10Gb/s Silicon Modulator Based on Bulk-Silicon Platform for DRAM Optical Interface

Lee, K. H.; Shin, Dongjae; Ji, Ho-Chul; Na, K. W.; Kim, S. G.; Bok, J. K.; You, Yong-Sang; Kim, S. S.; Joe, In-Sung; Suh, Sungsoo; Pyo, Junghyung; Shin, Yong-hwack; Ha, K. H.; Park, Y. D.; Chung, Chilhee

doi:10.1364/nfoec.2011.jtha033

Cited by 10 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, we implemented the electrical router separately in the register-transfer level (RTL) code, underscoring the hardware implementation complexity involved in the logic area and power consumption. Laser wall plug efficiency (Le) 0.25 [47] Transceiver bandwidth per wavelength 10 Gb/s [4] Maximum number of wavelengths 4…”

Section: Discussionmentioning

confidence: 99%

“…An optical transceiver with a bandwidth of 10 Gb/s per wavelength is used as the optical network interface [4]. Except for OWBM, the remaining comparison groups used an electrical router with 5-stage pipelines consisting of buffer write, route computation, switch allocation, switch traversal, and link traversal, with an operating clock frequency of 1 GHz.…”

Section: Discussionmentioning

confidence: 99%

“…Optical network-on-chip (ONoC) has emerged as a promising innovation that provides a significant communication bandwidth of hundreds of gigabits per wavelength, which cannot be achieved using electrical network-on-chip (ENoC) [3][4]. Furthermore, by harnessing the capability of wavelength-division multiplexing (WDM), ONoCs can provide scalable bandwidth with high energy efficiency for the upcoming application demands.…”

mentioning

confidence: 99%

See 2 more Smart Citations

OWBM: OSNR-Aware Wavelength Allocation and Branching Methods for Multicast Routing in Custom Topology-Based Optical Network-on-Chips

Kim,

Han

2024

IEEE Access

View full text Add to dashboard Cite

In light of the rapid advancements in big data and artificial intelligence applications, heterogeneous computing (HGC) platforms that integrate diverse computing units have gained traction with the aim of achieving energy efficiency and high performance. A custom topology-based optical network-on-chip (ONoC) that provides unparalleled diversity between computing nodes is expected to be the next-generation communication infrastructure for meeting the bandwidth and energy efficiency requirements of HGC. One of the recent challenges in the field of ONoCs is to accelerate multicast routing via wavelength division multiplexing (WDM), which dispatches data parallelly across non-interfering wavelengths. The optimization of network throughput and laser power efficiency revolves around two factors: the number of wavelengths and optical signal-to-noise ratio (OSNR). Accordingly, we introduce OSNR-aware wavelength allocation and branching methods for multicast routing (OWBM) tailored to an HGC platform in a customized ONoC. OWBM increases the wavelength resource efficiency by establishing independent routing paths in the partitioned destination nodes such that each routing path is guaranteed to be prevented from overlapping among the partitions. Moreover, the adaptive branching mechanism of OWBM adaptively selects path-based routing and OSNR-aware routing on the fly according to the wavelength allocation cases, further augmenting the throughput and laser power efficiency. Consequently, OWBM outperformed conventional tree-and path-based multicast approaches by elevating the average throughput by 47.39% and curbing the laser power consumption by up to 35.92% in various convolutional neural network benchmarks. Compared with the existing ONoC wavelength allocation techniques, the OWBM demonstrated a maximum of 42.46% enhanced wavelength utilization on a 64-core HGC platform. INDEX TERMSDeep learning kernel, heterogeneous computing platform, multicast routing, optical network-on-chip, wavelength allocation I. INTRODUCTION With the relentless growth of computer vision technology beyond extended realities (XRs) and the ubiquity of artificial in-telligence applications, the demand for energy-efficient computational systems is increasing. With the advancements in heterogeneous computing (HGC) platforms, general-purpose VOLUME 4, 2016 i This article has been accepted for publication in IEEE Access.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

OWBM: OSNR-Aware Wavelength Allocation and Branching Methods for Multicast Routing in Custom Topology-Based Optical Network-on-Chips

Kim,

Han

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Content may change prior to final publication. Photodetector sensitivity −20 dBm [40] Power margin of laser 13 dB [41] Transceiver bandwidth 10 Gb/s [42] Laser wall plug efficiency(Le) 0.25 [41] According to [34], the MR heating power is a quarter of the laser power. Taking this relationship into account, we determine the importance factors I 1 , I 2 , and I 3 of (2) in Section III.A for 0.5, 0.4, and 0.1, respectively.…”

Section: Discussionmentioning

confidence: 99%

Rapid Topology Generation and Core Mapping of Optical Network-on-Chip for Heterogeneous Computing Platform

