Reconfigurable multi-core architecture - a plausible solution to the von Neumann performance bottleneck

Lu, Chien-Hung; Lin, Chih‐Sheng; Chao, Hung-Lin; Shen, Jih-Sheng; Hsiung, Pao-Ann

doi:10.1504/ijais.2015.074399

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, each stage of information processing requires several steps where data are transferred between the processor and memory [ 5 , 6 ]. The processing steps are carried out sequentially, imposing initial limitations on the speed of such computing devices [ 7 , 8 , 9 , 10 , 11 , 12 ]. This creates time and energy problems, as the information must be transferred repeatedly between different system parts.…”

Section: Introductionmentioning

confidence: 99%

Approaches for Memristive Structures Using Scratching Probe Nanolithography: Towards Neuromorphic Applications

Tominov,

Vakulov,

Avilov

et al. 2023

Nanomaterials

View full text Add to dashboard Cite

This paper proposes two different approaches to studying resistive switching of oxide thin films using scratching probe nanolithography of atomic force microscopy (AFM). These approaches allow us to assess the effects of memristor size and top-contact thickness on resistive switching. For that purpose, we investigated scratching probe nanolithography regimes using the Taguchi method, which is known as a reliable method for improving the reliability of the result. The AFM parameters, including normal load, scratch distance, probe speed, and probe direction, are optimized on the photoresist thin film by the Taguchi method. As a result, the pinholes with diameter ranged from 25.4 ± 2.2 nm to 85.1 ± 6.3 nm, and the groove array with a depth of 40.5 ± 3.7 nm and a roughness at the bottom of less than a few nanometers was formed. Then, based on the Si/TiN/ZnO/photoresist structures, we fabricated and investigated memristors with different spot sizes and TiN top contact thickness. As a result, the HRS/LRS ratio, USET, and ILRS are well controlled for a memristor size from 27 nm to 83 nm and ranged from ~8 to ~128, from 1.4 ± 0.1 V to 1.8 ± 0.2 V, and from (1.7 ± 0.2) × 10−10 A to (4.2 ± 0.6) × 10−9 A, respectively. Furthermore, the HRS/LRS ratio and USET are well controlled at a TiN top contact thickness from 8.3 ± 1.1 nm to 32.4 ± 4.2 nm and ranged from ~22 to ~188 and from 1.15 ± 0.05 V to 1.62 ± 0.06 V, respectively. The results can be used in the engineering and manufacturing of memristive structures for neuromorphic applications of brain-inspired artificial intelligence systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Approaches for Memristive Structures Using Scratching Probe Nanolithography: Towards Neuromorphic Applications

Tominov,

Vakulov,

Avilov

et al. 2023

Nanomaterials

View full text Add to dashboard Cite

show abstract

“…Most computers are based on von Neumann architecture [ 4 , 5 ]. However, the architecture faces a limitation called “von Neumann bottleneck”—physical limitation of the information transfer between the central processor and memory block [ 6 , 7 ]. Finally, this led to a slowdown in the development of computing systems in terms of speed and power consumption.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Growth Parameters on Electrophysical and Memristive Properties of Vanadium Oxide Thin Films

et al. 2020

View full text Add to dashboard Cite

We have experimentally studied the influence of pulsed laser deposition parameters on the morphological and electrophysical parameters of vanadium oxide films. It is shown that an increase in the number of laser pulses from 10,000 to 60,000 and an oxygen pressure from 3 × 10−4 Torr to 3 × 10−2 Torr makes it possible to form vanadium oxide films with a thickness from 22.3 ± 4.4 nm to 131.7 ± 14.4 nm, a surface roughness from 7.8 ± 1.1 nm to 37.1 ± 11.2 nm, electron concentration from (0.32 ± 0.07) × 1017 cm−3 to (42.64 ± 4.46) × 1017 cm−3, electron mobility from 0.25 ± 0.03 cm2/(V·s) to 7.12 ± 1.32 cm2/(V·s), and resistivity from 6.32 ± 2.21 Ω·cm to 723.74 ± 89.21 Ω·cm. The regimes at which vanadium oxide films with a thickness of 22.3 ± 4.4 nm, a roughness of 7.8 ± 1.1 nm, and a resistivity of 6.32 ± 2.21 Ω·cm are obtained for their potential use in the fabrication of ReRAM neuromorphic systems. It is shown that a 22.3 ± 4.4 nm thick vanadium oxide film has the bipolar effect of resistive switching. The resistance in the high state was (89.42 ± 32.37) × 106 Ω, the resistance in the low state was equal to (6.34 ± 2.34) × 103 Ω, and the ratio RHRS/RLRS was about 14,104. The results can be used in the manufacture of a new generation of micro- and nanoelectronics elements to create ReRAM of neuromorphic systems based on vanadium oxide thin films.

show abstract

A Deep Model for Lung Cancer Type Identification by Densely Connected Convolutional Networks and Adaptive Boosting

et al. 2020

View full text Add to dashboard Cite

Timely diagnosis and determination to the type of lung cancer has important clinical significance. Generally, it requires multiple imaging methods to complement each other to obtain a comprehensive diagnosis. In this work, we propose a deep learning model to identify lung cancer type from CT images for patients in Shandong Provincial Hospital. It has a twofold challenge: artificial intelligent models trained by public datasets cannot meet such practical requires, and the amount of collected patients' data is quite few. To solve the twofold problem, we use image rotation, translation and transformation methods to expand and balance our training data, and then densely connected convolutional networks (DenseNet) is used to classify malignant tumor from images collected from, and finally adaptive boosting (adaboost) algorithm is used to aggregate multiple classification results to improve classification performance. Experimental results show that our method can achieve identifying accuracy 89.85%, which performs better than DenseNet without adaboost, ResNet, VGG16 and AlexNet. This provides an efficient, non-invasive detection tool for pathological diagnosis to lung cancer type. INDEX TERMS Adaboost algorithm, data enhancement, densely connected convolutional networks, lung cancer.

show abstract

Reconfigurable multi-core architecture - a plausible solution to the von Neumann performance bottleneck

Cited by 5 publications

References 13 publications

Approaches for Memristive Structures Using Scratching Probe Nanolithography: Towards Neuromorphic Applications

Approaches for Memristive Structures Using Scratching Probe Nanolithography: Towards Neuromorphic Applications

The Effect of Growth Parameters on Electrophysical and Memristive Properties of Vanadium Oxide Thin Films

A Deep Model for Lung Cancer Type Identification by Densely Connected Convolutional Networks and Adaptive Boosting

Contact Info

Product

Resources

About