Adaptive backoff synchronization techniques

Barrier synchronization in shared memory parallel machines has been widely implemented through busy-waiting on shared variables. However, typical implementations of barrier synchronization tend to produce hot-spots in terms of memory and network contention, thus creating performance bottlenecks that become markedly more pronounced as the number of cores or processors increases. To overcome such limitations, we present a novel hardware-based barrier mechanism in the context of many-core CMPs. Our proposal is based on global interconnection lines (G-lines) and the S-CSMA technique, which have been recently used to enhance a flow control mechanism (EVC) in the context of networks-on-chip. Based on this technology, we have designed a simple and scalable G-line-based network that operates independently of the main data network, and that is aimed at carrying out barrier synchronizations efficiently. In the ideal case, our design takes only 4 cycles to perform a barrier synchronization once all cores or threads have arrived at the barrier. As a proof of concept, we examine the benefits of our proposal by comparing it with one of the best software approaches (a binary combining-tree barrier). To do so, we run several kernels and scientific applications on top of the Sim-PowerCMP performance simulator that models a 32-core CMP with a 2D-mesh network configuration. Our proposal entails average reductions in terms of execution time of 68% and 21% for kernels and scientific applications, respectively. Additionally, network traffic is also lowered by 74% and 18%, respectively.

Important problems in Computational Medicine exist that can benefit from the implementation of adaptive mesh refinement techniques. Biological systems are so inherently complex that only efficient models running on state of the art hardware can begin to simulate reality. To tackle the complex geometries associated with medical applications we present a general purpose mesh generation scheme based upon the Delaunay tessellation algorithm and an iterative point generator. In addition, automatic, two- and three-dimensional adaptive mesh refinement methods are presented that are derived from local and global estimates of the finite element error. Mesh generation and adaptive refinement techniques are utilized to obtain accurate approximations of bioelectric fields within anatomically correct models of the heart and human thorax. Specifically, we explore the simulation of cardiac defibrillation and the general forward and inverse problems in electrocardiography (ECG). Comparisons between uniform and adaptive refinement techniques are made to highlight the computational efficiency and accuracy of adaptive methods in the solution of field problems in computational medicine.

This paper is devoted to the description of recent and prospective decorrelation techniques used in image processing. Two classes are taken into consideration : the universal or generic methods and the adaptive methods. The first class performs signal processing independently of its specificity. These methods only rely on statistical properties of the signal. They are principally based on orthogonal transforms and subband coding. In opposition, the adaptive techniques take the a posteriori contents of the images into account. Some of them adapt universal techniques to the signal content (i.e. adaptive subband coding or hybrid methods). Others are based on feature extraction processes which include more physical entities like edges and regions. For example, object approaches attempt to describe images as collections of regions characterized by their shape and their aspect.

Stochastic modelling is critical for studying many biochemical processes in a cell, in particular when some reacting species have low population numbers. For many such cellular processes the spatial distribution of the molecular species plays a key role. The evolution of spatially heterogeneous biochemical systems with some species in low amounts is accurately described by the mesoscopic model of the Reaction-Diffusion Master Equation. The Inhomogeneous Stochastic Simulation Algorithm provides an exact strategy to numerically solve this model, but it is computationally very expensive on realistic applications. We propose a novel adaptive time-stepping scheme for the tau-leaping method for approximating the solution of the Reaction-Diffusion Master Equation. This technique combines effective strategies for variable time-stepping with path preservation to reduce the computational cost, while maintaining the desired accuracy. The numerical tests on various examples arising in applications show the improved efficiency achieved by the new adaptive method.

High-precision and high-density three-dimensional point cloud models usually contain redundant data, which implies extra time and hardware costs in the subsequent data processing stage. To analyze and extract data more effectively, the point cloud must be simplified before data processing. Given that point cloud simplification must be sensitive to features to ensure that more valid information can be saved, in this paper, a new simplification algorithm for scattered point clouds with feature preservation, which can reduce the amount of data while retaining the features of data, is proposed. First, the Delaunay neighborhood of the point cloud is constructed, and then the edge points of the point cloud are extracted by the edge distribution characteristics of the point cloud. Second, the moving least-square method is used to obtain the normal vector of the point cloud and the valley ridge points of the model. Then, potential feature points are identified further and retained on the basis of the discrete gradient idea. Finally, non-feature points are extracted. Experimental results show that our method can be applied to models with different curvatures and effectively avoid the hole phenomenon in the simplification process. To further improve the robustness and anti-noise ability of the method, the neighborhood of the point cloud can be extended to multiple levels, and a balance between simplification speed and accuracy needs to be found.

