Optical Interconnects and Extreme Computing

Bergman, Keren; Shalf, John; Hausken, T.

doi:10.1364/opn.27.4.000032

Cited by 22 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the time of writing this review, we are approximately at the point where, with current and emerging technology, optics is poised to provide at least modest energy reductions for data links compared to electrical approaches, even for relatively short links between cabinets and in backplanes or module connections [14], [15], [16], [17], [18], [19], [20].…”

Section: A Goals For This Reviewmentioning

confidence: 99%

“…Energy per bit References and notes Wireless data 10 -30μJ [31] Internet: access 40 -80nJ [8]; (a),(b) Internet: routing 20nJ [9]; (c) Internet: optical WDM links 3nJ [32]; (d) Reading DRAM 5pJ [5]; (e) Communicating off chip 1 -20 pJ [5], [15], [16] Data link multiplexing and timing circuits ~ 2 pJ [24] Communicating across chip 600 fJ [5]; (f) Floating point operation 100fJ [5]; (g) Energy in DRAM cell 10fJ [33]; (h) Switching CMOS gate ~50aJ -3fJ [4], [6], [34], [35]; (i) 1 electron at 1V, or 1 photon @1eV 0.16aJ (160zJ) WDM -wavelength division multiplexing DRAM -dynamic random-access memory CMOS -complementary metal-oxide-semiconductor transistor (a) Uses projections to 2016 from [8] (b) Presumes wired connections (optical or electrical) to the network (c) Total for 20 "hops" per internet connection, and derating energies from the 2008 numbers in [9] using a factor of 0.74 per year (from [8]) for improved electronics energy efficiency. (d) Total for 20 "hops" per internet connection, and using projections to 2016 in [32] (e) Rounded sum of the DRAM access and interface energies as projected for 2017 in [5], for off-chip DRAM (f) Based on 2017 projects in [5] for a 10mm line on the chip (g) Double-precision fused multiply-add (floating-point) operation using the projection in [5] of ~ 6.5 pJ in 2017 for this 64-bit operation to calculate energy per bit.…”

Section: Operationmentioning

confidence: 99%

See 1 more Smart Citation

Attojoule Optoelectronics for Low-Energy Information Processing and Communications

Miller

2017

J. Lightwave Technol.

604

406

View full text Add to dashboard Cite

Optics offers unique opportunities for reducing energy in information processing and communications while simultaneously resolving the problem of interconnect bandwidth density inside machines. Such energy dissipation overall is now at environmentally significant levels; the source of that dissipation is progressively shifting from logic operations to interconnect energies. Without the prospect of substantial reduction in energy per bit communicated, we cannot continue the exponential growth of our use of information. The physics of optics and optoelectronics fundamentally addresses both interconnect energy and bandwidth density, and optics may be the only scalable solution to such problems. Here we summarize the corresponding background, status, opportunities, and research directions for optoelectronic technology and novel optics, including sub-femtojoule devices in waveguide and novel 2D array optical systems. We compare different approaches to low-energy optoelectronic output devices and their scaling, including lasers, modulators and LEDs, optical confinement approaches (such as resonators) to enhance effects, and the benefits of different material choices, including 2D materials and other quantum-confined structures. With such optoelectronic energy reductions, and the elimination of line charging dissipation by the use optical connections, the next major interconnect dissipations are in the electronic circuits for receiver amplifiers, timing recovery and multiplexing. We show we can address these through the integration of photodetectors to reduce or eliminate receiver circuit energies, free-space optics to eliminate the need for timing and multiplexing circuits (while also solving bandwidth density problems), and using optics generally to save power by running large synchronous systems. One target concept is interconnects from ~ 1 cm to ~ 10 m that have the same energy (~ 10fJ/bit) and simplicity as local electrical wires on chip.

show abstract

Section: A Goals For This Reviewmentioning

confidence: 99%

Section: Operationmentioning

confidence: 99%

Attojoule Optoelectronics for Low-Energy Information Processing and Communications

