We examine the current performance and future demands of interconnects to and on silicon chips. We compare electrical and optical interconnects and project the requirements for optoelectronic and optical devices if optics is to solve the major problems of interconnects for future high-performance silicon chips. Optics has potential benefits in interconnect density, energy, and timing. The necessity of low interconnect energy imposes low limits especially on the energy of the optical output devices, with a ~ 10 fJ/bit device energy target emerging. Some optical modulators and radical laser approaches may meet this requirement. Low (e.g., a few femtofarads or less) photodetector capacitance is important. Very compact wavelength splitters are essential for connecting the information to fibers. Dense waveguides are necessary on-chip or on boards for guided wave optical approaches, especially if very high clock rates or dense wavelength-division multiplexing (WDM) is to be avoided. Free-space optics potentially can handle the necessary bandwidths even without fast clocks or WDM. With such technology, however, optics may enable the continued scaling of interconnect capacity required by future chips.

Device Requirements for Optical Interconnects to Silicon Chips

The various arguments for introducing optical interconnections to silicon CMOS chips are summarized, and the challenges for optical, optoelectronic, and integration technologies are discussed. Optics could solve many physical problems of interconnects, including precise clock distribution, system synchronization (allowing larger synchronous zones, both on-chip and between chips), bandwidth and density of long interconnections, and reduction of power dissipation. Optics may relieve a broad range of design problems, such as crosstalk, voltage isolation, wave reflection, impedence matching, and pin inductance. It may allow continued scaling of existing architectures and enable novel highly interconnected or high-bandwidth architectures. No physical breakthrough is required to implement dense optical interconnects to silicon chips, though substantial technological work remains. Cost is a significant barrier to practical introduction, though revolutionary approaches exist that might achieve economies of scale. An Appendix analyzes scaling of on-chop global electrical interconnects, including line inductance and the skin effect, both of which impose significant additional constraints on future interconnects.

/pdf/rationale-and-challenges-for-optical-interconnects-to-5clh2238g9.pdf

Rationale and challenges for optical interconnects to electronic chips

The function of the engineering profession is to manipulate materials, energy, and information, thereby creating benefit for humankind. To do this successfully, engineers must have a knowledge of nature that goes beyond mere theory—knowledge that is traditionally gained in educational laboratories. Over the years, however, the nature of these laboratories has changed. This paper describes the history of some of these changes and explores in some depth a few of the major factors influencing laboratories today. In particular, the paper considers the lack of coherent learning objectives for laboratories and how this lack has limited the effectiveness of laboratories and hampered meaningful research in the area. A list of fundamental objectives is presented along with suggestions for possible future research.

http://web.stanford.edu/group/asee/wikiupload/6/69/Feisel_LabsInEngEd.pdf

The Role of the Laboratory in Undergraduate Engineering Education

Photonic systems for high-performance information processing have attracted renewed interest. Neuromorphic silicon photonics has the potential to integrate processing functions that vastly exceed the capabilities of electronics. We report first observations of a recurrent silicon photonic neural network, in which connections are configured by microring weight banks. A mathematical isomorphism between the silicon photonic circuit and a continuous neural network model is demonstrated through dynamical bifurcation analysis. Exploiting this isomorphism, a simulated 24-node silicon photonic neural network is programmed using “neural compiler” to solve a differential system emulation task. A 294-fold acceleration against a conventional benchmark is predicted. We also propose and derive power consumption analysis for modulator-class neurons that, as opposed to laser-class neurons, are compatible with silicon photonic platforms. At increased scale, Neuromorphic silicon photonics could access new regimes of ultrafast information processing for radio, control, and scientific computing.

/pdf/neuromorphic-photonic-networks-using-silicon-photonic-weight-3o4fn6wx4m.pdf

Neuromorphic photonic networks using silicon photonic weight banks.

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 subfemtojoule devices in waveguide and novel two-dimensional (2-D) 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 2-D 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 (∼10 fJ/bit) and simplicity as local electrical wires on chip.

Attojoule Optoelectronics for Low-Energy Information Processing and Communications

The symmetric self-electrooptic-effect device (S-SEED), a structure consisting of two p-i-n diodes electrically connected in series and acting as an optically bistable set-reset latch, is discussed. Applications and extensions of this device are also discussed. The devices do not require the critical biasing that is common to most optically bistable devices and thus is more useful for system applications. They have been optically cascaded in a photonic ring counter and have been used to perform different NOR, OR, NAND, and AND logic functions. Using the same device, a differential modulator that generates a set of complementary output beams with a single voltage control lead and a differential detector that gives an output voltage dependent on the ratio of the two optical input powers have been demonstrated. >

/pdf/symmetric-self-electrooptic-effect-device-optical-set-reset-d8tcyo6js3.pdf

Symmetric self-electrooptic effect device: optical set-reset latch, differential logic gate, and differential modulator/detector

We demonstrate an integrated symmetric self‐electro‐optic effect device consisting of two quantum well p‐i‐n diodes electrically connected in series. The device acts as a bistable optical memory element with individual set (S) and reset (R) inputs and complementary outputs (optical S‐R latch). The switching point is determined by the ratio of the two inputs, making the device insensitive to optical power supply fluctuations when both power beams are derived from the same source. The device also shows time‐sequential gain, in that the state can be set using low‐power beams and read out with subsequent high‐power beams. The device showed bistability for voltages greater than 3 V, incident optical switching energy densities of ∼16 fJ/μm2, and was tested to a switching time of 40 ns.

https://works.bepress.com/scott_hinton/40/download/

Symmetric self‐electro‐optic effect device: Optical set‐reset latch

Photonic technologies are reviewed that could become important components of future telecommunication systems. Photonic devices and systems are divided into two classes according to the function they perform. The first class, relational, refers to devices, that map the input channels to the output channels under external control. The second class, logic, perform some type or combination of Boolean logic functions. Some of the strengths and weaknesses of operating in the photonic domain are presented. Relational devices and their applications are discussed. Optical logic devices and their potential applications are reviewed. >

/pdf/architectural-considerations-for-photonic-switching-networks-1i2x1zt1o2.pdf

Architectural considerations for photonic switching networks

Free-space interconnection of widely spaced pixels may be implemented using microlenses, rather than conventional imaging. Advantages, problems, and studies of system capacity are discussed.

Optical Interconnections Using Microlens Arrays

The strengths and limitations of the photonic technology are reviewed, beginning with the temporal bandwidth limitations of photonic devices and then focusing on spatial bandwidth, commonly referred to as the parallelism of optics, and how it can be used in photonic fabrics. Some of the proposed photonic switching fabrics that are based on guided-wave devices are discussed, comprising switching fabrics based on space channels, using directional couplers and optical amplifiers, and those based on time channels. The latter include active reconfigurable fabrics based on TDM, time-slot interchangers, and universal time slots, in addition to passive shared media fabrics. Some of the switching fabrics that have been proposed using wavelength channels are outlined, and multidimensional fabrics are briefly reviewed. Photonic switching fabrics based on free-space devices are described, covering free-space relational switching fabrics, the basic hardware required for digital free-space optical fabrics, and digital free-space switching fabrics. >

Harvard Scott Hinton

Papers

Symmetric self-electrooptic effect device: optical set-reset latch, differential logic gate, and differential modulator/detector

Symmetric self‐electro‐optic effect device: Optical set‐reset latch

Architectural considerations for photonic switching networks

Optical Interconnections Using Microlens Arrays

Photonic switching fabrics