10  Gb/s optical random access memory (RAM) cell

Tsakyridis, Apostolos; Alexoudi, Theoni; Miliou, Amalia; Pleros, Nikos; Vagionas, Christos

doi:10.1364/ol.44.001821

Cited by 36 publications

(19 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…71 However, in past decades, a growing performance gap between processor performance and memory bandwidth, i.e., the "memory wall" problem, has hindered high-performance computation. 73 Electronic processors are also suffering from the tremendous energy consumption of digital transceiver circuits during massive data I/O connections. Increasing the memory-processor bandwidth and energy efficiency in interconnections is an effective way to diminish the data movement problem.…”

Section: Optical Interconnections In Computation Hardwarementioning

confidence: 99%

Silicon-based optoelectronics for general-purpose matrix computation: a review

Zhou

2022

Adv. Photon.

View full text Add to dashboard Cite

Conventional electronic processors, which are the mainstream and almost invincible hardware for computation, are approaching their limits in both computational power and energy efficiency, especially in large-scale matrix computation. By combining electronic, photonic, and optoelectronic devices and circuits together, silicon-based optoelectronic matrix computation has been demonstrating great capabilities and feasibilities. Matrix computation is one of the few general-purpose computations that have the potential to exceed the computation performance of digital logic circuits in energy efficiency, computational power, and latency. Moreover, electronic processors also suffer from the tremendous energy consumption of the digital transceiver circuits during high-capacity data interconnections. We review the recent progress in photonic matrix computation, including matrix-vector multiplication, convolution, and multiply-accumulate operations in artificial neural networks, quantum information processing, combinatorial optimization, and compressed sensing, with particular attention paid to energy consumption. We also summarize the advantages of siliconbased optoelectronic matrix computation in data interconnections and photonic-electronic integration over conventional optical computing processors. Looking toward the future of silicon-based optoelectronic matrix computations, we believe that silicon-based optoelectronics is a promising and comprehensive platform for disruptively improving general-purpose matrix computation performance in the post-Moore's law era.

show abstract

Section: Optical Interconnections In Computation Hardwarementioning

confidence: 99%

Silicon-based optoelectronics for general-purpose matrix computation: a review

Zhou

2022

Adv. Photon.

View full text Add to dashboard Cite

show abstract

“…When a control signal is injected into the device, it leads both SOAs performing close to their gain transparency region, as such the SOAs' carrier fluctuation and intensity modulation are greatly reduced, supporting clipping properties and strongly power equalized output pulses. On the other hand, when SOAs are operated in a symmetrically biased condition, as in simple WC or push-pull schemes [33], they are generating amplitude fluctuations, jitter and transient phenomena as described in more details in [34].…”

Section: Experimental Setup and Principle Of Operationmentioning

confidence: 99%

“…condition, as in simple WC or push-pull schemes [33], they are generating amplitude fluctuations, jitter and transient phenomena as described in more details in [34].…”

Section: Experimental Setup and Principle Of Operationmentioning

confidence: 99%

A Deeply Saturated Differentially-Biased SOA-MZI for 20 Gb/s Burst-Mode NRZ Traffic

et al. 2019

Self Cite

View full text Add to dashboard Cite

We experimentally demonstrate an optical Burst-Mode Wavelength Converter (BMWC) that simultaneously provides power equalization and wavelength conversion of Non-Return to Zero-On/Off Keying (NRZ-OOK) data and operates up to 20 Gb/s. It employs a balanced, differentially-biased, Semiconductor Optical Amplifier-Mach Zehnder Interferometer (SOA-MZI) operating in deeply saturated regime and its performance is evaluated at 10 Gb/s and 20 Gb/s with loud/soft peak–power ratios up to 9 dB and 5 dB, respectively. Bit Error Rate (BER) measurements reveal error free operation with up to 6.1 dB BER improvement at 10 Gb/s and 3.51 dB at 20 Gb/s, while the use of a single SOA-MZI yields 50% reduction in the number of active components against state-of-the-art BMWCs. Finally, the proposed BMWC is evaluated in non-dispersion compensated 25 km fiber transmission experiment, providing error-free operation with 1.43 dB BER improvement, validating its capabilities for potential employment in Passive Optical Networks (PON) and 5G fronthaul networks.

show abstract

“…However, high-speed, energy-efficient and compact photonic storage with true static random-access characteristics is still demanding to form the ultimate underlying memory sub-system for general-purpose optical computing. Various methods have been investigated for all-optical static random access memory (SRAM) cells, including semiconductor optical amplifier-Mach-Zehnder interferometer (SOA-MZI) configurations [11][12][13][14] , SOA-based ring lasers 15 , III-V photonic crystal cavities 16 and optomechanical cavities 17 . SOA-MZI based optical SRAM bit cell reported in 14 exhibit a speed of 10 Gbps, however, these devices are not compatible for large scale chip-level memory integration as it requires a large footprint in the order of mm 2 .…”

mentioning

confidence: 99%

“…Various methods have been investigated for all-optical static random access memory (SRAM) cells, including semiconductor optical amplifier-Mach-Zehnder interferometer (SOA-MZI) configurations [11][12][13][14] , SOA-based ring lasers 15 , III-V photonic crystal cavities 16 and optomechanical cavities 17 . SOA-MZI based optical SRAM bit cell reported in 14 exhibit a speed of 10 Gbps, however, these devices are not compatible for large scale chip-level memory integration as it requires a large footprint in the order of mm 2 . On the other hand, photonic crystal cavities 16 and nano-optomechanical cavities 17 can be integrated in a smaller footprint (∼ 100 µm 2 ), but require major modifications to the existing foundry processes involving material or device integration aspects.…”

mentioning

confidence: 99%