Miller

2017

J. Lightwave Technol.

604

406

View full text Add to dashboard Cite

show abstract

“…Picosecond response times in few-layer WSe 2 have been observed with autocorrelation measurements where the photo-excited carriers were extracted vertically using a van der Waals heterostructure [36]. In this design, the channel length is limited by the thickness of the WSe 2 rather than the spacing between two lateral electrodes.…”

Section: Black Phosphorus Photodetectorsmentioning

confidence: 99%

“…Relatedly, the demand for data storage and high-performance computing continues to grow at an exponential rate [2], keeping in step with Moore's law. This requires much higher bandwidth density for inter-chip communication than ever before (expected to surpass 40 Gbps per interconnect by 2020 [1]).…”

Section: Introductionmentioning

confidence: 99%

Integration of 2D materials on a silicon photonics platform for optoelectronics applications

Youngblood

2016

Nanophotonics

104

View full text Add to dashboard Cite

Owing to enormous growth in both data storage and the demand for high-performance computing, there has been a major effort to integrate telecom networks onchip. Silicon photonics is an ideal candidate, thanks to the maturity and economics of current CMOS processes in addition to the desirable optical properties of silicon in the near IR. The basics of optical communication require the ability to generate, modulate, and detect light, which is not currently possible with silicon alone. Growing germanium or III/V materials on silicon is technically challenging due to the mismatch between lattice constants and thermal properties. One proposed solution is to use two-dimensional materials, which have covalent bonds in-plane, but are held together by van der Waals forces out of plane. These materials have many unique electrical and optical properties and can be transferred to an arbitrary substrate without lattice matching requirements. This article reviews recent progress toward the integration of 2D materials on a silicon photonics platform for optoelectronic applications.

show abstract

“…Amid the persistent growth of data traffic and computational demands throughout the globe, photonic technologies are increasingly called upon to supplant electronic signal processing. Given the intrinsically high bandwidth available to optical carriers-coupled with low-loss transmission in optical fibers-photonics has successfully expanded into a variety of communications contexts, from long-haul spans to metro-area networks, datacenters [1,2], and high-performance computing (HPC) [3][4][5][6]. As performance at the single-core level has plateaued in recent years, parallel architectures now lead the way in HPC, so that data movement dominates much of the total power budget and thus can be viewed as perhaps the main hurdle on the path toward the Exascale regime (10 18 FLOPs/second) [4].…”

Section: Introductionmentioning

confidence: 99%

All-Optical Frequency Processor for Networking Applications

Lukens

et al. 2020

J. Lightwave Technol.

View full text Add to dashboard Cite

We propose an electro-optic approach for transparent optical networking, in which frequency channels are actively transformed into any desired mapping in a wavelength-multiplexed environment. Based on electro-optic phase modulators and Fourier-transform pulse shapers, our all-optical frequency processor (AFP) is examined numerically for the specific operations of frequency channel hopping and broadcasting, and found capable of implementing these transformations with favorable component requirements. Extending our analysis via a mutual-information-based metric for system optimization, we show how to optimize transformation performance under limited resources in a classical context, contrasting the results with those found using metrics motivated by quantum information, such as fidelity and success probability. Given its compatibility with on-chip implementation, as well as elimination of optical-to-electrical conversion in frequency channel switching, the AFP looks to offer valuable potential in silicon photonic network design.

show abstract

Optical Interconnects and Extreme Computing

Abstract: order-creating-national-strategic-computing-initiative Some believe that interconnects inevitably will need to employ WDM and integrated photonics, because of the scale promised by these technologies.

Cited by 22 publications

References 0 publications

Attojoule Optoelectronics for Low-Energy Information Processing and Communications

Attojoule Optoelectronics for Low-Energy Information Processing and Communications

Integration of 2D materials on a silicon photonics platform for optoelectronics applications

All-Optical Frequency Processor for Networking Applications

Contact Info

Product

Resources

About