Search

On CMP, programs commonly interference with each other. But for programs co-running on CMP, serious performance dropdown is not expected. With the growth of the program’s size, program’s contention for limited shared resources in the system will become increasingly intense, and the resulting impact on system performance will be even more pronounced. How to allocate and share limited shared resources among programs is a very important problem. In this paper we propose a new method to ensure the fairness of program’s performance on CMP. The share resource CPU and memory are included in our study. Meanwhile, the Linux resource management tool Cgroups is used to realize our idea. By the resource we profiled and the tool support, we realize a reasonable resource dividing method to ensure the fairness of program’s performance. The reasonable resource dividing method include three Engine. The experiment result show that making use of the fairness resource dividing method proposed by our paper, compared with operating system scheduling, program’s performance difference can be largely reduced.

Long short-term memory (LSTM) networks are widely used to handle temporal or sequential data, and have great potential for video recognition. Existing LSTM-based video recognition methods either insert LSTM modules at the end of 2D convolutional neural networks (CNNs), called global LSTM methods, or build networks solely by stacking multiple LSTM modules. Unfortunately, these LSTM-based video recognition methods are not competitive, compared to state-of-the-art 3D CNNs or two-stream CNNs. In order to fully explore the potential of LSTM, this paper rethinks its role in video recognition network architectures and proposes a novel Temporal Grafter Network (TGN). Specifically, we develop an efficient and effective variant of convolutional LSTM module, which is grafted between different stages of very deep 2D CNNs for temporal modeling and delivery. Our TGN can capture local motion patterns of varying scales inherent in feature maps from high to low resolutions, while attending to the spatial context information and modeling global temporal dependency across the whole video. The proposed TGN can capture and transmit temporal information throughout very deep 2D CNNs, overcoming the downsides of existing LSTM-based methods and being able to make full use of the potential of LSTM for effective video recognition and early action recognition. We perform extensive ablation study to verify the effectiveness of our proposed methods, and experiments on three widely used video benchmarks show that our methods can achieve performance matching or better than the state-of-the-arts. [ABSTRACT FROM AUTHOR]

This paper reports an enhancement of the electrical properties of micro-silicon carbide/silicone elastomer (m-SiC/SE) composites by adding nano-aluminum nitride (n-AlN) for the next-generation power module encapsulation applications. The electrical properties, such as nonlinear conductivity, DC breakdown strength, dielectric spectroscopy, and thermally stimulated discharge current, of the pure SE, m-SiC/SE microcomposite, and m-SiC/n-AlN/SE hybrid composites added with 1 wt%, 3 wt%, and 5 wt% n-AlN fillers are investigated. The m-SiC/n-AlN/SE hybrid composites exhibit better nonlinear conductivity characteristics and enhanced DC breakdown strength than the m-SiC/SE microcomposite. Amongst all materials, the 3 wt% n-AlN addition in the hybrid composite has the best enhancement effect on the nonlinear conductivity characteristics and DC breakdown strength. However, it has the lowest low-frequency real and imaginary permittivities among the SE micro and hybrid composites. Furthermore, a m-SiC/n-AlN heterogenous interface model is proposed to explain the mechanism of enhanced electrical properties of the m-SiC/n-AlN/SE composites. It is found that higher m-SiC/n-AlN heterogenous interface barriers are constructed after adding n-AlN fillers, thereby inhibiting the charge carrier transport at low electric fields. In contrast, more conductive paths are activated at high electric fields by the contacted m-SiC fillers via n-AlN fillers, promoting the charge carrier transport at high electric fields. [ABSTRACT FROM AUTHOR]

Metal halide perovskite films are promising candidates for applications in self-powered photodetectors owing to their astonishing photoelectric properties. Intragrain and structural defects present in the films can easily cause significant energy loss via carrier non-radiative recombination. Herein, a synergetic strategy of composition engineering and crystal engineering is developed for fabrication of (110)-uniaxially oriented FA0.2MA0.8PbI3 films on different substrates based on the pressure-induced fusion growth mechanism. The resulting composition-optimized films are composed of large grains with an average lateral size of 5 μm (on the SnO2 layer) and even 30.8 μm (directly on the Si substrate). Meanwhile, films with different thicknesses (0.2–1.5 μm) exhibit a single-crystal-like surface and single-crystal penetration across the film thickness, realizing lower trap densities, longer carrier lifetimes and excellent environmental stability. The corresponding perovskite self-powered photodetector presents a giant responsivity under white light (470 mA W−1 at 770 nm) and laser light (512 mA W−1, 671 nm) simultaneously. Moreover, the device exhibits markedly improved environmental stability, reproducibility, and a fast response. [ABSTRACT FROM AUTHOR]

The pharmacological activities of liquiritin (LT) are greatly limited by its insolubility and low oral absorption. The purpose of this study was to prepare LT-hydroxypropyl-beta-cyclodextrin inclusion complex (LT-HP-β-CD) to increase water solubility, oral bioavailability and antitumor effect of LT. Herein, saturated aqueous solution method was applied to prepare the LT-HP-β-CD prior to characterization via scanning electron microscope (SEM), infrared radiation (IR) spectroscopy, X-ray diffraction analysis (XRD), and differential scanning calorimetry (DSC). Also, in vitro release and in vivo pharmacokinetics were evaluated. Moreover, the anti-tumor activity of the formulation was investigated in the A549 lung cancer cells. The results of SEM, IR, XRD and DSC showed that LT-HP-β-CD was successfully formulated. In vitro release and oral bioavailability of LT-HP-β-CD compared with the free LT was significantly higher. Successfully, antitumor effect of LT was remarkably enhanced by the preparation of LT-HP-β-CD. Altogether, the LT-HP-β-CD represents a potential carrier for enhancing the water solubility and oral bioavailability of LT coupled with antitumor activity enhancement. [Display omitted] [ABSTRACT FROM AUTHOR]

VS2 with natural layered structure and metallic conductivity is a prospective candidate for sodium-ion batteries (SIBs) and potassium-ion batteries (PIBs). However, due to large radius of Na+ and K+, the limited interlayer spacing (0.57 nm) of VS2 generally determines high ion diffusion barrier and large volume variation, resulting in unsatisfactory electrochemical performance of SIBs and PIBs. In this work, flower-like VS2/N-doped carbon (VS2/N-C) with expanded (001) plane is grown on reduced graphene oxide (rGO) via a solvothermal and subsequently carbonization strategy. In the VS2/N-C@rGO nanohybrids, the ultrathin VS2 "petals" are alternately intercalated by the N-doped porous carbon monolayers to achieve an expanded interlayer spacing (1.02 nm), which can effectively reduce ions diffusion barrier, expose abundant active sites for Na+/K+ intercalation, and tolerate large volume variation. The N-C and rGO carbonous materials can significantly promote the electrical conductivity and structural stability. Benefited from the synergistic effect, the VS2/N-C@rGO electrode exhibits large reversible capacity (Na+: 407 mAh·g−1 at 1 A·g−1; K+: 334 mAh·g−1 at 0.2 A·g−1), high rate capacity (Na+: 273 mAh·g−1 at 8 A·g−1; K+: 186 mAh·g−1 at 5 A·g−1), and remarkable cycling stability (Na+: 316 mAh·g−1 at 2 A·g−1 after 1,400 cycles; K+: 216 mAh·g−1 at 1 A·g−1 after 500 cycles). [ABSTRACT FROM AUTHOR]