication was optical. However, in these examples, all the intra-node communication was electrical. Also, the conversion to optics was at the edge of the node/rack, requiring an electrical interconnect from the chip through several levels of packaging before conversion to photons. For machines with peak performance beyond 10PF, optics will play a far more important role. For example, in the planned POWER7-IH systems [3], all the board-to-board interconnects, will be optical. A major change in the packaging tightly integrates the optics onto the chip-level package. Optical transmitter and receiver modules are placed on the same ceramic Hub (switch) Module [4,5] , with each channel using a 10Gb/s signaling rate and 8b10b coding. Projections for future supercomputersBecause microprocessor clock speeds are not rapidly increasing, supercomputing performance improvements come from larger numbers of processing cores operating in parallel. For example [7], the #1 machine on the top500 list from June, 2002 was the NEC Earth-Simulator with 5120 single core processor chips, as compared to Roadrunner which has some 97,920 cores in 12,240 Cell Broadband Engine® processor chips plus 6,562 dual-core AMD Opteron® chips [8]. This increasing core and chip count drives increasing communication bandwidth at higher bitrates.Trends for optical interconnects in future supercomputers can be extrapolated from past growth. Historically, computational power has grown approximately 10x every 4 years [7], and this growth is expected to continue. Affordable supercomputing requires that the cost and power consumption of supercomputers grow more slowly than computational power. ...

show abstract

Section: Optics In Petascale Supercomputersmentioning

confidence: 99%

Optical Interconnects in Future Servers

Kash

Benner²,

Doany

et al. 2011

Optical Fiber Communication Conference/National Fiber Optic Engineers Conference 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…P HOTONIC networks-on-chip (NoC) are becoming an integral part of high-performance computing (HPC) platforms, high-end data centers, and high-performance chip multiprocessors [1]- [3], a development underlined by the fact that rack-to-rack communications in some of the fastest HPC systems are nowadays performed optically [4]. It is envisioned that this trend of using optical communications at an eversmaller scale will continue to grow, so that in future HPC platforms optics will play the main role in node-to-node and even intra-node communications [3].…”

Section: Introductionmentioning

confidence: 99%

Calculation of Bit Error Rates in Optical Systems With Silicon Photonic Wires

You

Panoiu

2015

IEEE J. Quantum Electron.

View full text Add to dashboard Cite

A theoretical approach to calculate the bit error rate (BER) in optical systems containing silicon photonic wires (Si-PhWs) is presented. Specifically, the optical link consists of a single-mode silicon-on-insulator strip waveguide followed by a direct-detection optical receiver containing an optical filter, an ideal square-law photodetector, and an electrical filter. We assume that the optical input consists of a superposition of a nonreturnto-zero ON-OFF keying modulated optical signal and an additive white Gaussian noise, the BER of the transmitted optical signal being calculated by using the time domain Karhunen-Loève expansion method. The propagation of the optical signal in the Si-PhW is described by employing both a rigorous theoretical model that incorporates all relevant linear and nonlinear optical effects and the mutual interaction between free-carriers and the optical field, as well as a linearized model valid in the low noise power regime. These analytical and computational tools are then used to comprehensively investigate the influence of the parameters characterizing the waveguide and optical signal on the transmission BER.

show abstract

“…In 2012, compact size optical I/O modules called MicroPOD were employed in Power775 and Blue Gene/Q systems [3,4]. 56 modules are integrated on a ceramic substrate on which a switch logic chip is mounted, and a high-bandwidth density of 1.9 Gb/s/mm 2 is achieved.…”

Section: Introductionmentioning

confidence: 99%

Assembly process for high bandwidth density organic optical MCM

Tokunari

Nakagawa

2014

IEEE CPMT Symposium Japan 2014

View full text Add to dashboard Cite

We develop a high-bandwidth density organic optical multi-chip module (MCM). A high packaging density is achieved by integrating bare optical chips, developing compact fiber connectors that connect perpendicularly to the surface of the module, and manufacturing total internal reflection mirrors by a precise laser ablation technique. An assembly procedure for the optical MCM is established. It is verified that the organic MCM is resistant to heat of reflow processes and that mirror quality does not degrade due to the lens array assembly process.

show abstract

Optics for High-Performance Servers and Supercomputers

Cited by 73 publications

References 1 publication

Optical Interconnects in Future Servers

Optical Interconnects in Future Servers

Calculation of Bit Error Rates in Optical Systems With Silicon Photonic Wires

Assembly process for high bandwidth density organic optical MCM

Contact Info

Product

Resources

About