At present, there are some scattered evidence data pertaining to the use of an adaptive technique of radiotherapy in treatment of malignant glial tumors of the brain. Our evidence data obtained in MRI in the course of treatment show that the initial treatment plan may become irrelevant due to some changes observed in the tumor configuration. In its turn, it bears witness to the topicality of developing and introducing adaptive methods and techniques in the brain tumor treatment, which are capable to increase efficacy and tolerability in patients with primary malignant tumors of the brain. Aim. Our aim has been to develop an adaptive stereotactic method of radiotherapy in treatment of primary malignant brain tumors, which shall be capable to increase efficacy and tolerability of radiation therapy as well as reduce radiation dose to normal structures in the brain. Materials and methods. Our method has been elaborated with recruiting a group of 10 patients diagnosed with primary glioblastoma G IV, which have received specialized treatment at the National Medical Research Centre for Oncology at the Ministry of Health, the Russian Federation, in the period 2021-2022. The average age of the above patients is 43,4 years. All patients have undergone microsurgery covering the total resection of the tumor (3 patients) and subtotal removal of the malignant tumor (7 patients). The average time interval between the surgery and radiotherapy is 32,5 days. Before treatment, an intravenous contrast enhancement MRI of the brain with an axial pitch of 1 mm has been conducted employing the contrast T1, contrast-free T1 and T2 FLAIR modes. Planning of radiotherapy for this sort of patients has been carried out employing BrainLab Elements и Varian Medical Systems Eclipse. The CTV was defined as a 2,0 cm margin around GTV with an anatomical correction. The CTV-to-PTV margin was 0,1 cm. Doses have been administered as follows: a single dose of 2 Gy up to a total dose of 60 Gy in 30 fractions. The brain has been MRI-scanned in all patients with the use of intravenously introduced contrast agents with an axial pitch of 1 mm employing enhanced contrast/contrast-free T1 sequences and T2 FLAIR to redefine the radiotherapy targets (GTV, CTV, PTV). At fraction 30 we have completed MRI in order to estimate the treatment outcome. In the average, the radiotherapy course has taken 42-45 days, holidays included. For the purpose of the radiation therapy, used have been the Novalis Tx Varian Tx linear accelerator of kinetic energy of the beam of 6 MeV. Results We have developed our own adaptive stereotactic method of radiotherapy to treat the primary malignant glial tumors in the brain, which is capable of tracing the configuration of the post-surgery cavity, the residual tumor and the brain structures in the course of radiotherapy and adapting the therapy plan thereto that makes possible to reduce tissue volumes exposed to radiation due to a decrease in the tumoral and peritumoral volumes of the tumor and post-operative cavity. Conclusion. Our analysis has shown that in the course of radiotherapy some anatomical changes in the tumor configuration are found. An adaptive approach applied to radiation therapy allows monitoring the above changing volumes and correcting the treatment plan.

: Predicting wind induced aerodynamic forces on aerospace structures is usually computationally expensive even for powerful computational facilities. For these unsteady computations, adaptive finite element technique may reduce the computer time and storage while keeping a desired accuracy. In this report, the p-version adaptive finite element method is implemented into a standard benchmark problem, the computational how around a circular cylinder, to compute aerodynamic forces. The error distribution for velocity is first estimated. Then, the polynomial order of the interpolation function is changed continuously in accordance with the changing of the error distribution. The second through fifth orders of polynomials are considered for the velocity in the adaptive method. One order less of polynomial is used for pressure. The benchmark problem of the flow around a circular cylinder with Reynolds number of 1000 is considered to study the performance.

Pixel pair matching (PPM) is widely used in digital image steganography. As an important derivation, adaptive pixel pair matching method (APPM) offers low distortion and allows embedded digits in any notational system. However, APPM needs additional space to store, calculate, and query neighborhood set, which needs extra cost. To solve these problems, a formula adaptive pixel pair matching (FAPPM) method is proposed in this paper. The basic idea of FAPPM is to use the formula to get the stego image pixel pair without searching the neighborhood set for the given image pixel pair. This will allow users to embed secret message directly without storing and searching the look-up table. Experimental results and analysis show that the proposed method could embed secret data directly without searching the neighborhood sets by using a formula and it still maintains flexibility in the selection of notional system, high image quality, and strong anti-steganalysis ability.

This paper proposes an adaptive subchannel and bit allocation method for OFDMA (orthogonal frequency division multiple access) based wireless LAN systems. The proposed adaptive subchannel and bit allocation method combines the adaptive subchannel allocation technique and adaptive modulation technique to improve the channel capacity of OFDMA system. This paper presents computer simulation results to demonstrate that the proposed method can achieve the higher frequency bandwidth efficiency and excellent signal quality even under severe frequency selective fading environment for point-to-multipoint wireless LAN systems.