2021

View full text Add to dashboard Cite

The explosive growth of deep learning (DL)-based artificial intelligence (AI) applications necessitates extraordinary computing capabilities that cannot be achieved using traditional CPU standalone computing. Therefore, the heavy mission-critical DL kernel computing currently relies on a heterogeneous computing (HGC) platform integrated with CPUs, GPUs, and accelerators, as well as substantial data storage elements. However, the metallic electrical interconnection in the existing manycore platform would not be sustainable for handling the massively increasing bandwidth demand of big data driven AI applications. Incorporating an optical network-on-chip (ONoC) for providing ultrahigh bandwidth, we propose a rapid topology generation and core mapping of ONoC (REGO) for energy-efficient HGC multicore architecture. The genetic algorithm (GA)-based REGO utilizes the structural characteristics of the optical router to the fitness function and thus compromises the trade-off between the required throughput, optical signal-to-noise ratio (OSNR), and total energy consumption. Furthermore, the crossover step accelerates the convergence speed by suppressing randomness in the GA, thus significantly reducing excessive running time owing to the NP-hard property. The generated ONoC through REGO demonstrates, on an average, an increase of 63.29 % and 22.80 % in throughput and a decrease of 50.24 % and 9.56 % in energy per bit, in the VGG-16 and VGG-19 compared with the conventional mesh-and torus-topologybased ONoCs, respectively. INDEX TERMSDeep learning kernel, genetic algorithm, heterogeneous computing platform, topology generation, optical network-on-chip I. INTRODUCTION Deep learning (DL), a class of machine learning algorithms, trains a nonlinear function approximator represented by a deep neural network (DNN) architecture using input-output pairs of training data [1]. The primary goal of DL is to improve accuracy by learning the weights through backward propagation of errors (backpropagation). Repetitive operations that occur while learning errors in backpropagation require extremely high parallelism and vector-matrix operations. Therefore, a heterogeneous computing (HGC) platform that combines various types of processors and dedicated accelerators is required instead of a legacy CPU-based architecture [2]. In addition, an ultra-wideband on-chip network infrastructure is essential for handling excessively heavy data traffic.Network-on-chip (NoC) is a scalable solution for onchip communication infrastructure that can handle the everincreasing processor cores integrated on a single chip. However, despite the continuing progress in transistor miniaturization, the challenging problems in the backend-of-the-line (BEOL) fabrication steps that form the interconnect layer using metallic interconnects impede the expansion of the onchip communication bandwidth. An optical NoC (ONoC) based on silicon photonics is being actively investigated as an alternative to electrical NoCs (ENoCs). Semiconductor industries such as IBM, Intel, and ...

show abstract

“…In recent years, experimental results have been reported of all-optical or direct electrical modulation [7][8][9] at the communication wavelengths, in poly-Si-based thin-film devices. However, waveguides made of as-deposited poly-Si introduce high optical losses from scattering at the grain boundaries, and the thermal crystallization temperature (∼1100 • C) necessary to maximize the optical and electronic material properties is above the suggested limit of 400 • C set for safe back-end integration [10,11].…”

Section: Introductionmentioning

confidence: 99%

Progress towards a high-performing a-Si:H-based electro-optic modulator

Rao

Coppola

Summonte

et al. 2014

J. Opt.

View full text Add to dashboard Cite

Hydrogenated amorphous silicon (a-Si:H) has recently emerged as a promising material to provide microchips with passive and active photonic functions through a back-end and CMOS-compatible technological process. In this paper, we discuss the performance achieved with different configurations of a-Si:H-based electro-optical amplitude modulators integrated into passive waveguides. All of the analysed devices are based on the plasma dispersion effect, a phenomenon that allows us to reach useful performance at the communication wavelength of λ ∼ 1.55 μm. The behaviour of the various proposed modulation approaches has been tested by ad hoc interferometric structures, such as Fabry–Perot integrated resonators or integrated Mach–Zehnder interferometer, as well as by multistack devices to enhance the static modulation efficiency. The performance of each modulator has been analysed through several figures of merit.

show abstract

10Gb/s Silicon Modulator Based on Bulk-Silicon Platform for DRAM Optical Interface

Cited by 10 publications

References 2 publications

OWBM: OSNR-Aware Wavelength Allocation and Branching Methods for Multicast Routing in Custom Topology-Based Optical Network-on-Chips

OWBM: OSNR-Aware Wavelength Allocation and Branching Methods for Multicast Routing in Custom Topology-Based Optical Network-on-Chips

Rapid Topology Generation and Core Mapping of Optical Network-on-Chip for Heterogeneous Computing Platform

Progress towards a high-performing a-Si:H-based electro-optic modulator

Contact Info

Product

Resources

About