In this paper, we propose a security protocol to detect sybil attacks for position based applications in privacy preserved vehicular ad hoc networks (VANETs). Vehicles in our protocol identify sybil attacks locally in a cooperative way by examining the rationality of vehicles' positions to their own neighbors. The attack detection utilizes the characteristics of communication and vehicles' GPS positions which are included in the periodically broadcasted safety related messages. No extra hardware and little communication and computation overhead will be introduced to vehicles. Therefore, our protocol is very light weighted and suitable for real applications. Moreover, a smart attacker scenario in which a malicious vehicle may adjust its communication range to avoid detection and the malicious vehicles' collusion scenario are also considered. Simulation results based on NS2 are presented to demonstrate the performance of the proposed protocol.

Design for test is an integral part of any VLSI chip. However, for secure systems extra precautions have to be taken to prevent that the test circuitry could reveal secret information. This paper addresses secure test for Physical Unclonable Function based systems. It investigates two secure Built-In Self-Test (BIST) solutions for Fuzzy Extractor (FE) which is the main component of PUF-based systems. The schemes target high stuck-at-fault (SAF) coverage by performing scan-chain free functional testing, to prevent scan-chain abuse for attacks. The first scheme reuses existing FE blocks (for pattern generation and compression) to minimize the area overhead, while the second scheme tests all the FE blocks simultaneously to minimize the test time. The schemes are integrated in FE design and simulated; the results show that for the first test scheme, a SAF fault coverage of 95 % can be realized with no more than 47.1k clock cycles at the cost of a negligible area overhead of only 2.2 %; while for the second test scheme a SAF fault coverage of 95 % can be realized with 3.5k clock cycles at the cost of 18.6 % area overhead. Higher fault coverages are possible to realize at extra cost (i.e., either by extending the test time, or by adding extra hardware, or a combination of both).

The aim of this research is to build adaptive interaction techniques and methods for speech user interfaces. The focus is on interaction methods which can adapt to the different users and interaction situations. This includes multilinguality, different communication strategies, robust error handling methods and complex structural elements. The research is done in the context of the Jaspis framework, which is a general architecture for speech application development. Jaspis is based on an adaptive interaction model, which includes input agents, dialogue agents and presentation agents. Using these it is possible to construct highly adaptive, modular and reusable interaction techniques for speech applications.

In this paper we present the derivation and the application of an adaptive nonintrusive spectral technique for uncertainty quantification. Spectral techniques can be used to reconstruct stochastic quantities of interest by means of a Fourier-like expansion. Their application to uncertainty propagation problems can be performed in a nonintrusive fashion by evaluating a set of projection integrals that is used to reconstruct the spectral expansion. We present the derivation of a new adaptive quadrature algorithm, based on the definition of a sparse grid, which can be used to evaluate these spectral coefficients. This new adaptive algorithm is applied to a reference uncertainty quantification problem consisting of a coupled time-dependent model. The benefits of using such an adaptive method are analyzed and discussed from the uncertainty propagation and computational points of view.

Such soil structures as river dikes, high way embankments and earth dams frequently have been damaged during major earth- quakes, often due to liquefaction of embankments and foundation soils. In most cases, unacceptable, large, permanent deformation has occurred due to liquefaction of the supporting, loose, cohesion- less foundation soil. The seismic design of soil structures in these liquefiable soils poses very difficult problems for analysis and design. The possibility of liquefaction necessitates further investi- gation not only experimentally but by numerical analysis. ABSTRACT The focus of this paper is on 3-D adaptive analysis method of liquefiable soil improvement of the approximate quality of nonlinear numerical simulation of the liquefaction process with large deformation. This adaptive tech- nique was applied to the 3-D non-linear FE analysis of liquefiable soil considering large deformation, including the liquefaction phenomenon. The cyclic elasto-plastic model and updated Lagrangian formulation were adopted in the three-dimensional FE analysis. The fission procedure belonging to the h-refinement indicated by the error estimator, a posteriori error estimate procedure depending on L 2 -norm of strain and superconvergent patch recov- ery method, was used. The convergence of this error estimate scheme and the effectiveness of h-adaptive mesh refinement were shown by simple examples. The adaptive FE method was applied to the three-dimensional prac- tical seismic analysis of an embankment constructed on liquefiable soil, and its efficacy demonstrated in detail. Application of the adaptive technique to the nonlinear analysis of saturated soil, including the liquefaction process, is a valuable step in the three-dimensional seismic analysis of liquefaction.

The operating temperature of a solid oxide fuel cell (SOFC) stack is a very important parameter to be controlled, which impacts the performance of the SOFC due to thermal cycling. In this paper, an adaptive fuzzy control method based on an affine nonlinear temperature model is developed to control the temperature of the SOFC within a specified range. Fuzzy logic systems are used to approximate nonlinear functions in the SOFC system and an adaptive technique is employed to construct the controller. Compared with the traditional fuzzy and proportion-integral-derivative (PID) control, the simulation results show that the designed adaptive fuzzy control method performed much better. So it is feasible to build an adaptive fuzzy controller for temperature control of the SOFC.